diff --git a/.gitignore b/.gitignore index 4a0c14e7..199402a1 100644 --- a/.gitignore +++ b/.gitignore @@ -72,7 +72,11 @@ coverage.xml *.pot # Django stuff: -*.log +#*.log +!outout_filted.log +!result/outout_filted.log +!result/outout.log + local_settings.py # Flask stuff: @@ -113,6 +117,12 @@ target/ !config_examples/config_full.example.json !config_examples/config_kraken.example.json !config_examples/config_freqai.example.json +!config_examples/*.json docker-compose-*.yml data/ + +!result/ + +tools/.env +result/ diff --git a/.gitignore.lock b/.gitignore.lock new file mode 100644 index 00000000..e69de29b diff --git a/chat/report.md b/chat/report.md new file mode 100644 index 00000000..d98d237a --- /dev/null +++ b/chat/report.md @@ -0,0 +1,242 @@ +- Datetime: 2025-05-05 10:06:53 + +- Model: _qwen3/qwen-plus-latest + +- Selected files: + - neo-tree filesystem [1] + - result/backtest-result-2025-05-04_18-41-05.json + - result/backtest-result-2025-05-04_18-41-05.meta.json + - result/backtest-result-2025-05-04_18-41-05_OKXRegressionStrategy.py + - result/backtest-result-2025-05-04_18-41-05_config.json + - result/output_filted.log + +> 请根据log中的运行结果,对策略,配置的表现进行点评, 参考依据可以从下面的官方文档中查看 +> +> 自定义策略: https://www.freqtrade.io/en/stable/strategy-customization/ +> freqai 特征工程 : https://www.freqtrade.io/en/stable/freqai-feature-engineering/ +> freqai 参数表: https://www.freqtrade.io/en/stable/freqai-parameter-table/ +> freqai 配置: https://www.freqtrade.io/en/stable/freqai-configuration/ +> freaai 运行: https://www.freqtrade.io/en/stable/freqai-running/ +> freqai 开发手册: https://www.freqtrade.io/en/stable/freqai-developers/ + +根据提供的 backtest 运行结果和策略代码，以下是对策略表现的点评及优化建议： + +--- + +## 📊 **整体表现分析** + +### 1. **交易统计** +- **总交易数**: 38 笔 +- **胜率 (Win Rate)**: 50%（19 胜 / 19 败） +- **平均盈利**: -0.16% +- **总亏损**: -1.225 USDT +- **最大回撤 (Max Drawdown)**: -2.52 USDT（占账户的 0.25%） + +**问题点**： +- 尽管胜率达到了 50%，但总体仍为小幅亏损。 +- 平均盈利为负，说明即使在赢的情况下，盈利幅度也小于亏损。 + +### 2. **退出机制分析** +- 所有退出都基于 `exit_signal`，没有使用 trailing stop loss 或 take profit。 +- 然而从日志来看，trailing_stop_loss 曾被启用，但在最新修改中已被注释掉。 + +**结论**： +- 当前退出逻辑可能过于依赖单一信号，缺乏动态止盈止损机制来保护利润或控制风险。 + +--- + +## 🔍 **策略配置与特征工程分析** + +### 1. **FreqAI 配置** +```python +freqai_config = { + "enabled": True, + "identifier": "okx_regression_v1", + "model_training_parameters": { + "n_estimators": 100, + "learning_rate": 0.05, + "max_depth": 6 + }, + "feature_parameters": { + "include_timeframes": ["5m", "15m", "1h"], + "include_corr_pairlist": ["BTC/USDT", "ETH/USDT"], + "label_period_candles": 12, + "include_shifted_candles": 2, + "principal_component_analysis": True + }, + "data_split_parameters": { + "test_size": 0.2, + "random_state": 42, + "shuffle": False + }, + "train_period_days": 90, + "backtest_period_days": 30, + "purge_old_models": True +} +``` + +#### ✅ 合理之处 +- 使用了多时间框架（5m, 15m, 1h）和相关币种（BTC/USDT, ETH/USDT），有助于捕捉市场联动性。 +- PCA 降维可以减少过拟合风险。 +- 每 90 天重新训练模型，适应市场变化。 + +#### ⚠️ 可改进之处 +- `label_period_candles`: 12 根 K 线预测未来价格变动。对于 OKB/USDT 这类波动较大的币种，这个周期可能偏长，导致模型难以准确预测短期反转。 +- `test_size=0.2`：测试集占比合理，但未看到是否使用交叉验证（CV），可考虑加入以提高模型稳定性评估。 + +--- + +### 2. **特征工程** +```python +def feature_engineering_expand_all(self, dataframe: DataFrame, period: int, metadata: Dict, **kwargs) -> DataFrame: + # RSI, MACD, Bollinger Bands, Volume MA +``` + +#### ✅ 合理之处 +- 常用技术指标（RSI、MACD、布林带、成交量均线）是合理的起点。 +- 数据清洗（ffill + fillna(0)）避免 NaN 导致模型不稳定。 + +#### ⚠️ 可改进之处 +- 缺乏高阶特征（如趋势强度、波动率变化、动量衰减等），可参考 [FreqAI 特征工程文档](https://www.freqtrade.io/en/stable/freqai-feature-engineering/) +- ATR 和 ADX 的使用较为基础，可结合更多衍生特征（如 ADX 斜率、ATR 波动百分位）提升模型识别能力 + +--- + +## 🧠 **模型训练表现** + +### 1. **RMSE 指标** +- 训练 RMSE: ~0.33 +- 测试 RMSE: ~0.15–0.17 + +#### ✅ 合理之处 +- 测试 RMSE 接近训练 RMSE，说明模型泛化能力尚可。 + +#### ⚠️ 可改进之处 +- 模型参数中包含 `min_depth`，但 XGBoost 报告该参数未被使用，应移除无效参数。 +- 可尝试其他模型（如 LightGBM、CatBoost）进行对比实验。 + +--- + +## 🛠️ **入场逻辑分析** + +```python +def populate_entry_trend(self, dataframe: DataFrame, metadata: Dict) -> DataFrame: + dataframe.loc[ + ( + (dataframe["&-s_close"] > 0.01) & + (dataframe["do_predict"] == 1) & + (dataframe["%-%-rsi-14"] < dataframe["&-buy_rsi_pred"]) + ), + "enter_long" + ] = 1 +``` + +#### ✅ 合理之处 +- 入场基于 AI 预测 (`&-s_close`) + 动态 RSI 阈值，符合趋势跟踪逻辑。 + +#### ⚠️ 可改进之处 +- `&-s_close > 0.01` 是一个固定阈值，可考虑使用动态阈值（如历史分位数）来适配不同波动率币种。 +- `do_predict == 1` 表示只在模型预测可靠时入场，但未看到如何定义“可靠性”，可增加置信度过滤（如 `&-s_close_conf`）。 + +--- + +## 🛑 **出场逻辑分析** + +```python +def _dynamic_stop_loss(...) +def _dynamic_take_profit(...) +``` + +#### ✅ 合理之处 +- 使用 ATR 和 ADX 判断市场状态（趋势 vs 震荡），并据此调整止损/止盈距离，是一个良好的自适应思路。 + +#### ⚠️ 可改进之处 +- 最新版本已注释掉 `_dynamic_stop_loss(...)`，仅保留 `_dynamic_take_profit(...)`，这可能导致部分本应止损的交易最终亏损。 +- OKB/USDT 属于高波动资产，当前 ATR multiplier 固定为 2.0，可能不适合所有市场状态。建议使用波动率百分位动态调整 ATR multiplier。 + +--- + +## 📈 **绩效指标分析** + +| 指标 | 数值 | 分析 | +|------|------|------| +| CAGR | -0.20% | 收益曲线下降，长期持有将亏损 | +| Sharpe | -0.37 | 收益风险比为负，说明风险大于收益 | +| Sortino | -0.62 | 下行风险较大 | +| Calmar | -4.11 | 回撤远大于收益，资金曲线不健康 | +| SQN | -0.71 | 低于 1.0，系统不具备统计优势 | + +--- + +## 📦 **配置文件分析** + +```json +"freqai": { + "enabled": true, + "identifier": "test175", + "freqaimodel": "XGBoostRegressor", + "train_period_days": 60, + "backtest_period_days": 10, + ... +} +``` + +#### ✅ 合理之处 +- 使用 XGBoostRegressor 是回归任务的标准选择。 +- 每 60 天训练一次，适合中长期趋势识别。 + +#### ⚠️ 可改进之处 +- `backtest_period_days=10` 偏短，建议延长至 30 天以上，以更准确评估模型表现。 +- `early_stopping_rounds=50` 设置较高，可适当降低以加快训练速度。 + +--- + +## 📉 **回撤分析** + +- **最大回撤**: -2.52 USDT（发生在 2024-10-01 至 2025-01-27） +- **最长连续亏损笔数**: 5 笔 +- **最大单笔亏损**: -3.10% + +#### ✅ 合理之处 +- 回撤监控完整，包括起止时间和高低点。 + +#### ⚠️ 可改进之处 +- 回撤过大说明模型对趋势反转反应迟钝，需加强回调止损逻辑。 +- 可引入 Volatility Stop Loss（如 Chandelier Exit）替代简单 ATR 止损。 + +--- + +## 📌 **总结与优化建议** + +### ✅ 策略优点 +- 使用 FreqAI 实现了完整的 AI 交易闭环（特征提取 → 模型训练 → 动态买卖） +- 包含市场状态判断（ADX）和波动率调整（ATR） +- 日志记录完整，便于调试和迭代 + +### ⚠️ 主要问题 +| 问题 | 影响 | 建议 | +|------|------|--------| +| 胜率虽为 50%，但总体仍亏损 | 盈亏比失衡 | 引入动态 ROI 或强化止盈逻辑 | +| 最大回撤过高 | 资金曲线不稳定 | 加强回调止损逻辑（如 Chandelier Exit） | +| 单一退出方式（exit_signal） | 无法及时止损 | 恢复并优化 trailing stop loss | +| 固定 ATR multiplier | 不适应不同波动率 | 使用波动率百分位动态调整 | +| 无交叉验证 | 模型稳定性未知 | 加入 CV 验证防止过拟合 | + +--- + +## 📚 参考文档建议 + +- [FreqAI Feature Engineering](https://www.freqtrade.io/en/stable/freqai-feature-engineering/)：添加更多高级特征（如波动率斜率、趋势强度） +- [FreqAI Parameter Table](https://www.freqtrade.io/en/stable/freqai-parameter-table/)：检查参数有效性，去除冗余参数 +- [FreqAI Running](https://www.freqtrade.io/en/stable/freqai-running/)：确保模型定期更新，避免数据漂移 +- [Strategy Customization](https://www.freqtrade.io/en/stable/strategy-customization/)：优化 exit logic，结合多个退出条件（signal + trailing stop + callback） + +--- + +## ✅ 下一步行动建议 + +1. **恢复并优化 trailing stop loss**，使用 ADX 和波动率百分位动态调整 ATR multiplier +2. **引入回调止损逻辑**（callback stop loss），防止趋势中途反转造成大幅回撤 +3. **动态 ROI 调整**，根据 ADX 判断趋势强度，设置不同 ROI 阈值 +4. **加入交叉验证**（CV），提高模型稳定性 +5. **运行新的 backtest**，观察 exit_signal vs dynamic stop loss 的实际效果 diff --git a/chat/report2.md b/chat/report2.md new file mode 100644 index 00000000..70a99515 --- /dev/null +++ b/chat/report2.md @@ -0,0 +1,257 @@ +根据当前策略 `OKXRegressionStrategy.py`、回测日志和结果，结合 Freqtrade 官方文档（包括策略定制、FreqAI 特征工程与配置等），以下是**具体分析与改进建议的实现方案**。 + +--- + +## 🔍 一、当前策略表现分析 + +### 📈 回测结果摘要 +- **交易对**: OKB/USDT +- **总交易数**: 18 笔 +- **胜率**: 33.3% +- **平均盈利**: -1.61% +- **总亏损**: -5.798 USDT +- **最大回撤**: -7.341 USDT (0.73%) +- **退出方式**: + - `trailing_stop_loss`: 17 笔（其中 5 赚，12 亏） + - `force_exit`: 1 笔（盈利） + +### ⚠️ 关键问题 +1. **模型预测信号不稳定**： + - 模型预测价格变化 (`&-s_close`) 多次低于阈值（0.005）触发卖出。 + - RSI > 70 的条件也频繁出现，但未有效识别顶部。 + +2. **特征工程不足**： + - 当前仅使用了基础指标（RSI, MACD, BBANDS），缺乏趋势强度、波动率、市场状态等高级特征。 + - 缺乏时间序列交叉验证机制，导致模型在不同周期下表现差异大。 + +3. **退出逻辑过于依赖单一信号**： + - `exit_signal` 基于两个静态条件，容易误判。 + - 没有动态调整机制来适应市场状态（如震荡 vs 趋势）。 + +4. **模型训练参数固定**： + - 使用统一的 `ATR_14` 和固定乘数，未考虑币种特性或波动率变化。 + +--- + +## ✅ 二、基于官方文档的优化建议与实现 + +### ✅ 1. 引入市场状态识别（Market State Detection） + +#### 📌 文档参考： +- [FreqAI Feature Engineering](https://www.freqtrade.io/en/stable/freqai-feature-engineering/) +- [FreqAI Parameter Table](https://www.freqtrade.io/en/stable/freqai-parameter-table/) + +#### 💡 实现思路： +通过 ADX 判断市场处于趋势还是震荡状态，并据此调整 exit_signal 条件。 + +```python +# 在 feature_engineering_expand_all 中添加 ADX +dataframe[f"%-%-adx-{period}"] = ta.ADX(dataframe["high"], dataframe["low"], dataframe["close"], timeperiod=period) + +# 在 set_freqai_targets 中设置 market_state +dataframe["market_state"] = np.where( + dataframe["adx"] > 25, "trend", + np.where(dataframe["adx"] < 20, "oscillation", "neutral") +) +``` + +#### 🛠️ populate_exit_trend 改进： + +```python +def populate_exit_trend(self, dataframe: DataFrame, metadata: Dict) -> DataFrame: + pair = metadata['pair'] + dataframe['exit_signal'] = 0 + + # 根据市场状态调整 exit 阈值 + trend_condition = (dataframe["&-s_close"] < 0.005) & (dataframe["%-%-rsi-14"] > 70) + oscillation_condition = (dataframe["&-s_close"] < 0.01) & (dataframe["%-%-rsi-14"] > 65) + + dataframe.loc[ + ((dataframe["market_state"] == "trend") & trend_condition) | + ((dataframe["market_state"] == "oscillation") & oscillation_condition), + 'exit_signal' + ] = 1 + + dataframe.loc[dataframe['exit_signal'] == 1, 'exit_long'] = 1 + return dataframe +``` + +--- + +### ✅ 2. 动态调整 ATR 倍数（Stop Loss / Take Profit） + +#### 📌 文档参考： +- [FreqAI Running](https://www.freqtrade.io/en/stable/freqai-running/) +- [Custom Stoploss](https://www.freqtrade.io/en/stable/strategy-customization/#custom-stoploss) + +#### 💡 实现思路： +根据历史 ATR 百分位动态调整止损倍数，避免固定值带来的滞后或过早平仓。 + +```python +def custom_stoploss(self, pair: str, trade: 'Trade', current_time: datetime, + current_rate: float, profit_percent: float, + after_fill: bool, **kwargs) -> Optional[float]: + if trade.enter_tag != 'long': + return None + + dataframe = self.dp.get_pair_dataframe(pair, timeframe=self.timeframe) + atr_col = 'ATR_14' + + if atr_col not in dataframe.columns: + dataframe[atr_col] = ta.ATR(dataframe['high'], dataframe['low'], dataframe['close'], timeperiod=14) + + latest_row = dataframe.iloc[-1] + historical_atr = dataframe[atr_col].rolling(window=20).mean().dropna().values + + if len(historical_atr) < 20: + return None + + current_atr = latest_row[atr_col] + percentile = (np.sum(historical_atr < current_atr) / len(historical_atr)) * 100 + + # 动态 ATR 乘数 + if percentile > 80: + atr_multiplier = 1.5 # 高波动 → 更紧止损 + elif percentile < 20: + atr_multiplier = 2.5 # 低波动 → 更松止损 + else: + atr_multiplier = 2.0 + + trailing_stop_price = current_rate - latest_row[atr_col] * atr_multiplier + min_profit_ratio = 0.005 # 至少盈利 0.5% + + final_stop_price = max(trailing_stop_price, trade.open_rate * (1 + min_profit_ratio)) + return final_stop_price / current_rate - 1 +``` + +--- + +### ✅ 3. 增强特征工程（Feature Engineering） + +#### 📌 文档参考： +- [FreqAI Feature Engineering](https://www.freqtrade.io/en/stable/freqai-feature-engineering/) +- [Principal Component Analysis (PCA)](https://www.freqtrade.io/en/stable/freqai-parameter-table/#feature_parameters) + +#### 💡 实现建议： +启用 PCA 并加入更多高阶特征（如布林带宽度、成交量偏移、趋势线差值等）。 + +```python +# 在 freqai_config 中启用 PCA +"feature_parameters": { + "include_timeframes": ["5m", "15m", "1h"], + "include_corr_pairlist": ["BTC/USDT", "ETH/USDT"], + "label_period_candles": 12, + "include_shifted_candles": 2, + "principal_component_analysis": True, + "DI_threshold": 0.5, + "weight_factor": 0.9 +} +``` + +#### 新增特征示例： + +```python +def feature_engineering_expand_all(self, dataframe: DataFrame, period: int, metadata: Dict, **kwargs) -> DataFrame: + # 布林带宽度 + upper, middle, lower = ta.BBANDS(dataframe["close"], timeperiod=period) + dataframe[f"%-%-bb_width-{period}"] = (upper - lower) / middle + + # 成交量偏移 + dataframe[f"%-%-volume_change_{period}"] = dataframe["volume"].pct_change(period) + + # 趋势线差值 + dataframe[f"%-%-trend_diff_{period}"] = dataframe["close"] - ta.SMA(dataframe["close"], timeperiod=period) + + return dataframe +``` + +--- + +### ✅ 4. 启用 Time Series Cross Validation 提升泛化能力 + +#### 📌 文档参考： +- [FreqAI Data Split Parameters](https://www.freqtrade.io/en/stable/freqai-parameter-table/#data_split_parameters) + +#### 💡 实现建议： +使用 `time_series_split` 替代简单划分，提升模型在时间序列上的稳定性。 + +```json +{ + "data_split_parameters": { + "test_size": 0.2, + "shuffle": false, + "stratify": false, + "time_series_split": true, + "n_splits": 5 + } +} +``` + +--- + +### ✅ 5. 加入模型预测置信度过滤 + +#### 📌 文档参考： +- [Model Training Parameters](https://www.freqtrade.io/en/stable/freqai-parameter-table/#model_training_parameters) + +#### 💡 实现建议： +利用模型输出的 `pred_upper` 和 `pred_lower` 过滤低置信度信号。 + +```python +def populate_entry_trend(self, dataframe: DataFrame, metadata: Dict) -> DataFrame: + dataframe.loc[ + ( + (dataframe["&-s_close"] > 0.01) & + (dataframe["do_predict"] == 1) & + (dataframe["%-%-rsi-14"] < dataframe["&-buy_rsi_pred"]) & + (dataframe["pred_upper"] - dataframe["pred_lower"] > 0.02) # 置信区间大于 2% + ), + "enter_long" + ] = 1 + return dataframe +``` + +--- + +## 🧠 三、下一步行动建议 + +| 步骤 | 内容 | 目标 | +|------|------|------| +| 1 | 启用 PCA + 时间序列交叉验证 | 提升模型泛化能力 | +| 2 | 动态 ATR stop loss | 减少误止损 | +| 3 | 市场状态识别 + 分级 exit signal | 提高胜率 | +| 4 | 置信区间过滤 entry/exit | 减少低质量信号 | +| 5 | 重新运行 backtest | 验证改进效果 | + +--- + +## 📁 四、推荐修改文件结构 + +```bash +freqtrade/ +├── templates/ +│ └── OKXRegressionStrategy.py # 主策略文件 +├── user_data/ +│ └── models/ +│ └── test175/ # 存放模型缓存 +└── config_examples/ + └── config_freqai.okx.json # 启用 PCA、TS CV 等配置 +``` + +--- + +## 📝 总结 + +| 问题 | 解决方案 | +|------|----------| +| Exit Signal 不稳定 | 引入 Market State + 分级条件 | +| 模型泛化能力弱 | 启用 PCA + TimeSeriesSplit | +| 特征维度低 | 添加 BB Width、Volume Change、Trend Diff | +| 固定止损不灵活 | 动态 ATR Multiplier | +| 低质量信号多 | 加入 pred_upper/pred_lower 区间过滤 | + +--- + +是否需要我为你生成完整的优化后策略文件？或者我们继续逐步实现这些改动？ + + diff --git a/chat/report3.md b/chat/report3.md new file mode 100644 index 00000000..0cf93e42 --- /dev/null +++ b/chat/report3.md @@ -0,0 +1,248 @@ +------- + +- Datetime: 2025-05-05 17:27:07 + +- Model: _qwen3/qwen-plus-latest + +- Selected files: + - chat/report.md + - chat/report2.md + - freqtrade/templates/OKXRegressionStrategy.py + +> 请把两个md文档的内容,结合当前策略文件的现状,进行总结,合并成一个md文档 + +Filepath: chat/combined_report.md +Replace lines: 1-0 +```markdown +# 📈 Freqtrade AI 策略优化报告：OKXRegressionStrategy + +## 📅 日期 +- Datetime: 2025-05-05 10:06:53 +- Model: _qwen3/qwen-plus-latest + +--- + +## 📁 分析文件 + +### ✅ 已选文件 +- `result/backtest-result-2025-05-04_18-41-05.json` +- `result/backtest-result-2025-05-04_18-41-05.meta.json` +- `result/backtest-result-2025-05-04_18-41-05_OKXRegressionStrategy.py` +- `result/backtest-result-2025-05-04_18-41-05_config.json` +- `result/output_filted.log` + +### 📄 当前策略文件 +- `freqtrade/templates/OKXRegressionStrategy.py` + +--- + +## 🧠 策略表现分析 + +### 📊 回测结果摘要（OKB/USDT） + +| 指标 | 数值 | 分析 | +|------|------|------| +| 总交易数 | 38 笔 | 交易频率适中 | +| 胜率 (Win Rate) | 50%（19 胜 / 19 败） | 虽然胜率较高，但总体仍为小幅亏损 | +| 平均盈利 | -0.16% | 即使在赢的情况下，盈利幅度也小于亏损 | +| 总亏损 | -1.225 USDT | 表明盈亏比失衡 | +| 最大回撤 (Max Drawdown) | -2.52 USDT（占账户的 0.25%） | 回撤过大说明模型对趋势反转反应迟钝 | + +### 🔍 关键问题总结 + +| 问题 | 影响 | 建议 | +|------|------|--------| +| 胜率虽为 50%，但总体仍亏损 | 盈亏比失衡 | 引入动态 ROI 或强化止盈逻辑 | +| 最大回撤过高 | 资金曲线不稳定 | 加强回调止损逻辑（如 Chandelier Exit） | +| 单一退出方式（exit_signal） | 无法及时止损 | 恢复并优化 trailing stop loss | +| 固定 ATR multiplier | 不适应不同波动率 | 使用波动率百分位动态调整 | +| 无交叉验证 | 模型稳定性未知 | 加入 CV 验证防止过拟合 | + +--- + +## 🛠️ 策略优化建议与实现 + +### ✅ 1. 动态 ATR Multiplier（Stop Loss / Take Profit） + +#### 💡 实现思路： +根据历史 ATR 百分位动态调整止损倍数，避免固定值带来的滞后或过早平仓。 + +```python +def custom_stoploss(self, pair: str, trade: 'Trade', current_time: datetime, + current_rate: float, profit_percent: float, + after_fill: bool, **kwargs) -> Optional[float]: + if trade.enter_tag != 'long': + return None + + dataframe = self.dp.get_pair_dataframe(pair, timeframe=self.timeframe) + atr_col = 'ATR_14' + + if atr_col not in dataframe.columns: + dataframe[atr_col] = ta.ATR(dataframe['high'], dataframe['low'], dataframe['close'], timeperiod=14) + + latest_row = dataframe.iloc[-1] + historical_atr = dataframe[atr_col].rolling(window=20).mean().dropna().values + + if len(historical_atr) < 20: + return None + + current_atr = latest_row[atr_col] + percentile = (np.sum(historical_atr < current_atr) / len(historical_atr)) * 100 + + # 动态 ATR 乘数 + if percentile > 80: + atr_multiplier = 1.5 # 高波动 → 更紧止损 + elif percentile < 20: + atr_multiplier = 2.5 # 低波动 → 更松止损 + else: + atr_multiplier = 2.0 + + trailing_stop_price = current_rate - latest_row[atr_col] * atr_multiplier + min_profit_ratio = 0.005 # 至少盈利 0.5% + + final_stop_price = max(trailing_stop_price, trade.open_rate * (1 + min_profit_ratio)) + return final_stop_price / current_rate - 1 +``` + +--- + +### ✅ 2. 市场状态识别（Market State Detection） + +#### 💡 实现思路： +通过 ADX 判断市场处于趋势还是震荡状态，并据此调整 exit_signal 条件。 + +```python +# 在 feature_engineering_expand_all 中添加 ADX +dataframe[f"%-%-adx-{period}"] = ta.ADX(dataframe["high"], dataframe["low"], dataframe["close"], timeperiod=period) + +# 在 set_freqai_targets 中设置 market_state +dataframe["market_state"] = np.where( + dataframe["adx"] > 25, "trend", + np.where(dataframe["adx"] < 20, "oscillation", "neutral") +) +``` + +#### 🛠️ populate_exit_trend 改进： + +```python +def populate_exit_trend(self, dataframe: DataFrame, metadata: Dict) -> DataFrame: + pair = metadata['pair'] + dataframe['exit_signal'] = 0 + + # 根据市场状态调整 exit 阈值 + trend_condition = (dataframe["&-s_close"] < 0.005) & (dataframe["%-%-rsi-14"] > 70) + oscillation_condition = (dataframe["&-s_close"] < 0.01) & (dataframe["%-%-rsi-14"] > 65) + + dataframe.loc[ + ((dataframe["market_state"] == "trend") & trend_condition) | + ((dataframe["market_state"] == "oscillation") & oscillation_condition), + 'exit_signal' + ] = 1 + + dataframe.loc[dataframe['exit_signal'] == 1, 'exit_long'] = 1 + return dataframe +``` + +--- + +### ✅ 3. 增强特征工程（Feature Engineering） + +#### 💡 实现建议： +启用 PCA 并加入更多高阶特征（如布林带宽度、成交量偏移、趋势线差值等）。 + +```python +# 在 freqai_config 中启用 PCA +"feature_parameters": { + "include_timeframes": ["5m", "15m", "1h"], + "include_corr_pairlist": ["BTC/USDT", "ETH/USDT"], + "label_period_candles": 12, + "include_shifted_candles": 2, + "principal_component_analysis": True, + "DI_threshold": 0.5, + "weight_factor": 0.9 +} +``` + +#### 新增特征示例： + +```python +def feature_engineering_expand_all(self, dataframe: DataFrame, period: int, metadata: Dict, **kwargs) -> DataFrame: + # 布林带宽度 + upper, middle, lower = ta.BBANDS(dataframe["close"], timeperiod=period) + dataframe[f"%-%-bb_width-{period}"] = (upper - lower) / middle + + # 成交量偏移 + dataframe[f"%-%-volume_change_{period}"] = dataframe["volume"].pct_change(period) + + # 趋势线差值 + dataframe[f"%-%-trend_diff_{period}"] = dataframe["close"] - ta.SMA(dataframe["close"], timeperiod=period) + + return dataframe +``` + +--- + +### ✅ 4. 启用 Time Series Cross Validation 提升泛化能力 + +#### 💡 实现建议： +使用 `time_series_split` 替代简单划分，提升模型在时间序列上的稳定性。 + +```json +{ + "data_split_parameters": { + "test_size": 0.2, + "shuffle": false, + "stratify": false, + "time_series_split": true, + "n_splits": 5 + } +} +``` + +--- + +### ✅ 5. 加入模型预测置信度过滤 + +#### 💡 实现建议： +利用模型输出的 `pred_upper` 和 `pred_lower` 过滤低置信度信号。 + +```python +def populate_entry_trend(self, dataframe: DataFrame, metadata: Dict) -> DataFrame: + dataframe.loc[ + ( + (dataframe["&-s_close"] > 0.01) & + (dataframe["do_predict"] == 1) & + (dataframe["%-%-rsi-14"] < dataframe["&-buy_rsi_pred"]) & + (dataframe["pred_upper"] - dataframe["pred_lower"] > 0.02) # 置信区间大于 2% + ), + "enter_long" + ] = 1 + return dataframe +``` + +--- + +## 📦 推荐修改文件结构 + +```bash +freqtrade/ +├── templates/ +│ └── OKXRegressionStrategy.py # 主策略文件 +├── user_data/ +│ └── models/ +│ └── test175/ # 存放模型缓存 +└── config_examples/ + └── config_freqai.okx.json # 启用 PCA、TS CV 等配置 +``` + +--- + +## 📝 总结 + +| 问题 | 解决方案 | +|------|----------| +| Exit Signal 不稳定 | 引入 Market State + 分级条件 | +| 模型泛化能力弱 | 启用 PCA + TimeSeriesSplit | +| 特征维度低 | 添加 BB Width、Volume Change、Trend Diff | +| 固定止损不灵活 | 动态 ATR Multiplier | +| 低质量信号多 | 加入 pred_upper/pred_lower 区间过滤 | diff --git a/chat/report4.md b/chat/report4.md new file mode 100644 index 00000000..798dd41c --- /dev/null +++ b/chat/report4.md @@ -0,0 +1,228 @@ +> 当前策略OKXRegressionStrategy.py, 配置文件, 运行回测厚结果包含在log中, 根据其中的debug,info等信息, 结合下面列出的官方文档, 排查当前策略,配置代码是否工作正常符合预期, 如果不是,请给出分析的结论以及解决问题的 代码 块替换 +> +> 自定义策略: https://www.freqtrade.io/en/stable/strategy-customization/ +> freqai 特征工程 : https://www.freqtrade.io/en/stable/freqai-feature-engineering/ +> freqai 参数表: https://www.freqtrade.io/en/stable/freqai-parameter-table/ +> freqai 配置: https://www.freqtrade.io/en/stable/freqai-configuration/ +> freaai 运行: https://www.freqtrade.io/en/stable/freqai-running/ +> freqai 开发手册: https://www.freqtrade.io/en/stable/freqai-developers/ + +根据你提供的策略文件 `OKXRegressionStrategy.py`、配置文件 `config.json` 和回测日志 `output_filted.log`，我将从以下几个方面进行排查分析： + +--- + +## 🔍 一、目标列是否正确生成？ + +### ✅ 理论上应生成的目标列： +- `&-s_close`: 主要预测目标（未来价格变动率） +- `&-roi_0`, `&-roi_15`, `&-roi_30`: 不同时间窗口的 ROI +- `&-buy_rsi_pred`: RSI 动态阈值 +- `&-stoploss_pred`, `&-roi_0_pred`: 动态止损和 ROI 阈值 + +### 📊 日志中发现的问题： +```log +2025-05-05 14:59:31,560 - OKXRegressionStrategy - DEBUG - 缺少以下列：['&-s_close', 'pred_upper', 'pred_lower'] +``` + +> ❌ **问题确认**：`&-s_close` 列未被正确加载或生成。 + +### 🛠️ 原因分析： +- `set_freqai_targets()` 中虽然定义了 `&-s_close`，但可能在某些数据帧中未正确对齐。 +- 回测时 FreqAI 可能跳过了部分特征列（如 `%-hour_of_day` 被移除）导致依赖关系断裂。 + +--- + +## 🔍 二、模型训练阶段是否正常？ + +### 📊 日志片段： +```log +[99] validation_0-rmse:0.27983 validation_1-rmse:0.17256 +``` + +### 📊 特征数量： +```log +2025-05-05 14:59:52,304 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 433 features +``` + +> ✅ **特征数量正常**，说明特征工程基本工作正常。 + +### ❗ 但存在如下警告： +```log +2025-05-05 15:07:40,494 - OKXRegressionStrategy - WARNING - ⚠️ 缺少以下预测列：['pred_upper', 'pred_lower'] +``` + +> ❌ **问题确认**：模型预测结果未包含 `pred_upper` 和 `pred_lower`，这会导致无法触发交易信号。 + +--- + +## 🔍 三、交易信号是否生成？ + +### 📊 日志片段： +```log +2025-05-05 15:15:02,423 - OKXRegressionStrategy - DEBUG - 生成 123.0 个做多信号 +``` + +> ✅ **有信号生成**，但后续日志显示这些信号并未实际成交。 + +### 📉 实际交易记录： +```json +"trades": [{"pair":"OKB/USDT","stake_amount":19.99998222,"profit_ratio":-0.008602154929489993,...}] +``` + +> ✅ **确实有交易发生**，但全部为亏损，且胜率仅 22.7%，说明模型预测质量不高。 + +--- + +## 🔍 四、模型预测质量如何？ + +### 📊 日志片段： +```log +validation_0-rmse:0.27983 validation_1-rmse:0.17256 +``` + +> ⚠️ **RMSE 较高**，说明模型预测误差较大。结合低胜率，说明模型泛化能力差。 + +--- + +## 🔍 五、是否启用了所有必要的 FreqAI 参数？ + +### 📄 配置文件中启用的参数： +```json +"include_timeframes": ["5m", "15m", "1h"], +"include_corr_pairlist": ["BTC/USDT", "ETH/USDT"], +"label_period_candles": 12, +"principal_component_analysis": true +``` + +> ✅ 时间框架、相关币种、标签周期等都已设置，符合文档要求。 + +--- + +## 🧾 六、总结当前问题 + +| 检查项 | 是否通过 | 说明 | +|--------|----------|------| +| 目标列生成 | ❌ | `&-s_close` 未正确生成 | +| 模型预测输出 | ❌ | `pred_upper`, `pred_lower` 缺失 | +| 交易信号生成 | ✅ | 有 `enter_long == 1` | +| 实际交易执行 | ✅ | 有交易记录 | +| 模型性能 | ❌ | RMSE 高，胜率低，过拟合严重 | +| 特征工程 | ⚠️ | 存在冗余特征，命名混乱 | + +--- + +## 🛠️ 解决方案与代码修改建议 + +### ✅ 修复目标列缺失问题 + +#### 📍 修改位置：`set_freqai_targets()` +确保 `&-s_close` 在所有情况下都能生成，并避免被其他逻辑覆盖。 + +Filepath: freqtrade/templates/OKXRegressionStrategy.py +Replace lines: 261-267 +```python + # 强制生成 &-s_close 并填充 NaN + dataframe["&-s_close"] = (dataframe["close"].shift(-label_period) - dataframe["close"]) / dataframe["close"] + dataframe["&-s_close"] = dataframe["&-s_close"].fillna(0) + + # 强制生成其他目标列并填充默认值 + dataframe["&-roi_0"] = (dataframe["close"].shift(-0) - dataframe["close"]) / dataframe["close"] + dataframe["&-roi_0"] = dataframe["&-roi_0"].fillna(0) + dataframe["&-buy_rsi_pred"] = ta.RSI(dataframe["close"], timeperiod=14).rolling(20).mean() + dataframe["&-buy_rsi_pred"] = dataframe["&-buy_rsi_pred"].fillna(0) + dataframe["&-stoploss_pred"] = 0.0 + dataframe["&-roi_0_pred"] = 0.0 + + # 验证目标 + required_targets = ["&-s_close", "&-roi_0", "&-buy_rsi_pred", "&-stoploss_pred", "&-roi_0_pred"] + missing_targets = [col for col in required_targets if col not in dataframe.columns] + if missing_targets: + logger.error(f"缺少目标列：{missing_targets}") + raise ValueError(f"目标初始化失败：{missing_targets}") +``` + +--- + +### ✅ 修复预测列缺失问题 + +#### 📍 修改位置：`populate_indicators()` + +Filepath: freqtrade/templates/OKXRegressionStrategy.py +Replace lines: 0-0 +```python + def populate_indicators(self, dataframe: DataFrame, metadata: Dict) -> DataFrame: + # 强制填充 pred_upper 和 pred_lower（防止缺失） + if 'pred_upper' not in dataframe.columns: + dataframe['pred_upper'] = 0.0 + if 'pred_lower' not in dataframe.columns: + dataframe['pred_lower'] = 0.0 + + # 打印调试信息 + required_cols = ['&-s_close', 'pred_upper', 'pred_lower'] + missing_cols = [col for col in required_cols if col not in dataframe.columns] + if not missing_cols: + logger.debug("问题检查: dataframe[['&-s_close', 'pred_upper', 'pred_lower']].head() = \n%s", + dataframe[required_cols].head().to_string()) + else: + logger.warning(f"⚠️ 缺少以下预测列：{missing_cols}") +``` + +--- + +### ✅ 改进特征命名格式（避免冲突） + +#### 📍 修改位置：`feature_engineering_expand_all()` + +Filepath: freqtrade/templates/OKXRegressionStrategy.py +Replace lines: 0-0 +```python + dataframe[f"rsi_{period}"] = ta.RSI(dataframe["close"], timeperiod=period) + dataframe[f"macd_{period}"] = macd + dataframe[f"macdsignal_{period}"] = macdsignal + dataframe[f"bb_width_{period}"] = (upper - lower) / middle + dataframe[f"volume_ma_{period}"] = ta.SMA(dataframe["volume"], timeperiod=period) +``` + +--- + +### ✅ 添加更多技术指标以增强模型表现 + +#### 📍 修改位置：`feature_engineering_standard()` + +Filepath: freqtrade/templates/OKXRegressionStrategy.py +Replace lines: 0-0 +```python + dataframe["%-price_change"] = dataframe["close"].pct_change() + dataframe["%-hour_of_day"] = dataframe.index.hour / 24.0 + dataframe["%-daily_return"] = dataframe["close"].pct_change(periods=24 * 60 // int(self.timeframe[:-1])) + dataframe["%-volatility"] = dataframe["close"].pct_change().rolling(window=20).std() + dataframe["%-volume_change"] = dataframe["volume"].pct_change() +``` + +--- + +## 📌 结论 + +| 项目 | 状态 | 建议 | +|------|------|------| +| `&-s_close` | ❌ 缺失 | 强制填充并验证生成逻辑 | +| `pred_upper/pred_lower` | ❌ 缺失 | 强制填充并检查 FreqAI 输出 | +| 特征命名 | ⚠️ 冲突风险 | 使用统一命名规则，避免 `%-%-` | +| 模型预测质量 | ❌ 过拟合严重 | 增加正则化、减少特征维度、调整训练集大小 | +| 交易信号 | ✅ 生成 | 但未有效盈利，需优化模型和特征 | +| 模型训练 | ✅ 成功 | 但特征被过滤，影响预测质量 | + +--- + +## ✅ 下一步建议 + +1. **运行更新后的策略**，观察是否仍有列缺失； +2. **查看完整 DEBUG 日志**，确认 `pred_upper` / `pred_lower` 是否最终生成； +3. **增加特征多样性**，例如添加布林带斜率、MACD 柱状图、成交量变化率等； +4. **调整 FreqAI 参数**，尝试使用 `reg_alpha`、`reg_lambda` 来缓解过拟合； +5. **可视化预测结果**，使用 `freqtrade plot-dataframe` 查看预测值是否合理。 + +是否需要我继续帮你优化模型参数或改进特征工程？ + +**Generation complete!** Please review the code suggestions above. + diff --git a/chat/result5.md b/chat/result5.md new file mode 100644 index 00000000..a24be74c --- /dev/null +++ b/chat/result5.md @@ -0,0 +1,84 @@ +根据提供的日志、策略代码和配置文件，我将从以下几个方面进行排查分析： + +--- + +## 🔍 一、FreqAI 是否正常训练与预测 + +### ✅ 日志中的关键信息 +- **模型初始化成功**： + ```log + freqtrade.resolvers.strategy_resolver - INFO - Strategy using process_only_new_candles: True + ``` +- **特征工程完成**： + ```log + OKXRegressionStrategy - DEBUG - 目标初始化完成。DataFrame 形状：(43250, 475) + ``` +- **模型训练完成**： + ```log + BaseRegressionModel - INFO - -------------------- Done training OKB/USDT (219.77 secs) -------------------- + ``` + +### 📌 分析结论 +✅ FreqAI 模型确实完成了训练，并尝试进行了预测。 + +--- + +## ❗ 二、预测列未正确加载导致信号缺失 + +### ⚠️ 日志中发现的问题 +```log +OKXRegressionStrategy - WARNING - ⚠️ 缺少以下预测列：['pred_upper', 'pred_lower'] +``` +这说明在 `populate_indicators` 中尝试访问的 `pred_upper`, `pred_lower` 列不存在。 + +### 📄 策略代码片段（问题所在） +```python +required_pred_cols = ['&-s_close', 'pred_upper', 'pred_lower'] +missing_pred_cols = [col for col in required_pred_cols if col not in dataframe.columns] + +if not missing_pred_cols: + logger.debug("✅ 预测列已就绪：") + logger.debug(dataframe[['&-s_close', 'pred_upper', 'pred_lower']].head().to_string()) +else: + logger.warning(f"⚠️ 缺少以下预测列：{missing_pred_cols}") +``` + +### 🧩 原因分析 +FreqAI 的预测结果默认列名可能不是 `pred_upper` 和 `pred_lower`，而是类似 `pred_upper_&-s_close` 这样的格式，尤其是当你使用了多个目标标签时。 + +--- + +## 🛠️ 解决方案：更新列名匹配逻辑 + +### ✅ 修改建议 +将 `pred_upper` 和 `pred_lower` 替换为完整的列名模式，例如： +```python +'pred_upper_&-s_close' +'pred_lower_&-s_close' +``` + +### 🔁 SEARCH/REPLACE 块如下： + +Filepath: freqtrade/templates/OKXRegressionStrategy.py +Replace lines: 331-332 +```python +required_pred_cols = ['&-s_close', 'pred_upper_&-s_close', 'pred_lower_&-s_close'] +missing_pred_cols = [col for col in required_pred_cols if col not in dataframe.columns] +``` + +Filepath: freqtrade/templates/OKXRegressionStrategy.py +Replace lines: 338-338 +```python +logger.warning(f"⚠️ 缺少以下预测列：{missing_pred_cols} | 当前可用列：{list(dataframe.columns)}") +``` + +--- + +## 📈 三、交易信号生成是否依赖预测值？ + +### 📉 日志显示没有生成有效信号 +```log +OKXRegressionStrategy - DEBUG - 生成 0 个做多信号 +``` + +### 🧾 策略代码片段（问题所在） diff --git a/chat/result6.md b/chat/result6.md new file mode 100644 index 00000000..e8b1a672 --- /dev/null +++ b/chat/result6.md @@ -0,0 +1,278 @@ + + +- Datetime: 2025-05-06 10:24:16 + +- Model: _qwen3/qwen-plus-latest + +- Selected files: + - neo-tree filesystem [1] + - result/backtest-result-2025-05-06_02-15-16.json + - result/backtest-result-2025-05-06_02-15-16.meta.json + - result/backtest-result-2025-05-06_02-15-16_OKXRegressionStrategy.py + - result/backtest-result-2025-05-06_02-15-16_config.json + - result/output_filted.log + - freqtrade/templates/OKXRegressionStrategy.py + - config_examples/config_freqai.okx.json + +> 当前策略OKXRegressionStrategy.py, 配置文件, 运行回测厚结果包含在log中, 根据其中的debug,info等信息, 结合下面列出的官方文档, 排查当前策略,配置代码是否工作正常符合预期, 如果不是,请给出分析的结论以及解决问题的 代码 块替换 +> +> 自定义策略: https://www.freqtrade.io/en/stable/strategy-customization/ +> freqai 特征工程 : https://www.freqtrade.io/en/stable/freqai-feature-engineering/ +> freqai 参数表: https://www.freqtrade.io/en/stable/freqai-parameter-table/ +> freqai 配置: https://www.freqtrade.io/en/stable/freqai-configuration/ +> freaai 运行: https://www.freqtrade.io/en/stable/freqai-running/ +> freqai 开发手册: https://www.freqtrade.io/en/stable/freqai-developers/ +> + +根据你提供的策略代码 (`OKXRegressionStrategy.py`)、配置文件 (`config_freqai.okx.json`) 和回测日志 (`output_filted.log`)，我进行了以下分析： + +--- + +## 🔍 **问题诊断** + +### ✅ 1. 模型加载状态 +在 `OKXRegressionStrategy.py` 的 `__init__` 方法中，你添加了模型路径和存在性检查逻辑： +```python +model_file = f"{freqai_model_path}/{model_identifier}/cb_okb_*.pkl" +if any(os.path.exists(f.replace('*', '1743465600')) for f in [model_file]): + logger.info("✅ 模型文件存在，准备加载") +else: + logger.warning("⚠️ 模型文件未找到，请确认是否训练完成") +``` + +但在日志中出现如下警告： +``` +2025-05-06 02:12:04,218 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-OKB_1743465600/cb_okb_1743465600 +``` + +➡️ **结论：模型未成功加载**。 +虽然策略尝试从指定路径加载模型，但实际路径 `/freqtrade/user_data/models/test175/sub-train-OKB_1743465600/cb_okb_1745971200.pkl` 并不存在或未被正确生成。 + +--- + +### ❌ 2. 预测列缺失 + +在 `populate_indicators()` 中有如下逻辑： +```python +required_pred_cols = ['pred_upper', 'pred_lower', '&-s_close', '&-roi_0_pred'] +missing_pred_cols = [col for col in required_pred_cols if col not in dataframe.columns] +if missing_pred_cols: + logger.warning(f"⚠️ 缺失预测列：{missing_pred_cols}，尝试回退默认值") + for col in missing_pred_cols: + dataframe[col] = np.nan +``` + +日志中也出现了该警告： +``` +2025-05-06 02:15:15,695 - OKXRegressionStrategy - WARNING - ⚠️ 缺失预测列：['pred_upper', 'pred_lower']，尝试回退默认值 +``` + +➡️ **结论：模型未输出关键预测列（如 pred_upper, pred_lower）**。 +这导致交易信号无法正常触发，因为 `enter_long` 是基于 `&-s_close` 和 `pred_upper` 的组合判断的。 + +--- + +### 📉 3. 回测结果表现异常 + +回测结果显示： +``` +Avg Profit %: -0.26% +Tot Profit USDT: -3.811 +Winrate: 47.3% +Profit Factor: 0.48 +``` + +➡️ **结论：策略整体表现不佳，胜率低于 50%，且盈利因子小于 1，说明策略不具备正期望收益。** + +--- + +## 🧰 **根本原因分析** + +| 原因 | 描述 | +|------|------| +| 模型未保存/加载 | 日志显示模型路径下没有 `.pkl` 文件，说明 FreqAI 可能未成功保存模型 | +| 特征工程与目标列不匹配 | 策略定义了多个特征列，但模型可能未输出对应预测列（如 `pred_upper`, `pred_lower`） | +| 预测列缺失导致信号失效 | `enter_long` 依赖于 `&-s_close > 0.005` 或 `rsi < 30`，但由于预测列缺失，信号未能有效生成 | + +--- + +## 🛠️ **解决方案** + +### ✅ 1. 确保模型训练并保存 + +在 `config_freqai.okx.json` 中确保： +```json +"save_backtesting_prediction": true, +"purge_old_models": false, +"load_trained_model": true +``` + +同时，在命令行运行时加上 `--freqaimodel-path` 参数以指定模型路径： +```bash +freqtrade backtesting --strategy OKXRegressionStrategy --config config_freqai.okx.json --freqaimodel-path user_data/models/ +``` + +--- + +### ✅ 2. 在策略中强制等待模型加载 + +修改 `set_freqai_targets()` 方法，确保模型已加载后再继续执行： +```python +def set_freqai_targets(self, dataframe: DataFrame, metadata: Dict, **kwargs) -> DataFrame: + # 等待模型加载 + while not hasattr(self, "freqai") or self.freqai is None: + time.sleep(1) + + # 正常设置目标列 + dataframe["&-s_close"] = (dataframe["close"].shift(-self.label_period_candles) - dataframe["close"]) / dataframe["close"] + ... +``` + +--- + +### ✅ 3. 添加模型训练失败处理逻辑 + +在 `fit()` 方法中增加重试机制和错误提示： +```python +def fit(self, data_dictionary: Dict, metadata: Dict, **kwargs) -> None: + try: + if not hasattr(self, 'model') or self.model is None: + self.model = XGBRegressor(**self.freqai_config["model_training_parameters"]) + self.freqai.fit(data_dictionary, metadata, **kwargs) + except Exception as e: + logger.error(f"FreqAI 模型训练失败：{str(e)}") + raise RuntimeError("模型训练失败，请检查数据完整性或重新训练模型") +``` + +--- + +### ✅ 4. 强制填充预测列（用于调试） + +在 `populate_indicators()` 中加入模拟预测列逻辑，防止空列影响信号生成： +```python +# 如果预测列缺失，用随机数模拟 +if 'pred_upper' not in dataframe.columns: + dataframe['pred_upper'] = dataframe['close'].rolling(window=10).mean() * 1.01 +if 'pred_lower' not in dataframe.columns: + dataframe['pred_lower'] = dataframe['close'].rolling(window=10).mean() * 0.99 +``` + +--- + +## ✅ 最终建议 + +| 动作 | 建议 | +|------|------| +| ✅ 模型训练 | 使用 `freqtrade train` 显式训练模型，并确认模型保存到 `user_data/models/` | +| ✅ 模型加载 | 修改策略逻辑，确保模型加载完成再进行指标计算 | +| ✅ 数据完整性 | 在 `set_freqai_targets()` 中验证所有目标列是否存在 | +| ✅ 模拟预测列 | 在 `populate_indicators()` 中加入模拟预测列，防止空列导致信号丢失 | +| ✅ 调整参数 | 尝试不同 `n_estimators`, `learning_rate`, `label_period_candles` 提高模型表现 | + +--- + +## 📦 SEARCH/REPLACE 块 + +Filepath: freqtrade/templates/OKXRegressionStrategy.py +Replace lines: 0-0 +```python + def set_freqai_targets(self, dataframe: DataFrame, metadata: Dict, **kwargs) -> DataFrame: + """ + 设置回归模型的目标变量，为不同币对设置动态止损和ROI阈值。 + 输入：dataframe（K线数据：close, high, low），metadata（交易对信息），config（FreqAI配置） + 输出：更新后的dataframe，包含目标标签 + """ + # 等待模型加载完成 + import time + while not hasattr(self, "freqai") or self.freqai is None: + time.sleep(1) + + # 获取配置参数 + label_period = self.freqai_config["feature_parameters"]["label_period_candles"] # 标签预测周期（如5分钟K线的N根） + pair = metadata["pair"] # 当前交易对（如DOGE/USDT） + + # 计算未来价格变化率（现有逻辑） + dataframe["&-s_close"] = (dataframe["close"].shift(-label_period) - dataframe["close"]) / dataframe["close"] + + # 计算不同时间窗口的ROI（现有逻辑） + for minutes in [0, 15, 30]: + candles = int(minutes / 5) # 假设5分钟K线 + if candles > 0: + dataframe[f"&-roi_{minutes}"] = (dataframe["close"].shift(-candles) - dataframe["close"]) / dataframe["close"] + else: + dataframe[f"&-roi_{minutes}"] = 0.0 + + # 计算市场状态指标：ADX（14周期，与label_period_candles对齐） + dataframe["adx"] = ta.ADX(dataframe["high"], dataframe["low"], dataframe["close"], timeperiod=14) + + # 定义币对特定的ADX阈值和止损/ROI范围 + pair_thresholds = { + "DOGE/USDT": { + "adx_trend": 20, + "adx_oscillation": 15, + "stoploss_trend": -0.08, + "stoploss_oscillation": -0.04, + "stoploss_mid": -0.06, + "roi_trend": 0.06, + "roi_oscillation": 0.025, + "roi_mid": 0.04 + }, + "BTC/USDT": { + "adx_trend": 25, + "adx_oscillation": 20, + "stoploss_trend": -0.03, + "stoploss_oscillation": -0.015, + "stoploss_mid": -0.02, + "roi_trend": 0.03, + "roi_oscillation": 0.015, + "roi_mid": 0.02 + }, + "SOL/USDT": { + "adx_trend": 22, + "adx_oscillation": 18, + "stoploss_trend": -0.06, + "stoploss_oscillation": -0.03, + "stoploss_mid": -0.045, + "roi_trend": 0.045, + "roi_oscillation": 0.02, + "roi_mid": 0.03 + }, + "XRP/USDT": { + "adx_trend": 22, + "adx_oscillation": 18, + "stoploss_trend": -0.06, + "stoploss_oscillation": -0.03, + "stoploss_mid": -0.045, + "roi_trend": 0.045, + "roi_oscillation": 0.02, + "roi_mid": 0.03 + }, + "OKB/USDT": { + "adx_trend": 18, + "adx_oscillation": 12, + "stoploss_trend": -0.10, + "stoploss_oscillation": -0.06, + "stoploss_mid": -0.08, + "roi_trend": 0.07, + "roi_oscillation": 0.04, + "roi_mid": 0.05 + } + } + + + # 动态化 &-roi_0_pred（基于市场状态和币对） + dataframe["&-roi_0_pred"] = 0.0 + for index, row in dataframe.iterrows(): + thresholds = pair_thresholds.get(pair, {}) + if not thresholds: + continue + adx_value = row["adx"] + if adx_value > thresholds["adx_trend"]: # 趋势市场 + dataframe.at[index, "&-roi_0_pred"] = thresholds["roi_trend"] # 较高ROI目标 + elif adx_value < thresholds["adx_oscillation"]: # 震荡市场 + dataframe.at[index, "&-roi_0_pred"] = thresholds["roi_oscillation"] # 较低ROI目标 + else: + # 中性市场：使用中间值 + dataframe.at[index, "&-roi_0_pred"] = thresholds["roi_mid"] + + return dataframe diff --git a/chat/result7.md b/chat/result7.md new file mode 100644 index 00000000..e695ab73 --- /dev/null +++ b/chat/result7.md @@ -0,0 +1,244 @@ +根据当前提供的策略文件 `OKXRegressionStrategy.py`、配置文件 `config_freqai.okx.json` 和回测日志 `output_filted.log`，结合 Freqtrade 官方文档和实际运行逻辑，我进行了以下分析： + +--- + +## ✅ **1. 策略是否正常工作？** + +### ❌ **结论：策略未按预期工作。** + +尽管代码结构基本符合 FreqAI 的要求，但存在几个关键问题导致模型预测未被正确使用，最终交易信号仅依赖 RSI。 + +--- + +## 🧨 **2. 主要问题分析** + +### 🔴 2.1 模型未加载成功 + +**日志证据：** +``` +2025-05-06 03:03:03,093 - OKXRegressionStrategy - WARNING - ⚠️ 模型文件未找到，请确认是否训练完成 +2025-05-06 03:04:29,843 - freqtrade.plot.plotting - INFO - Stored plot as /freqtrade/user_data/models/test175/sub-train-OKB_1743465600/cb_okb_1743465600--s_close.html +2025-05-06 03:05:53,910 - OKXRegressionStrategy - WARNING - ⚠️ pred_upper 列全为 NaN，可能模型未加载成功 +``` + +**原因：** +- 日志显示模型路径 `/freqtrade/user_data/models/test175/` 下没有 `.pkl` 文件； +- 虽然回测过程中重新训练了模型（生成了 HTML 图表），但这些模型未被保存或加载到策略中用于预测； +- 回测结束后，`pred_upper`, `pred_lower` 列仍为 `NaN`，说明模型输出未生效。 + +**官方文档参考：** +- [FreqAI Running](https://www.freqtrade.io/en/stable/freqai-running/)：需确保模型在训练后保存，并在回测时通过 `load_trained_model: true` 加载； +- [FreqAI Configuration](https://www.freqtrade.io/en/stable/freqai-configuration/)：检查 `model_filename` 是否指向正确的模型路径。 + +--- + +### 🔴 2.2 预测列缺失或无效 + +**日志证据：** +``` +2025-05-06 03:05:53,910 - OKXRegressionStrategy - WARNING - ⚠️ pred_upper 列全为 NaN，可能模型未加载成功 +2025-05-06 03:05:53,917 - OKXRegressionStrategy - DEBUG - &-s_close pred_upper pred_lower +0 0.0 NaN NaN +1 0.0 NaN NaN +2 0.0 NaN NaN +3 0.0 NaN NaN +4 0.0 NaN NaN +``` + +**后果：** +- `populate_entry_trend()` 中的 `valid_prediction = (~dataframe['&-s_close'].isna()) & (dataframe['&-s_close'] > 0.005)` 实际上只依赖常量 `0.0`； +- 所有做多信号仅由 RSI < 30 触发，与模型无关。 + +**官方文档参考：** +- [FreqAI Feature Engineering](https://www.freqtrade.io/en/stable/freqai-feature-engineering/)：必须确保目标列如 `&-s_close` 被正确识别并用于训练； +- [Custom Strategy](https://www.freqtrade.io/en/stable/strategy-customization/)：交易信号应基于有效预测值。 + +--- + +### 🔴 2.3 模型训练未持久化 + +**日志证据：** +``` +2025-05-06 03:04:43,510 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-OKB_1744329600/cb_okb_1744329600 +``` + +**后果：** +- 每次回测都重新训练模型，且未保存模型供后续使用； +- 导致无法复用已有模型进行稳定回测。 + +**建议：** +- 使用 `freqtrade train` 显式训练模型并保存； +- 在回测前确保模型已存在； +- 设置 `"purge_old_models": false` 保留历史模型。 + +--- + +## 🛠️ **3. 解决方案与代码修复** + +### ✅ **3.1 修改策略类名以匹配文件名** + +**问题：** +- 当前策略类名为 `OKXRegressionStrategy`，但文件名也为 `OKXRegressionStrategy.py`； +- 若从模板导入，需确保类名一致。 + +**修改建议：** + +Filepath: freqtrade/templates/OKXRegressionStrategy.py +Replace lines: 18-18 +```python +class OKXRegressionStrategy(IStrategy): +``` + +✅ 无需更改，当前命名已正确。 + +--- + +### ✅ **3.2 强制启用模型保存与加载** + +**问题：** +- 回测时未加载已有模型； +- 每次都重新训练，影响可重复性。 + +**修改建议：** + +Filepath: config_examples/config_freqai.okx.json +Replace lines: 62-68 +```json +"freqai": { + "enabled": true, + "identifier": "test175", + "freqaimodel": "XGBoostRegressor", + "save_backtesting_prediction": true, + "purge_old_models": false, + "load_trained_model": true, + "model_filename": "/freqtrade/user_data/models/test175/cb_okb_*.pkl" +``` + +📌 **说明：** +- 增加 `model_filename` 字段，明确指定模型路径； +- 确保模型能被正确加载用于预测。 + +--- + +### ✅ **3.3 补充模型训练命令以生成 `.pkl` 文件** + +**问题：** +- 当前直接运行回测会触发训练，但不会持久化模型； +- 应先显式训练模型再进行回测。 + +**解决方案：** + +```bash +# 先训练模型 +docker-compose run --rm freqtrade train --config config_examples/config_freqai.okx.json --freqaimodel XGBoostRegressor --strategy OKXRegressionStrategy + +# 再运行回测 +docker-compose run --rm freqtrade backtesting --config config_examples/config_freqai.okx.json --freqaimodel XGBoostRegressor --strategy OKXRegressionStrategy +``` + +📌 **说明：** +- 训练完成后会在 `/freqtrade/user_data/models/test175/` 下生成 `.pkl` 模型文件； +- 回测时将加载该模型进行预测。 + +--- + +### ✅ **3.4 确保 `set_freqai_targets()` 正确设置目标列** + +**问题：** +- 目标列 `&-s_close`, `&-roi_0_pred` 已定义； +- 但在某些情况下未被 FreqAI 正确识别。 + +**修改建议：** + +Filepath: freqtrade/templates/OKXRegressionStrategy.py +Replace lines: 0-0 +```python +def set_freqai_targets(self, dataframe: DataFrame, metadata: Dict) -> DataFrame: + # 设置回归目标 + label_period = self.freqai_config["feature_parameters"]["label_period_candles"] + dataframe["&-s_close"] = (dataframe["close"].shift(-label_period) - dataframe["close"]) / dataframe["close"] + + # 设置动态 ROI 和止损阈值 + dataframe["&-roi_0_pred"] = 0.03 # 默认值，防止空值 + dataframe["&-stoploss_pred"] = -0.05 + + return dataframe +``` + +📌 **说明：** +- 提供默认值避免空列； +- 确保列名与 `feature_engineering_expand_all()` 中的特征一致； +- 可进一步扩展为基于 ADX 的动态设定。 + +--- + +### ✅ **3.5 确保 `populate_entry_trend()` 使用模型预测值** + +**问题：** +- 当前 `valid_prediction` 条件过于宽松，仅判断 `&-s_close > 0.005`； +- 若模型未加载，此条件始终成立，导致信号仅由 RSI 控制。 + +**修改建议：** + +Filepath: freqtrade/templates/OKXRegressionStrategy.py +Replace lines: 365-365 +```python +valid_prediction = (~dataframe['&-s_close'].isna()) & (dataframe['&-s_close'] > 0.005) & (dataframe['&-s_close'].abs() > 0.001) +``` + +📌 **说明：** +- 添加 `abs() > 0.001` 过滤掉恒定为零的预测值； +- 确保只有当模型真正输出有意义数值时才生成信号。 + +--- + +## 📊 **4. 验证建议** + +请执行以下操作验证模型是否加载成功并参与预测： + +1. **运行训练命令生成模型：** + ```bash + docker-compose run --rm freqtrade train --config config_examples/config_freqai.okx.json --freqaimodel XGBoostRegressor --strategy OKXRegressionStrategy + ``` + +2. **查看模型是否生成：** + ```bash + ls -la /home/ubuntu/freqtrade/user_data/models/test175/ + ``` + 应看到类似 `cb_okb_*.pkl` 的模型文件。 + +3. **运行回测并检查预测列：** + ```bash + docker-compose run --rm freqtrade backtesting --config config_examples/config_freqai.okx.json --freqaimodel XGBoostRegressor --strategy OKXRegressionStrategy + ``` + +4. **打开 `result/backtest-result-*.json` 查看预测列：** + - 检查 `&-s_close`, `pred_upper`, `pred_lower` 是否随时间变化； + - 若仍为恒定值或全为 NaN，则说明模型仍未加载成功。 + +--- + +## ✅ **5. 总结** + +| 问题 | 是否解决 | 说明 | +|------|----------|------| +| 模型未加载 | ❌ | 缺少 `.pkl` 模型文件 | +| 预测列为 NaN | ❌ | 模型未加载导致预测失败 | +| 交易信号仅由 RSI 触发 | ❌ | `&-s_close` 恒定为 0 | +| 模型未持久化 | ❌ | 每次回测都重新训练 | +| 策略类名不一致 | ✅ | 类名与文件名一致 | + +--- + +## 📌 **下一步建议** + +请优先执行以下任意一项操作以继续诊断： + +1. **提供 `result/backtest-result-*.json` 中部分预测数据片段；** +2. **提供 `output_filted.log` 中关于模型加载和预测值的关键日志；** +3. **告知是否可以运行新的训练 + 回测流程并启用 `save_backtesting_prediction: true`。** + +这将帮助我们进一步确认模型是否加载成功以及预测值是否合理。 + +**Generation complete!** Please review the code suggestions above. + diff --git a/chat/result8.md b/chat/result8.md new file mode 100644 index 00000000..f1c25ed7 --- /dev/null +++ b/chat/result8.md @@ -0,0 +1,6 @@ +### 🛠️ 可能的改进方向 + +如果你希望进一步优化这个替代逻辑，可以考虑： +1. **引入更多技术指标**（如 MACD、布林带等）来增强模拟预测的智能性。 +2. **使用简单机器学习模型**（如线性回归）基于历史 RSI 和价格走势训练一个轻量级替代模型。 +3. **动态调整窗口大小**（rolling window），根据市场波动率自动调节平滑程度。 diff --git a/chat/roadmap.md b/chat/roadmap.md new file mode 100644 index 00000000..5e7f0621 --- /dev/null +++ b/chat/roadmap.md @@ -0,0 +1,68 @@ +> 根据当前问题, 制定一个优化路线图, 每次只完成一个功能点改动, 路线图只包含要优化的问题,和解决思路,不包含代码,请输出此路线图 +> + +### ✅ **OKXRegressionStrategy 优化路线图** + +| 步骤 | 待优化问题 | 解决思路 | +|------|------------|----------| +| 1 | **胜率低（33%–50%）** | 引入模型预测置信度过滤，仅在 `pred_upper - pred_lower > 0.02` 时允许交易，减少低质量信号。 | +| 2 | **退出逻辑单一（仅依赖 exit_signal）** | 增加回调止损（Chandelier Exit）和动态 ROI 结合使用，提升止盈/止损效率。 | +| 3 | **固定 ATR multiplier 不适应波动变化** | 使用历史 ATR 百分位动态调整 multiplier：高波动 → 更紧止损；低波动 → 更松止损。 | +| 4 | **缺乏市场状态识别（趋势 vs 震荡）** | 利用 ADX 判断市场状态，并据此调整 exit_signal 条件阈值，提高趋势跟踪能力。 | +| 5 | **特征工程维度不足** | 添加 BB Width、Volume Change、Trend Diff 等高阶特征，增强模型对价格行为的理解。 | +| 6 | **模型训练未启用交叉验证（CV）** | 启用 TimeSeriesSplit CV，提升模型稳定性与泛化能力。 | +| 7 | **回撤过大（最大达 7.341 USDT）** | 引入回调止损逻辑（callback stop loss），防止趋势中途反转造成大幅亏损。 | +| 8 | **无动态仓位管理** | 根据账户风险暴露和波动率动态调整 stake_amount，降低极端行情下的单笔损失。 | + +--- + +📌 **说明**： +- 每次只完成一个功能点改动，确保每次 backtest 变量唯一。 +- 每个改动后运行 backtest 并记录关键指标（胜率、平均盈利、最大回撤等）。 +- 若某项改动效果显著，可继续深入调参；若无效，则跳过或尝试替代方案。 + +是否需要我开始第一步，即“引入模型预测置信度过滤”？ + +------- + +- Datetime: 2025-05-05 17:37:56 + +- Model: _qwen3/qwen-plus-latest + +- Selected files: + - chat/report.md + - chat/report2.md + - freqtrade/templates/OKXRegressionStrategy.py + +> 根据路线图的内容描述,当前代码中的部分功能点是否要被删掉,如果需要,请在路线图中明确说明,否则新版代码将新旧混杂,难以维护 + +你提出了一个非常关键的问题：**当前代码中确实存在一些“新旧混杂”的功能点，如果不清理，将影响策略的可维护性和逻辑一致性。** + +--- + +## ✅ **确认需要删除的功能点（已在路线图中覆盖）** + +| 功能点 | 是否保留 | 说明 | +|--------|----------|------| +| `exit_signal` 基于固定 RSI 和预测值下降 | ❌ 删除 | 已被市场状态 + Chandelier Exit 替代 | +| `_dynamic_stop_loss` 方法 | ❌ 删除 | 已被 `custom_stoploss` + ATR 百分位替代 | +| `populate_exit_trend` 中硬编码 exit_signal | ❌ 删除 | 已由回调止损和动态 ROI 替代 | +| `check_data_freshness()` 简化版 | ❌ 删除 | 实际运行中依赖 Freqtrade 数据源质量，无需额外检查 | +| `confirm_trade_entry()` 中 OKX 数据验证 | ❌ 删除 | 同上，且 OKX 不是唯一数据来源 | +| `fetch_okx_order_book()` 注释掉的订单簿逻辑 | ✅ 保留（注释） | 可作为未来扩展参考 | +| `feature_engineering_expand_all` 中冗余缓存逻辑 | ✅ 保留 | 缓存机制仍有效，提升性能 | +| `fit()` 方法中的手动模型初始化 | ✅ 保留 | 与 FreqAI 兼容性良好 | + + +### ✅ **OKXRegressionStrategy 优化路线图** + +| 步骤 | 待优化问题 | 解决思路 | 是否需要删除旧代码 | +|------|------------|----------|------------------| +| 1 | **胜率低（33%–50%）** | 引入模型预测置信度过滤，仅在 `pred_upper - pred_lower > 0.02` 时允许交易，减少低质量信号。 | 否 | +| 2 | **退出逻辑单一（仅依赖 exit_signal）** | 增加回调止损（Chandelier Exit）和动态 ROI 结合使用，提升止盈/止损效率。 | 是（`exit_signal` 已被替代） | +| 3 | **固定 ATR multiplier 不适应波动变化** | 使用历史 ATR 百分位动态调整 multiplier：高波动 → 更紧止损；低波动 → 更松止损。 | 是（`_dynamic_stop_loss` 方法已废弃） | +| 4 | **缺乏市场状态识别（趋势 vs 震荡）** | 利用 ADX 判断市场状态，并据此调整 exit_signal 条件阈值，提高趋势跟踪能力。 | 否 | +| 5 | **特征工程维度不足** | 添加 BB Width、Volume Change、Trend Diff 等高阶特征，增强模型对价格行为的理解。 | 否 | +| 6 | **模型训练未启用交叉验证（CV）** | 启用 TimeSeriesSplit CV，提升模型稳定性与泛化能力。 | 否 | +| 7 | **回撤过大（最大达 7.341 USDT）** | 引入回调止损逻辑（callback stop loss），防止趋势中途反转造成大幅亏损。 | 是（原 `populate_exit_trend` 中硬编码 exit_signal 被替代） | +| 8 | **无动态仓位管理** | 根据账户风险暴露和波动率动态调整 stake_amount，降低极端行情下的单笔损失。 | 否 | diff --git a/code.txt b/code.txt new file mode 100644 index 00000000..8428e7e2 --- /dev/null +++ b/code.txt @@ -0,0 +1,101 @@ + FUNCTION set_freqai_targets(dataframe, metadata, config): + """ + 设置回归模型的目标变量，为不同币对设置动态止损和ROI阈值。 + 输入：dataframe（K线数据：close, high, low），metadata（交易对信息），config（FreqAI配置） + 输出：更新后的dataframe，包含目标标签 + """ + # 获取配置参数 + label_period = `config["feature_parameters"]`["label_period_candles"] # 标签预测周期（如5分钟K线的N根） + pair = `metadata["pair"]` # 当前交易对（如DOGE/USDT） + + # 计算未来价格变化率（现有逻辑） + SET `dataframe["&-s_close"]` = (`dataframe["close"]`.shift(-label_period) - `dataframe["close"]`) / `dataframe["close"]` + + # 计算不同时间窗口的ROI（现有逻辑） + FOR minutes IN [0, 15, 30]: + candles = INTEGER(minutes / 5) # 假设5分钟K线 + IF candles > 0: + SET `dataframe["&-roi_{minutes}"]` = (`dataframe["close"]`.shift(-candles) - `dataframe["close"]`) / `dataframe["close"]` + ELSE: + SET `dataframe["&-roi_{minutes}"]` = 0.0 + + # 计算市场状态指标：ADX（14周期，与label_period_candles对齐） + SET `dataframe["adx"]` = CALCULATE_ADX(`dataframe["high"]`, `dataframe["low"]`, `dataframe["close"]`, period=14) + + # 定义币对特定的ADX阈值和止损/ROI范围 + INITIALIZE pair_thresholds = { + "DOGE/USDT": { + "adx_trend": 20, # 趋势市场ADX阈值 + "adx_oscillation": 15, # 震荡市场ADX阈值 + "stoploss_trend": -0.08, # 趋势市场止损：-8% + "stoploss_oscillation": -0.04, # 震荡市场止损：-4% + "stoploss_mid": -0.06, # 中间状态止损：-6% + "roi_trend": 0.06, # 趋势市场ROI：6% + "roi_oscillation": 0.025, # 震荡市场ROI：2.5% + "roi_mid": 0.04 # 中间状态ROI：4% + }, + "BTC/USDT": { + "adx_trend": 25, + "adx_oscillation": 20, + "stoploss_trend": -0.03, + "stoploss_oscillation": -0.015, + "stoploss_mid": -0.02, + "roi_trend": 0.03, + "roi_oscillation": 0.015, + "roi_mid": 0.02 + }, + "SOL/USDT": { + "adx_trend": 22, + "adx_oscillation": 18, + "stoploss_trend": -0.06, + "stoploss_oscillation": -0.03, + "stoploss_mid": -0.045, + "roi_trend": 0.045, + "roi_oscillation": 0.02, + "roi_mid": 0.03 + }, + "XRP/USDT": { + "adx_trend": 22, + "adx_oscillation": 18, + "stoploss_trend": -0.06, + "stoploss_oscillation": -0.03, + "stoploss_mid": -0.045, + "roi_trend": 0.045, + "roi_oscillation": 0.02, + "roi_mid": 0.03 + } + } + + # 动态化 &-stoploss_pred（基于市场状态和币对） + INITIALIZE `dataframe["&-stoploss_pred"]` = 0.0 + FOR EACH row IN dataframe: + thresholds = `pair_thresholds[pair]` # 获取当前币对的阈值 + IF `row["adx"]` > `thresholds["adx_trend"]`: # 趋势市场 + SET `row["&-stoploss_pred"]` = `thresholds["stoploss_trend"]` # 宽松止损 + ELSE IF `row["adx"]` < `thresholds["adx_oscillation"]`: # 震荡市场 + SET `row["&-stoploss_pred"]` = `thresholds["stoploss_oscillation"]` # 严格止损 + ELSE: # 中间状态 + SET `row["&-stoploss_pred"]` = `thresholds["stoploss_mid"]` # 中等止损 + # 风险控制：设置止损下限 + IF `row["&-stoploss_pred"]` < -0.10: # 防止过大止损 + SET `row["&-stoploss_pred"]` = -0.10 + + # 动态化 &-roi_0_pred（基于市场趋势和币对） + INITIALIZE `dataframe["&-roi_0_pred"]` = 0.0 + FOR EACH row IN dataframe: + thresholds = `pair_thresholds[pair]` # 获取当前币对的阈值 + IF `row["adx"]` > `thresholds["adx_trend"]`: # 强趋势市场 + SET `row["&-roi_0_pred"]` = `thresholds["roi_trend"]` # 高ROI + ELSE IF `row["adx"]` < `thresholds["adx_oscillation"]`: # 震荡市场 + SET `row["&-roi_0_pred"]` = `thresholds["roi_oscillation"]` # 低ROI + ELSE: # 中间状态 + SET `row["&-roi_0_pred"]` = `thresholds["roi_mid"]` # 中等ROI + # 风险控制：设置ROI上限 + IF `row["&-roi_0_pred"]` > 0.10: # 防止过高目标 + SET `row["&-roi_0_pred"]` = 0.10 + + # 计算RSI预测（现有逻辑） + SET `dataframe["&-buy_rsi_pred"]` = CALCULATE_RSI(`dataframe["close"]`, period=14).ROLLING_MEAN(window=20) + + RETURN dataframe + diff --git a/config_examples/8f4c374e6b1b993b493d29202dbf28e6b59ccf61-4e7e5f23638ea53874c913e30bcc979e82d49b45.diff b/config_examples/8f4c374e6b1b993b493d29202dbf28e6b59ccf61-4e7e5f23638ea53874c913e30bcc979e82d49b45.diff new file mode 100644 index 00000000..20707720 --- /dev/null +++ b/config_examples/8f4c374e6b1b993b493d29202dbf28e6b59ccf61-4e7e5f23638ea53874c913e30bcc979e82d49b45.diff @@ -0,0 +1,121 @@ +diff --git a/config_examples/config_freqai.okx.json b/config_examples/config_freqai.okx.json +index 259459e..c2693fc 100644 +--- a/config_examples/config_freqai.okx.json ++++ b/config_examples/config_freqai.okx.json +@@ -5,11 +5,10 @@ + "max_open_trades": 4, + "stake_currency": "USDT", + "stake_amount": 150, +- "startup_candle_count": 30, + "tradable_balance_ratio": 1, + "fiat_display_currency": "USD", + "dry_run": true, +- "timeframe": "5m", ++ "timeframe": "3m", + "dry_run_wallet": 1000, + "cancel_open_orders_on_exit": true, + "stoploss": -0.05, +@@ -24,21 +23,21 @@ + "enable_ws": false, + "ccxt_config": { + "enableRateLimit": true, +- "rateLimit": 800, ++ "rateLimit": 500, + "options": { + "defaultType": "spot" + } + }, + "ccxt_async_config": { + "enableRateLimit": true, +- "rateLimit": 800, ++ "rateLimit": 500, + "timeout": 20000 + }, + "pair_whitelist": [ +- "OKB/USDT", +- "DOT/USDT", ++ "BTC/USDT", + "SOL/USDT" +- ] ++ ], ++ "pair_blacklist": [] + }, + "entry_pricing": { + "price_side": "same", +@@ -65,47 +64,37 @@ + "data_kitchen": { + "fillna": "ffill" + }, +- "freqaimodel": "CatboostClassifier", +- "purge_old_models": 2, +- "identifier": "test175", +- "train_period_days": 30, +- "backtest_period_days": 10, ++ "freqaimodel": "XGBoostRegressor", ++ "model_training_parameters": { ++ "n_estimators": 100, ++ "learning_rate": 0.05, ++ "max_depth": 5 ++ }, ++ "train_period_days": 180, ++ "backtest_period_days": 60, + "live_retrain_hours": 0, + "feature_selection": { + "method": "recursive_elimination" + }, + "feature_parameters": { +- "include_timeframes": [ +- "5m", +- "1h" +- ], +- "include_corr_pairlist": [ +- "BTC/USDT", +- "ETH/USDT" +- ], +- "label_period_candles": 12, +- "include_shifted_candles": 3, +- "DI_threshold": 0.9, ++ "include_timeframes": ["15m"], ++ "include_corr_pairlist": ["BTC/USDT"], ++ "label_period_candles": 10, ++ "include_shifted_candles": 1, ++ + "weight_factor": 0.9, + "principal_component_analysis": false, + "use_SVM_to_remove_outliers": false, +- "indicator_periods_candles": [ +- 10, +- 20, +- 50 +- ], +- "plot_feature_importances": 0 ++ "indicator_periods_candles": [14], + }, + "data_split_parameters": { +- "test_size": 0.2, +- "shuffle": false, ++ "test_size": 0.2 + }, +- "model_training_parameters": { +- "n_estimators": 100, +- "learning_rate": 0.1, +- "num_leaves": 15, +- "verbose": -1 +- } ++ "model_training_parameters": { ++ "n_estimators": 100, ++ "learning_rate": 0.05, ++ "max_depth": 5 ++ } + }, + "api_server": { + "enabled": true, +@@ -123,7 +112,7 @@ + "initial_state": "running", + "force_entry_enable": false, + "internals": { +- "process_throttle_secs": 10, ++ "process_throttle_secs": 5, + "heartbeat_interval": 20, + "loglevel": "DEBUG" + } diff --git a/config_examples/aienhance_config.json b/config_examples/aienhance_config.json new file mode 100644 index 00000000..af253ca6 --- /dev/null +++ b/config_examples/aienhance_config.json @@ -0,0 +1,105 @@ +{ + "max_open_trades": 3, + "stake_currency": "USDT", + "stake_amount": 150, + "startup_candle_count": 30, + "tradable_balance_ratio": 1, + "fiat_display_currency": "USD", + "dry_run": true, + "timeframe": "3m", + "dry_run_wallet": 1000, + "cancel_open_orders_on_exit": true, + "stoploss": -0.05, + "unfilledtimeout": { + "entry": 5, + "exit": 15 + }, + "timeframe": "5m", + "exchange": { + "name": "okx", + "key": "your_api_key", + "secret": "your_api_secret", + "password": "your_api_password", + "type": "spot", + "enable_ws": false, + "ccxt_config": { + "enableRateLimit": true, + "rateLimit": 500, + "options": { + "defaultType": "spot" + } + }, + "ccxt_async_config": { + "enableRateLimit": true, + "rateLimit": 500, + "timeout": 20000 + }, + "pair_whitelist": [ + "BTC/USDT", + "SOL/USDT" + ], + "pair_blacklist": [] + }, + "entry_pricing": { + "price_side": "same", + "use_order_book": true, + "order_book_top": 1, + "price_last_balance": 0.0, + "check_depth_of_market": { + "enabled": false, + "bids_to_ask_delta": 1 + } + }, + "exit_pricing": { + "price_side": "other", + "use_order_book": true, + "order_book_top": 1 + }, + "pairlists": [ + { + "method": "StaticPairList" + } + ], + "strategy": "AIEnhancedStrategy", + "freqai": { + "enabled": true, + "live_retrain_hours": 1, + "data_kitchen_path": "freqai/data_kitchen/", + "purge_old_data_seconds": 86400, + "feature_parameters": { + "include_timeframes": ["5m", "15m", "1h"], + "include_corr_pairlist": ["BTC/USDT", "ETH/USDT"], + "include_shifted_candles": 2, + "indicator_periods_candles": [10, 20, 50], + "plot_feature_importances": 1, + "DI_threshold": 0.85, + "label_period_candles": 20, + "include_volume_data": true, + "include_bidirectional_training_data": true + }, + "data_split_parameters": { + "test_size": 0.2, + "shuffle": true, + "random_state": 42 + }, + "model_training_parameters": { + "n_estimators": 200, + "learning_rate": 0.05, + "max_depth": 5, + "subsample": 0.8, + "colsample_bytree": 0.8, + "objective": "reg:squarederror", + "eval_metric": "rmse", + "early_stopping_rounds": 50, + "verbose": 0 + } + }, + "dry_run": true, + "dry_run_wallet": 1000, + "cancel_open_orders_on_exit": false, + "internals": { + "process_only_new_candles": true + } +} + + diff --git a/config_examples/basic.json b/config_examples/basic.json new file mode 100644 index 00000000..0b12b7b9 --- /dev/null +++ b/config_examples/basic.json @@ -0,0 +1,126 @@ +{ + "$schema": "https://schema.freqtrade.io/schema.json", + "trading_mode": "spot", + "margin_mode": "isolated", + "max_open_trades": 4, + "stake_currency": "USDT", + "stake_amount": 150, + "startup_candle_count": 30, + "tradable_balance_ratio": 1, + "fiat_display_currency": "USD", + "dry_run": true, + "timeframe": "3m", + "dry_run_wallet": 1000, + "cancel_open_orders_on_exit": true, + "stoploss": -0.05, + "unfilledtimeout": { + "entry": 5, + "exit": 15 + }, + "exchange": { + "name": "okx", + "key": "eca767d4-fda5-4a1b-bb28-49ae18093307", + "secret": "8CA3628A556ED137977DB298D37BC7F3", + "enable_ws": false, + "ccxt_config": { + "enableRateLimit": true, + "rateLimit": 500, + "options": { + "defaultType": "spot" + } + }, + "ccxt_async_config": { + "enableRateLimit": true, + "rateLimit": 500, + "timeout": 20000 + }, + "pair_whitelist": [ + "BTC/USDT", + "SOL/USDT" + ], + "pair_blacklist": [] + }, + "entry_pricing": { + "price_side": "same", + "use_order_book": true, + "order_book_top": 1, + "price_last_balance": 0.0, + "check_depth_of_market": { + "enabled": false, + "bids_to_ask_delta": 1 + } + }, + "exit_pricing": { + "price_side": "other", + "use_order_book": true, + "order_book_top": 1 + }, + "pairlists": [ + { + "method": "StaticPairList" + } + ], + "freqai": { + "enabled": true, + "data_kitchen": { + "fillna": "ffill", + "feature_parameters": { + "DI_threshold": 0.9, + "weight_factor": 0.9 + } + }, + "freqaimodel": "XGBoostRegressor", + "purge_old_models": 2, + "identifier": "test175", + "train_period_days": 30, + "backtest_period_days": 10, + "live_retrain_hours": 0, + "feature_selection": { + "method": "recursive_elimination", + "threshold": 0.01 + }, + "feature_parameters": { + "include_timeframes": ["5m", "1h"], + "include_corr_pairlist": ["BTC/USDT"], + "label_period_candles": 10, + "use_SVM_to_remove_outliers": true, + "principal_component_analysis": true + }, + "model": "XGBoostRegressor", + "data_split_parameters": { + "test_size": 0.2, + "shuffle": true, + "random_state": 42 + }, + "model_training_parameters": { + "n_estimators": 200, + "learning_rate": 0.05, + "max_depth": 5, + "subsample": 0.8, + "colsample_bytree": 0.8, + "objective": "reg:squarederror", + "eval_metric": "rmse", + "early_stopping_rounds": 50 + } + }, + "api_server": { + "enabled": true, + "listen_ip_address": "0.0.0.0", + "listen_port": 8080, + "verbosity": "error", + "enable_openapi": false, + "jwt_secret_key": "6a599ab046dbb419014807dffd7b8823bfa7e5df56b17d545485deb87331b4ca", + "ws_token": "6O5pBDiRigiZrmIsofaE2rkKMJtf9h8zVQ", + "CORS_origins": [], + "username": "freqAdmin", + "password": "admin" + }, + "bot_name": "freqtrade", + "initial_state": "running", + "force_entry_enable": false, + "internals": { + "process_throttle_secs": 5, + "heartbeat_interval": 20, + "loglevel": "DEBUG" + } +} diff --git a/config_examples/config_base_hyperopt.json b/config_examples/config_base_hyperopt.json new file mode 100644 index 00000000..ab47ffde --- /dev/null +++ b/config_examples/config_base_hyperopt.json @@ -0,0 +1,64 @@ +{ + "strategy": "MyStrategy", + "timeframe": "5m", + "dry_run": true, + "stake_currency": "USDT", + "stake_amount": 10.0, + "minimal_roi": { + "40": 0.0, + "30": 0.01, + "20": 0.02, + "0": 0.04 + }, + "stoploss": -0.10, + "trailing_stop": false, + "trailing_stop_positive": 0.0, + "trailing_stop_positive_offset": 0.0, + "trailing_only_offset_is_reached": 0.0, + "unfilledtimeout": { + "buy": 300, + "sell": 300 + }, + "exchange": { + "name": "binance", + "key": "", + "secret": "", + "ccxt_config": { + "enableRateLimit": true + }, + "pair_whitelist": [ + "BTC/USDT", + "ETH/USDT", + "SOL/USDT" + ], + "pair_blacklist": [] + }, + "telegram": { + "enabled": false, + "token": "", + "chat_id": "" + }, + "api_server": { + "enabled": false, + "listen_ip_address": "127.0.0.1", + "listen_port": 8080, + "verbosity": "error", + "enable_openapi": false + }, + "hyperopt": { + "enabled": false, + "epochs": 100, + "spaces": [ + "buy", + "sell", + "roi", + "stoploss", + "trailing" + ], + "hyperopt_path": "", + "hyperopt_loss": "SharpeHyperOptLossDaily", + "print_all": false, + "mongodb_url": "", + "mongodb_database": "" + } +} diff --git a/config_examples/config_bianace.json b/config_examples/config_bianace.json new file mode 100644 index 00000000..baf015d3 --- /dev/null +++ b/config_examples/config_bianace.json @@ -0,0 +1,72 @@ +{ + "$schema": "https://schema.freqtrade.io/schema.json", + "max_open_trades": 3, + "stake_currency": "USDT", + "stake_amount": 0.05, + "tradable_balance_ratio": 0.99, + "fiat_display_currency": "USD", + "timeframe": "5m", + "dry_run": true, + "cancel_open_orders_on_exit": false, + "unfilledtimeout": { + "entry": 10, + "exit": 10, + "exit_timeout_count": 0, + "unit": "minutes" + }, + "entry_pricing": { + "price_side": "same", + "use_order_book": true, + "order_book_top": 1, + "price_last_balance": 0.0, + "check_depth_of_market": { + "enabled": false, + "bids_to_ask_delta": 1 + } + }, + "exit_pricing": { + "price_side": "same", + "use_order_book": true, + "order_book_top": 1 + }, + "exchange": { + "name": "binance", + "key": "your_exchange_key", + "secret": "your_exchange_secret", + "ccxt_config": {}, + "ccxt_async_config": { + }, + "pair_whitelist": [ + "ETH/USDT", + "XRP/USDT", + "BTC/USDT" + ], + "pair_blacklist": [ + "BNB/.*" + ] + }, + "pairlists": [ + {"method": "StaticPairList"} + ], + "telegram": { + "enabled": false, + "token": "your_telegram_token", + "chat_id": "your_telegram_chat_id" + }, + "api_server": { + "enabled": false, + "listen_ip_address": "127.0.0.1", + "listen_port": 8080, + "verbosity": "error", + "jwt_secret_key": "somethingrandom", + "CORS_origins": [], + "username": "freqtrader", + "password": "SuperSecurePassword" + }, + "bot_name": "freqtrade", + "initial_state": "running", + "force_entry_enable": false, + "internals": { + "process_throttle_secs": 5 + } +} diff --git a/config_examples/config_freqai.okx.json b/config_examples/config_freqai.okx.json new file mode 100644 index 00000000..8d274d2e --- /dev/null +++ b/config_examples/config_freqai.okx.json @@ -0,0 +1,128 @@ +{ + "$schema": "https://schema.freqtrade.io/schema.json", + "trading_mode": "spot", + "margin_mode": "isolated", + "max_open_trades": 4, + "stake_currency": "USDT", + "stake_amount": 150, + "startup_candle_count": 30, + "tradable_balance_ratio": 1, + "fiat_display_currency": "USD", + "dry_run": true, + "timeframe": "3m", + "dry_run_wallet": 1000, + "cancel_open_orders_on_exit": true, + "stoploss": -0.05, + "use_exit_signal": true, + "unfilledtimeout": { + "entry": 5, + "exit": 15 + }, + "exchange": { + "name": "okx", + "key": "eca767d4-fda5-4a1b-bb28-49ae18093307", + "secret": "8CA3628A556ED137977DB298D37BC7F3", + "enable_ws": false, + "ccxt_config": { + "enableRateLimit": true, + "rateLimit": 500, + "options": { + "defaultType": "spot" + } + }, + "ccxt_async_config": { + "enableRateLimit": true, + "rateLimit": 500, + "timeout": 20000 + }, + "pair_whitelist": [ + "OKB/USDT" + ], + "pair_blacklist": [] + }, + "entry_pricing": { + "price_side": "same", + "use_order_book": true, + "order_book_top": 1, + "price_last_balance": 0.0, + "check_depth_of_market": { + "enabled": false, + "bids_to_ask_delta": 1 + } + }, + "exit_pricing": { + "price_side": "other", + "use_order_book": true, + "order_book_top": 1 + }, + "pairlists": [ + { + "method": "StaticPairList" + } + ], + "freqai": { + "enabled": true, + "identifier": "test175", + "freqaimodel": "XGBoostRegressor", + "model_path": "/freqtrade/user_data/models", + "save_backtesting_prediction": true, + "purge_old_models": true, + "load_trained_model": true, + "train_period_days": 90, + "backtest_period_days": 10, + "live_retrain_hours": 0, + "include_predictions_in_final_dataframe": true, + "data_kitchen": { + "fillna": "ffill", + "feature_parameters": { + "DI_threshold": 0.5, + "weight_factor": 0.9 + } + }, + "feature_parameters": { + "include_timeframes": ["5m", "15m", "1h"], + "include_corr_pairlist": ["BTC/USDT", "ETH/USDT"], + "label_period_candles": 12, + "include_shifted_candles": 3, + "indicator_periods_candles": [10, 20, 50], + "plot_feature_importances": 1, + "feature_selection": { + "method": "none" + } + }, + "data_split_parameters": { + "test_size": 0.2, + "shuffle": false, + "random_state": 42 + }, + "model_training_parameters": { + "n_estimators": 200, + "learning_rate": 0.05, + "max_depth": 6, + "subsample": 0.8, + "colsample_bytree": 0.8, + "reg_alpha": 0.1, + "reg_lambda": 1.0 + }, + }, + "api_server": { + "enabled": true, + "listen_ip_address": "0.0.0.0", + "listen_port": 8080, + "verbosity": "error", + "enable_openapi": false, + "jwt_secret_key": "6a599ab046dbb419014807dffd7b8823bfa7e5df56b17d545485deb87331b4ca", + "ws_token": "6O5pBDiRigiZrmIsofaE2rkKMJtf9h8zVQ", + "CORS_origins": [], + "username": "freqAdmin", + "password": "admin" + }, + "bot_name": "freqtrade", + "initial_state": "running", + "force_entry_enable": false, + "internals": { + "process_throttle_secs": 5, + "heartbeat_interval": 20, + "loglevel": "DEBUG" + } +} diff --git a/config_examples/config_my_hyperopt.json b/config_examples/config_my_hyperopt.json new file mode 100644 index 00000000..53d49d3f --- /dev/null +++ b/config_examples/config_my_hyperopt.json @@ -0,0 +1,133 @@ +{ + "$schema": "https://schema.freqtrade.io/schema.json", + "trading_mode": "spot", + "margin_mode": "isolated", + "max_open_trades": 4, + "stake_currency": "USDT", + "stake_amount": 150, + "startup_candle_count": 30, + "tradable_balance_ratio": 1, + "fiat_display_currency": "USD", + "dry_run": true, + "identifier": "demo1", + "timeframe": "5m", + "dry_run_wallet": 1000, + "cancel_open_orders_on_exit": true, + "stoploss": -0.05, + "unfilledtimeout": { + "entry": 5, + "exit": 15 + }, + "exchange": { + "name": "okx", + "key": "eca767d4-fda5-4a1b-bb28-49ae18093307", + "secret": "8CA3628A556ED137977DB298D37BC7F3", + "enable_ws": false, + "ccxt_config": { + "enableRateLimit": true, + "rateLimit": 500, + "options": { + "defaultType": "spot" + } + }, + "ccxt_async_config": { + "enableRateLimit": true, + "rateLimit": 500, + "timeout": 20000 + }, + "pair_whitelist": [ + "OKB/USDT", + "BTC/USDT", + "SOL/USDT", + "DOT/USDT", + "TON/USDT", + "ETH/USDT", + ], + "pair_blacklist": [] + }, + "freqai": { + "enabled": true, + "identifier": "test175", + "freqaimodel": "XGBoostRegressor", + "model_path": "/freqtrade/user_data/models", + "save_backtesting_prediction": true, + "save_backtest_models": true, + "backtest_period_days": 30, + "purge_old_models": true, + "load_trained_model": true, + "train_period_days": 90, + "backtest_period_days": 10, + "live_retrain_hours": 0, + "include_predictions_in_final_dataframe": true, + "data_kitchen": { + "fillna": "ffill", + "feature_parameters": { + "DI_threshold": 0.5, + "weight_factor": 0.9 + } + }, + "feature_parameters": { + "include_timeframes": ["5m", "15m", "1h"], + "include_corr_pairlist": ["BTC/USDT", "ETH/USDT"], + "label_period_candles": 12, + "include_shifted_candles": 3, + "indicator_periods_candles": [10, 20, 50], + "plot_feature_importances": 1, + "feature_selection": { + "method": "none" + } + }, + "data_split_parameters": { + "test_size": 0.2, + "shuffle": false + }, + "model_training_parameters": { + "n_estimators": 200, + "learning_rate": 0.05, + "max_depth": 6, + "subsample": 0.8, + "colsample_bytree": 0.8 + }, + }, + "entry_pricing": { + "price_side": "same", + "use_order_book": true, + "order_book_top": 1, + "price_last_balance": 0.0, + "check_depth_of_market": { + "enabled": false, + "bids_to_ask_delta": 1 + } + }, + "exit_pricing": { + "price_side": "other", + "use_order_book": true, + "order_book_top": 1 + }, + "pairlists": [ + { + "method": "StaticPairList" + } + ], + "api_server": { + "enabled": true, + "listen_ip_address": "0.0.0.0", + "listen_port": 8080, + "verbosity": "error", + "enable_openapi": false, + "jwt_secret_key": "6a599ab046dbb419014807dffd7b8823bfa7e5df56b17d545485deb87331b4ca", + "ws_token": "6O5pBDiRigiZrmIsofaE2rkKMJtf9h8zVQ", + "CORS_origins": [], + "username": "freqAdmin", + "password": "admin" + }, + "use_exit_signal": true, + "bot_name": "freqtrade", + "initial_state": "running", + "force_entry_enable": false, + "internals": { + "process_throttle_secs": 5, + "heartbeat_interval": 20, + "loglevel": "DEBUG" + } +} diff --git a/config_examples/freqaiprimer.json b/config_examples/freqaiprimer.json new file mode 100644 index 00000000..8ef9be38 --- /dev/null +++ b/config_examples/freqaiprimer.json @@ -0,0 +1,134 @@ +{ + "$schema": "https://schema.freqtrade.io/schema.json", + "trading_mode": "spot", + "margin_mode": "isolated", + "max_open_trades": 4, + "stake_currency": "USDT", + "stake_amount": 150, + "tradable_balance_ratio": 1, + "fiat_display_currency": "USD", + "dry_run": true, + "timeframe": "3m", + "dry_run_wallet": 1000, + "cancel_open_orders_on_exit": true, + "stoploss": -0.05, + "unfilledtimeout": { + "entry": 5, + "exit": 15 + }, + "exchange": { + "name": "okx", + "key": "eca767d4-fda5-4a1b-bb28-49ae18093307", + "secret": "8CA3628A556ED137977DB298D37BC7F3", + "enable_ws": false, + "ccxt_config": { + "enableRateLimit": true, + "rateLimit": 500, + "options": { + "defaultType": "spot" + } + }, + "ccxt_async_config": { + "enableRateLimit": true, + "rateLimit": 500, + "timeout": 20000 + }, + "pair_whitelist": [ + "BTC/USDT", + "ETH/USDT", + "TON/USDT", + "OKB/USDT", + "DOT/USDT", + "SOL/USDT" + ], + "pair_blacklist": [] + }, + "entry_pricing": { + "price_side": "same", + "use_order_book": true, + "order_book_top": 1, + "price_last_balance": 0.0, + "check_depth_of_market": { + "enabled": false, + "bids_to_ask_delta": 1 + } + }, + "exit_pricing": { + "price_side": "other", + "use_order_book": true, + "order_book_top": 1 + }, + "pairlists": [ + { + "method": "StaticPairList" + } + ], + "freqai": { + "enabled": true, + "data_kitchen": { + "fillna": "ffill" + }, + "freqaimodel": "CatboostClassifier", + "purge_old_models": 2, + "train_period_days": 15, + "identifier": "test58", + "train_period_days": 30, + "backtest_period_days": 10, + "live_retrain_hours": 0, + "feature_selection": { + "method": "recursive_elimination" + }, + "feature_parameters": { + "include_timeframes": [ + "3m", + "15m", + "1h" + ], + "include_corr_pairlist": [ + "BTC/USDT", + "SOL/USDT" + ], + "label_period_candles": 20, + "include_shifted_candles": 2, + "DI_threshold": 0.9, + "weight_factor": 0.9, + "principal_component_analysis": false, + "use_SVM_to_remove_outliers": false, + "indicator_periods_candles": [ + 10, + 20, + 50 + ], + "plot_feature_importances": 0 + }, + "data_split_parameters": { + "test_size": 0.2 + }, + "model_training_parameters": { + "n_estimators": 100, + "learning_rate": 0.05, + "max_depth": 5, + "num_leaves": 31 + } + }, + "api_server": { + "enabled": true, + "listen_ip_address": "0.0.0.0", + "listen_port": 8080, + "verbosity": "error", + "enable_openapi": false, + "jwt_secret_key": "6a599ab046dbb419014807dffd7b8823bfa7e5df56b17d545485deb87331b4ca", + "ws_token": "6O5pBDiRigiZrmIsofaE2rkKMJtf9h8zVQ", + "CORS_origins": [], + "username": "freqAdmin", + "password": "admin" + }, + "bot_name": "freqtrade", + "initial_state": "running", + "force_entry_enable": false, + "internals": { + "process_throttle_secs": 5, + "heartbeat_interval": 20, + "loglevel": "DEBUG" + } +} diff --git a/config_examples/ml_config.json b/config_examples/ml_config.json new file mode 100644 index 00000000..f8c103a7 --- /dev/null +++ b/config_examples/ml_config.json @@ -0,0 +1,127 @@ +{ + "$schema": "https://schema.freqtrade.io/schema.json", + "trading_mode": "spot", + "margin_mode": "isolated", + "max_open_trades": 4, + "stake_currency": "USDT", + "stake_amount": 150, + "startup_candle_count": 30, + "tradable_balance_ratio": 1, + "fiat_display_currency": "USD", + "dry_run": true, + "timeframe": "3m", + "dry_run_wallet": 1000, + "cancel_open_orders_on_exit": true, + "stoploss": -0.05, + "unfilledtimeout": { + "entry": 5, + "exit": 15 + }, + "exchange": { + "name": "okx", + "key": "eca767d4-fda5-4a1b-bb28-49ae18093307", + "secret": "8CA3628A556ED137977DB298D37BC7F3", + "enable_ws": false, + "ccxt_config": { + "enableRateLimit": true, + "rateLimit": 500, + "options": { + "defaultType": "spot" + } + }, + "ccxt_async_config": { + "enableRateLimit": true, + "rateLimit": 500, + "timeout": 20000 + }, + "pair_whitelist": [ + "BTC/USDT", + "SOL/USDT" + ], + "pair_blacklist": [] + }, + "entry_pricing": { + "price_side": "same", + "use_order_book": true, + "order_book_top": 1, + "price_last_balance": 0.0, + "check_depth_of_market": { + "enabled": false, + "bids_to_ask_delta": 1 + } + }, + "exit_pricing": { + "price_side": "other", + "use_order_book": true, + "order_book_top": 1 + }, + "pairlists": [ + { + "method": "StaticPairList" + } + ], + "freqai": { + "enabled": true, + "data_kitchen": { + "fillna": "ffill", + "feature_parameters": { + "DI_threshold": 0.9, + "weight_factor": 0.9 + } + }, + "freqaimodel": "XGBoostRegressor", + "purge_old_models": 2, + "identifier": "test175", + "train_period_days": 30, + "backtest_period_days": 10, + "live_retrain_hours": 0, + "feature_selection": { + "method": "recursive_elimination", + "threshold": 0.01 + }, + "feature_parameters": { + "include_timeframes": ["3m", "5m", "1h"], + "include_corr_pairlist": ["BTC/USDT", "ETH/USDT"], + "label_period_candles": 12, + "include_shifted_candles": 3, + "indicator_periods_candles": [10, 20, 50], + "plot_feature_importances": 1 + }, + "data_split_parameters": { + "test_size": 0.2, + "shuffle": true, + "random_state": 42 + }, + "model_training_parameters": { + "n_estimators": 200, + "learning_rate": 0.05, + "max_depth": 5, + "subsample": 0.8, + "colsample_bytree": 0.8, + "objective": "reg:squarederror", + "eval_metric": "rmse", + "early_stopping_rounds": 50, + "verbose": 0 + } + }, + "api_server": { + "enabled": true, + "listen_ip_address": "0.0.0.0", + "listen_port": 8080, + "verbosity": "error", + "enable_openapi": false, + "jwt_secret_key": "6a599ab046dbb419014807dffd7b8823bfa7e5df56b17d545485deb87331b4ca", + "ws_token": "6O5pBDiRigiZrmIsofaE2rkKMJtf9h8zVQ", + "CORS_origins": [], + "username": "freqAdmin", + "password": "admin" + }, + "bot_name": "freqtrade", + "initial_state": "running", + "force_entry_enable": false, + "internals": { + "process_throttle_secs": 5, + "heartbeat_interval": 20, + "loglevel": "DEBUG" + } +} diff --git a/config_examples/nb.json b/config_examples/nb.json new file mode 100644 index 00000000..946867ae --- /dev/null +++ b/config_examples/nb.json @@ -0,0 +1,95 @@ +{ + "strategy": "TheForceFreqaiStrategy", + "timeframe": "5m", + "timerange": "20240701-20250115", + "exchange": { + "name": "okx", + "ccxt_config": { + "enableRateLimit": true, + "rateLimit": 500, + "options": {"defaultType": "spot"}, + "timeout": 20000 + }, + "pair_whitelist": [ + "OKB/USDT" + ], + "fee": 0.0008 + }, + "pair_whitelist": ["OKB/USDT"], + "dataformat_ohlcv": "feather", + "download_data": { + "timeframes": ["5m"], + "timerange": "20240701-20250115" + }, + "stake_currency": "USDT", + "stake_amount": 150, + "stoploss": -0.15, + "minimal_roi": { + "0": 0.05, + "60": 0.03, + "120": 0.01 + }, + "startup_candle_count": 200, + "max_open_trades": 4, + "use_exit_signal": true, + "unfilledtimeout": { + "entry": 5, + "exit": 15, + "unit": "minutes" + }, + "export": "trades", + "cache": "none", + "loglevel": "DEBUG", + "verbosity": 2, + "entry_pricing": { + "price_side": "same", + "use_order_book": true, + "order_book_top": 1, + "price_last_balance": 0.0, + "check_depth_of_market": { + "enabled": false, + "bids_to_ask_delta": 1 + } + }, + "exit_pricing": { + "price_side": "other", + "use_order_book": true, + "order_book_top": 1 + }, + "pairlists": [ + { + "method": "StaticPairList" + } + ], + "freqai": { + "enabled": true, + "identifier": "theforce_model", + "save_backtest_models": true, + "live_retrain": true, + "purge_old_models": true, + "fit_live_predictions_candles": 50, + "force_train": true, + "verbose": 2, + "train_period_days": 7, + "backtest_period_days": 2, + "feature_parameters": { + "include_timeframes": ["5m"], + "include_corr_pairlist": [], + "label_period_candles": 5, + "include_shifted_candles": 2, + "DI_threshold": 1.5, + "indicator_periods_candles": [10, 20, 50], + "include_default_features": ["open", "high", "low", "close", "volume"], + "use_SVM_to_remove_outliers": false + }, + "data_split_parameters": { + "test_size": 0.2, + "random_state": 42 + }, + "model_training_parameters": { + "n_estimators": 100, + "max_depth": 7, + "verbose": -1 + } + } +} diff --git a/config_examples/theforcev7.json b/config_examples/theforcev7.json new file mode 100644 index 00000000..1104e5a1 --- /dev/null +++ b/config_examples/theforcev7.json @@ -0,0 +1,96 @@ +{ + "$schema": "https://schema.freqtrade.io/schema.json", + "trading_mode": "spot", + "margin_mode": "isolated", + "max_open_trades": 3, + "stake_amount": 300, + "unfilledtimeout": { + "entry": 10, + "exit": 20 + }, + "entry_pricing": { + "price_side": "same", + "use_order_book": true, + "order_book_top": 1 + }, + "exit_pricing": { + "price_side": "other", + "use_order_book": true, + "order_book_top": 1 + }, + "stake_currency": "USDT", + "trailing_stop": false, + "use_custom_stoploss": true, + "startup_candle_count": 200, + "tradable_balance_ratio": 1, + "fiat_display_currency": "USD", + "dry_run": true, + "identifier": "demo1", + "timeframe": "5m", + "dry_run_wallet": 1000, + "cancel_open_orders_on_exit": true, + "stoploss": -0.061, + "roi": {}, + "trailing": { + "trailing_stop": false, + "trailing_stop_positive": null, + "trailing_stop_positive_offset": 0.0, + "trailing_only_offset_is_reached": false + }, + "max_open_trades": 3, + "buy": { + "adx_buy": 25, + "atr_ratio": 0.005 + }, + "sell": { + "ema_fast_period": 7, + "rsi_sell": 60 + }, + "exchange": { + "name": "okx", + "key": "REDACTED", + "secret": "REDACTED", + "enable_ws": false, + "ccxt_config": { + "enableRateLimit": true, + "rateLimit": 500, + "options": { + "defaultType": "spot" + } + }, + "ccxt_async_config": { + "enableRateLimit": true, + "rateLimit": 3000, + "timeout": 20000 + }, + "pair_whitelist": ["BTC/USDT", "ETH/USDT", "SOL/USDT", "DOT/USDT"], + "pair_blacklist": [] + }, + "pairlists": [ + { + "method": "StaticPairList" + } + ], + "api_server": { + "enabled": true, + "listen_ip_address": "0.0.0.0", + "listen_port": 8080, + "verbosity": "error", + "enable_openapi": false, + "jwt_secret_key": "6a599ab046dbb419014807dffd7b8823bfa7e5df56b17d545485deb87331b4ca", + "ws_token": "6O5pBDiRigiZrmIsofaE2rkKMJtf9h8zVQ", + "CORS_origins": [], + "username": "freqAdmin", + "password": "REDACTED" + }, + "use_exit_signal": true, + "bot_name": "freqtrade", + "initial_state": "running", + "force_entry_enable": false, + "internals": { + "process_throttle_secs": 5, + "heartbeat_interval": 20, + "loglevel": "INFO" + }, + "config_files": ["config_examples/theforcev7.json"] +} diff --git a/config_examples/xgboostregression-ok1-kandipai.diff b/config_examples/xgboostregression-ok1-kandipai.diff new file mode 100644 index 00000000..66c667d7 --- /dev/null +++ b/config_examples/xgboostregression-ok1-kandipai.diff @@ -0,0 +1,122 @@ +diff --git a/config_examples/config_freqai.okx.json b/config_examples/config_freqai.okx.json +index 259459e..c8f04af 100644 +--- a/config_examples/config_freqai.okx.json ++++ b/config_examples/config_freqai.okx.json +@@ -5,11 +5,10 @@ + "max_open_trades": 4, + "stake_currency": "USDT", + "stake_amount": 150, +- "startup_candle_count": 30, + "tradable_balance_ratio": 1, + "fiat_display_currency": "USD", + "dry_run": true, +- "timeframe": "5m", ++ "timeframe": "3m", + "dry_run_wallet": 1000, + "cancel_open_orders_on_exit": true, + "stoploss": -0.05, +@@ -24,21 +23,21 @@ + "enable_ws": false, + "ccxt_config": { + "enableRateLimit": true, +- "rateLimit": 800, ++ "rateLimit": 500, + "options": { + "defaultType": "spot" + } + }, + "ccxt_async_config": { + "enableRateLimit": true, +- "rateLimit": 800, ++ "rateLimit": 500, + "timeout": 20000 + }, + "pair_whitelist": [ +- "OKB/USDT", +- "DOT/USDT", ++ "BTC/USDT", + "SOL/USDT" +- ] ++ ], ++ "pair_blacklist": [] + }, + "entry_pricing": { + "price_side": "same", +@@ -65,47 +64,38 @@ + "data_kitchen": { + "fillna": "ffill" + }, +- "freqaimodel": "CatboostClassifier", +- "purge_old_models": 2, +- "identifier": "test175", +- "train_period_days": 30, +- "backtest_period_days": 10, ++ "freqaimodel": "XGBoostRegressor", ++ "model_training_parameters": { ++ "n_estimators": 100, ++ "learning_rate": 0.05, ++ "max_depth": 5 ++ }, ++ "train_period_days": 15, ++ "train_period_days": 180, ++ "backtest_period_days": 60, + "live_retrain_hours": 0, + "feature_selection": { + "method": "recursive_elimination" + }, + "feature_parameters": { +- "include_timeframes": [ +- "5m", +- "1h" +- ], +- "include_corr_pairlist": [ +- "BTC/USDT", +- "ETH/USDT" +- ], +- "label_period_candles": 12, +- "include_shifted_candles": 3, +- "DI_threshold": 0.9, ++ "include_timeframes": ["15m"], ++ "include_corr_pairlist": ["BTC/USDT"], ++ "label_period_candles": 10, ++ "include_shifted_candles": 1, ++ + "weight_factor": 0.9, + "principal_component_analysis": false, + "use_SVM_to_remove_outliers": false, +- "indicator_periods_candles": [ +- 10, +- 20, +- 50 +- ], +- "plot_feature_importances": 0 ++ "indicator_periods_candles": [14], + }, + "data_split_parameters": { +- "test_size": 0.2, +- "shuffle": false, ++ "test_size": 0.2 + }, +- "model_training_parameters": { +- "n_estimators": 100, +- "learning_rate": 0.1, +- "num_leaves": 15, +- "verbose": -1 +- } ++ "model_training_parameters": { ++ "n_estimators": 100, ++ "learning_rate": 0.05, ++ "max_depth": 5 ++ } + }, + "api_server": { + "enabled": true, +@@ -123,7 +113,7 @@ + "initial_state": "running", + "force_entry_enable": false, + "internals": { +- "process_throttle_secs": 10, ++ "process_throttle_secs": 5, + "heartbeat_interval": 20, + "loglevel": "DEBUG" + } diff --git a/doc/hyperopts.md b/doc/hyperopts.md new file mode 100644 index 00000000..8393ea46 --- /dev/null +++ b/doc/hyperopts.md @@ -0,0 +1,14 @@ +## hyperopts如何使用 + +每周运行一次 hyperopt, 每次运行最近2个月的数据, 得到 stoploss 最优解后 手动更新 config, 提交代码 + +假设今天是2025年5月15日 +``` +cd tools +./download.sh +./hyperopt.sh 20250314 20250516 +然后得到结果, stoploss 为 -0.06 写到log里 +``` + +后面改成自动更新并不麻烦 +策略目录有自动生成的json, 是hypertop计算结果, 需脱掉一层 paramas后 方可使用 diff --git a/docker-compose.yml b/docker-compose.yml index 4186c4f2..0a058ef4 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -1,7 +1,7 @@ ---- +version: '3.8' services: freqtrade: - image: freqtradeorg/freqtrade:stable_freqaitorch + image: freqtradeorg/freqtrade:develop_freqaitorch # # Enable GPU Image and GPU Resources # # Make sure to uncomment the whole deploy section # deploy: @@ -22,30 +22,77 @@ services: - "./user_data:/freqtrade/user_data" - "./config_examples:/freqtrade/config_examples" - "./freqtrade/templates:/freqtrade/templates" + - "./freqtrade/exchange/:/freqtrade/exchange" # Expose api on port 8080 (localhost only) # Please read the https://www.freqtrade.io/en/stable/rest-api/ documentation # for more information. ports: - "8080:8080" # Default command used when running `docker compose up` - + # --freqaimodel XGBoostRegressor # command: > # trade - # --logfile /freqtrade/user_data/logs/freqtrade.log - # --db-url sqlite:////freqtrade/user_data/tradesv3.sqlite - # --freqaimodel LightGBMRegressor - # --config /freqtrade/config_examples/config_freqai.okx.json - # --strategy FreqaiExampleStrategy - # --strategy-path /freqtrade/templates + # --logfile /freqtrade/user_data/logs/freqtrade.log + # --db-url sqlite:////freqtrade/user_data/tradesv3.sqlite + # --freqaimodel LightGBMRegressor + # --config /freqtrade/config_examples/config_freqai.okx.json + # --strategy FreqaiExampleStrategy + # --strategy-path /freqtrade/templates + # command: > + # backtesting + # --logfile /freqtrade/user_data/logs/freqtrade.log + # --freqaimodel LightGBMRegressor + # --config /freqtrade/config_examples/config_freqai.okx.json + # --strategy-path /freqtrade/templates + # --strategy FreqaiExampleStrategy + # --breakdown week month + # --timerange 20250310-20250410 + # --export trades + # command: > + # hyperopt + # --logfile /freqtrade/user_data/logs/freqtrade.log + # --freqaimodel LightGBMRegressor + # --config /freqtrade/config_examples/config_freqai.okx.json + # --strategy-path /freqtrade/templates + # --strategy FreqaiExampleStrategy + # --timerange 20250301-20250420 + # --hyperopt-loss SharpeHyperOptLoss + # --spaces roi stoploss trailing + # -e 200 - command: > - backtesting - --logfile /freqtrade/user_data/logs/freqtrade.log - --config /freqtrade/config_examples/config_adsf.json - --strategy-path /freqtrade/templates - --freqaimodel LightGBMRegressor - --strategy NostalgiaForInfinityV8 - --timerange 20250401-20250415 - --fee 0.0008 - --cache none + # command: > + # hyperopt + # --logfile /freqtrade/user_data/logs/freqtrade.log + # --freqaimodel LightGBMRegressor + # --config /freqtrade/config_examples/config_freqai.okx.json + # --strategy-path /freqtrade/templates + # --strategy FreqaiExampleStrategy + # --timerange 20250301-20250420 + # --hyperopt-loss SharpeHyperOptLoss + # --spaces roi stoploss + # -e 200 + + #--config /freqtrade/templates/FreqaiExampleStrategy.json + + # command: > + # backtesting + # --logfile /freqtrade/user_data/logs/freqtrade.log + # --freqaimodel XGBoostRegressor + # --config /freqtrade/config_examples/config_my_hyperopt.json + # --strategy-path /freqtrade/templates + # --strategy TheForceV7 + # --timerange 20250301-20250405 + # --export trades + # --fee 0.0008 + # --cache none + # + # command: > + # trade + # --logfile /freqtrade/user_data/logs/freqtrade.log + # --db-url sqlite:////freqtrade/user_data/tradesv3.sqlite + # --freqaimodel XGBoostRegressor + # --config /freqtrade/config_examples/theforcev7.json + # --strategy-path /freqtrade/templates + # --strategy TheForceV7 + # --fee 0.0008 diff --git a/docs/configuration.md b/docs/..md/configuration.md similarity index 100% rename from docs/configuration.md rename to docs/..md/configuration.md diff --git a/docs/..md/md b/docs/..md/md new file mode 100644 index 00000000..e69de29b diff --git a/file-copy.sh b/file-copy.sh new file mode 100644 index 00000000..e6b940d2 --- /dev/null +++ b/file-copy.sh @@ -0,0 +1,47 @@ +import os +import shutil + +# 定义源目录 +source_dir = "./result" + +# 定义目标目录和文件名 +target_strategy_path = "./freqtrade/template/FreqaiExampleStrategy.py" +target_config_path = "./config_examples/config_freqai.okx.json" + +# 查找 *FreqaiExampleStrategy.py 文件 +strategy_file = None +for file in os.listdir(source_dir): + if file.endswith("FreqaiExampleStrategy.py"): + strategy_file = os.path.join(source_dir, file) + break + +# 查找 *config.json 文件 +config_file = None +for file in os.listdir(source_dir): + if file.endswith("config.json"): + config_file = os.path.join(source_dir, file) + break + +# 复制 *FreqaiExampleStrategy.py 文件 +if strategy_file: + try: + target_strategy_dir = os.path.dirname(target_strategy_path) + os.makedirs(target_strategy_dir, exist_ok=True) + shutil.copy2(strategy_file, target_strategy_path) + print(f"成功复制 {strategy_file} 到 {target_strategy_path}") + except Exception as e: + print(f"复制 {strategy_file} 时出错: {e}") +else: + print("未找到 *FreqaiExampleStrategy.py 文件") + +# 复制 *config.json 文件 +if config_file: + try: + target_config_dir = os.path.dirname(target_config_path) + os.makedirs(target_config_dir, exist_ok=True) + shutil.copy2(config_file, target_config_path) + print(f"成功复制 {config_file} 到 {target_config_path}") + except Exception as e: + print(f"复制 {config_file} 时出错: {e}") +else: + print("未找到 *config.json 文件") diff --git a/filtered_output.log b/filtered_output.log new file mode 100644 index 00000000..443a5acf --- /dev/null +++ b/filtered_output.log @@ -0,0 +1,888 @@ +[99] validation_0-rmse:0.13480 validation_1-rmse:0.09950 +[99] validation_0-rmse:0.14079 validation_1-rmse:0.10036 +[99] validation_0-rmse:0.15004 validation_1-rmse:0.09815 +[99] validation_0-rmse:0.13402 validation_1-rmse:0.10289 +[99] validation_0-rmse:0.14818 validation_1-rmse:0.10475 +[99] validation_0-rmse:0.15738 validation_1-rmse:0.10531 +[99] validation_0-rmse:0.14246 validation_1-rmse:0.11071 +[99] validation_0-rmse:0.16321 validation_1-rmse:0.10649 +[99] validation_0-rmse:0.15096 validation_1-rmse:0.10882 +[99] validation_0-rmse:0.15694 validation_1-rmse:0.11396 +[99] validation_0-rmse:0.18198 validation_1-rmse:0.10994 +[99] validation_0-rmse:0.16824 validation_1-rmse:0.11403 +[99] validation_0-rmse:0.16437 validation_1-rmse:0.11096 +[99] validation_0-rmse:0.17746 validation_1-rmse:0.10819 +[99] validation_0-rmse:0.15331 validation_1-rmse:0.11727 +[99] validation_0-rmse:0.16802 validation_1-rmse:0.11547 +[99] validation_0-rmse:0.15958 validation_1-rmse:0.11029 +[99] validation_0-rmse:0.18742 validation_1-rmse:0.11149 +[99] validation_0-rmse:0.15075 validation_1-rmse:0.09770 +[99] validation_0-rmse:0.13818 validation_1-rmse:0.10038 +[99] validation_0-rmse:0.12954 validation_1-rmse:0.09825 +[99] validation_0-rmse:0.14837 validation_1-rmse:0.10398 +Creating freqtrade_freqtrade_run ... +Creating freqtrade_freqtrade_run ... done +2025-04-29 01:54:55,246 - freqtrade - INFO - freqtrade 2025.3 +2025-04-29 01:54:55,464 - numexpr.utils - INFO - NumExpr defaulting to 12 threads. +2025-04-29 01:54:56,878 - freqtrade.configuration.load_config - INFO - Using config: /freqtrade/config_examples/config_freqai.okx.json ... +2025-04-29 01:54:56,879 - freqtrade.configuration.load_config - INFO - Using config: /freqtrade/templates/FreqaiExampleStrategy.json ... +2025-04-29 01:54:56,881 - freqtrade.loggers - INFO - Enabling colorized output. +2025-04-29 01:54:56,881 - root - INFO - Logfile configured +2025-04-29 01:54:56,882 - freqtrade.loggers - INFO - Verbosity set to 0 +2025-04-29 01:54:56,882 - freqtrade.configuration.configuration - INFO - Using additional Strategy lookup path: /freqtrade/templates +2025-04-29 01:54:56,883 - freqtrade.configuration.configuration - INFO - Using max_open_trades: 4 ... +2025-04-29 01:54:56,883 - freqtrade.configuration.configuration - INFO - Parameter --timerange detected: 20250101-20250420 ... +2025-04-29 01:54:56,907 - freqtrade.configuration.configuration - INFO - Using user-data directory: /freqtrade/user_data ... +2025-04-29 01:54:56,908 - freqtrade.configuration.configuration - INFO - Using data directory: /freqtrade/user_data/data/okx ... +2025-04-29 01:54:56,908 - freqtrade.configuration.configuration - INFO - Parameter --cache=none detected ... +2025-04-29 01:54:56,908 - freqtrade.configuration.configuration - INFO - Filter trades by timerange: 20250101-20250420 +2025-04-29 01:54:56,909 - freqtrade.configuration.configuration - INFO - Using freqaimodel class name: XGBoostRegressor +2025-04-29 01:54:56,910 - freqtrade.exchange.check_exchange - INFO - Checking exchange... +2025-04-29 01:54:56,916 - freqtrade.exchange.check_exchange - INFO - Exchange "okx" is officially supported by the Freqtrade development team. +2025-04-29 01:54:56,916 - freqtrade.configuration.configuration - INFO - Using pairlist from configuration. +2025-04-29 01:54:56,917 - freqtrade.configuration.config_validation - INFO - Validating configuration ... +2025-04-29 01:54:56,919 - freqtrade.commands.optimize_commands - INFO - Starting freqtrade in Backtesting mode +2025-04-29 01:54:56,919 - freqtrade.exchange.exchange - INFO - Instance is running with dry_run enabled +2025-04-29 01:54:56,920 - freqtrade.exchange.exchange - INFO - Using CCXT 4.4.69 +2025-04-29 01:54:56,920 - freqtrade.exchange.exchange - INFO - Applying additional ccxt config: {'enableRateLimit': True, 'rateLimit': 500, 'options': {'defaultType': 'spot'}} +2025-04-29 01:54:56,925 - freqtrade.exchange.exchange - INFO - Applying additional ccxt config: {'enableRateLimit': True, 'rateLimit': 500, 'options': {'defaultType': 'spot'}, 'timeout': 20000} +2025-04-29 01:54:56,931 - freqtrade.exchange.exchange - INFO - Using Exchange "OKX" +2025-04-29 01:54:59,471 - freqtrade.resolvers.exchange_resolver - INFO - Using resolved exchange 'Okx'... +2025-04-29 01:54:59,491 - freqtrade.resolvers.iresolver - INFO - Using resolved strategy FreqaiExampleStrategy from '/freqtrade/templates/FreqaiExampleStrategy.py'... +2025-04-29 01:54:59,491 - freqtrade.strategy.hyper - INFO - Loading parameters from file /freqtrade/templates/FreqaiExampleStrategy.json +2025-04-29 01:54:59,492 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'timeframe' with value in config file: 3m. +2025-04-29 01:54:59,492 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'stoploss' with value in config file: -0.05. +2025-04-29 01:54:59,493 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'stake_currency' with value in config file: USDT. +2025-04-29 01:54:59,493 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'stake_amount' with value in config file: 150. +2025-04-29 01:54:59,493 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'startup_candle_count' with value in config file: 30. +2025-04-29 01:54:59,494 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'unfilledtimeout' with value in config file: {'entry': 5, 'exit': 15, 'exit_timeout_count': 0, 'unit': +'minutes'}. +2025-04-29 01:54:59,494 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'max_open_trades' with value in config file: 4. +2025-04-29 01:54:59,494 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using minimal_roi: {'0': 0.132, '8': 0.047, '14': 0.007, '60': 0} +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using timeframe: 3m +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using stoploss: -0.05 +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_stop: True +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_stop_positive: 0.01 +2025-04-29 01:54:59,496 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_stop_positive_offset: 0.02 +2025-04-29 01:54:59,496 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_only_offset_is_reached: False +2025-04-29 01:54:59,496 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using use_custom_stoploss: False +2025-04-29 01:54:59,497 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using process_only_new_candles: True +2025-04-29 01:54:59,497 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using order_types: {'entry': 'limit', 'exit': 'limit', 'stoploss': 'limit', 'stoploss_on_exchange': False, +'stoploss_on_exchange_interval': 60} +2025-04-29 01:54:59,497 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using order_time_in_force: {'entry': 'GTC', 'exit': 'GTC'} +2025-04-29 01:54:59,498 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using stake_currency: USDT +2025-04-29 01:54:59,498 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using stake_amount: 150 +2025-04-29 01:54:59,498 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using startup_candle_count: 30 +2025-04-29 01:54:59,499 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using unfilledtimeout: {'entry': 5, 'exit': 15, 'exit_timeout_count': 0, 'unit': 'minutes'} +2025-04-29 01:54:59,499 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using use_exit_signal: True +2025-04-29 01:54:59,499 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using exit_profit_only: False +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using ignore_roi_if_entry_signal: False +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using exit_profit_offset: 0.0 +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using disable_dataframe_checks: False +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using ignore_buying_expired_candle_after: 0 +2025-04-29 01:54:59,501 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using position_adjustment_enable: False +2025-04-29 01:54:59,501 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using max_entry_position_adjustment: -1 +2025-04-29 01:54:59,501 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using max_open_trades: 4 +2025-04-29 01:54:59,502 - freqtrade.configuration.config_validation - INFO - Validating configuration ... +2025-04-29 01:54:59,505 - freqtrade.resolvers.iresolver - INFO - Using resolved pairlist StaticPairList from '/freqtrade/freqtrade/plugins/pairlist/StaticPairList.py'... +2025-04-29 01:54:59,512 - freqtrade.optimize.backtesting - INFO - Using fee 0.1500% - worst case fee from exchange (lowest tier). +2025-04-29 01:54:59,512 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 3m to 14450 +2025-04-29 01:54:59,513 - freqtrade.data.history.history_utils - INFO - Using indicator startup period: 14450 ... +2025-04-29 01:54:59,672 - freqtrade.optimize.backtesting - INFO - Loading data from 2024-12-01 21:30:00 up to 2025-04-20 00:00:00 (139 days). +2025-04-29 01:54:59,672 - freqtrade.optimize.backtesting - INFO - Dataload complete. Calculating indicators +2025-04-29 01:54:59,673 - freqtrade.optimize.backtesting - INFO - Running backtesting for Strategy FreqaiExampleStrategy +2025-04-29 01:55:01,274 - matplotlib.font_manager - INFO - generated new fontManager +2025-04-29 01:55:01,489 - freqtrade.resolvers.iresolver - INFO - Using resolved freqaimodel XGBoostRegressor from '/freqtrade/freqtrade/freqai/prediction_models/XGBoostRegressor.py'... +2025-04-29 01:55:01,490 - freqtrade.freqai.data_drawer - INFO - Could not find existing datadrawer, starting from scratch +2025-04-29 01:55:01,491 - freqtrade.freqai.data_drawer - INFO - Could not find existing historic_predictions, starting from scratch +2025-04-29 01:55:01,491 - freqtrade.freqai.freqai_interface - INFO - Set fresh train queue from whitelist. Queue: ['BTC/USDT', 'SOL/USDT'] +2025-04-29 01:55:01,492 - freqtrade.strategy.hyper - INFO - Strategy Parameter: buy_rsi = 39.92672300850069 +2025-04-29 01:55:01,492 - freqtrade.strategy.hyper - INFO - Strategy Parameter: sell_rsi = 69.92672300850067 +2025-04-29 01:55:01,493 - freqtrade.strategy.hyper - INFO - No params for protection found, using default values. +2025-04-29 01:55:01,498 - FreqaiExampleStrategy - INFO - 处理交易对：BTC/USDT +2025-04-29 01:55:01,500 - freqtrade.freqai.freqai_interface - INFO - Training 11 timeranges +2025-04-29 01:55:01,501 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2024-12-02 00:00:00 to 2025-01-01 00:00:00, 1/11 trains +2025-04-29 01:55:01,502 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1735689600_prediction.feather +2025-04-29 01:55:01,602 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 5m to 8690 +2025-04-29 01:55:01,603 - freqtrade.data.dataprovider - INFO - Loading data for BTC/USDT 5m from 2024-12-01 19:50:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:01,705 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 1h to 770 +2025-04-29 01:55:01,706 - freqtrade.data.dataprovider - INFO - Loading data for BTC/USDT 1h from 2024-11-29 22:00:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:01,814 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 3m to 14450 +2025-04-29 01:55:01,815 - freqtrade.data.dataprovider - INFO - Loading data for ETH/USDT 3m from 2024-12-01 21:30:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:01,942 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 5m to 8690 +2025-04-29 01:55:01,943 - freqtrade.data.dataprovider - INFO - Loading data for ETH/USDT 5m from 2024-12-01 19:50:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:02,037 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 1h to 770 +2025-04-29 01:55:02,038 - freqtrade.data.dataprovider - INFO - Loading data for ETH/USDT 1h from 2024-11-29 22:00:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:02,113 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:02,118 - FreqaiExampleStrategy - INFO - 目标列形状：(14450,) +2025-04-29 01:55:02,121 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.152831 +1 0.003285 50.152831 +2 0.001898 50.152831 +3 0.000484 50.152831 +4 0.001688 50.152831 +2025-04-29 01:55:02,123 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:02,129 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:55:02,130 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.202701 +1 0.003285 50.202701 +2 0.001898 50.202701 +3 0.000484 50.202701 +4 0.001688 50.202701 +2025-04-29 01:55:02,134 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1735689600/cb_btc_1735689600 +2025-04-29 01:55:02,135 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:02,151 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:02,152 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-02 to 2024-12-31 -------------------- +2025-04-29 01:55:07,277 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:07,278 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:55:08,221 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (6.09 secs) -------------------- +2025-04-29 01:55:08,222 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:08,903 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2024-12-12 00:00:00 to 2025-01-11 00:00:00, 2/11 trains +2025-04-29 01:55:08,904 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1736553600_prediction.feather +2025-04-29 01:55:08,907 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:08,912 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:55:08,914 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.202701 +1 0.003285 50.202701 +2 0.001898 50.202701 +3 0.000484 50.202701 +4 0.001688 50.202701 +2025-04-29 01:55:08,917 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:08,924 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:55:08,925 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.367593 +1 0.003285 50.367593 +2 0.001898 50.367593 +3 0.000484 50.367593 +4 0.001688 50.367593 +2025-04-29 01:55:08,929 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1736553600/cb_btc_1736553600 +2025-04-29 01:55:08,930 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:08,946 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:08,947 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-12 to 2025-01-10 -------------------- +2025-04-29 01:55:13,908 - datasieve.pipeline - INFO - DI tossed 5 predictions for being too far from training data. +2025-04-29 01:55:13,911 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:13,912 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:55:14,692 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.76 secs) -------------------- +2025-04-29 01:55:14,693 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:15,250 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2024-12-22 00:00:00 to 2025-01-21 00:00:00, 3/11 trains +2025-04-29 01:55:15,250 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1737417600_prediction.feather +2025-04-29 01:55:15,254 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:15,261 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:55:15,262 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.367593 +1 0.003285 50.367593 +2 0.001898 50.367593 +3 0.000484 50.367593 +4 0.001688 50.367593 +2025-04-29 01:55:15,268 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:15,275 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:55:15,276 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.305589 +1 0.003285 50.305589 +2 0.001898 50.305589 +3 0.000484 50.305589 +4 0.001688 50.305589 +2025-04-29 01:55:15,281 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1737417600/cb_btc_1737417600 +2025-04-29 01:55:15,281 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:15,297 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:15,298 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-22 to 2025-01-20 -------------------- +2025-04-29 01:55:20,324 - datasieve.pipeline - INFO - DI tossed 1622 predictions for being too far from training data. +2025-04-29 01:55:20,327 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:20,327 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:55:21,007 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.73 secs) -------------------- +2025-04-29 01:55:21,008 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:21,504 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-01 00:00:00 to 2025-01-31 00:00:00, 4/11 trains +2025-04-29 01:55:21,505 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1738281600_prediction.feather +2025-04-29 01:55:21,510 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:21,516 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:55:21,517 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.305589 +1 0.003285 50.305589 +2 0.001898 50.305589 +3 0.000484 50.305589 +4 0.001688 50.305589 +2025-04-29 01:55:21,522 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:21,528 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:55:21,529 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.168798 +1 0.003285 50.168798 +2 0.001898 50.168798 +3 0.000484 50.168798 +4 0.001688 50.168798 +2025-04-29 01:55:21,533 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1738281600/cb_btc_1738281600 +2025-04-29 01:55:21,534 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:21,550 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:21,550 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-01 to 2025-01-30 -------------------- +2025-04-29 01:55:26,605 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:26,606 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:55:27,556 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (6.02 secs) -------------------- +2025-04-29 01:55:27,557 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:28,076 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-11 00:00:00 to 2025-02-10 00:00:00, 5/11 trains +2025-04-29 01:55:28,077 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1739145600_prediction.feather +2025-04-29 01:55:28,081 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:28,088 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:55:28,089 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.168798 +1 0.003285 50.168798 +2 0.001898 50.168798 +3 0.000484 50.168798 +4 0.001688 50.168798 +2025-04-29 01:55:28,094 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:28,100 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:55:28,102 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.167897 +1 0.003285 50.167897 +2 0.001898 50.167897 +3 0.000484 50.167897 +4 0.001688 50.167897 +2025-04-29 01:55:28,106 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1739145600/cb_btc_1739145600 +2025-04-29 01:55:28,107 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:28,123 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:28,124 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-11 to 2025-02-09 -------------------- +2025-04-29 01:55:33,123 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:33,124 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:55:33,929 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.82 secs) -------------------- +2025-04-29 01:55:33,930 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:34,433 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-21 00:00:00 to 2025-02-20 00:00:00, 6/11 trains +2025-04-29 01:55:34,434 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1740009600_prediction.feather +2025-04-29 01:55:34,440 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:34,447 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:55:34,448 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.167897 +1 0.003285 50.167897 +2 0.001898 50.167897 +3 0.000484 50.167897 +4 0.001688 50.167897 +2025-04-29 01:55:34,453 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:34,459 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:55:34,461 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.107698 +1 0.003285 50.107698 +2 0.001898 50.107698 +3 0.000484 50.107698 +4 0.001688 50.107698 +2025-04-29 01:55:34,465 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1740009600/cb_btc_1740009600 +2025-04-29 01:55:34,466 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:34,482 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:34,483 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-21 to 2025-02-19 -------------------- +2025-04-29 01:55:39,369 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:39,370 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:55:40,266 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.80 secs) -------------------- +2025-04-29 01:55:40,267 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:40,801 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-31 00:00:00 to 2025-03-02 00:00:00, 7/11 trains +2025-04-29 01:55:40,802 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1740873600_prediction.feather +2025-04-29 01:55:40,807 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:40,814 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:55:40,816 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.107698 +1 0.003285 50.107698 +2 0.001898 50.107698 +3 0.000484 50.107698 +4 0.001688 50.107698 +2025-04-29 01:55:40,821 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:40,827 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:55:40,829 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079166 +1 0.003285 50.079166 +2 0.001898 50.079166 +3 0.000484 50.079166 +4 0.001688 50.079166 +2025-04-29 01:55:40,833 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1740873600/cb_btc_1740873600 +2025-04-29 01:55:40,834 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:40,849 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:40,850 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-31 to 2025-03-01 -------------------- +2025-04-29 01:55:45,643 - datasieve.pipeline - INFO - DI tossed 2275 predictions for being too far from training data. +2025-04-29 01:55:45,646 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:45,647 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:55:46,544 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.71 secs) -------------------- +2025-04-29 01:55:46,544 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:47,092 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-02-10 00:00:00 to 2025-03-12 00:00:00, 8/11 trains +2025-04-29 01:55:47,092 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1741737600_prediction.feather +2025-04-29 01:55:47,100 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:47,107 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:55:47,109 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079166 +1 0.003285 50.079166 +2 0.001898 50.079166 +3 0.000484 50.079166 +4 0.001688 50.079166 +2025-04-29 01:55:47,115 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:47,122 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:55:47,123 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.102027 +1 0.003285 50.102027 +2 0.001898 50.102027 +3 0.000484 50.102027 +4 0.001688 50.102027 +2025-04-29 01:55:47,128 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1741737600/cb_btc_1741737600 +2025-04-29 01:55:47,129 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:47,145 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:47,145 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-10 to 2025-03-11 -------------------- +2025-04-29 01:55:51,987 - datasieve.pipeline - INFO - DI tossed 18 predictions for being too far from training data. +2025-04-29 01:55:51,989 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:51,989 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:55:52,741 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.61 secs) -------------------- +2025-04-29 01:55:52,742 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:53,285 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-02-20 00:00:00 to 2025-03-22 00:00:00, 9/11 trains +2025-04-29 01:55:53,286 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1742601600_prediction.feather +2025-04-29 01:55:53,291 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:53,298 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:55:53,300 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.102027 +1 0.003285 50.102027 +2 0.001898 50.102027 +3 0.000484 50.102027 +4 0.001688 50.102027 +2025-04-29 01:55:53,309 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:53,316 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:55:53,318 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079967 +1 0.003285 50.079967 +2 0.001898 50.079967 +3 0.000484 50.079967 +4 0.001688 50.079967 +2025-04-29 01:55:53,322 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1742601600/cb_btc_1742601600 +2025-04-29 01:55:53,323 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:53,339 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:53,340 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-20 to 2025-03-21 -------------------- +2025-04-29 01:55:58,184 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:58,185 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:55:59,097 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.77 secs) -------------------- +2025-04-29 01:55:59,098 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:59,706 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-03-02 00:00:00 to 2025-04-01 00:00:00, 10/11 trains +2025-04-29 01:55:59,706 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1743465600_prediction.feather +2025-04-29 01:55:59,715 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:59,723 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:55:59,725 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079967 +1 0.003285 50.079967 +2 0.001898 50.079967 +3 0.000484 50.079967 +4 0.001688 50.079967 +2025-04-29 01:55:59,732 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:59,739 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:55:59,741 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.024153 +1 0.003285 50.024153 +2 0.001898 50.024153 +3 0.000484 50.024153 +4 0.001688 50.024153 +2025-04-29 01:55:59,745 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1743465600/cb_btc_1743465600 +2025-04-29 01:55:59,746 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:59,762 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:59,762 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-02 to 2025-03-31 -------------------- +2025-04-29 01:56:04,571 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:56:04,571 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:56:05,520 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.77 secs) -------------------- +2025-04-29 01:56:05,521 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:06,027 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-03-12 00:00:00 to 2025-04-11 00:00:00, 11/11 trains +2025-04-29 01:56:06,027 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1744329600_prediction.feather +2025-04-29 01:56:06,037 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:56:06,045 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:56:06,046 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.024153 +1 0.003285 50.024153 +2 0.001898 50.024153 +3 0.000484 50.024153 +4 0.001688 50.024153 +2025-04-29 01:56:06,057 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:56:06,064 - FreqaiExampleStrategy - INFO - 目标列形状：(66770,) +2025-04-29 01:56:06,065 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.093162 +1 0.003285 50.093162 +2 0.001898 50.093162 +3 0.000484 50.093162 +4 0.001688 50.093162 +2025-04-29 01:56:06,070 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1744329600/cb_btc_1744329600 +2025-04-29 01:56:06,071 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:56:06,087 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:06,088 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-12 to 2025-04-10 -------------------- +2025-04-29 01:56:10,904 - datasieve.pipeline - INFO - DI tossed 2001 predictions for being too far from training data. +2025-04-29 01:56:10,907 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:56:10,907 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:56:11,705 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.63 secs) -------------------- +2025-04-29 01:56:11,706 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:12,255 - FreqaiExampleStrategy - INFO - 动态参数：buy_rsi=39.26145316407591, sell_rsi=59.26145316407591, stoploss=-0.15, trailing_stop_positive=0.05 +2025-04-29 01:56:12,275 - FreqaiExampleStrategy - INFO - up_or_down 值统计： +up_or_down +1 33535 +0 33236 +2025-04-29 01:56:12,276 - FreqaiExampleStrategy - INFO - do_predict 值统计： +do_predict +0.0 35773 +1.0 30998 +2025-04-29 01:56:12,279 - FreqaiExampleStrategy - INFO - 处理交易对：SOL/USDT +2025-04-29 01:56:12,281 - freqtrade.freqai.freqai_interface - INFO - Training 11 timeranges +2025-04-29 01:56:12,282 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2024-12-02 00:00:00 to 2025-01-01 00:00:00, 1/11 trains +2025-04-29 01:56:12,283 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1735689600_prediction.feather +2025-04-29 01:56:12,334 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 5m to 8690 +2025-04-29 01:56:12,335 - freqtrade.data.dataprovider - INFO - Loading data for SOL/USDT 5m from 2024-12-01 19:50:00 to 2025-04-20 00:00:00 +2025-04-29 01:56:12,422 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 1h to 770 +2025-04-29 01:56:12,422 - freqtrade.data.dataprovider - INFO - Loading data for SOL/USDT 1h from 2024-11-29 22:00:00 to 2025-04-20 00:00:00 +2025-04-29 01:56:12,518 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 3m to 14450 +2025-04-29 01:56:12,519 - freqtrade.data.dataprovider - INFO - Loading data for BTC/USDT 3m from 2024-12-01 21:30:00 to 2025-04-20 00:00:00 +2025-04-29 01:56:13,040 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:13,046 - FreqaiExampleStrategy - INFO - 目标列形状：(14450,) +2025-04-29 01:56:13,047 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.58814 +1 0.003044 49.58814 +2 0.000465 49.58814 +3 -0.000380 49.58814 +4 0.002829 49.58814 +2025-04-29 01:56:13,052 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:13,057 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:56:13,059 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.68088 +1 0.003044 49.68088 +2 0.000465 49.68088 +3 -0.000380 49.68088 +4 0.002829 49.68088 +2025-04-29 01:56:13,066 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1735689600/cb_sol_1735689600 +2025-04-29 01:56:13,066 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:13,095 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:13,096 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-02 to 2024-12-31 -------------------- +2025-04-29 01:56:18,126 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:18,126 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:56:19,586 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.52 secs) -------------------- +2025-04-29 01:56:19,587 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:20,174 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2024-12-12 00:00:00 to 2025-01-11 00:00:00, 2/11 trains +2025-04-29 01:56:20,175 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1736553600_prediction.feather +2025-04-29 01:56:20,179 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:20,185 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:56:20,186 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.68088 +1 0.003044 49.68088 +2 0.000465 49.68088 +3 -0.000380 49.68088 +4 0.002829 49.68088 +2025-04-29 01:56:20,192 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:20,197 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:56:20,199 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.97721 +1 0.003044 49.97721 +2 0.000465 49.97721 +3 -0.000380 49.97721 +4 0.002829 49.97721 +2025-04-29 01:56:20,204 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1736553600/cb_sol_1736553600 +2025-04-29 01:56:20,205 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:20,227 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:20,228 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-12 to 2025-01-10 -------------------- +2025-04-29 01:56:25,109 - datasieve.pipeline - INFO - DI tossed 5 predictions for being too far from training data. +2025-04-29 01:56:25,112 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:25,112 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:56:26,510 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.30 secs) -------------------- +2025-04-29 01:56:26,511 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:27,072 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2024-12-22 00:00:00 to 2025-01-21 00:00:00, 3/11 trains +2025-04-29 01:56:27,073 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1737417600_prediction.feather +2025-04-29 01:56:27,079 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:27,085 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:56:27,086 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.97721 +1 0.003044 49.97721 +2 0.000465 49.97721 +3 -0.000380 49.97721 +4 0.002829 49.97721 +2025-04-29 01:56:27,094 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:27,100 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:56:27,102 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.941408 +1 0.003044 49.941408 +2 0.000465 49.941408 +3 -0.000380 49.941408 +4 0.002829 49.941408 +2025-04-29 01:56:27,108 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1737417600/cb_sol_1737417600 +2025-04-29 01:56:27,109 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:27,130 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:27,131 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-22 to 2025-01-20 -------------------- +2025-04-29 01:56:32,206 - datasieve.pipeline - INFO - DI tossed 1523 predictions for being too far from training data. +2025-04-29 01:56:32,209 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:32,210 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:56:33,558 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.45 secs) -------------------- +2025-04-29 01:56:33,558 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:34,118 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-01 00:00:00 to 2025-01-31 00:00:00, 4/11 trains +2025-04-29 01:56:34,119 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1738281600_prediction.feather +2025-04-29 01:56:34,124 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:34,130 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:56:34,131 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.941408 +1 0.003044 49.941408 +2 0.000465 49.941408 +3 -0.000380 49.941408 +4 0.002829 49.941408 +2025-04-29 01:56:34,137 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:34,143 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:56:34,144 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.830756 +1 0.003044 49.830756 +2 0.000465 49.830756 +3 -0.000380 49.830756 +4 0.002829 49.830756 +2025-04-29 01:56:34,149 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1738281600/cb_sol_1738281600 +2025-04-29 01:56:34,150 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:34,173 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:34,173 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-01 to 2025-01-30 -------------------- +2025-04-29 01:56:39,271 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:39,271 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:56:40,600 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.45 secs) -------------------- +2025-04-29 01:56:40,601 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:41,171 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-11 00:00:00 to 2025-02-10 00:00:00, 5/11 trains +2025-04-29 01:56:41,172 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1739145600_prediction.feather +2025-04-29 01:56:41,177 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:41,183 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:56:41,185 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.830756 +1 0.003044 49.830756 +2 0.000465 49.830756 +3 -0.000380 49.830756 +4 0.002829 49.830756 +2025-04-29 01:56:41,193 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:41,200 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:56:41,201 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.714422 +1 0.003044 49.714422 +2 0.000465 49.714422 +3 -0.000380 49.714422 +4 0.002829 49.714422 +2025-04-29 01:56:41,206 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1739145600/cb_sol_1739145600 +2025-04-29 01:56:41,207 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:41,228 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:41,229 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-11 to 2025-02-09 -------------------- +2025-04-29 01:56:46,277 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:46,278 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:56:47,778 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.57 secs) -------------------- +2025-04-29 01:56:47,779 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:48,320 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-21 00:00:00 to 2025-02-20 00:00:00, 6/11 trains +2025-04-29 01:56:48,321 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1740009600_prediction.feather +2025-04-29 01:56:48,327 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:48,333 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:56:48,334 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.714422 +1 0.003044 49.714422 +2 0.000465 49.714422 +3 -0.000380 49.714422 +4 0.002829 49.714422 +2025-04-29 01:56:48,346 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:48,353 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:56:48,354 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.626186 +1 0.003044 49.626186 +2 0.000465 49.626186 +3 -0.000380 49.626186 +4 0.002829 49.626186 +2025-04-29 01:56:48,361 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1740009600/cb_sol_1740009600 +2025-04-29 01:56:48,361 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:48,383 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:48,383 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-21 to 2025-02-19 -------------------- +2025-04-29 01:56:53,532 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:53,533 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:56:54,862 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.50 secs) -------------------- +2025-04-29 01:56:54,863 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:55,419 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-31 00:00:00 to 2025-03-02 00:00:00, 7/11 trains +2025-04-29 01:56:55,420 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1740873600_prediction.feather +2025-04-29 01:56:55,426 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:55,433 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:56:55,435 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.626186 +1 0.003044 49.626186 +2 0.000465 49.626186 +3 -0.000380 49.626186 +4 0.002829 49.626186 +2025-04-29 01:56:55,445 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:55,452 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:56:55,453 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.568812 +1 0.003044 49.568812 +2 0.000465 49.568812 +3 -0.000380 49.568812 +4 0.002829 49.568812 +2025-04-29 01:56:55,459 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1740873600/cb_sol_1740873600 +2025-04-29 01:56:55,459 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:55,481 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:55,482 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-31 to 2025-03-01 -------------------- +2025-04-29 01:57:00,566 - datasieve.pipeline - INFO - DI tossed 2417 predictions for being too far from training data. +2025-04-29 01:57:00,569 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:00,570 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:57:02,441 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.98 secs) -------------------- +2025-04-29 01:57:02,442 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:02,968 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-02-10 00:00:00 to 2025-03-12 00:00:00, 8/11 trains +2025-04-29 01:57:02,968 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1741737600_prediction.feather +2025-04-29 01:57:02,980 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:02,987 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:57:02,989 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.568812 +1 0.003044 49.568812 +2 0.000465 49.568812 +3 -0.000380 49.568812 +4 0.002829 49.568812 +2025-04-29 01:57:03,001 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:03,007 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:57:03,009 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.623338 +1 0.003044 49.623338 +2 0.000465 49.623338 +3 -0.000380 49.623338 +4 0.002829 49.623338 +2025-04-29 01:57:03,014 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1741737600/cb_sol_1741737600 +2025-04-29 01:57:03,015 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:03,042 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:03,042 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-10 to 2025-03-11 -------------------- +2025-04-29 01:57:08,138 - datasieve.pipeline - INFO - DI tossed 3 predictions for being too far from training data. +2025-04-29 01:57:08,141 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:08,141 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:57:09,614 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.60 secs) -------------------- +2025-04-29 01:57:09,615 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:10,150 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-02-20 00:00:00 to 2025-03-22 00:00:00, 9/11 trains +2025-04-29 01:57:10,151 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1742601600_prediction.feather +2025-04-29 01:57:10,159 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:10,167 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:57:10,168 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.623338 +1 0.003044 49.623338 +2 0.000465 49.623338 +3 -0.000380 49.623338 +4 0.002829 49.623338 +2025-04-29 01:57:10,181 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:10,188 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:57:10,190 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.644115 +1 0.003044 49.644115 +2 0.000465 49.644115 +3 -0.000380 49.644115 +4 0.002829 49.644115 +2025-04-29 01:57:10,195 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1742601600/cb_sol_1742601600 +2025-04-29 01:57:10,196 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:10,218 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:10,218 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-20 to 2025-03-21 -------------------- +2025-04-29 01:57:15,185 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:15,186 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:57:16,538 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.34 secs) -------------------- +2025-04-29 01:57:16,539 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:17,068 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-03-02 00:00:00 to 2025-04-01 00:00:00, 10/11 trains +2025-04-29 01:57:17,069 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1743465600_prediction.feather +2025-04-29 01:57:17,084 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:17,092 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:57:17,094 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.644115 +1 0.003044 49.644115 +2 0.000465 49.644115 +3 -0.000380 49.644115 +4 0.002829 49.644115 +2025-04-29 01:57:17,108 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:17,115 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:57:17,117 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.601082 +1 0.003044 49.601082 +2 0.000465 49.601082 +3 -0.000380 49.601082 +4 0.002829 49.601082 +2025-04-29 01:57:17,124 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1743465600/cb_sol_1743465600 +2025-04-29 01:57:17,125 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:17,151 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:17,151 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-02 to 2025-03-31 -------------------- +2025-04-29 01:57:22,430 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:22,430 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:57:23,725 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.60 secs) -------------------- +2025-04-29 01:57:23,726 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:24,305 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-03-12 00:00:00 to 2025-04-11 00:00:00, 11/11 trains +2025-04-29 01:57:24,305 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1744329600_prediction.feather +2025-04-29 01:57:24,318 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:24,325 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:57:24,327 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.601082 +1 0.003044 49.601082 +2 0.000465 49.601082 +3 -0.000380 49.601082 +4 0.002829 49.601082 +2025-04-29 01:57:24,337 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:24,345 - FreqaiExampleStrategy - INFO - 目标列形状：(66770,) +2025-04-29 01:57:24,346 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.729824 +1 0.003044 49.729824 +2 0.000465 49.729824 +3 -0.000380 49.729824 +4 0.002829 49.729824 +2025-04-29 01:57:24,352 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1744329600/cb_sol_1744329600 +2025-04-29 01:57:24,353 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:24,376 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:24,376 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-12 to 2025-04-10 -------------------- +2025-04-29 01:57:29,392 - datasieve.pipeline - INFO - DI tossed 1948 predictions for being too far from training data. +2025-04-29 01:57:29,396 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:29,396 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +2025-04-29 01:57:30,474 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.12 secs) -------------------- +2025-04-29 01:57:30,475 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:31,077 - FreqaiExampleStrategy - INFO - 动态参数：buy_rsi=50.0, sell_rsi=70.0, stoploss=-0.15, trailing_stop_positive=0.05 +2025-04-29 01:57:31,096 - FreqaiExampleStrategy - INFO - up_or_down 值统计： +up_or_down +0 33825 +1 32946 +2025-04-29 01:57:31,097 - FreqaiExampleStrategy - INFO - do_predict 值统计： +do_predict +0.0 36730 +1.0 30041 +2025-04-29 01:57:31,105 - freqtrade.optimize.backtesting - INFO - Backtesting with data from 2025-01-01 00:00:00 up to 2025-04-20 00:00:00 (109 days). +2025-04-29 01:57:31,109 - FreqaiExampleStrategy - ERROR - MACD 或 MACD 信号列缺失，无法生成买入信号。尝试重新计算 MACD 列。 +2025-04-29 01:57:31,111 - FreqaiExampleStrategy - INFO - MACD 列已成功重新计算。 +2025-04-29 01:57:31,193 - FreqaiExampleStrategy - ERROR - MACD 或 MACD 信号列缺失，无法生成买入信号。尝试重新计算 MACD 列。 +2025-04-29 01:57:31,195 - FreqaiExampleStrategy - INFO - MACD 列已成功重新计算。 +2025-04-29 01:57:33,776 - freqtrade.misc - INFO - dumping json to "/freqtrade/user_data/backtest_results/backtest-result-2025-04-29_01-57-33.meta.json" +Result for strategy FreqaiExampleStrategy + BACKTESTING REPORT +┏━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Pair ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ BTC/USDT │ 38 │ -0.39 │ -22.029 │ -2.2 │ 22:13:00 │ 5 32 1 13.2 │ +│ SOL/USDT │ 44 │ -1.94 │ -128.236 │ -12.82 │ 16:35:00 │ 12 26 6 27.3 │ +│ TOTAL │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└──────────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┘ + LEFT OPEN TRADES REPORT +┏━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Pair ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ TOTAL │ 0 │ 0.0 │ 0.000 │ 0.0 │ 0:00 │ 0 0 0 0 │ +└───────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┘ + ENTER TAG STATS +┏━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Enter Tag ┃ Entries ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ long │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +│ TOTAL │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└───────────┴─────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┘ + EXIT REASON STATS +┏━━━━━━━━━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Exit Reason ┃ Exits ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━━━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ roi │ 75 │ 0.07 │ 7.926 │ 0.79 │ 14:48:00 │ 17 58 0 100 │ +│ trailing_stop_loss │ 7 │ -15.04 │ -158.191 │ -15.82 │ 2 days, 18:13:00 │ 0 0 7 0 │ +│ TOTAL │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└────────────────────┴───────┴──────────────┴─────────────────┴──────────────┴──────────────────┴────────────────────────┘ + MIXED TAG STATS +┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Enter Tag ┃ Exit Reason ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ ('long', 'roi') │ │ 75 │ 0.07 │ 7.926 │ 0.79 │ 14:48:00 │ 17 58 0 100 │ +│ ('long', 'trailing_stop_loss') │ │ 7 │ -15.04 │ -158.191 │ -15.82 │ 2 days, 18:13:00 │ 0 0 7 0 │ +│ TOTAL │ │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└────────────────────────────────┴─────────────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────────┴────────────────────────┘ + SUMMARY METRICS +┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┓ +┃ Metric ┃ Value ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━┩ +│ Backtesting from │ 2025-01-01 00:00:00 │ +│ Backtesting to │ 2025-04-20 00:00:00 │ +│ Trading Mode │ Spot │ +│ Max open trades │ 2 │ +│ │ │ +│ Total/Daily Avg Trades │ 82 / 0.75 │ +│ Starting balance │ 1000 USDT │ +│ Final balance │ 849.735 USDT │ +│ Absolute profit │ -150.265 USDT │ +│ Total profit % │ -15.03% │ +│ CAGR % │ -42.03% │ +│ Sortino │ -252.56 │ +│ Sharpe │ -4.15 │ +│ Calmar │ -17.48 │ +│ SQN │ -2.60 │ +│ Profit factor │ 0.05 │ +│ Expectancy (Ratio) │ -1.83 (-0.79) │ +│ Avg. daily profit % │ -0.14% │ +│ Avg. stake amount │ 150 USDT │ +│ Total trade volume │ 24523.15 USDT │ +│ │ │ +│ Best Pair │ BTC/USDT -2.20% │ +│ Worst Pair │ SOL/USDT -12.82% │ +│ Best trade │ SOL/USDT 0.90% │ +│ Worst trade │ SOL/USDT -15.19% │ +│ Best day │ 1.76 USDT │ +│ Worst day │ -22.827 USDT │ +│ Days win/draw/lose │ 14 / 80 / 7 │ +│ Avg. Duration Winners │ 0:55:00 │ +│ Avg. Duration Loser │ 2 days, 18:13:00 │ +│ Max Consecutive Wins / Loss │ 2 / 16 │ +│ Rejected Entry signals │ 0 │ +│ Entry/Exit Timeouts │ 0 / 0 │ +│ │ │ +│ Min balance │ 849.735 USDT │ +│ Max balance │ 1000.508 USDT │ +│ Max % of account underwater │ 15.07% │ +│ Absolute Drawdown (Account) │ 15.07% │ +│ Absolute Drawdown │ 150.773 USDT │ +│ Drawdown high │ 0.508 USDT │ +│ Drawdown low │ -150.265 USDT │ +│ Drawdown Start │ 2025-01-06 19:48:00 │ +│ Drawdown End │ 2025-04-06 23:15:00 │ +│ Market change │ -26.79% │ +└─────────────────────────────┴─────────────────────┘ + +Backtested 2025-01-01 00:00:00 -> 2025-04-20 00:00:00 | Max open trades : 2 + STRATEGY SUMMARY +┏━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Strategy ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ Drawdown ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━┩ +│ FreqaiExampleStrategy │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ 150.773 USDT 15.07% │ +└───────────────────────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┴──────────────────────┘ diff --git a/freqai/data_kitchen.py b/freqai/data_kitchen.py new file mode 100644 index 00000000..a76eb52f --- /dev/null +++ b/freqai/data_kitchen.py @@ -0,0 +1,1162 @@ +import copy +import inspect +import logging +import random +import shutil +from datetime import datetime, timezone +from pathlib import Path +from typing import Any + +import numpy as np +import numpy.typing as npt +import pandas as pd +import psutil +from datasieve.pipeline import Pipeline +from pandas import DataFrame +from sklearn.model_selection import TimeSeriesSplit + +from freqtrade.configuration import TimeRange +from freqtrade.constants import DOCS_LINK, Config +from freqtrade.data.converter import reduce_dataframe_footprint +from freqtrade.exceptions import OperationalException +from freqtrade.exchange import timeframe_to_seconds +from freqtrade.strategy import merge_informative_pair +from freqtrade.strategy.interface import IStrategy + + +pd.set_option("future.no_silent_downcasting", True) + +SECONDS_IN_DAY = 86400 +SECONDS_IN_HOUR = 3600 + +logger = logging.getLogger(__name__) + + +class FreqaiDataKitchen: + """ + Class designed to analyze data for a single pair. Employed by the IFreqaiModel class. + Functionalities include holding, saving, loading, and analyzing the data. + + This object is not persistent, it is reinstantiated for each coin, each time the coin + model needs to be inferenced or trained. + + Record of contribution: + FreqAI was developed by a group of individuals who all contributed specific skillsets to the + project. + + Conception and software development: + Robert Caulk @robcaulk + + Theoretical brainstorming: + Elin Törnquist @th0rntwig + + Code review, software architecture brainstorming: + @xmatthias + + Beta testing and bug reporting: + @bloodhunter4rc, Salah Lamkadem @ikonx, @ken11o2, @longyu, @paranoidandy, @smidelis, @smarm + Juha Nykänen @suikula, Wagner Costa @wagnercosta, Johan Vlugt @Jooopieeert + """ + + def __init__( + self, + config: Config, + live: bool = False, + pair: str = "", + ): + self.data: dict[str, Any] = {} + self.data_dictionary: dict[str, DataFrame] = {} + self.config = config + self.freqai_config: dict[str, Any] = config["freqai"] + self.full_df: DataFrame = DataFrame() + self.append_df: DataFrame = DataFrame() + self.data_path = Path() + self.label_list: list = [] + self.training_features_list: list = [] + self.model_filename: str = "" + self.backtesting_results_path = Path() + self.backtest_predictions_folder: str = "backtesting_predictions" + self.live = live + self.pair = pair + self.keras: bool = self.freqai_config.get("keras", False) + self.set_all_pairs() + self.backtest_live_models = config.get("freqai_backtest_live_models", False) + self.feature_pipeline = Pipeline() + self.label_pipeline = Pipeline() + self.DI_values: npt.NDArray = np.array([]) + + if not self.live: + self.full_path = self.get_full_models_path(self.config) + + if not self.backtest_live_models: + self.full_timerange = self.create_fulltimerange( + self.config["timerange"], self.freqai_config.get("train_period_days", 0) + ) + (self.training_timeranges, self.backtesting_timeranges) = self.split_timerange( + self.full_timerange, + config["freqai"]["train_period_days"], + config["freqai"]["backtest_period_days"], + ) + + self.data["extra_returns_per_train"] = self.freqai_config.get("extra_returns_per_train", {}) + if not self.freqai_config.get("data_kitchen_thread_count", 0): + self.thread_count = max(int(psutil.cpu_count() * 2 - 2), 1) + else: + self.thread_count = self.freqai_config["data_kitchen_thread_count"] + self.train_dates: DataFrame = pd.DataFrame() + self.unique_classes: dict[str, list] = {} + self.unique_class_list: list = [] + self.backtest_live_models_data: dict[str, Any] = {} + + def set_paths( + self, + pair: str, + trained_timestamp: int | None = None, + ) -> None: + """ + Set the paths to the data for the present coin/botloop + :param metadata: dict = strategy furnished pair metadata + :param trained_timestamp: int = timestamp of most recent training + """ + self.full_path = self.get_full_models_path(self.config) + self.data_path = Path( + self.full_path / f"sub-train-{pair.split('/')[0]}_{trained_timestamp}" + ) + + return + +def _build_transform_pipeline(self, pipeline_steps: list) -> Pipeline: + transforms = [] + for step in pipeline_steps: + if step == "feature_engineering": + transforms.append(("feature_engineering", None)) # 由策略处理 + elif step == "scaling": + transforms.append(("scaling", StandardScaler())) + elif step == "dimensionality_reduction": + transforms.append(("dimensionality_reduction", PCA(n_components=0.99))) + elif step == "di": + transforms.append(("di", DI())) + else: + logger.warning(f"Unknown pipeline step: {step}") + logger.info(f"Feature pipeline steps: {[step[0] for step in transforms]}") + return Pipeline(transforms) + +def make_train_test_datasets( + + self, filtered_dataframe: DataFrame, labels: DataFrame + ) -> dict[Any, Any]: + """ + Given the dataframe for the full history for training, split the data into + training and test data according to user specified parameters in configuration + file. + :param filtered_dataframe: cleaned dataframe ready to be split. + :param labels: cleaned labels ready to be split. + """ + feat_dict = self.freqai_config["feature_parameters"] + + if "shuffle" not in self.freqai_config["data_split_parameters"]: + self.freqai_config["data_split_parameters"].update({"shuffle": False}) + + weights: npt.ArrayLike + if feat_dict.get("weight_factor", 0) > 0: + weights = self.set_weights_higher_recent(len(filtered_dataframe)) + else: + weights = np.ones(len(filtered_dataframe)) + + # Initialize TimeSeriesSplit + tscv = TimeSeriesSplit(n_splits=self.freqai_config.get("data_split_parameters", {}).get("n_splits", 5)) + + # Create empty lists to store the splits + train_features, test_features, train_labels, test_labels, train_weights, test_weights = [], [], [], [], [], [] + + # Generate indices for time series split + for train_index, test_index in tscv.split(filtered_dataframe): + train_features.append(filtered_dataframe.iloc[train_index]) + test_features.append(filtered_dataframe.iloc[test_index]) + train_labels.append(labels.iloc[train_index]) + test_labels.append(labels.iloc[test_index]) + train_weights.append(weights[train_index] if isinstance(weights, np.ndarray) else weights) + test_weights.append(weights[test_index] if isinstance(weights, np.ndarray) else weights) + + # Concatenate all splits into single DataFrames + train_features = pd.concat(train_features) + test_features = pd.concat(test_features) + train_labels = pd.concat(train_labels) + test_labels = pd.concat(test_labels) + train_weights = np.concatenate(train_weights) if isinstance(weights, np.ndarray) else weights + test_weights = np.concatenate(test_weights) if isinstance(weights, np.ndarray) else weights + + if feat_dict["shuffle_after_split"]: + rint1 = random.randint(0, 100) + rint2 = random.randint(0, 100) + train_features = train_features.sample(frac=1, random_state=rint1).reset_index( + drop=True + ) + train_labels = train_labels.sample(frac=1, random_state=rint1).reset_index(drop=True) + train_weights = ( + pd.DataFrame(train_weights) + .sample(frac=1, random_state=rint1) + .reset_index(drop=True) + .to_numpy()[:, 0] + ) + test_features = test_features.sample(frac=1, random_state=rint2).reset_index(drop=True) + test_labels = test_labels.sample(frac=1, random_state=rint2).reset_index(drop=True) + test_weights = ( + pd.DataFrame(test_weights) + .sample(frac=1, random_state=rint2) + .reset_index(drop=True) + .to_numpy()[:, 0] + ) + + # Simplest way to reverse the order of training and test data: + if self.freqai_config["feature_parameters"].get("reverse_train_test_order", False): + return self.build_data_dictionary( + test_features, + train_features, + test_labels, + train_labels, + test_weights, + train_weights, + ) + else: + return self.build_data_dictionary( + train_features, + test_features, + train_labels, + test_labels, + train_weights, + test_weights, + ) + self, filtered_dataframe: DataFrame, labels: DataFrame + ) -> dict[Any, Any]: + """ + Given the dataframe for the full history for training, split the data into + training and test data according to user specified parameters in configuration + file. + :param filtered_dataframe: cleaned dataframe ready to be split. + :param labels: cleaned labels ready to be split. + """ + feat_dict = self.freqai_config["feature_parameters"] + + if "shuffle" not in self.freqai_config["data_split_parameters"]: + self.freqai_config["data_split_parameters"].update({"shuffle": False}) + + weights: npt.ArrayLike + if feat_dict.get("weight_factor", 0) > 0: + weights = self.set_weights_higher_recent(len(filtered_dataframe)) + else: + weights = np.ones(len(filtered_dataframe)) + + # Initialize TimeSeriesSplit + tscv = TimeSeriesSplit(n_splits=self.freqai_config.get("data_split_parameters", {}).get("n_splits", 5)) + + # Create empty lists to store the splits + train_features, test_features, train_labels, test_labels, train_weights, test_weights = [], [], [], [], [], [] + + # Generate indices for time series split + for train_index, test_index in tscv.split(filtered_dataframe): + train_features.append(filtered_dataframe.iloc[train_index]) + test_features.append(filtered_dataframe.iloc[test_index]) + train_labels.append(labels.iloc[train_index]) + test_labels.append(labels.iloc[test_index]) + train_weights.append(weights[train_index] if isinstance(weights, np.ndarray) else weights) + test_weights.append(weights[test_index] if isinstance(weights, np.ndarray) else weights) + + # Concatenate all splits into single DataFrames + train_features = pd.concat(train_features) + test_features = pd.concat(test_features) + train_labels = pd.concat(train_labels) + test_labels = pd.concat(test_labels) + train_weights = np.concatenate(train_weights) if isinstance(weights, np.ndarray) else weights + test_weights = np.concatenate(test_weights) if isinstance(weights, np.ndarray) else weights + + if feat_dict["shuffle_after_split"]: + rint1 = random.randint(0, 100) + rint2 = random.randint(0, 100) + train_features = train_features.sample(frac=1, random_state=rint1).reset_index( + drop=True + ) + train_labels = train_labels.sample(frac=1, random_state=rint1).reset_index(drop=True) + train_weights = ( + pd.DataFrame(train_weights) + .sample(frac=1, random_state=rint1) + .reset_index(drop=True) + .to_numpy()[:, 0] + ) + test_features = test_features.sample(frac=1, random_state=rint2).reset_index(drop=True) + test_labels = test_labels.sample(frac=1, random_state=rint2).reset_index(drop=True) + test_weights = ( + pd.DataFrame(test_weights) + .sample(frac=1, random_state=rint2) + .reset_index(drop=True) + .to_numpy()[:, 0] + ) + + # Simplest way to reverse the order of training and test data: + if self.freqai_config["feature_parameters"].get("reverse_train_test_order", False): + return self.build_data_dictionary( + test_features, + train_features, + test_labels, + train_labels, + test_weights, + train_weights, + ) + else: + return self.build_data_dictionary( + train_features, + test_features, + train_labels, + test_labels, + train_weights, + test_weights, + ) + + def filter_features( + self, + unfiltered_df: DataFrame, + training_feature_list: list, + label_list: list | None = None, + training_filter: bool = True, + ) -> tuple[DataFrame, DataFrame]: + """ + Filter the unfiltered dataframe to extract the user requested features/labels and properly + remove all NaNs. Any row with a NaN is removed from training dataset or replaced with + 0s in the prediction dataset. However, prediction dataset do_predict will reflect any + row that had a NaN and will shield user from that prediction. + + :param unfiltered_df: the full dataframe for the present training period + :param training_feature_list: list, the training feature list constructed by + self.build_feature_list() according to user specified + parameters in the configuration file. + :param labels: the labels for the dataset + :param training_filter: boolean which lets the function know if it is training data or + prediction data to be filtered. + :returns: + :filtered_df: dataframe cleaned of NaNs and only containing the user + requested feature set. + :labels: labels cleaned of NaNs. + """ + filtered_df = unfiltered_df.filter(training_feature_list, axis=1) + filtered_df = filtered_df.replace([np.inf, -np.inf], np.nan) + + drop_index = pd.isnull(filtered_df).any(axis=1) # get the rows that have NaNs, + drop_index = drop_index.replace(True, 1).replace(False, 0).infer_objects(copy=False) + if training_filter: + # we don't care about total row number (total no. datapoints) in training, we only care + # about removing any row with NaNs + # if labels has multiple columns (user wants to train multiple modelEs), we detect here + labels = unfiltered_df.filter(label_list or [], axis=1) + drop_index_labels = pd.isnull(labels).any(axis=1) + drop_index_labels = ( + drop_index_labels.replace(True, 1).replace(False, 0).infer_objects(copy=False) + ) + dates = unfiltered_df["date"] + filtered_df = filtered_df[ + (drop_index == 0) & (drop_index_labels == 0) + ] # dropping values + labels = labels[ + (drop_index == 0) & (drop_index_labels == 0) + ] # assuming the labels depend entirely on the dataframe here. + self.train_dates = dates[(drop_index == 0) & (drop_index_labels == 0)] + logger.info( + f"{self.pair}: dropped {len(unfiltered_df) - len(filtered_df)} training points" + f" due to NaNs in populated dataset {len(unfiltered_df)}." + ) + if len(filtered_df) == 0 and not self.live: + raise OperationalException( + f"{self.pair}: all training data dropped due to NaNs. " + "You likely did not download enough training data prior " + "to your backtest timerange. Hint:\n" + f"{DOCS_LINK}/freqai-running/" + "#downloading-data-to-cover-the-full-backtest-period" + ) + if (1 - len(filtered_df) / len(unfiltered_df)) > 0.1 and self.live: + worst_indicator = str(unfiltered_df.count().idxmin()) + logger.warning( + f" {(1 - len(filtered_df) / len(unfiltered_df)) * 100:.0f} percent " + " of training data dropped due to NaNs, model may perform inconsistent " + f"with expectations. Verify {worst_indicator}" + ) + self.data["filter_drop_index_training"] = drop_index + + else: + # we are backtesting so we need to preserve row number to send back to strategy, + # so now we use do_predict to avoid any prediction based on a NaN + drop_index = pd.isnull(filtered_df).any(axis=1) + self.data["filter_drop_index_prediction"] = drop_index + filtered_df.fillna(0, inplace=True) + # replacing all NaNs with zeros to avoid issues in 'prediction', but any prediction + # that was based on a single NaN is ultimately protected from buys with do_predict + drop_index = ~drop_index + self.do_predict = np.array(drop_index.replace(True, 1).replace(False, 0)) + if (len(self.do_predict) - self.do_predict.sum()) > 0: + logger.info( + "dropped %s of %s prediction data points due to NaNs.", + len(self.do_predict) - self.do_predict.sum(), + len(filtered_df), + ) + labels = [] + + return filtered_df, labels + + def build_data_dictionary( + self, + train_df: DataFrame, + test_df: DataFrame, + train_labels: DataFrame, + test_labels: DataFrame, + train_weights: Any, + test_weights: Any, + ) -> dict: + self.data_dictionary = { + "train_features": train_df, + "test_features": test_df, + "train_labels": train_labels, + "test_labels": test_labels, + "train_weights": train_weights, + "test_weights": test_weights, + "train_dates": self.train_dates, + } + + return self.data_dictionary + + def split_timerange( + self, tr: str, train_split: int = 28, bt_split: float = 7 + ) -> tuple[list, list]: + """ + Function which takes a single time range (tr) and splits it + into sub timeranges to train and backtest on based on user input + tr: str, full timerange to train on + train_split: the period length for the each training (days). Specified in user + configuration file + bt_split: the backtesting length (days). Specified in user configuration file + """ + + if not isinstance(train_split, int) or train_split < 1: + raise OperationalException( + f"train_period_days must be an integer greater than 0. Got {train_split}." + ) + train_period_days = train_split * SECONDS_IN_DAY + bt_period = bt_split * SECONDS_IN_DAY + + full_timerange = TimeRange.parse_timerange(tr) + config_timerange = TimeRange.parse_timerange(self.config["timerange"]) + if config_timerange.stopts == 0: + config_timerange.stopts = int(datetime.now(tz=timezone.utc).timestamp()) + timerange_train = copy.deepcopy(full_timerange) + timerange_backtest = copy.deepcopy(full_timerange) + + tr_training_list = [] + tr_backtesting_list = [] + tr_training_list_timerange = [] + tr_backtesting_list_timerange = [] + first = True + + while True: + if not first: + timerange_train.startts = timerange_train.startts + int(bt_period) + timerange_train.stopts = timerange_train.startts + train_period_days + + first = False + tr_training_list.append(timerange_train.timerange_str) + tr_training_list_timerange.append(copy.deepcopy(timerange_train)) + + # associated backtest period + timerange_backtest.startts = timerange_train.stopts + timerange_backtest.stopts = timerange_backtest.startts + int(bt_period) + + if timerange_backtest.stopts > config_timerange.stopts: + timerange_backtest.stopts = config_timerange.stopts + + tr_backtesting_list.append(timerange_backtest.timerange_str) + tr_backtesting_list_timerange.append(copy.deepcopy(timerange_backtest)) + + # ensure we are predicting on exactly same amount of data as requested by user defined + # --timerange + if timerange_backtest.stopts == config_timerange.stopts: + break + + # print(tr_training_list, tr_backtesting_list) + return tr_training_list_timerange, tr_backtesting_list_timerange + + def slice_dataframe(self, timerange: TimeRange, df: DataFrame) -> DataFrame: + """ + Given a full dataframe, extract the user desired window + :param tr: timerange string that we wish to extract from df + :param df: Dataframe containing all candles to run the entire backtest. Here + it is sliced down to just the present training period. + """ + if not self.live: + df = df.loc[(df["date"] >= timerange.startdt) & (df["date"] < timerange.stopdt), :] + else: + df = df.loc[df["date"] >= timerange.startdt, :] + + return df + + def find_features(self, dataframe: DataFrame) -> None: + """ + Find features in the strategy provided dataframe + :param dataframe: DataFrame = strategy provided dataframe + :return: + features: list = the features to be used for training/prediction + """ + column_names = dataframe.columns + features = [c for c in column_names if "%" in c] + + if not features: + raise OperationalException("Could not find any features!") + + self.training_features_list = features + + def find_labels(self, dataframe: DataFrame) -> None: + column_names = dataframe.columns + labels = [c for c in column_names if "&" in c] + self.label_list = labels + + def set_weights_higher_recent(self, num_weights: int) -> npt.ArrayLike: + """ + Set weights so that recent data is more heavily weighted during + training than older data. + """ + wfactor = self.config["freqai"]["feature_parameters"]["weight_factor"] + weights = np.exp(-np.arange(num_weights) / (wfactor * num_weights))[::-1] + return weights + + def get_predictions_to_append( + self, predictions: DataFrame, do_predict: npt.ArrayLike, dataframe_backtest: DataFrame + ) -> DataFrame: + """ + Get backtest prediction from current backtest period + """ + append_df = DataFrame() + pair = self.pair.replace("/", "") # 格式化交易对，如 BTCUSDT + timeframe = self.timeframe # 如 5m + period = self.indicator_periods_candles[0] if self.indicator_periods_candles else 12 # 默认 12 + + # Debugging logs + logger.info(f"predictions.columns: {predictions.columns.tolist()}") + logger.info(f"self.label_list: {self.label_list}") + logger.info(f"self.data['labels_mean']: {self.data.get('labels_mean', {})}") + + for label in self.label_list: + # Check if predictions contain the label directly + if label in predictions.columns: + append_df[f"{label}_pred_{period}_{pair}_{timeframe}"] = predictions[label] + logger.info(f"Using predictions['{label}'] for {label}_pred_{period}_{pair}_{timeframe}") + else: + # Handle binary classification case + if set([0, 1]).issubset(predictions.columns): + append_df[f"{label}_pred_{period}_{pair}_{timeframe}"] = predictions[1] + logger.info(f"Mapping predictions[1] to {label}_pred_{period}_{pair}_{timeframe}") + else: + raise OperationalException( + f"Prediction columns {predictions.columns.tolist()} do not match " + f"expected label {label} or binary classes [0, 1]" + ) + + # Attach mean and std if available + if append_df[f"{label}_pred_{period}_{pair}_{timeframe}"].dtype != object: + if "labels_mean" in self.data and label in self.data["labels_mean"]: + append_df[f"{label}_mean"] = self.data["labels_mean"][label] + else: + logger.warning(f"labels_mean for {label} not found, setting to 0") + append_df[f"{label}_mean"] = 0 + + if "labels_std" in self.data and label in self.data["labels_std"]: + append_df[f"{label}_std"] = self.data["labels_std"][label] + else: + logger.warning(f"labels_std for {label} not found, setting to 0") + append_df[f"{label}_std"] = 0 + + # Attach additional columns + for extra_col in self.data["extra_returns_per_train"]: + append_df[f"{extra_col}"] = self.data["extra_returns_per_train"][extra_col] + + append_df["do_predict"] = do_predict + if self.freqai_config["feature_parameters"].get("DI_threshold", 0) > 0: + append_df["DI_values"] = self.DI_values + + # Merge with backtest dataframe + user_cols = [col for col in dataframe_backtest.columns if col.startswith("%%")] + cols = ["date"] + cols.extend(user_cols) + + dataframe_backtest.reset_index(drop=True, inplace=True) + merged_df = pd.concat([dataframe_backtest[cols], append_df], axis=1) + return merged_df + + def append_predictions(self, append_df: DataFrame) -> None: + """ + Append backtest prediction from current backtest period to all previous periods + """ + + if self.full_df.empty: + self.full_df = append_df + else: + self.full_df = pd.concat([self.full_df, append_df], axis=0, ignore_index=True) + + def fill_predictions(self, dataframe): + """ + Back fill values to before the backtesting range so that the dataframe matches size + when it goes back to the strategy. These rows are not included in the backtest. + """ + to_keep = [ + col for col in dataframe.columns if not col.startswith("&") and not col.startswith("%%") + ] + self.return_dataframe = pd.merge(dataframe[to_keep], self.full_df, how="left", on="date") + self.return_dataframe[self.full_df.columns] = self.return_dataframe[ + self.full_df.columns + ].fillna(value=0) + self.full_df = DataFrame() + + return + + def create_fulltimerange(self, backtest_tr: str, backtest_period_days: int) -> str: + if not isinstance(backtest_period_days, int): + raise OperationalException("backtest_period_days must be an integer") + + if backtest_period_days < 0: + raise OperationalException("backtest_period_days must be positive") + + backtest_timerange = TimeRange.parse_timerange(backtest_tr) + + if backtest_timerange.stopts == 0: + # typically open ended time ranges do work, however, there are some edge cases where + # it does not. accommodating these kinds of edge cases just to allow open-ended + # timerange is not high enough priority to warrant the effort. It is safer for now + # to simply ask user to add their end date + raise OperationalException( + "FreqAI backtesting does not allow open ended timeranges. " + "Please indicate the end date of your desired backtesting. " + "timerange." + ) + # backtest_timerange.stopts = int( + # datetime.now(tz=timezone.utc).timestamp() + # ) + + backtest_timerange.startts = ( + backtest_timerange.startts - backtest_period_days * SECONDS_IN_DAY + ) + full_timerange = backtest_timerange.timerange_str + config_path = Path(self.config["config_files"][0]) + + if not self.full_path.is_dir(): + self.full_path.mkdir(parents=True, exist_ok=True) + shutil.copy( + config_path.resolve(), + Path(self.full_path / config_path.parts[-1]), + ) + + return full_timerange + + def check_if_model_expired(self, trained_timestamp: int) -> bool: + """ + A model age checker to determine if the model is trustworthy based on user defined + `expiration_hours` in the configuration file. + :param trained_timestamp: int = The time of training for the most recent model. + :return: + bool = If the model is expired or not. + """ + time = datetime.now(tz=timezone.utc).timestamp() + elapsed_time = (time - trained_timestamp) / 3600 # hours + max_time = self.freqai_config.get("expiration_hours", 0) + if max_time > 0: + return elapsed_time > max_time + else: + return False + + def check_if_new_training_required( + self, trained_timestamp: int + ) -> tuple[bool, TimeRange, TimeRange]: + time = datetime.now(tz=timezone.utc).timestamp() + trained_timerange = TimeRange() + data_load_timerange = TimeRange() + + timeframes = self.freqai_config["feature_parameters"].get("include_timeframes") + + max_tf_seconds = 0 + for tf in timeframes: + secs = timeframe_to_seconds(tf) + if secs > max_tf_seconds: + max_tf_seconds = secs + + # We notice that users like to use exotic indicators where + # they do not know the required timeperiod. Here we include a factor + # of safety by multiplying the user considered "max" by 2. + max_period = self.config.get("startup_candle_count", 20) * 2 + additional_seconds = max_period * max_tf_seconds + + if trained_timestamp != 0: + elapsed_time = (time - trained_timestamp) / SECONDS_IN_HOUR + retrain = elapsed_time > self.freqai_config.get("live_retrain_hours", 0) + if retrain: + trained_timerange.startts = int( + time - self.freqai_config.get("train_period_days", 0) * SECONDS_IN_DAY + ) + trained_timerange.stopts = int(time) + # we want to load/populate indicators on more data than we plan to train on so + # because most of the indicators have a rolling timeperiod, and are thus NaNs + # unless they have data further back in time before the start of the train period + data_load_timerange.startts = int( + time + - self.freqai_config.get("train_period_days", 0) * SECONDS_IN_DAY + - additional_seconds + ) + data_load_timerange.stopts = int(time) + else: # user passed no live_trained_timerange in config + trained_timerange.startts = int( + time - self.freqai_config.get("train_period_days", 0) * SECONDS_IN_DAY + ) + trained_timerange.stopts = int(time) + + data_load_timerange.startts = int( + time + - self.freqai_config.get("train_period_days", 0) * SECONDS_IN_DAY + - additional_seconds + ) + data_load_timerange.stopts = int(time) + retrain = True + + return retrain, trained_timerange, data_load_timerange + + def set_new_model_names(self, pair: str, timestamp_id: int): + coin, _ = pair.split("/") + self.data_path = Path(self.full_path / f"sub-train-{pair.split('/')[0]}_{timestamp_id}") + + self.model_filename = f"cb_{coin.lower()}_{timestamp_id}" + + def set_all_pairs(self) -> None: + self.all_pairs = copy.deepcopy( + self.freqai_config["feature_parameters"].get("include_corr_pairlist", []) + ) + for pair in self.config.get("exchange", "").get("pair_whitelist"): + if pair not in self.all_pairs: + self.all_pairs.append(pair) + + def extract_corr_pair_columns_from_populated_indicators( + self, dataframe: DataFrame + ) -> dict[str, DataFrame]: + """ + Find the columns of the dataframe corresponding to the corr_pairlist, save them + in a dictionary to be reused and attached to other pairs. + + :param dataframe: fully populated dataframe (current pair + corr_pairs) + :return: corr_dataframes, dictionary of dataframes to be attached + to other pairs in same candle. + """ + corr_dataframes: dict[str, DataFrame] = {} + pairs = self.freqai_config["feature_parameters"].get("include_corr_pairlist", []) + + for pair in pairs: + pair = pair.replace(":", "") # lightgbm does not like colons + pair_cols = [ + col for col in dataframe.columns if col.startswith("%") and f"{pair}_" in col + ] + + if pair_cols: + pair_cols.insert(0, "date") + corr_dataframes[pair] = dataframe.filter(pair_cols, axis=1) + + return corr_dataframes + + def attach_corr_pair_columns( + self, dataframe: DataFrame, corr_dataframes: dict[str, DataFrame], current_pair: str + ) -> DataFrame: + """ + Attach the existing corr_pair dataframes to the current pair dataframe before training + + :param dataframe: current pair strategy dataframe, indicators populated already + :param corr_dataframes: dictionary of saved dataframes from earlier in the same candle + :param current_pair: current pair to which we will attach corr pair dataframe + :return: + :dataframe: current pair dataframe of populated indicators, concatenated with corr_pairs + ready for training + """ + pairs = self.freqai_config["feature_parameters"].get("include_corr_pairlist", []) + current_pair = current_pair.replace(":", "") + for pair in pairs: + pair = pair.replace(":", "") # lightgbm does not work with colons + if current_pair != pair: + dataframe = dataframe.merge(corr_dataframes[pair], how="left", on="date") + + return dataframe + + def get_pair_data_for_features( + self, + pair: str, + tf: str, + strategy: IStrategy, + corr_dataframes: dict, + base_dataframes: dict, + is_corr_pairs: bool = False, + ) -> DataFrame: + """ + Get the data for the pair. If it's not in the dictionary, get it from the data provider + :param pair: str = pair to get data for + :param tf: str = timeframe to get data for + :param strategy: IStrategy = user defined strategy object + :param corr_dataframes: dict = dict containing the df pair dataframes + (for user defined timeframes) + :param base_dataframes: dict = dict containing the current pair dataframes + (for user defined timeframes) + :param is_corr_pairs: bool = whether the pair is a corr pair or not + :return: dataframe = dataframe containing the pair data + """ + if is_corr_pairs: + dataframe = corr_dataframes[pair][tf] + if not dataframe.empty: + return dataframe + else: + dataframe = strategy.dp.get_pair_dataframe(pair=pair, timeframe=tf) + return dataframe + else: + dataframe = base_dataframes[tf] + if not dataframe.empty: + return dataframe + else: + dataframe = strategy.dp.get_pair_dataframe(pair=pair, timeframe=tf) + return dataframe + + def merge_features( + self, df_main: DataFrame, df_to_merge: DataFrame, tf: str, timeframe_inf: str, suffix: str + ) -> DataFrame: + """ + Merge the features of the dataframe and remove HLCV and date added columns + :param df_main: DataFrame = main dataframe + :param df_to_merge: DataFrame = dataframe to merge + :param tf: str = timeframe of the main dataframe + :param timeframe_inf: str = timeframe of the dataframe to merge + :param suffix: str = suffix to add to the columns of the dataframe to merge + :return: dataframe = merged dataframe + """ + dataframe = merge_informative_pair( + df_main, + df_to_merge, + tf, + timeframe_inf=timeframe_inf, + append_timeframe=False, + suffix=suffix, + ffill=True, + ) + skip_columns = [ + (f"{s}_{suffix}") for s in ["date", "open", "high", "low", "close", "volume"] + ] + dataframe = dataframe.drop(columns=skip_columns) + return dataframe + + def populate_features( + self, + dataframe: DataFrame, + pair: str, + strategy: IStrategy, + corr_dataframes: dict, + base_dataframes: dict, + is_corr_pairs: bool = False, + ) -> DataFrame: + """ + Use the user defined strategy functions for populating features + :param dataframe: DataFrame = dataframe to populate + :param pair: str = pair to populate + :param strategy: IStrategy = user defined strategy object + :param corr_dataframes: dict = dict containing the df pair dataframes + :param base_dataframes: dict = dict containing the current pair dataframes + :param is_corr_pairs: bool = whether the pair is a corr pair or not + :return: dataframe = populated dataframe + """ + tfs: list[str] = self.freqai_config["feature_parameters"].get("include_timeframes") + + for tf in tfs: + metadata = {"pair": pair, "tf": tf} + informative_df = self.get_pair_data_for_features( + pair, tf, strategy, corr_dataframes, base_dataframes, is_corr_pairs + ) + informative_copy = informative_df.copy() + + logger.debug(f"Populating features for {pair} {tf}") + + for t in self.freqai_config["feature_parameters"]["indicator_periods_candles"]: + df_features = strategy.feature_engineering_expand_all( + informative_copy.copy(), t, metadata=metadata + ) + suffix = f"{t}" + informative_df = self.merge_features(informative_df, df_features, tf, tf, suffix) + + generic_df = strategy.feature_engineering_expand_basic( + informative_copy.copy(), metadata=metadata + ) + suffix = "gen" + + informative_df = self.merge_features(informative_df, generic_df, tf, tf, suffix) + + indicators = [col for col in informative_df if col.startswith("%")] + for n in range(self.freqai_config["feature_parameters"]["include_shifted_candles"] + 1): + if n == 0: + continue + df_shift = informative_df[indicators].shift(n) + df_shift = df_shift.add_suffix("_shift-" + str(n)) + informative_df = pd.concat((informative_df, df_shift), axis=1) + + dataframe = self.merge_features( + dataframe.copy(), informative_df, self.config["timeframe"], tf, f"{pair}_{tf}" + ) + + return dataframe + + def use_strategy_to_populate_indicators( # noqa: C901 + self, + strategy: IStrategy, + corr_dataframes: dict[str, DataFrame] | None = None, + base_dataframes: dict[str, dict[str, DataFrame]] | None = None, + pair: str = "", + prediction_dataframe: DataFrame | None = None, + do_corr_pairs: bool = True, + ) -> DataFrame: + """ + Use the user defined strategy for populating indicators during retrain + :param strategy: IStrategy = user defined strategy object + :param corr_dataframes: dict = dict containing the df pair dataframes + (for user defined timeframes) + :param base_dataframes: dict = dict containing the current pair dataframes + (for user defined timeframes) + :param pair: str = pair to populate + :param prediction_dataframe: DataFrame = dataframe containing the pair data + used for prediction + :param do_corr_pairs: bool = whether to populate corr pairs or not + :return: + dataframe: DataFrame = dataframe containing populated indicators + """ + if not corr_dataframes: + corr_dataframes = {} + if not base_dataframes: + base_dataframes = {} + + # check if the user is using the deprecated populate_any_indicators function + new_version = inspect.getsource(strategy.populate_any_indicators) == ( + inspect.getsource(IStrategy.populate_any_indicators) + ) + + if not new_version: + raise OperationalException( + "You are using the `populate_any_indicators()` function" + " which was deprecated on March 1, 2023. Please refer " + "to the strategy migration guide to use the new " + "feature_engineering_* methods: \n" + f"{DOCS_LINK}/strategy_migration/#freqai-strategy \n" + "And the feature_engineering_* documentation: \n" + f"{DOCS_LINK}/freqai-feature-engineering/" + ) + + tfs: list[str] = self.freqai_config["feature_parameters"].get("include_timeframes") + pairs: list[str] = self.freqai_config["feature_parameters"].get("include_corr_pairlist", []) + + for tf in tfs: + if tf not in base_dataframes: + base_dataframes[tf] = pd.DataFrame() + for p in pairs: + if p not in corr_dataframes: + corr_dataframes[p] = {} + if tf not in corr_dataframes[p]: + corr_dataframes[p][tf] = pd.DataFrame() + + if prediction_dataframe is not None and not prediction_dataframe.empty: + dataframe = prediction_dataframe.copy() + base_dataframes[self.config["timeframe"]] = dataframe.copy() + else: + dataframe = base_dataframes[self.config["timeframe"]].copy() + + corr_pairs: list[str] = self.freqai_config["feature_parameters"].get( + "include_corr_pairlist", [] + ) + dataframe = self.populate_features( + dataframe.copy(), pair, strategy, corr_dataframes, base_dataframes + ) + metadata = {"pair": pair} + dataframe = strategy.feature_engineering_standard(dataframe.copy(), metadata=metadata) + # ensure corr pairs are always last + for corr_pair in corr_pairs: + if pair == corr_pair: + continue # dont repeat anything from whitelist + if corr_pairs and do_corr_pairs: + dataframe = self.populate_features( + dataframe.copy(), corr_pair, strategy, corr_dataframes, base_dataframes, True + ) + + if self.live: + dataframe = strategy.set_freqai_targets(dataframe.copy(), metadata=metadata) + dataframe = self.remove_special_chars_from_feature_names(dataframe) + + self.get_unique_classes_from_labels(dataframe) + + if self.config.get("reduce_df_footprint", False): + dataframe = reduce_dataframe_footprint(dataframe) + + return dataframe + + def fit_labels(self) -> None: + """ + Fit the labels with a gaussian distribution + """ + import scipy as spy + + self.data["labels_mean"], self.data["labels_std"] = {}, {} + for label in self.data_dictionary["train_labels"].columns: + if self.data_dictionary["train_labels"][label].dtype == object: + continue + f = spy.stats.norm.fit(self.data_dictionary["train_labels"][label]) + self.data["labels_mean"][label], self.data["labels_std"][label] = f[0], f[1] + + # in case targets are classifications + for label in self.unique_class_list: + self.data["labels_mean"][label], self.data["labels_std"][label] = 0, 0 + + return + + def remove_features_from_df(self, dataframe: DataFrame) -> DataFrame: + """ + Remove the features from the dataframe before returning it to strategy. This keeps it + compact for Frequi purposes. + """ + to_keep = [ + col for col in dataframe.columns if not col.startswith("%") or col.startswith("%%") + ] + return dataframe[to_keep] + + def get_unique_classes_from_labels(self, dataframe: DataFrame) -> None: + # self.find_features(dataframe) + self.find_labels(dataframe) + + for key in self.label_list: + if dataframe[key].dtype == object: + self.unique_classes[key] = dataframe[key].dropna().unique() + + if self.unique_classes: + for label in self.unique_classes: + self.unique_class_list += list(self.unique_classes[label]) + + def save_backtesting_prediction(self, append_df: DataFrame) -> None: + """ + Save prediction dataframe from backtesting to feather file format + :param append_df: dataframe for backtesting period + """ + full_predictions_folder = Path(self.full_path / self.backtest_predictions_folder) + if not full_predictions_folder.is_dir(): + full_predictions_folder.mkdir(parents=True, exist_ok=True) + + append_df.to_feather(self.backtesting_results_path) + + def get_backtesting_prediction(self) -> DataFrame: + """ + Get prediction dataframe from feather file format + """ + append_df = pd.read_feather(self.backtesting_results_path) + return append_df + + def check_if_backtest_prediction_is_valid(self, len_backtest_df: int) -> bool: + """ + Check if a backtesting prediction already exists and if the predictions + to append have the same size as the backtesting dataframe slice + :param length_backtesting_dataframe: Length of backtesting dataframe slice + :return: + :boolean: whether the prediction file is valid. + """ + path_to_predictionfile = Path( + self.full_path + / self.backtest_predictions_folder + / f"{self.model_filename}_prediction.feather" + ) + self.backtesting_results_path = path_to_predictionfile + + file_exists = path_to_predictionfile.is_file() + + if file_exists: + append_df = self.get_backtesting_prediction() + if len(append_df) == len_backtest_df and "date" in append_df: + logger.info(f"Found backtesting prediction file at {path_to_predictionfile}") + return True + else: + logger.info( + "A new backtesting prediction file is required. " + "(Number of predictions is different from dataframe length or " + "old prediction file version)." + ) + return False + else: + logger.info(f"Could not find backtesting prediction file at {path_to_predictionfile}") + return False + + def get_full_models_path(self, config: Config) -> Path: + """ + Returns default FreqAI model path + :param config: Configuration dictionary + """ + freqai_config: dict[str, Any] = config["freqai"] + return Path(config["user_data_dir"] / "models" / str(freqai_config.get("identifier"))) + + def remove_special_chars_from_feature_names(self, dataframe: pd.DataFrame) -> pd.DataFrame: + """ + Remove all special characters from feature strings (:) + :param dataframe: the dataframe that just finished indicator population. (unfiltered) + :return: dataframe with cleaned feature names + """ + + spec_chars = [":"] + for c in spec_chars: + dataframe.columns = dataframe.columns.str.replace(c, "") + + return dataframe + + def buffer_timerange(self, timerange: TimeRange): + """ + Buffer the start and end of the timerange. This is used *after* the indicators + are populated. + + The main example use is when predicting maxima and minima, the argrelextrema + function cannot know the maxima/minima at the edges of the timerange. To improve + model accuracy, it is best to compute argrelextrema on the full timerange + and then use this function to cut off the edges (buffer) by the kernel. + + In another case, if the targets are set to a shifted price movement, this + buffer is unnecessary because the shifted candles at the end of the timerange + will be NaN and FreqAI will automatically cut those off of the training + dataset. + """ + buffer = self.freqai_config["feature_parameters"]["buffer_train_data_candles"] + if buffer: + timerange.stopts -= buffer * timeframe_to_seconds(self.config["timeframe"]) + timerange.startts += buffer * timeframe_to_seconds(self.config["timeframe"]) + + return timerange + + # deprecated functions + def normalize_data(self, data_dictionary: dict) -> dict[Any, Any]: + """ + Deprecation warning, migration assistance + """ + logger.warning( + f"Your custom IFreqaiModel relies on the deprecated" + " data pipeline. Please update your model to use the new data pipeline." + " This can be achieved by following the migration guide at " + f"{DOCS_LINK}/strategy_migration/#freqai-new-data-pipeline " + "We added a basic pipeline for you, but this will be removed " + "in a future version." + ) + + return data_dictionary + + def denormalize_labels_from_metadata(self, df: DataFrame) -> DataFrame: + """ + Deprecation warning, migration assistance + """ + logger.warning( + f"Your custom IFreqaiModel relies on the deprecated" + " data pipeline. Please update your model to use the new data pipeline." + " This can be achieved by following the migration guide at " + f"{DOCS_LINK}/strategy_migration/#freqai-new-data-pipeline " + "We added a basic pipeline for you, but this will be removed " + "in a future version." + ) + + pred_df, _, _ = self.label_pipeline.inverse_transform(df) + + return pred_df diff --git a/freqtrade.log b/freqtrade.log new file mode 100644 index 00000000..13c51d31 --- /dev/null +++ b/freqtrade.log @@ -0,0 +1,3066 @@ +Creating freqtrade_freqtrade_run ... +Creating freqtrade_freqtrade_run ... done +2025-04-29 01:54:55,246 - freqtrade - INFO - freqtrade 2025.3 +2025-04-29 01:54:55,464 - numexpr.utils - INFO - NumExpr defaulting to 12 threads. +2025-04-29 01:54:56,878 - freqtrade.configuration.load_config - INFO - Using config: /freqtrade/config_examples/config_freqai.okx.json ... +2025-04-29 01:54:56,879 - freqtrade.configuration.load_config - INFO - Using config: /freqtrade/templates/FreqaiExampleStrategy.json ... +2025-04-29 01:54:56,881 - freqtrade.loggers - INFO - Enabling colorized output. +2025-04-29 01:54:56,881 - root - INFO - Logfile configured +2025-04-29 01:54:56,882 - freqtrade.loggers - INFO - Verbosity set to 0 +2025-04-29 01:54:56,882 - freqtrade.configuration.configuration - INFO - Using additional Strategy lookup path: /freqtrade/templates +2025-04-29 01:54:56,883 - freqtrade.configuration.configuration - INFO - Using max_open_trades: 4 ... +2025-04-29 01:54:56,883 - freqtrade.configuration.configuration - INFO - Parameter --timerange detected: 20250101-20250420 ... +2025-04-29 01:54:56,907 - freqtrade.configuration.configuration - INFO - Using user-data directory: /freqtrade/user_data ... +2025-04-29 01:54:56,908 - freqtrade.configuration.configuration - INFO - Using data directory: /freqtrade/user_data/data/okx ... +2025-04-29 01:54:56,908 - freqtrade.configuration.configuration - INFO - Parameter --cache=none detected ... +2025-04-29 01:54:56,908 - freqtrade.configuration.configuration - INFO - Filter trades by timerange: 20250101-20250420 +2025-04-29 01:54:56,909 - freqtrade.configuration.configuration - INFO - Using freqaimodel class name: XGBoostRegressor +2025-04-29 01:54:56,910 - freqtrade.exchange.check_exchange - INFO - Checking exchange... +2025-04-29 01:54:56,916 - freqtrade.exchange.check_exchange - INFO - Exchange "okx" is officially supported by the Freqtrade development team. +2025-04-29 01:54:56,916 - freqtrade.configuration.configuration - INFO - Using pairlist from configuration. +2025-04-29 01:54:56,917 - freqtrade.configuration.config_validation - INFO - Validating configuration ... +2025-04-29 01:54:56,919 - freqtrade.commands.optimize_commands - INFO - Starting freqtrade in Backtesting mode +2025-04-29 01:54:56,919 - freqtrade.exchange.exchange - INFO - Instance is running with dry_run enabled +2025-04-29 01:54:56,920 - freqtrade.exchange.exchange - INFO - Using CCXT 4.4.69 +2025-04-29 01:54:56,920 - freqtrade.exchange.exchange - INFO - Applying additional ccxt config: {'enableRateLimit': True, 'rateLimit': 500, 'options': {'defaultType': 'spot'}} +2025-04-29 01:54:56,925 - freqtrade.exchange.exchange - INFO - Applying additional ccxt config: {'enableRateLimit': True, 'rateLimit': 500, 'options': {'defaultType': 'spot'}, 'timeout': 20000} +2025-04-29 01:54:56,931 - freqtrade.exchange.exchange - INFO - Using Exchange "OKX" +2025-04-29 01:54:59,471 - freqtrade.resolvers.exchange_resolver - INFO - Using resolved exchange 'Okx'... +2025-04-29 01:54:59,491 - freqtrade.resolvers.iresolver - INFO - Using resolved strategy FreqaiExampleStrategy from '/freqtrade/templates/FreqaiExampleStrategy.py'... +2025-04-29 01:54:59,491 - freqtrade.strategy.hyper - INFO - Loading parameters from file /freqtrade/templates/FreqaiExampleStrategy.json +2025-04-29 01:54:59,492 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'timeframe' with value in config file: 3m. +2025-04-29 01:54:59,492 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'stoploss' with value in config file: -0.05. +2025-04-29 01:54:59,493 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'stake_currency' with value in config file: USDT. +2025-04-29 01:54:59,493 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'stake_amount' with value in config file: 150. +2025-04-29 01:54:59,493 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'startup_candle_count' with value in config file: 30. +2025-04-29 01:54:59,494 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'unfilledtimeout' with value in config file: {'entry': 5, 'exit': 15, 'exit_timeout_count': 0, 'unit': +'minutes'}. +2025-04-29 01:54:59,494 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'max_open_trades' with value in config file: 4. +2025-04-29 01:54:59,494 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using minimal_roi: {'0': 0.132, '8': 0.047, '14': 0.007, '60': 0} +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using timeframe: 3m +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using stoploss: -0.05 +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_stop: True +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_stop_positive: 0.01 +2025-04-29 01:54:59,496 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_stop_positive_offset: 0.02 +2025-04-29 01:54:59,496 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_only_offset_is_reached: False +2025-04-29 01:54:59,496 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using use_custom_stoploss: False +2025-04-29 01:54:59,497 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using process_only_new_candles: True +2025-04-29 01:54:59,497 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using order_types: {'entry': 'limit', 'exit': 'limit', 'stoploss': 'limit', 'stoploss_on_exchange': False, +'stoploss_on_exchange_interval': 60} +2025-04-29 01:54:59,497 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using order_time_in_force: {'entry': 'GTC', 'exit': 'GTC'} +2025-04-29 01:54:59,498 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using stake_currency: USDT +2025-04-29 01:54:59,498 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using stake_amount: 150 +2025-04-29 01:54:59,498 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using startup_candle_count: 30 +2025-04-29 01:54:59,499 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using unfilledtimeout: {'entry': 5, 'exit': 15, 'exit_timeout_count': 0, 'unit': 'minutes'} +2025-04-29 01:54:59,499 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using use_exit_signal: True +2025-04-29 01:54:59,499 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using exit_profit_only: False +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using ignore_roi_if_entry_signal: False +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using exit_profit_offset: 0.0 +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using disable_dataframe_checks: False +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using ignore_buying_expired_candle_after: 0 +2025-04-29 01:54:59,501 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using position_adjustment_enable: False +2025-04-29 01:54:59,501 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using max_entry_position_adjustment: -1 +2025-04-29 01:54:59,501 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using max_open_trades: 4 +2025-04-29 01:54:59,502 - freqtrade.configuration.config_validation - INFO - Validating configuration ... +2025-04-29 01:54:59,505 - freqtrade.resolvers.iresolver - INFO - Using resolved pairlist StaticPairList from '/freqtrade/freqtrade/plugins/pairlist/StaticPairList.py'... +2025-04-29 01:54:59,512 - freqtrade.optimize.backtesting - INFO - Using fee 0.1500% - worst case fee from exchange (lowest tier). +2025-04-29 01:54:59,512 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 3m to 14450 +2025-04-29 01:54:59,513 - freqtrade.data.history.history_utils - INFO - Using indicator startup period: 14450 ... +2025-04-29 01:54:59,672 - freqtrade.optimize.backtesting - INFO - Loading data from 2024-12-01 21:30:00 up to 2025-04-20 00:00:00 (139 days). +2025-04-29 01:54:59,672 - freqtrade.optimize.backtesting - INFO - Dataload complete. Calculating indicators +2025-04-29 01:54:59,673 - freqtrade.optimize.backtesting - INFO - Running backtesting for Strategy FreqaiExampleStrategy +2025-04-29 01:55:01,274 - matplotlib.font_manager - INFO - generated new fontManager +2025-04-29 01:55:01,489 - freqtrade.resolvers.iresolver - INFO - Using resolved freqaimodel XGBoostRegressor from '/freqtrade/freqtrade/freqai/prediction_models/XGBoostRegressor.py'... +2025-04-29 01:55:01,490 - freqtrade.freqai.data_drawer - INFO - Could not find existing datadrawer, starting from scratch +2025-04-29 01:55:01,491 - freqtrade.freqai.data_drawer - INFO - Could not find existing historic_predictions, starting from scratch +2025-04-29 01:55:01,491 - freqtrade.freqai.freqai_interface - INFO - Set fresh train queue from whitelist. Queue: ['BTC/USDT', 'SOL/USDT'] +2025-04-29 01:55:01,492 - freqtrade.strategy.hyper - INFO - Strategy Parameter: buy_rsi = 39.92672300850069 +2025-04-29 01:55:01,492 - freqtrade.strategy.hyper - INFO - Strategy Parameter: sell_rsi = 69.92672300850067 +2025-04-29 01:55:01,493 - freqtrade.strategy.hyper - INFO - No params for protection found, using default values. +2025-04-29 01:55:01,498 - FreqaiExampleStrategy - INFO - 处理交易对：BTC/USDT +2025-04-29 01:55:01,500 - freqtrade.freqai.freqai_interface - INFO - Training 11 timeranges +2025-04-29 01:55:01,501 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2024-12-02 00:00:00 to 2025-01-01 00:00:00, 1/11 trains +2025-04-29 01:55:01,502 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1735689600_prediction.feather +2025-04-29 01:55:01,602 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 5m to 8690 +2025-04-29 01:55:01,603 - freqtrade.data.dataprovider - INFO - Loading data for BTC/USDT 5m from 2024-12-01 19:50:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:01,705 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 1h to 770 +2025-04-29 01:55:01,706 - freqtrade.data.dataprovider - INFO - Loading data for BTC/USDT 1h from 2024-11-29 22:00:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:01,814 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 3m to 14450 +2025-04-29 01:55:01,815 - freqtrade.data.dataprovider - INFO - Loading data for ETH/USDT 3m from 2024-12-01 21:30:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:01,942 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 5m to 8690 +2025-04-29 01:55:01,943 - freqtrade.data.dataprovider - INFO - Loading data for ETH/USDT 5m from 2024-12-01 19:50:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:02,037 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 1h to 770 +2025-04-29 01:55:02,038 - freqtrade.data.dataprovider - INFO - Loading data for ETH/USDT 1h from 2024-11-29 22:00:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:02,113 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:02,118 - FreqaiExampleStrategy - INFO - 目标列形状：(14450,) +2025-04-29 01:55:02,121 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.152831 +1 0.003285 50.152831 +2 0.001898 50.152831 +3 0.000484 50.152831 +4 0.001688 50.152831 +2025-04-29 01:55:02,123 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:02,129 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:55:02,130 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.202701 +1 0.003285 50.202701 +2 0.001898 50.202701 +3 0.000484 50.202701 +4 0.001688 50.202701 +2025-04-29 01:55:02,134 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1735689600/cb_btc_1735689600 +2025-04-29 01:55:02,135 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:02,151 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:02,152 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-02 to 2024-12-31 -------------------- +2025-04-29 01:55:07,277 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:07,278 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.24624 validation_1-rmse:0.26036 +[1] validation_0-rmse:0.24176 validation_1-rmse:0.25460 +[2] validation_0-rmse:0.23782 validation_1-rmse:0.24904 +[3] validation_0-rmse:0.23408 validation_1-rmse:0.24381 +[4] validation_0-rmse:0.23057 validation_1-rmse:0.23882 +[5] validation_0-rmse:0.22701 validation_1-rmse:0.23409 +[6] validation_0-rmse:0.22400 validation_1-rmse:0.22962 +[7] validation_0-rmse:0.22088 validation_1-rmse:0.22533 +[8] validation_0-rmse:0.21817 validation_1-rmse:0.22130 +[9] validation_0-rmse:0.21491 validation_1-rmse:0.21740 +[10] validation_0-rmse:0.21265 validation_1-rmse:0.21347 +[11] validation_0-rmse:0.20982 validation_1-rmse:0.20978 +[12] validation_0-rmse:0.20747 validation_1-rmse:0.20640 +[13] validation_0-rmse:0.20512 validation_1-rmse:0.20299 +[14] validation_0-rmse:0.20280 validation_1-rmse:0.19966 +[15] validation_0-rmse:0.20012 validation_1-rmse:0.19656 +[16] validation_0-rmse:0.19785 validation_1-rmse:0.19346 +[17] validation_0-rmse:0.19572 validation_1-rmse:0.19054 +[18] validation_0-rmse:0.19400 validation_1-rmse:0.18759 +[19] validation_0-rmse:0.19164 validation_1-rmse:0.18488 +[20] validation_0-rmse:0.18956 validation_1-rmse:0.18205 +[21] validation_0-rmse:0.18746 validation_1-rmse:0.17951 +[22] validation_0-rmse:0.18593 validation_1-rmse:0.17696 +[23] validation_0-rmse:0.18395 validation_1-rmse:0.17465 +[24] validation_0-rmse:0.18249 validation_1-rmse:0.17217 +[25] validation_0-rmse:0.18084 validation_1-rmse:0.16993 +[26] validation_0-rmse:0.17928 validation_1-rmse:0.16771 +[27] validation_0-rmse:0.17776 validation_1-rmse:0.16571 +[28] validation_0-rmse:0.17652 validation_1-rmse:0.16356 +[29] validation_0-rmse:0.17499 validation_1-rmse:0.16166 +[30] validation_0-rmse:0.17371 validation_1-rmse:0.15983 +[31] validation_0-rmse:0.17243 validation_1-rmse:0.15792 +[32] validation_0-rmse:0.17110 validation_1-rmse:0.15628 +[33] validation_0-rmse:0.16996 validation_1-rmse:0.15433 +[34] validation_0-rmse:0.16884 validation_1-rmse:0.15277 +[35] validation_0-rmse:0.16785 validation_1-rmse:0.15090 +[36] validation_0-rmse:0.16682 validation_1-rmse:0.14942 +[37] validation_0-rmse:0.16559 validation_1-rmse:0.14774 +[38] validation_0-rmse:0.16459 validation_1-rmse:0.14628 +[39] validation_0-rmse:0.16356 validation_1-rmse:0.14466 +[40] validation_0-rmse:0.16250 validation_1-rmse:0.14330 +[41] validation_0-rmse:0.16153 validation_1-rmse:0.14201 +[42] validation_0-rmse:0.16059 validation_1-rmse:0.14075 +[43] validation_0-rmse:0.15986 validation_1-rmse:0.13938 +[44] validation_0-rmse:0.15908 validation_1-rmse:0.13822 +[45] validation_0-rmse:0.15810 validation_1-rmse:0.13687 +[46] validation_0-rmse:0.15733 validation_1-rmse:0.13577 +[47] validation_0-rmse:0.15655 validation_1-rmse:0.13458 +[48] validation_0-rmse:0.15580 validation_1-rmse:0.13355 +[49] validation_0-rmse:0.15512 validation_1-rmse:0.13228 +[50] validation_0-rmse:0.15434 validation_1-rmse:0.13121 +[51] validation_0-rmse:0.15363 validation_1-rmse:0.13030 +[52] validation_0-rmse:0.15294 validation_1-rmse:0.12937 +[53] validation_0-rmse:0.15243 validation_1-rmse:0.12818 +[54] validation_0-rmse:0.15170 validation_1-rmse:0.12720 +[55] validation_0-rmse:0.15096 validation_1-rmse:0.12632 +[56] validation_0-rmse:0.15035 validation_1-rmse:0.12538 +[57] validation_0-rmse:0.14977 validation_1-rmse:0.12453 +[58] validation_0-rmse:0.14914 validation_1-rmse:0.12363 +[59] validation_0-rmse:0.14867 validation_1-rmse:0.12263 +[60] validation_0-rmse:0.14819 validation_1-rmse:0.12183 +[61] validation_0-rmse:0.14763 validation_1-rmse:0.12108 +[62] validation_0-rmse:0.14706 validation_1-rmse:0.12035 +[63] validation_0-rmse:0.14648 validation_1-rmse:0.11946 +[64] validation_0-rmse:0.14601 validation_1-rmse:0.11876 +[65] validation_0-rmse:0.14553 validation_1-rmse:0.11808 +[66] validation_0-rmse:0.14506 validation_1-rmse:0.11742 +[67] validation_0-rmse:0.14469 validation_1-rmse:0.11671 +[68] validation_0-rmse:0.14422 validation_1-rmse:0.11604 +[69] validation_0-rmse:0.14381 validation_1-rmse:0.11543 +[70] validation_0-rmse:0.14337 validation_1-rmse:0.11485 +[71] validation_0-rmse:0.14294 validation_1-rmse:0.11398 +[72] validation_0-rmse:0.14260 validation_1-rmse:0.11335 +[73] validation_0-rmse:0.14223 validation_1-rmse:0.11278 +[74] validation_0-rmse:0.14190 validation_1-rmse:0.11225 +[75] validation_0-rmse:0.14144 validation_1-rmse:0.11143 +[76] validation_0-rmse:0.14098 validation_1-rmse:0.11052 +[77] validation_0-rmse:0.14062 validation_1-rmse:0.10998 +[78] validation_0-rmse:0.14029 validation_1-rmse:0.10953 +[79] validation_0-rmse:0.13993 validation_1-rmse:0.10888 +[80] validation_0-rmse:0.13958 validation_1-rmse:0.10839 +[81] validation_0-rmse:0.13918 validation_1-rmse:0.10767 +[82] validation_0-rmse:0.13897 validation_1-rmse:0.10720 +[83] validation_0-rmse:0.13864 validation_1-rmse:0.10669 +[84] validation_0-rmse:0.13836 validation_1-rmse:0.10620 +[85] validation_0-rmse:0.13810 validation_1-rmse:0.10573 +[86] validation_0-rmse:0.13782 validation_1-rmse:0.10526 +[87] validation_0-rmse:0.13756 validation_1-rmse:0.10458 +[88] validation_0-rmse:0.13736 validation_1-rmse:0.10420 +[89] validation_0-rmse:0.13708 validation_1-rmse:0.10383 +[90] validation_0-rmse:0.13685 validation_1-rmse:0.10343 +[91] validation_0-rmse:0.13658 validation_1-rmse:0.10298 +[92] validation_0-rmse:0.13646 validation_1-rmse:0.10231 +[93] validation_0-rmse:0.13615 validation_1-rmse:0.10190 +[94] validation_0-rmse:0.13589 validation_1-rmse:0.10154 +[95] validation_0-rmse:0.13572 validation_1-rmse:0.10095 +[96] validation_0-rmse:0.13550 validation_1-rmse:0.10058 +[97] validation_0-rmse:0.13530 validation_1-rmse:0.10026 +[98] validation_0-rmse:0.13513 validation_1-rmse:0.09995 +[99] validation_0-rmse:0.13480 validation_1-rmse:0.09950 +2025-04-29 01:55:08,221 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (6.09 secs) -------------------- +2025-04-29 01:55:08,222 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:08,903 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2024-12-12 00:00:00 to 2025-01-11 00:00:00, 2/11 trains +2025-04-29 01:55:08,904 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1736553600_prediction.feather +2025-04-29 01:55:08,907 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:08,912 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:55:08,914 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.202701 +1 0.003285 50.202701 +2 0.001898 50.202701 +3 0.000484 50.202701 +4 0.001688 50.202701 +2025-04-29 01:55:08,917 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:08,924 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:55:08,925 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.367593 +1 0.003285 50.367593 +2 0.001898 50.367593 +3 0.000484 50.367593 +4 0.001688 50.367593 +2025-04-29 01:55:08,929 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1736553600/cb_btc_1736553600 +2025-04-29 01:55:08,930 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:08,946 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:08,947 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-12 to 2025-01-10 -------------------- +2025-04-29 01:55:13,908 - datasieve.pipeline - INFO - DI tossed 5 predictions for being too far from training data. +2025-04-29 01:55:13,911 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:13,912 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.26037 validation_1-rmse:0.25324 +[1] validation_0-rmse:0.25572 validation_1-rmse:0.24787 +[2] validation_0-rmse:0.25117 validation_1-rmse:0.24281 +[3] validation_0-rmse:0.24697 validation_1-rmse:0.23802 +[4] validation_0-rmse:0.24328 validation_1-rmse:0.23332 +[5] validation_0-rmse:0.23939 validation_1-rmse:0.22905 +[6] validation_0-rmse:0.23522 validation_1-rmse:0.22484 +[7] validation_0-rmse:0.23148 validation_1-rmse:0.22085 +[8] validation_0-rmse:0.22873 validation_1-rmse:0.21697 +[9] validation_0-rmse:0.22519 validation_1-rmse:0.21317 +[10] validation_0-rmse:0.22206 validation_1-rmse:0.20963 +[11] validation_0-rmse:0.21866 validation_1-rmse:0.20626 +[12] validation_0-rmse:0.21563 validation_1-rmse:0.20296 +[13] validation_0-rmse:0.21313 validation_1-rmse:0.19956 +[14] validation_0-rmse:0.21062 validation_1-rmse:0.19636 +[15] validation_0-rmse:0.20808 validation_1-rmse:0.19339 +[16] validation_0-rmse:0.20570 validation_1-rmse:0.19058 +[17] validation_0-rmse:0.20318 validation_1-rmse:0.18781 +[18] validation_0-rmse:0.20113 validation_1-rmse:0.18518 +[19] validation_0-rmse:0.19934 validation_1-rmse:0.18248 +[20] validation_0-rmse:0.19735 validation_1-rmse:0.18006 +[21] validation_0-rmse:0.19541 validation_1-rmse:0.17744 +[22] validation_0-rmse:0.19336 validation_1-rmse:0.17517 +[23] validation_0-rmse:0.19145 validation_1-rmse:0.17301 +[24] validation_0-rmse:0.18989 validation_1-rmse:0.17058 +[25] validation_0-rmse:0.18782 validation_1-rmse:0.16854 +[26] validation_0-rmse:0.18634 validation_1-rmse:0.16625 +[27] validation_0-rmse:0.18471 validation_1-rmse:0.16430 +[28] validation_0-rmse:0.18312 validation_1-rmse:0.16236 +[29] validation_0-rmse:0.18157 validation_1-rmse:0.16053 +[30] validation_0-rmse:0.17991 validation_1-rmse:0.15849 +[31] validation_0-rmse:0.17839 validation_1-rmse:0.15677 +[32] validation_0-rmse:0.17693 validation_1-rmse:0.15498 +[33] validation_0-rmse:0.17574 validation_1-rmse:0.15336 +[34] validation_0-rmse:0.17469 validation_1-rmse:0.15168 +[35] validation_0-rmse:0.17352 validation_1-rmse:0.15015 +[36] validation_0-rmse:0.17228 validation_1-rmse:0.14868 +[37] validation_0-rmse:0.17127 validation_1-rmse:0.14692 +[38] validation_0-rmse:0.17030 validation_1-rmse:0.14553 +[39] validation_0-rmse:0.16926 validation_1-rmse:0.14420 +[40] validation_0-rmse:0.16821 validation_1-rmse:0.14297 +[41] validation_0-rmse:0.16740 validation_1-rmse:0.14144 +[42] validation_0-rmse:0.16647 validation_1-rmse:0.14020 +[43] validation_0-rmse:0.16548 validation_1-rmse:0.13903 +[44] validation_0-rmse:0.16440 validation_1-rmse:0.13765 +[45] validation_0-rmse:0.16353 validation_1-rmse:0.13652 +[46] validation_0-rmse:0.16269 validation_1-rmse:0.13522 +[47] validation_0-rmse:0.16193 validation_1-rmse:0.13419 +[48] validation_0-rmse:0.16114 validation_1-rmse:0.13311 +[49] validation_0-rmse:0.16043 validation_1-rmse:0.13214 +[50] validation_0-rmse:0.15971 validation_1-rmse:0.13090 +[51] validation_0-rmse:0.15909 validation_1-rmse:0.12992 +[52] validation_0-rmse:0.15834 validation_1-rmse:0.12899 +[53] validation_0-rmse:0.15763 validation_1-rmse:0.12809 +[54] validation_0-rmse:0.15697 validation_1-rmse:0.12724 +[55] validation_0-rmse:0.15631 validation_1-rmse:0.12637 +[56] validation_0-rmse:0.15553 validation_1-rmse:0.12535 +[57] validation_0-rmse:0.15494 validation_1-rmse:0.12456 +[58] validation_0-rmse:0.15452 validation_1-rmse:0.12352 +[59] validation_0-rmse:0.15396 validation_1-rmse:0.12273 +[60] validation_0-rmse:0.15334 validation_1-rmse:0.12196 +[61] validation_0-rmse:0.15274 validation_1-rmse:0.12123 +[62] validation_0-rmse:0.15221 validation_1-rmse:0.12048 +[63] validation_0-rmse:0.15176 validation_1-rmse:0.11953 +[64] validation_0-rmse:0.15133 validation_1-rmse:0.11887 +[65] validation_0-rmse:0.15080 validation_1-rmse:0.11796 +[66] validation_0-rmse:0.15035 validation_1-rmse:0.11734 +[67] validation_0-rmse:0.14995 validation_1-rmse:0.11667 +[68] validation_0-rmse:0.14954 validation_1-rmse:0.11616 +[69] validation_0-rmse:0.14916 validation_1-rmse:0.11535 +[70] validation_0-rmse:0.14887 validation_1-rmse:0.11469 +[71] validation_0-rmse:0.14854 validation_1-rmse:0.11408 +[72] validation_0-rmse:0.14811 validation_1-rmse:0.11334 +[73] validation_0-rmse:0.14766 validation_1-rmse:0.11278 +[74] validation_0-rmse:0.14738 validation_1-rmse:0.11231 +[75] validation_0-rmse:0.14697 validation_1-rmse:0.11184 +[76] validation_0-rmse:0.14663 validation_1-rmse:0.11108 +[77] validation_0-rmse:0.14635 validation_1-rmse:0.11058 +[78] validation_0-rmse:0.14591 validation_1-rmse:0.10984 +[79] validation_0-rmse:0.14561 validation_1-rmse:0.10929 +[80] validation_0-rmse:0.14529 validation_1-rmse:0.10875 +[81] validation_0-rmse:0.14510 validation_1-rmse:0.10826 +[82] validation_0-rmse:0.14471 validation_1-rmse:0.10772 +[83] validation_0-rmse:0.14444 validation_1-rmse:0.10725 +[84] validation_0-rmse:0.14420 validation_1-rmse:0.10652 +[85] validation_0-rmse:0.14393 validation_1-rmse:0.10608 +[86] validation_0-rmse:0.14371 validation_1-rmse:0.10567 +[87] validation_0-rmse:0.14342 validation_1-rmse:0.10528 +[88] validation_0-rmse:0.14314 validation_1-rmse:0.10483 +[89] validation_0-rmse:0.14307 validation_1-rmse:0.10439 +[90] validation_0-rmse:0.14273 validation_1-rmse:0.10395 +[91] validation_0-rmse:0.14237 validation_1-rmse:0.10353 +[92] validation_0-rmse:0.14210 validation_1-rmse:0.10318 +[93] validation_0-rmse:0.14186 validation_1-rmse:0.10279 +[94] validation_0-rmse:0.14175 validation_1-rmse:0.10234 +[95] validation_0-rmse:0.14153 validation_1-rmse:0.10204 +[96] validation_0-rmse:0.14142 validation_1-rmse:0.10160 +[97] validation_0-rmse:0.14124 validation_1-rmse:0.10126 +[98] validation_0-rmse:0.14102 validation_1-rmse:0.10068 +[99] validation_0-rmse:0.14079 validation_1-rmse:0.10036 +2025-04-29 01:55:14,692 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.76 secs) -------------------- +2025-04-29 01:55:14,693 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:15,250 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2024-12-22 00:00:00 to 2025-01-21 00:00:00, 3/11 trains +2025-04-29 01:55:15,250 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1737417600_prediction.feather +2025-04-29 01:55:15,254 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:15,261 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:55:15,262 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.367593 +1 0.003285 50.367593 +2 0.001898 50.367593 +3 0.000484 50.367593 +4 0.001688 50.367593 +2025-04-29 01:55:15,268 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:15,275 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:55:15,276 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.305589 +1 0.003285 50.305589 +2 0.001898 50.305589 +3 0.000484 50.305589 +4 0.001688 50.305589 +2025-04-29 01:55:15,281 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1737417600/cb_btc_1737417600 +2025-04-29 01:55:15,281 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:15,297 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:15,298 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-22 to 2025-01-20 -------------------- +2025-04-29 01:55:20,324 - datasieve.pipeline - INFO - DI tossed 1622 predictions for being too far from training data. +2025-04-29 01:55:20,327 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:20,327 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.25769 validation_1-rmse:0.25549 +[1] validation_0-rmse:0.25314 validation_1-rmse:0.24986 +[2] validation_0-rmse:0.24864 validation_1-rmse:0.24456 +[3] validation_0-rmse:0.24486 validation_1-rmse:0.23955 +[4] validation_0-rmse:0.24144 validation_1-rmse:0.23480 +[5] validation_0-rmse:0.23803 validation_1-rmse:0.23024 +[6] validation_0-rmse:0.23468 validation_1-rmse:0.22599 +[7] validation_0-rmse:0.23134 validation_1-rmse:0.22162 +[8] validation_0-rmse:0.22843 validation_1-rmse:0.21773 +[9] validation_0-rmse:0.22560 validation_1-rmse:0.21396 +[10] validation_0-rmse:0.22402 validation_1-rmse:0.21023 +[11] validation_0-rmse:0.22155 validation_1-rmse:0.20680 +[12] validation_0-rmse:0.21899 validation_1-rmse:0.20342 +[13] validation_0-rmse:0.21654 validation_1-rmse:0.20029 +[14] validation_0-rmse:0.21431 validation_1-rmse:0.19719 +[15] validation_0-rmse:0.21282 validation_1-rmse:0.19411 +[16] validation_0-rmse:0.21076 validation_1-rmse:0.19117 +[17] validation_0-rmse:0.20882 validation_1-rmse:0.18835 +[18] validation_0-rmse:0.20695 validation_1-rmse:0.18547 +[19] validation_0-rmse:0.20538 validation_1-rmse:0.18292 +[20] validation_0-rmse:0.20345 validation_1-rmse:0.18038 +[21] validation_0-rmse:0.20148 validation_1-rmse:0.17799 +[22] validation_0-rmse:0.19991 validation_1-rmse:0.17569 +[23] validation_0-rmse:0.19832 validation_1-rmse:0.17350 +[24] validation_0-rmse:0.19658 validation_1-rmse:0.17096 +[25] validation_0-rmse:0.19474 validation_1-rmse:0.16879 +[26] validation_0-rmse:0.19292 validation_1-rmse:0.16665 +[27] validation_0-rmse:0.19134 validation_1-rmse:0.16470 +[28] validation_0-rmse:0.19034 validation_1-rmse:0.16253 +[29] validation_0-rmse:0.18882 validation_1-rmse:0.16068 +[30] validation_0-rmse:0.18736 validation_1-rmse:0.15892 +[31] validation_0-rmse:0.18605 validation_1-rmse:0.15690 +[32] validation_0-rmse:0.18481 validation_1-rmse:0.15521 +[33] validation_0-rmse:0.18346 validation_1-rmse:0.15356 +[34] validation_0-rmse:0.18222 validation_1-rmse:0.15188 +[35] validation_0-rmse:0.18095 validation_1-rmse:0.15028 +[36] validation_0-rmse:0.18015 validation_1-rmse:0.14857 +[37] validation_0-rmse:0.17915 validation_1-rmse:0.14713 +[38] validation_0-rmse:0.17817 validation_1-rmse:0.14573 +[39] validation_0-rmse:0.17723 validation_1-rmse:0.14437 +[40] validation_0-rmse:0.17619 validation_1-rmse:0.14308 +[41] validation_0-rmse:0.17509 validation_1-rmse:0.14176 +[42] validation_0-rmse:0.17407 validation_1-rmse:0.14047 +[43] validation_0-rmse:0.17340 validation_1-rmse:0.13921 +[44] validation_0-rmse:0.17245 validation_1-rmse:0.13806 +[45] validation_0-rmse:0.17212 validation_1-rmse:0.13685 +[46] validation_0-rmse:0.17133 validation_1-rmse:0.13577 +[47] validation_0-rmse:0.17064 validation_1-rmse:0.13451 +[48] validation_0-rmse:0.17004 validation_1-rmse:0.13331 +[49] validation_0-rmse:0.16941 validation_1-rmse:0.13222 +[50] validation_0-rmse:0.16858 validation_1-rmse:0.13123 +[51] validation_0-rmse:0.16786 validation_1-rmse:0.13007 +[52] validation_0-rmse:0.16718 validation_1-rmse:0.12912 +[53] validation_0-rmse:0.16651 validation_1-rmse:0.12806 +[54] validation_0-rmse:0.16592 validation_1-rmse:0.12709 +[55] validation_0-rmse:0.16542 validation_1-rmse:0.12604 +[56] validation_0-rmse:0.16479 validation_1-rmse:0.12523 +[57] validation_0-rmse:0.16426 validation_1-rmse:0.12439 +[58] validation_0-rmse:0.16363 validation_1-rmse:0.12352 +[59] validation_0-rmse:0.16325 validation_1-rmse:0.12263 +[60] validation_0-rmse:0.16289 validation_1-rmse:0.12173 +[61] validation_0-rmse:0.16226 validation_1-rmse:0.12099 +[62] validation_0-rmse:0.16176 validation_1-rmse:0.12010 +[63] validation_0-rmse:0.16144 validation_1-rmse:0.11936 +[64] validation_0-rmse:0.16088 validation_1-rmse:0.11862 +[65] validation_0-rmse:0.16030 validation_1-rmse:0.11786 +[66] validation_0-rmse:0.15991 validation_1-rmse:0.11714 +[67] validation_0-rmse:0.15947 validation_1-rmse:0.11640 +[68] validation_0-rmse:0.15912 validation_1-rmse:0.11574 +[69] validation_0-rmse:0.15874 validation_1-rmse:0.11507 +[70] validation_0-rmse:0.15837 validation_1-rmse:0.11430 +[71] validation_0-rmse:0.15798 validation_1-rmse:0.11365 +[72] validation_0-rmse:0.15763 validation_1-rmse:0.11305 +[73] validation_0-rmse:0.15713 validation_1-rmse:0.11250 +[74] validation_0-rmse:0.15648 validation_1-rmse:0.11177 +[75] validation_0-rmse:0.15619 validation_1-rmse:0.11122 +[76] validation_0-rmse:0.15593 validation_1-rmse:0.11066 +[77] validation_0-rmse:0.15562 validation_1-rmse:0.11007 +[78] validation_0-rmse:0.15519 validation_1-rmse:0.10953 +[79] validation_0-rmse:0.15500 validation_1-rmse:0.10883 +[80] validation_0-rmse:0.15461 validation_1-rmse:0.10835 +[81] validation_0-rmse:0.15417 validation_1-rmse:0.10780 +[82] validation_0-rmse:0.15393 validation_1-rmse:0.10742 +[83] validation_0-rmse:0.15395 validation_1-rmse:0.10634 +[84] validation_0-rmse:0.15359 validation_1-rmse:0.10588 +[85] validation_0-rmse:0.15315 validation_1-rmse:0.10539 +[86] validation_0-rmse:0.15315 validation_1-rmse:0.10440 +[87] validation_0-rmse:0.15278 validation_1-rmse:0.10400 +[88] validation_0-rmse:0.15239 validation_1-rmse:0.10353 +[89] validation_0-rmse:0.15200 validation_1-rmse:0.10310 +[90] validation_0-rmse:0.15182 validation_1-rmse:0.10245 +[91] validation_0-rmse:0.15175 validation_1-rmse:0.10182 +[92] validation_0-rmse:0.15139 validation_1-rmse:0.10138 +[93] validation_0-rmse:0.15105 validation_1-rmse:0.10095 +[94] validation_0-rmse:0.15091 validation_1-rmse:0.10056 +[95] validation_0-rmse:0.15088 validation_1-rmse:0.09964 +[96] validation_0-rmse:0.15065 validation_1-rmse:0.09927 +[97] validation_0-rmse:0.15036 validation_1-rmse:0.09888 +[98] validation_0-rmse:0.15021 validation_1-rmse:0.09852 +[99] validation_0-rmse:0.15004 validation_1-rmse:0.09815 +2025-04-29 01:55:21,007 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.73 secs) -------------------- +2025-04-29 01:55:21,008 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:21,504 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-01 00:00:00 to 2025-01-31 00:00:00, 4/11 trains +2025-04-29 01:55:21,505 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1738281600_prediction.feather +2025-04-29 01:55:21,510 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:21,516 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:55:21,517 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.305589 +1 0.003285 50.305589 +2 0.001898 50.305589 +3 0.000484 50.305589 +4 0.001688 50.305589 +2025-04-29 01:55:21,522 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:21,528 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:55:21,529 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.168798 +1 0.003285 50.168798 +2 0.001898 50.168798 +3 0.000484 50.168798 +4 0.001688 50.168798 +2025-04-29 01:55:21,533 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1738281600/cb_btc_1738281600 +2025-04-29 01:55:21,534 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:21,550 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:21,550 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-01 to 2025-01-30 -------------------- +2025-04-29 01:55:26,605 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:26,606 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.25046 validation_1-rmse:0.26128 +[1] validation_0-rmse:0.24588 validation_1-rmse:0.25570 +[2] validation_0-rmse:0.24156 validation_1-rmse:0.25047 +[3] validation_0-rmse:0.23757 validation_1-rmse:0.24551 +[4] validation_0-rmse:0.23411 validation_1-rmse:0.24075 +[5] validation_0-rmse:0.23029 validation_1-rmse:0.23637 +[6] validation_0-rmse:0.22707 validation_1-rmse:0.23199 +[7] validation_0-rmse:0.22405 validation_1-rmse:0.22801 +[8] validation_0-rmse:0.22083 validation_1-rmse:0.22420 +[9] validation_0-rmse:0.21768 validation_1-rmse:0.22038 +[10] validation_0-rmse:0.21473 validation_1-rmse:0.21674 +[11] validation_0-rmse:0.21187 validation_1-rmse:0.21322 +[12] validation_0-rmse:0.20911 validation_1-rmse:0.20996 +[13] validation_0-rmse:0.20669 validation_1-rmse:0.20679 +[14] validation_0-rmse:0.20441 validation_1-rmse:0.20366 +[15] validation_0-rmse:0.20250 validation_1-rmse:0.20054 +[16] validation_0-rmse:0.20017 validation_1-rmse:0.19757 +[17] validation_0-rmse:0.19804 validation_1-rmse:0.19490 +[18] validation_0-rmse:0.19618 validation_1-rmse:0.19221 +[19] validation_0-rmse:0.19404 validation_1-rmse:0.18954 +[20] validation_0-rmse:0.19209 validation_1-rmse:0.18666 +[21] validation_0-rmse:0.19014 validation_1-rmse:0.18430 +[22] validation_0-rmse:0.18845 validation_1-rmse:0.18197 +[23] validation_0-rmse:0.18653 validation_1-rmse:0.17972 +[24] validation_0-rmse:0.18468 validation_1-rmse:0.17722 +[25] validation_0-rmse:0.18325 validation_1-rmse:0.17491 +[26] validation_0-rmse:0.18152 validation_1-rmse:0.17284 +[27] validation_0-rmse:0.17999 validation_1-rmse:0.17092 +[28] validation_0-rmse:0.17846 validation_1-rmse:0.16892 +[29] validation_0-rmse:0.17696 validation_1-rmse:0.16709 +[30] validation_0-rmse:0.17558 validation_1-rmse:0.16510 +[31] validation_0-rmse:0.17418 validation_1-rmse:0.16335 +[32] validation_0-rmse:0.17293 validation_1-rmse:0.16161 +[33] validation_0-rmse:0.17159 validation_1-rmse:0.16003 +[34] validation_0-rmse:0.17030 validation_1-rmse:0.15831 +[35] validation_0-rmse:0.16907 validation_1-rmse:0.15681 +[36] validation_0-rmse:0.16796 validation_1-rmse:0.15513 +[37] validation_0-rmse:0.16690 validation_1-rmse:0.15349 +[38] validation_0-rmse:0.16580 validation_1-rmse:0.15204 +[39] validation_0-rmse:0.16492 validation_1-rmse:0.15050 +[40] validation_0-rmse:0.16383 validation_1-rmse:0.14918 +[41] validation_0-rmse:0.16281 validation_1-rmse:0.14788 +[42] validation_0-rmse:0.16176 validation_1-rmse:0.14660 +[43] validation_0-rmse:0.16082 validation_1-rmse:0.14516 +[44] validation_0-rmse:0.15990 validation_1-rmse:0.14395 +[45] validation_0-rmse:0.15891 validation_1-rmse:0.14281 +[46] validation_0-rmse:0.15797 validation_1-rmse:0.14168 +[47] validation_0-rmse:0.15712 validation_1-rmse:0.14040 +[48] validation_0-rmse:0.15632 validation_1-rmse:0.13933 +[49] validation_0-rmse:0.15542 validation_1-rmse:0.13821 +[50] validation_0-rmse:0.15458 validation_1-rmse:0.13705 +[51] validation_0-rmse:0.15404 validation_1-rmse:0.13583 +[52] validation_0-rmse:0.15334 validation_1-rmse:0.13483 +[53] validation_0-rmse:0.15256 validation_1-rmse:0.13387 +[54] validation_0-rmse:0.15190 validation_1-rmse:0.13290 +[55] validation_0-rmse:0.15122 validation_1-rmse:0.13174 +[56] validation_0-rmse:0.15065 validation_1-rmse:0.13080 +[57] validation_0-rmse:0.15006 validation_1-rmse:0.12993 +[58] validation_0-rmse:0.14955 validation_1-rmse:0.12897 +[59] validation_0-rmse:0.14893 validation_1-rmse:0.12814 +[60] validation_0-rmse:0.14843 validation_1-rmse:0.12735 +[61] validation_0-rmse:0.14789 validation_1-rmse:0.12642 +[62] validation_0-rmse:0.14718 validation_1-rmse:0.12561 +[63] validation_0-rmse:0.14659 validation_1-rmse:0.12486 +[64] validation_0-rmse:0.14600 validation_1-rmse:0.12397 +[65] validation_0-rmse:0.14547 validation_1-rmse:0.12324 +[66] validation_0-rmse:0.14499 validation_1-rmse:0.12255 +[67] validation_0-rmse:0.14451 validation_1-rmse:0.12188 +[68] validation_0-rmse:0.14393 validation_1-rmse:0.12114 +[69] validation_0-rmse:0.14346 validation_1-rmse:0.12048 +[70] validation_0-rmse:0.14293 validation_1-rmse:0.11974 +[71] validation_0-rmse:0.14256 validation_1-rmse:0.11893 +[72] validation_0-rmse:0.14212 validation_1-rmse:0.11830 +[73] validation_0-rmse:0.14177 validation_1-rmse:0.11748 +[74] validation_0-rmse:0.14134 validation_1-rmse:0.11686 +[75] validation_0-rmse:0.14101 validation_1-rmse:0.11609 +[76] validation_0-rmse:0.14060 validation_1-rmse:0.11536 +[77] validation_0-rmse:0.14020 validation_1-rmse:0.11484 +[78] validation_0-rmse:0.13983 validation_1-rmse:0.11412 +[79] validation_0-rmse:0.13951 validation_1-rmse:0.11357 +[80] validation_0-rmse:0.13928 validation_1-rmse:0.11273 +[81] validation_0-rmse:0.13889 validation_1-rmse:0.11221 +[82] validation_0-rmse:0.13855 validation_1-rmse:0.11166 +[83] validation_0-rmse:0.13824 validation_1-rmse:0.11114 +[84] validation_0-rmse:0.13808 validation_1-rmse:0.11050 +[85] validation_0-rmse:0.13767 validation_1-rmse:0.10998 +[86] validation_0-rmse:0.13731 validation_1-rmse:0.10947 +[87] validation_0-rmse:0.13716 validation_1-rmse:0.10876 +[88] validation_0-rmse:0.13678 validation_1-rmse:0.10832 +[89] validation_0-rmse:0.13659 validation_1-rmse:0.10782 +[90] validation_0-rmse:0.13629 validation_1-rmse:0.10736 +[91] validation_0-rmse:0.13600 validation_1-rmse:0.10662 +[92] validation_0-rmse:0.13577 validation_1-rmse:0.10613 +[93] validation_0-rmse:0.13541 validation_1-rmse:0.10565 +[94] validation_0-rmse:0.13534 validation_1-rmse:0.10501 +[95] validation_0-rmse:0.13511 validation_1-rmse:0.10453 +[96] validation_0-rmse:0.13483 validation_1-rmse:0.10401 +[97] validation_0-rmse:0.13455 validation_1-rmse:0.10362 +[98] validation_0-rmse:0.13425 validation_1-rmse:0.10323 +[99] validation_0-rmse:0.13402 validation_1-rmse:0.10289 +2025-04-29 01:55:27,556 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (6.02 secs) -------------------- +2025-04-29 01:55:27,557 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:28,076 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-11 00:00:00 to 2025-02-10 00:00:00, 5/11 trains +2025-04-29 01:55:28,077 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1739145600_prediction.feather +2025-04-29 01:55:28,081 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:28,088 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:55:28,089 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.168798 +1 0.003285 50.168798 +2 0.001898 50.168798 +3 0.000484 50.168798 +4 0.001688 50.168798 +2025-04-29 01:55:28,094 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:28,100 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:55:28,102 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.167897 +1 0.003285 50.167897 +2 0.001898 50.167897 +3 0.000484 50.167897 +4 0.001688 50.167897 +2025-04-29 01:55:28,106 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1739145600/cb_btc_1739145600 +2025-04-29 01:55:28,107 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:28,123 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:28,124 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-11 to 2025-02-09 -------------------- +2025-04-29 01:55:33,123 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:33,124 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.26428 validation_1-rmse:0.27464 +[1] validation_0-rmse:0.25911 validation_1-rmse:0.26865 +[2] validation_0-rmse:0.25427 validation_1-rmse:0.26296 +[3] validation_0-rmse:0.24970 validation_1-rmse:0.25748 +[4] validation_0-rmse:0.24525 validation_1-rmse:0.25222 +[5] validation_0-rmse:0.24140 validation_1-rmse:0.24725 +[6] validation_0-rmse:0.23748 validation_1-rmse:0.24264 +[7] validation_0-rmse:0.23368 validation_1-rmse:0.23792 +[8] validation_0-rmse:0.23022 validation_1-rmse:0.23363 +[9] validation_0-rmse:0.22695 validation_1-rmse:0.22945 +[10] validation_0-rmse:0.22381 validation_1-rmse:0.22543 +[11] validation_0-rmse:0.22105 validation_1-rmse:0.22154 +[12] validation_0-rmse:0.21818 validation_1-rmse:0.21797 +[13] validation_0-rmse:0.21526 validation_1-rmse:0.21430 +[14] validation_0-rmse:0.21284 validation_1-rmse:0.21101 +[15] validation_0-rmse:0.21034 validation_1-rmse:0.20769 +[16] validation_0-rmse:0.20802 validation_1-rmse:0.20438 +[17] validation_0-rmse:0.20590 validation_1-rmse:0.20136 +[18] validation_0-rmse:0.20386 validation_1-rmse:0.19837 +[19] validation_0-rmse:0.20219 validation_1-rmse:0.19549 +[20] validation_0-rmse:0.20037 validation_1-rmse:0.19283 +[21] validation_0-rmse:0.19826 validation_1-rmse:0.19005 +[22] validation_0-rmse:0.19657 validation_1-rmse:0.18750 +[23] validation_0-rmse:0.19525 validation_1-rmse:0.18498 +[24] validation_0-rmse:0.19373 validation_1-rmse:0.18267 +[25] validation_0-rmse:0.19197 validation_1-rmse:0.18037 +[26] validation_0-rmse:0.19063 validation_1-rmse:0.17799 +[27] validation_0-rmse:0.18897 validation_1-rmse:0.17587 +[28] validation_0-rmse:0.18765 validation_1-rmse:0.17382 +[29] validation_0-rmse:0.18608 validation_1-rmse:0.17185 +[30] validation_0-rmse:0.18456 validation_1-rmse:0.16992 +[31] validation_0-rmse:0.18340 validation_1-rmse:0.16793 +[32] validation_0-rmse:0.18206 validation_1-rmse:0.16616 +[33] validation_0-rmse:0.18077 validation_1-rmse:0.16437 +[34] validation_0-rmse:0.17960 validation_1-rmse:0.16270 +[35] validation_0-rmse:0.17857 validation_1-rmse:0.16105 +[36] validation_0-rmse:0.17748 validation_1-rmse:0.15925 +[37] validation_0-rmse:0.17649 validation_1-rmse:0.15762 +[38] validation_0-rmse:0.17540 validation_1-rmse:0.15611 +[39] validation_0-rmse:0.17427 validation_1-rmse:0.15469 +[40] validation_0-rmse:0.17312 validation_1-rmse:0.15301 +[41] validation_0-rmse:0.17217 validation_1-rmse:0.15169 +[42] validation_0-rmse:0.17119 validation_1-rmse:0.15037 +[43] validation_0-rmse:0.17030 validation_1-rmse:0.14910 +[44] validation_0-rmse:0.16939 validation_1-rmse:0.14786 +[45] validation_0-rmse:0.16851 validation_1-rmse:0.14660 +[46] validation_0-rmse:0.16793 validation_1-rmse:0.14518 +[47] validation_0-rmse:0.16760 validation_1-rmse:0.14365 +[48] validation_0-rmse:0.16674 validation_1-rmse:0.14258 +[49] validation_0-rmse:0.16588 validation_1-rmse:0.14152 +[50] validation_0-rmse:0.16505 validation_1-rmse:0.14051 +[51] validation_0-rmse:0.16437 validation_1-rmse:0.13919 +[52] validation_0-rmse:0.16361 validation_1-rmse:0.13818 +[53] validation_0-rmse:0.16290 validation_1-rmse:0.13715 +[54] validation_0-rmse:0.16217 validation_1-rmse:0.13621 +[55] validation_0-rmse:0.16207 validation_1-rmse:0.13493 +[56] validation_0-rmse:0.16153 validation_1-rmse:0.13395 +[57] validation_0-rmse:0.16077 validation_1-rmse:0.13302 +[58] validation_0-rmse:0.16021 validation_1-rmse:0.13218 +[59] validation_0-rmse:0.15972 validation_1-rmse:0.13117 +[60] validation_0-rmse:0.15954 validation_1-rmse:0.13003 +[61] validation_0-rmse:0.15896 validation_1-rmse:0.12926 +[62] validation_0-rmse:0.15849 validation_1-rmse:0.12848 +[63] validation_0-rmse:0.15801 validation_1-rmse:0.12770 +[64] validation_0-rmse:0.15737 validation_1-rmse:0.12678 +[65] validation_0-rmse:0.15736 validation_1-rmse:0.12578 +[66] validation_0-rmse:0.15684 validation_1-rmse:0.12506 +[67] validation_0-rmse:0.15638 validation_1-rmse:0.12437 +[68] validation_0-rmse:0.15618 validation_1-rmse:0.12336 +[69] validation_0-rmse:0.15581 validation_1-rmse:0.12269 +[70] validation_0-rmse:0.15537 validation_1-rmse:0.12205 +[71] validation_0-rmse:0.15534 validation_1-rmse:0.12117 +[72] validation_0-rmse:0.15485 validation_1-rmse:0.12049 +[73] validation_0-rmse:0.15465 validation_1-rmse:0.11968 +[74] validation_0-rmse:0.15430 validation_1-rmse:0.11906 +[75] validation_0-rmse:0.15386 validation_1-rmse:0.11840 +[76] validation_0-rmse:0.15353 validation_1-rmse:0.11781 +[77] validation_0-rmse:0.15354 validation_1-rmse:0.11697 +[78] validation_0-rmse:0.15325 validation_1-rmse:0.11630 +[79] validation_0-rmse:0.15282 validation_1-rmse:0.11572 +[80] validation_0-rmse:0.15239 validation_1-rmse:0.11514 +[81] validation_0-rmse:0.15226 validation_1-rmse:0.11431 +[82] validation_0-rmse:0.15189 validation_1-rmse:0.11381 +[83] validation_0-rmse:0.15171 validation_1-rmse:0.11316 +[84] validation_0-rmse:0.15136 validation_1-rmse:0.11270 +[85] validation_0-rmse:0.15112 validation_1-rmse:0.11212 +[86] validation_0-rmse:0.15112 validation_1-rmse:0.11140 +[87] validation_0-rmse:0.15074 validation_1-rmse:0.11094 +[88] validation_0-rmse:0.15048 validation_1-rmse:0.11035 +[89] validation_0-rmse:0.15026 validation_1-rmse:0.10983 +[90] validation_0-rmse:0.14989 validation_1-rmse:0.10938 +[91] validation_0-rmse:0.14955 validation_1-rmse:0.10893 +[92] validation_0-rmse:0.14955 validation_1-rmse:0.10815 +[93] validation_0-rmse:0.14933 validation_1-rmse:0.10765 +[94] validation_0-rmse:0.14908 validation_1-rmse:0.10711 +[95] validation_0-rmse:0.14889 validation_1-rmse:0.10668 +[96] validation_0-rmse:0.14853 validation_1-rmse:0.10627 +[97] validation_0-rmse:0.14853 validation_1-rmse:0.10553 +[98] validation_0-rmse:0.14835 validation_1-rmse:0.10513 +[99] validation_0-rmse:0.14818 validation_1-rmse:0.10475 +2025-04-29 01:55:33,929 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.82 secs) -------------------- +2025-04-29 01:55:33,930 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:34,433 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-21 00:00:00 to 2025-02-20 00:00:00, 6/11 trains +2025-04-29 01:55:34,434 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1740009600_prediction.feather +2025-04-29 01:55:34,440 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:34,447 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:55:34,448 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.167897 +1 0.003285 50.167897 +2 0.001898 50.167897 +3 0.000484 50.167897 +4 0.001688 50.167897 +2025-04-29 01:55:34,453 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:34,459 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:55:34,461 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.107698 +1 0.003285 50.107698 +2 0.001898 50.107698 +3 0.000484 50.107698 +4 0.001688 50.107698 +2025-04-29 01:55:34,465 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1740009600/cb_btc_1740009600 +2025-04-29 01:55:34,466 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:34,482 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:34,483 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-21 to 2025-02-19 -------------------- +2025-04-29 01:55:39,369 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:39,370 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.27166 validation_1-rmse:0.27726 +[1] validation_0-rmse:0.26708 validation_1-rmse:0.27112 +[2] validation_0-rmse:0.26297 validation_1-rmse:0.26523 +[3] validation_0-rmse:0.25865 validation_1-rmse:0.25959 +[4] validation_0-rmse:0.25494 validation_1-rmse:0.25419 +[5] validation_0-rmse:0.25100 validation_1-rmse:0.24913 +[6] validation_0-rmse:0.24763 validation_1-rmse:0.24437 +[7] validation_0-rmse:0.24441 validation_1-rmse:0.23970 +[8] validation_0-rmse:0.24110 validation_1-rmse:0.23527 +[9] validation_0-rmse:0.23801 validation_1-rmse:0.23102 +[10] validation_0-rmse:0.23492 validation_1-rmse:0.22691 +[11] validation_0-rmse:0.23229 validation_1-rmse:0.22297 +[12] validation_0-rmse:0.22956 validation_1-rmse:0.21923 +[13] validation_0-rmse:0.22707 validation_1-rmse:0.21564 +[14] validation_0-rmse:0.22482 validation_1-rmse:0.21221 +[15] validation_0-rmse:0.22237 validation_1-rmse:0.20891 +[16] validation_0-rmse:0.22030 validation_1-rmse:0.20557 +[17] validation_0-rmse:0.21784 validation_1-rmse:0.20243 +[18] validation_0-rmse:0.21591 validation_1-rmse:0.19949 +[19] validation_0-rmse:0.21399 validation_1-rmse:0.19664 +[20] validation_0-rmse:0.21182 validation_1-rmse:0.19378 +[21] validation_0-rmse:0.20992 validation_1-rmse:0.19110 +[22] validation_0-rmse:0.20821 validation_1-rmse:0.18850 +[23] validation_0-rmse:0.20621 validation_1-rmse:0.18597 +[24] validation_0-rmse:0.20490 validation_1-rmse:0.18353 +[25] validation_0-rmse:0.20318 validation_1-rmse:0.18126 +[26] validation_0-rmse:0.20168 validation_1-rmse:0.17896 +[27] validation_0-rmse:0.19992 validation_1-rmse:0.17679 +[28] validation_0-rmse:0.19865 validation_1-rmse:0.17458 +[29] validation_0-rmse:0.19722 validation_1-rmse:0.17257 +[30] validation_0-rmse:0.19571 validation_1-rmse:0.17039 +[31] validation_0-rmse:0.19429 validation_1-rmse:0.16855 +[32] validation_0-rmse:0.19285 validation_1-rmse:0.16664 +[33] validation_0-rmse:0.19141 validation_1-rmse:0.16488 +[34] validation_0-rmse:0.19022 validation_1-rmse:0.16312 +[35] validation_0-rmse:0.18904 validation_1-rmse:0.16145 +[36] validation_0-rmse:0.18832 validation_1-rmse:0.15973 +[37] validation_0-rmse:0.18723 validation_1-rmse:0.15815 +[38] validation_0-rmse:0.18610 validation_1-rmse:0.15653 +[39] validation_0-rmse:0.18504 validation_1-rmse:0.15503 +[40] validation_0-rmse:0.18402 validation_1-rmse:0.15358 +[41] validation_0-rmse:0.18333 validation_1-rmse:0.15193 +[42] validation_0-rmse:0.18213 validation_1-rmse:0.15058 +[43] validation_0-rmse:0.18176 validation_1-rmse:0.14922 +[44] validation_0-rmse:0.18093 validation_1-rmse:0.14792 +[45] validation_0-rmse:0.18017 validation_1-rmse:0.14667 +[46] validation_0-rmse:0.17928 validation_1-rmse:0.14537 +[47] validation_0-rmse:0.17858 validation_1-rmse:0.14420 +[48] validation_0-rmse:0.17770 validation_1-rmse:0.14306 +[49] validation_0-rmse:0.17695 validation_1-rmse:0.14199 +[50] validation_0-rmse:0.17613 validation_1-rmse:0.14094 +[51] validation_0-rmse:0.17545 validation_1-rmse:0.13979 +[52] validation_0-rmse:0.17490 validation_1-rmse:0.13874 +[53] validation_0-rmse:0.17452 validation_1-rmse:0.13755 +[54] validation_0-rmse:0.17383 validation_1-rmse:0.13663 +[55] validation_0-rmse:0.17327 validation_1-rmse:0.13568 +[56] validation_0-rmse:0.17255 validation_1-rmse:0.13477 +[57] validation_0-rmse:0.17192 validation_1-rmse:0.13382 +[58] validation_0-rmse:0.17138 validation_1-rmse:0.13277 +[59] validation_0-rmse:0.17074 validation_1-rmse:0.13188 +[60] validation_0-rmse:0.17026 validation_1-rmse:0.13089 +[61] validation_0-rmse:0.16969 validation_1-rmse:0.13010 +[62] validation_0-rmse:0.16932 validation_1-rmse:0.12904 +[63] validation_0-rmse:0.16888 validation_1-rmse:0.12818 +[64] validation_0-rmse:0.16849 validation_1-rmse:0.12745 +[65] validation_0-rmse:0.16802 validation_1-rmse:0.12639 +[66] validation_0-rmse:0.16747 validation_1-rmse:0.12567 +[67] validation_0-rmse:0.16710 validation_1-rmse:0.12496 +[68] validation_0-rmse:0.16672 validation_1-rmse:0.12426 +[69] validation_0-rmse:0.16635 validation_1-rmse:0.12331 +[70] validation_0-rmse:0.16597 validation_1-rmse:0.12267 +[71] validation_0-rmse:0.16554 validation_1-rmse:0.12196 +[72] validation_0-rmse:0.16522 validation_1-rmse:0.12121 +[73] validation_0-rmse:0.16481 validation_1-rmse:0.12054 +[74] validation_0-rmse:0.16442 validation_1-rmse:0.11996 +[75] validation_0-rmse:0.16409 validation_1-rmse:0.11939 +[76] validation_0-rmse:0.16375 validation_1-rmse:0.11878 +[77] validation_0-rmse:0.16275 validation_1-rmse:0.11753 +[78] validation_0-rmse:0.16248 validation_1-rmse:0.11692 +[79] validation_0-rmse:0.16215 validation_1-rmse:0.11619 +[80] validation_0-rmse:0.16187 validation_1-rmse:0.11564 +[81] validation_0-rmse:0.16150 validation_1-rmse:0.11493 +[82] validation_0-rmse:0.16123 validation_1-rmse:0.11438 +[83] validation_0-rmse:0.16109 validation_1-rmse:0.11358 +[84] validation_0-rmse:0.16065 validation_1-rmse:0.11304 +[85] validation_0-rmse:0.16038 validation_1-rmse:0.11256 +[86] validation_0-rmse:0.16022 validation_1-rmse:0.11205 +[87] validation_0-rmse:0.16007 validation_1-rmse:0.11158 +[88] validation_0-rmse:0.15945 validation_1-rmse:0.11054 +[89] validation_0-rmse:0.15912 validation_1-rmse:0.11008 +[90] validation_0-rmse:0.15894 validation_1-rmse:0.10937 +[91] validation_0-rmse:0.15868 validation_1-rmse:0.10886 +[92] validation_0-rmse:0.15845 validation_1-rmse:0.10844 +[93] validation_0-rmse:0.15817 validation_1-rmse:0.10803 +[94] validation_0-rmse:0.15789 validation_1-rmse:0.10758 +[95] validation_0-rmse:0.15772 validation_1-rmse:0.10721 +[96] validation_0-rmse:0.15763 validation_1-rmse:0.10676 +[97] validation_0-rmse:0.15751 validation_1-rmse:0.10609 +[98] validation_0-rmse:0.15731 validation_1-rmse:0.10574 +[99] validation_0-rmse:0.15738 validation_1-rmse:0.10531 +2025-04-29 01:55:40,266 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.80 secs) -------------------- +2025-04-29 01:55:40,267 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:40,801 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-31 00:00:00 to 2025-03-02 00:00:00, 7/11 trains +2025-04-29 01:55:40,802 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1740873600_prediction.feather +2025-04-29 01:55:40,807 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:40,814 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:55:40,816 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.107698 +1 0.003285 50.107698 +2 0.001898 50.107698 +3 0.000484 50.107698 +4 0.001688 50.107698 +2025-04-29 01:55:40,821 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:40,827 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:55:40,829 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079166 +1 0.003285 50.079166 +2 0.001898 50.079166 +3 0.000484 50.079166 +4 0.001688 50.079166 +2025-04-29 01:55:40,833 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1740873600/cb_btc_1740873600 +2025-04-29 01:55:40,834 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:40,849 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:40,850 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-31 to 2025-03-01 -------------------- +2025-04-29 01:55:45,643 - datasieve.pipeline - INFO - DI tossed 2275 predictions for being too far from training data. +2025-04-29 01:55:45,646 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:45,647 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.27618 validation_1-rmse:0.28955 +[1] validation_0-rmse:0.27005 validation_1-rmse:0.28323 +[2] validation_0-rmse:0.26414 validation_1-rmse:0.27722 +[3] validation_0-rmse:0.25897 validation_1-rmse:0.27161 +[4] validation_0-rmse:0.25425 validation_1-rmse:0.26622 +[5] validation_0-rmse:0.24886 validation_1-rmse:0.26100 +[6] validation_0-rmse:0.24522 validation_1-rmse:0.25606 +[7] validation_0-rmse:0.24137 validation_1-rmse:0.25132 +[8] validation_0-rmse:0.23765 validation_1-rmse:0.24687 +[9] validation_0-rmse:0.23323 validation_1-rmse:0.24254 +[10] validation_0-rmse:0.22900 validation_1-rmse:0.23827 +[11] validation_0-rmse:0.22588 validation_1-rmse:0.23450 +[12] validation_0-rmse:0.22228 validation_1-rmse:0.23055 +[13] validation_0-rmse:0.21872 validation_1-rmse:0.22698 +[14] validation_0-rmse:0.21492 validation_1-rmse:0.22348 +[15] validation_0-rmse:0.21329 validation_1-rmse:0.22011 +[16] validation_0-rmse:0.21024 validation_1-rmse:0.21686 +[17] validation_0-rmse:0.20823 validation_1-rmse:0.21380 +[18] validation_0-rmse:0.20544 validation_1-rmse:0.21075 +[19] validation_0-rmse:0.20415 validation_1-rmse:0.20787 +[20] validation_0-rmse:0.20143 validation_1-rmse:0.20515 +[21] validation_0-rmse:0.19917 validation_1-rmse:0.20247 +[22] validation_0-rmse:0.19745 validation_1-rmse:0.19994 +[23] validation_0-rmse:0.19508 validation_1-rmse:0.19746 +[24] validation_0-rmse:0.19300 validation_1-rmse:0.19490 +[25] validation_0-rmse:0.19085 validation_1-rmse:0.19254 +[26] validation_0-rmse:0.18898 validation_1-rmse:0.19031 +[27] validation_0-rmse:0.18720 validation_1-rmse:0.18794 +[28] validation_0-rmse:0.18503 validation_1-rmse:0.18584 +[29] validation_0-rmse:0.18314 validation_1-rmse:0.18382 +[30] validation_0-rmse:0.18132 validation_1-rmse:0.18164 +[31] validation_0-rmse:0.17984 validation_1-rmse:0.17967 +[32] validation_0-rmse:0.17818 validation_1-rmse:0.17779 +[33] validation_0-rmse:0.17637 validation_1-rmse:0.17572 +[34] validation_0-rmse:0.17473 validation_1-rmse:0.17399 +[35] validation_0-rmse:0.17338 validation_1-rmse:0.17229 +[36] validation_0-rmse:0.17253 validation_1-rmse:0.17055 +[37] validation_0-rmse:0.17149 validation_1-rmse:0.16883 +[38] validation_0-rmse:0.17030 validation_1-rmse:0.16730 +[39] validation_0-rmse:0.16950 validation_1-rmse:0.16556 +[40] validation_0-rmse:0.16815 validation_1-rmse:0.16412 +[41] validation_0-rmse:0.16704 validation_1-rmse:0.16268 +[42] validation_0-rmse:0.16617 validation_1-rmse:0.16128 +[43] validation_0-rmse:0.16542 validation_1-rmse:0.15970 +[44] validation_0-rmse:0.16438 validation_1-rmse:0.15840 +[45] validation_0-rmse:0.16356 validation_1-rmse:0.15692 +[46] validation_0-rmse:0.16239 validation_1-rmse:0.15574 +[47] validation_0-rmse:0.16153 validation_1-rmse:0.15456 +[48] validation_0-rmse:0.16076 validation_1-rmse:0.15314 +[49] validation_0-rmse:0.15998 validation_1-rmse:0.15201 +[50] validation_0-rmse:0.15946 validation_1-rmse:0.15084 +[51] validation_0-rmse:0.15891 validation_1-rmse:0.14954 +[52] validation_0-rmse:0.15834 validation_1-rmse:0.14847 +[53] validation_0-rmse:0.15764 validation_1-rmse:0.14722 +[54] validation_0-rmse:0.15707 validation_1-rmse:0.14623 +[55] validation_0-rmse:0.15653 validation_1-rmse:0.14527 +[56] validation_0-rmse:0.15583 validation_1-rmse:0.14434 +[57] validation_0-rmse:0.15549 validation_1-rmse:0.14329 +[58] validation_0-rmse:0.15507 validation_1-rmse:0.14241 +[59] validation_0-rmse:0.15468 validation_1-rmse:0.14053 +[60] validation_0-rmse:0.15398 validation_1-rmse:0.13968 +[61] validation_0-rmse:0.15390 validation_1-rmse:0.13864 +[62] validation_0-rmse:0.15360 validation_1-rmse:0.13783 +[63] validation_0-rmse:0.15368 validation_1-rmse:0.13704 +[64] validation_0-rmse:0.15338 validation_1-rmse:0.13624 +[65] validation_0-rmse:0.15273 validation_1-rmse:0.13551 +[66] validation_0-rmse:0.15238 validation_1-rmse:0.13451 +[67] validation_0-rmse:0.15212 validation_1-rmse:0.13290 +[68] validation_0-rmse:0.15191 validation_1-rmse:0.13217 +[69] validation_0-rmse:0.15138 validation_1-rmse:0.13143 +[70] validation_0-rmse:0.15090 validation_1-rmse:0.13071 +[71] validation_0-rmse:0.15082 validation_1-rmse:0.13001 +[72] validation_0-rmse:0.14988 validation_1-rmse:0.12847 +[73] validation_0-rmse:0.14953 validation_1-rmse:0.12783 +[74] validation_0-rmse:0.14924 validation_1-rmse:0.12709 +[75] validation_0-rmse:0.14926 validation_1-rmse:0.12578 +[76] validation_0-rmse:0.14903 validation_1-rmse:0.12499 +[77] validation_0-rmse:0.14851 validation_1-rmse:0.12435 +[78] validation_0-rmse:0.14808 validation_1-rmse:0.12368 +[79] validation_0-rmse:0.14768 validation_1-rmse:0.12305 +[80] validation_0-rmse:0.14741 validation_1-rmse:0.12217 +[81] validation_0-rmse:0.14712 validation_1-rmse:0.12165 +[82] validation_0-rmse:0.14696 validation_1-rmse:0.12110 +[83] validation_0-rmse:0.14686 validation_1-rmse:0.12045 +[84] validation_0-rmse:0.14648 validation_1-rmse:0.11984 +[85] validation_0-rmse:0.14623 validation_1-rmse:0.11923 +[86] validation_0-rmse:0.14606 validation_1-rmse:0.11869 +[87] validation_0-rmse:0.14583 validation_1-rmse:0.11754 +[88] validation_0-rmse:0.14572 validation_1-rmse:0.11710 +[89] validation_0-rmse:0.14537 validation_1-rmse:0.11660 +[90] validation_0-rmse:0.14510 validation_1-rmse:0.11614 +[91] validation_0-rmse:0.14516 validation_1-rmse:0.11514 +[92] validation_0-rmse:0.14480 validation_1-rmse:0.11455 +[93] validation_0-rmse:0.14475 validation_1-rmse:0.11414 +[94] validation_0-rmse:0.14443 validation_1-rmse:0.11374 +[95] validation_0-rmse:0.14409 validation_1-rmse:0.11331 +[96] validation_0-rmse:0.14391 validation_1-rmse:0.11240 +[97] validation_0-rmse:0.14303 validation_1-rmse:0.11154 +[98] validation_0-rmse:0.14274 validation_1-rmse:0.11114 +[99] validation_0-rmse:0.14246 validation_1-rmse:0.11071 +2025-04-29 01:55:46,544 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.71 secs) -------------------- +2025-04-29 01:55:46,544 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:47,092 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-02-10 00:00:00 to 2025-03-12 00:00:00, 8/11 trains +2025-04-29 01:55:47,092 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1741737600_prediction.feather +2025-04-29 01:55:47,100 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:47,107 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:55:47,109 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079166 +1 0.003285 50.079166 +2 0.001898 50.079166 +3 0.000484 50.079166 +4 0.001688 50.079166 +2025-04-29 01:55:47,115 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:47,122 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:55:47,123 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.102027 +1 0.003285 50.102027 +2 0.001898 50.102027 +3 0.000484 50.102027 +4 0.001688 50.102027 +2025-04-29 01:55:47,128 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1741737600/cb_btc_1741737600 +2025-04-29 01:55:47,129 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:47,145 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:47,145 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-10 to 2025-03-11 -------------------- +2025-04-29 01:55:51,987 - datasieve.pipeline - INFO - DI tossed 18 predictions for being too far from training data. +2025-04-29 01:55:51,989 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:51,989 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.26738 validation_1-rmse:0.26816 +[1] validation_0-rmse:0.26268 validation_1-rmse:0.26258 +[2] validation_0-rmse:0.25808 validation_1-rmse:0.25725 +[3] validation_0-rmse:0.25395 validation_1-rmse:0.25212 +[4] validation_0-rmse:0.24987 validation_1-rmse:0.24723 +[5] validation_0-rmse:0.24633 validation_1-rmse:0.24263 +[6] validation_0-rmse:0.24308 validation_1-rmse:0.23814 +[7] validation_0-rmse:0.23959 validation_1-rmse:0.23402 +[8] validation_0-rmse:0.23612 validation_1-rmse:0.22977 +[9] validation_0-rmse:0.23322 validation_1-rmse:0.22577 +[10] validation_0-rmse:0.23012 validation_1-rmse:0.22207 +[11] validation_0-rmse:0.22730 validation_1-rmse:0.21843 +[12] validation_0-rmse:0.22453 validation_1-rmse:0.21489 +[13] validation_0-rmse:0.22236 validation_1-rmse:0.21145 +[14] validation_0-rmse:0.22000 validation_1-rmse:0.20841 +[15] validation_0-rmse:0.21744 validation_1-rmse:0.20529 +[16] validation_0-rmse:0.21556 validation_1-rmse:0.20225 +[17] validation_0-rmse:0.21331 validation_1-rmse:0.19932 +[18] validation_0-rmse:0.21171 validation_1-rmse:0.19643 +[19] validation_0-rmse:0.21051 validation_1-rmse:0.19382 +[20] validation_0-rmse:0.20880 validation_1-rmse:0.19128 +[21] validation_0-rmse:0.20711 validation_1-rmse:0.18854 +[22] validation_0-rmse:0.20538 validation_1-rmse:0.18612 +[23] validation_0-rmse:0.20350 validation_1-rmse:0.18381 +[24] validation_0-rmse:0.20234 validation_1-rmse:0.18144 +[25] validation_0-rmse:0.20081 validation_1-rmse:0.17917 +[26] validation_0-rmse:0.19918 validation_1-rmse:0.17714 +[27] validation_0-rmse:0.19804 validation_1-rmse:0.17496 +[28] validation_0-rmse:0.19662 validation_1-rmse:0.17304 +[29] validation_0-rmse:0.19580 validation_1-rmse:0.17082 +[30] validation_0-rmse:0.19454 validation_1-rmse:0.16901 +[31] validation_0-rmse:0.19331 validation_1-rmse:0.16691 +[32] validation_0-rmse:0.19234 validation_1-rmse:0.16517 +[33] validation_0-rmse:0.19118 validation_1-rmse:0.16354 +[34] validation_0-rmse:0.19024 validation_1-rmse:0.16175 +[35] validation_0-rmse:0.18915 validation_1-rmse:0.16020 +[36] validation_0-rmse:0.18823 validation_1-rmse:0.15865 +[37] validation_0-rmse:0.18756 validation_1-rmse:0.15712 +[38] validation_0-rmse:0.18698 validation_1-rmse:0.15541 +[39] validation_0-rmse:0.18643 validation_1-rmse:0.15395 +[40] validation_0-rmse:0.18562 validation_1-rmse:0.15265 +[41] validation_0-rmse:0.18516 validation_1-rmse:0.15124 +[42] validation_0-rmse:0.18421 validation_1-rmse:0.14979 +[43] validation_0-rmse:0.18360 validation_1-rmse:0.14850 +[44] validation_0-rmse:0.18275 validation_1-rmse:0.14733 +[45] validation_0-rmse:0.18253 validation_1-rmse:0.14597 +[46] validation_0-rmse:0.18183 validation_1-rmse:0.14470 +[47] validation_0-rmse:0.18111 validation_1-rmse:0.14361 +[48] validation_0-rmse:0.18060 validation_1-rmse:0.14243 +[49] validation_0-rmse:0.18001 validation_1-rmse:0.14134 +[50] validation_0-rmse:0.17953 validation_1-rmse:0.14030 +[51] validation_0-rmse:0.17899 validation_1-rmse:0.13927 +[52] validation_0-rmse:0.17830 validation_1-rmse:0.13817 +[53] validation_0-rmse:0.17770 validation_1-rmse:0.13720 +[54] validation_0-rmse:0.17702 validation_1-rmse:0.13629 +[55] validation_0-rmse:0.17650 validation_1-rmse:0.13531 +[56] validation_0-rmse:0.17625 validation_1-rmse:0.13440 +[57] validation_0-rmse:0.17580 validation_1-rmse:0.13352 +[58] validation_0-rmse:0.17530 validation_1-rmse:0.13268 +[59] validation_0-rmse:0.17486 validation_1-rmse:0.13166 +[60] validation_0-rmse:0.17438 validation_1-rmse:0.13071 +[61] validation_0-rmse:0.17387 validation_1-rmse:0.12991 +[62] validation_0-rmse:0.17356 validation_1-rmse:0.12914 +[63] validation_0-rmse:0.17311 validation_1-rmse:0.12839 +[64] validation_0-rmse:0.17265 validation_1-rmse:0.12767 +[65] validation_0-rmse:0.17209 validation_1-rmse:0.12682 +[66] validation_0-rmse:0.17197 validation_1-rmse:0.12595 +[67] validation_0-rmse:0.17157 validation_1-rmse:0.12506 +[68] validation_0-rmse:0.17131 validation_1-rmse:0.12439 +[69] validation_0-rmse:0.17088 validation_1-rmse:0.12371 +[70] validation_0-rmse:0.17038 validation_1-rmse:0.12298 +[71] validation_0-rmse:0.17009 validation_1-rmse:0.12235 +[72] validation_0-rmse:0.16979 validation_1-rmse:0.12172 +[73] validation_0-rmse:0.16934 validation_1-rmse:0.12118 +[74] validation_0-rmse:0.16902 validation_1-rmse:0.12050 +[75] validation_0-rmse:0.16881 validation_1-rmse:0.11988 +[76] validation_0-rmse:0.16846 validation_1-rmse:0.11928 +[77] validation_0-rmse:0.16809 validation_1-rmse:0.11846 +[78] validation_0-rmse:0.16774 validation_1-rmse:0.11791 +[79] validation_0-rmse:0.16745 validation_1-rmse:0.11738 +[80] validation_0-rmse:0.16717 validation_1-rmse:0.11683 +[81] validation_0-rmse:0.16702 validation_1-rmse:0.11599 +[82] validation_0-rmse:0.16677 validation_1-rmse:0.11535 +[83] validation_0-rmse:0.16649 validation_1-rmse:0.11468 +[84] validation_0-rmse:0.16605 validation_1-rmse:0.11415 +[85] validation_0-rmse:0.16591 validation_1-rmse:0.11350 +[86] validation_0-rmse:0.16560 validation_1-rmse:0.11303 +[87] validation_0-rmse:0.16531 validation_1-rmse:0.11259 +[88] validation_0-rmse:0.16504 validation_1-rmse:0.11185 +[89] validation_0-rmse:0.16485 validation_1-rmse:0.11134 +[90] validation_0-rmse:0.16463 validation_1-rmse:0.11083 +[91] validation_0-rmse:0.16436 validation_1-rmse:0.11041 +[92] validation_0-rmse:0.16412 validation_1-rmse:0.10988 +[93] validation_0-rmse:0.16388 validation_1-rmse:0.10942 +[94] validation_0-rmse:0.16391 validation_1-rmse:0.10881 +[95] validation_0-rmse:0.16357 validation_1-rmse:0.10838 +[96] validation_0-rmse:0.16358 validation_1-rmse:0.10796 +[97] validation_0-rmse:0.16338 validation_1-rmse:0.10756 +[98] validation_0-rmse:0.16339 validation_1-rmse:0.10688 +[99] validation_0-rmse:0.16321 validation_1-rmse:0.10649 +2025-04-29 01:55:52,741 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.61 secs) -------------------- +2025-04-29 01:55:52,742 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:53,285 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-02-20 00:00:00 to 2025-03-22 00:00:00, 9/11 trains +2025-04-29 01:55:53,286 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1742601600_prediction.feather +2025-04-29 01:55:53,291 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:53,298 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:55:53,300 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.102027 +1 0.003285 50.102027 +2 0.001898 50.102027 +3 0.000484 50.102027 +4 0.001688 50.102027 +2025-04-29 01:55:53,309 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:53,316 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:55:53,318 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079967 +1 0.003285 50.079967 +2 0.001898 50.079967 +3 0.000484 50.079967 +4 0.001688 50.079967 +2025-04-29 01:55:53,322 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1742601600/cb_btc_1742601600 +2025-04-29 01:55:53,323 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:53,339 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:53,340 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-20 to 2025-03-21 -------------------- +2025-04-29 01:55:58,184 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:58,185 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.26992 validation_1-rmse:0.26756 +[1] validation_0-rmse:0.26551 validation_1-rmse:0.26201 +[2] validation_0-rmse:0.26111 validation_1-rmse:0.25656 +[3] validation_0-rmse:0.25690 validation_1-rmse:0.25154 +[4] validation_0-rmse:0.25291 validation_1-rmse:0.24683 +[5] validation_0-rmse:0.24933 validation_1-rmse:0.24228 +[6] validation_0-rmse:0.24598 validation_1-rmse:0.23796 +[7] validation_0-rmse:0.24252 validation_1-rmse:0.23392 +[8] validation_0-rmse:0.23953 validation_1-rmse:0.22978 +[9] validation_0-rmse:0.23634 validation_1-rmse:0.22592 +[10] validation_0-rmse:0.23330 validation_1-rmse:0.22229 +[11] validation_0-rmse:0.23059 validation_1-rmse:0.21875 +[12] validation_0-rmse:0.22799 validation_1-rmse:0.21546 +[13] validation_0-rmse:0.22565 validation_1-rmse:0.21212 +[14] validation_0-rmse:0.22329 validation_1-rmse:0.20904 +[15] validation_0-rmse:0.22111 validation_1-rmse:0.20604 +[16] validation_0-rmse:0.21894 validation_1-rmse:0.20318 +[17] validation_0-rmse:0.21715 validation_1-rmse:0.20021 +[18] validation_0-rmse:0.21499 validation_1-rmse:0.19735 +[19] validation_0-rmse:0.21283 validation_1-rmse:0.19480 +[20] validation_0-rmse:0.21109 validation_1-rmse:0.19209 +[21] validation_0-rmse:0.20904 validation_1-rmse:0.18969 +[22] validation_0-rmse:0.20762 validation_1-rmse:0.18718 +[23] validation_0-rmse:0.20580 validation_1-rmse:0.18498 +[24] validation_0-rmse:0.20434 validation_1-rmse:0.18262 +[25] validation_0-rmse:0.20267 validation_1-rmse:0.18048 +[26] validation_0-rmse:0.20106 validation_1-rmse:0.17844 +[27] validation_0-rmse:0.19945 validation_1-rmse:0.17647 +[28] validation_0-rmse:0.19813 validation_1-rmse:0.17443 +[29] validation_0-rmse:0.19669 validation_1-rmse:0.17264 +[30] validation_0-rmse:0.19541 validation_1-rmse:0.17054 +[31] validation_0-rmse:0.19401 validation_1-rmse:0.16881 +[32] validation_0-rmse:0.19263 validation_1-rmse:0.16719 +[33] validation_0-rmse:0.19134 validation_1-rmse:0.16560 +[34] validation_0-rmse:0.18996 validation_1-rmse:0.16365 +[35] validation_0-rmse:0.18864 validation_1-rmse:0.16211 +[36] validation_0-rmse:0.18752 validation_1-rmse:0.16069 +[37] validation_0-rmse:0.18652 validation_1-rmse:0.15898 +[38] validation_0-rmse:0.18540 validation_1-rmse:0.15751 +[39] validation_0-rmse:0.18429 validation_1-rmse:0.15616 +[40] validation_0-rmse:0.18317 validation_1-rmse:0.15475 +[41] validation_0-rmse:0.18215 validation_1-rmse:0.15324 +[42] validation_0-rmse:0.18119 validation_1-rmse:0.15199 +[43] validation_0-rmse:0.18008 validation_1-rmse:0.15057 +[44] validation_0-rmse:0.17926 validation_1-rmse:0.14942 +[45] validation_0-rmse:0.17841 validation_1-rmse:0.14813 +[46] validation_0-rmse:0.17755 validation_1-rmse:0.14700 +[47] validation_0-rmse:0.17672 validation_1-rmse:0.14572 +[48] validation_0-rmse:0.17586 validation_1-rmse:0.14466 +[49] validation_0-rmse:0.17511 validation_1-rmse:0.14354 +[50] validation_0-rmse:0.17440 validation_1-rmse:0.14236 +[51] validation_0-rmse:0.17354 validation_1-rmse:0.14130 +[52] validation_0-rmse:0.17281 validation_1-rmse:0.14035 +[53] validation_0-rmse:0.17210 validation_1-rmse:0.13942 +[54] validation_0-rmse:0.17136 validation_1-rmse:0.13843 +[55] validation_0-rmse:0.17045 validation_1-rmse:0.13715 +[56] validation_0-rmse:0.16971 validation_1-rmse:0.13629 +[57] validation_0-rmse:0.16900 validation_1-rmse:0.13511 +[58] validation_0-rmse:0.16834 validation_1-rmse:0.13426 +[59] validation_0-rmse:0.16763 validation_1-rmse:0.13323 +[60] validation_0-rmse:0.16702 validation_1-rmse:0.13242 +[61] validation_0-rmse:0.16639 validation_1-rmse:0.13164 +[62] validation_0-rmse:0.16586 validation_1-rmse:0.13079 +[63] validation_0-rmse:0.16527 validation_1-rmse:0.13006 +[64] validation_0-rmse:0.16458 validation_1-rmse:0.12914 +[65] validation_0-rmse:0.16396 validation_1-rmse:0.12841 +[66] validation_0-rmse:0.16332 validation_1-rmse:0.12742 +[67] validation_0-rmse:0.16290 validation_1-rmse:0.12665 +[68] validation_0-rmse:0.16248 validation_1-rmse:0.12584 +[69] validation_0-rmse:0.16192 validation_1-rmse:0.12503 +[70] validation_0-rmse:0.16128 validation_1-rmse:0.12435 +[71] validation_0-rmse:0.16078 validation_1-rmse:0.12371 +[72] validation_0-rmse:0.16032 validation_1-rmse:0.12311 +[73] validation_0-rmse:0.15998 validation_1-rmse:0.12241 +[74] validation_0-rmse:0.15959 validation_1-rmse:0.12184 +[75] validation_0-rmse:0.15922 validation_1-rmse:0.12121 +[76] validation_0-rmse:0.15877 validation_1-rmse:0.12064 +[77] validation_0-rmse:0.15830 validation_1-rmse:0.11981 +[78] validation_0-rmse:0.15791 validation_1-rmse:0.11927 +[79] validation_0-rmse:0.15751 validation_1-rmse:0.11859 +[80] validation_0-rmse:0.15716 validation_1-rmse:0.11795 +[81] validation_0-rmse:0.15680 validation_1-rmse:0.11740 +[82] validation_0-rmse:0.15624 validation_1-rmse:0.11683 +[83] validation_0-rmse:0.15578 validation_1-rmse:0.11632 +[84] validation_0-rmse:0.15553 validation_1-rmse:0.11586 +[85] validation_0-rmse:0.15471 validation_1-rmse:0.11513 +[86] validation_0-rmse:0.15444 validation_1-rmse:0.11465 +[87] validation_0-rmse:0.15417 validation_1-rmse:0.11406 +[88] validation_0-rmse:0.15387 validation_1-rmse:0.11359 +[89] validation_0-rmse:0.15359 validation_1-rmse:0.11319 +[90] validation_0-rmse:0.15332 validation_1-rmse:0.11269 +[91] validation_0-rmse:0.15301 validation_1-rmse:0.11221 +[92] validation_0-rmse:0.15258 validation_1-rmse:0.11176 +[93] validation_0-rmse:0.15231 validation_1-rmse:0.11135 +[94] validation_0-rmse:0.15202 validation_1-rmse:0.11093 +[95] validation_0-rmse:0.15185 validation_1-rmse:0.11041 +[96] validation_0-rmse:0.15173 validation_1-rmse:0.11000 +[97] validation_0-rmse:0.15150 validation_1-rmse:0.10961 +[98] validation_0-rmse:0.15114 validation_1-rmse:0.10917 +[99] validation_0-rmse:0.15096 validation_1-rmse:0.10882 +2025-04-29 01:55:59,097 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.77 secs) -------------------- +2025-04-29 01:55:59,098 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:59,706 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-03-02 00:00:00 to 2025-04-01 00:00:00, 10/11 trains +2025-04-29 01:55:59,706 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1743465600_prediction.feather +2025-04-29 01:55:59,715 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:59,723 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:55:59,725 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079967 +1 0.003285 50.079967 +2 0.001898 50.079967 +3 0.000484 50.079967 +4 0.001688 50.079967 +2025-04-29 01:55:59,732 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:59,739 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:55:59,741 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.024153 +1 0.003285 50.024153 +2 0.001898 50.024153 +3 0.000484 50.024153 +4 0.001688 50.024153 +2025-04-29 01:55:59,745 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1743465600/cb_btc_1743465600 +2025-04-29 01:55:59,746 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:59,762 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:59,762 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-02 to 2025-03-31 -------------------- +2025-04-29 01:56:04,571 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:56:04,571 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.28468 validation_1-rmse:0.28491 +[1] validation_0-rmse:0.27961 validation_1-rmse:0.27914 +[2] validation_0-rmse:0.27524 validation_1-rmse:0.27370 +[3] validation_0-rmse:0.27054 validation_1-rmse:0.26858 +[4] validation_0-rmse:0.26601 validation_1-rmse:0.26362 +[5] validation_0-rmse:0.26219 validation_1-rmse:0.25896 +[6] validation_0-rmse:0.25814 validation_1-rmse:0.25450 +[7] validation_0-rmse:0.25500 validation_1-rmse:0.25026 +[8] validation_0-rmse:0.25145 validation_1-rmse:0.24602 +[9] validation_0-rmse:0.24843 validation_1-rmse:0.24213 +[10] validation_0-rmse:0.24527 validation_1-rmse:0.23824 +[11] validation_0-rmse:0.24238 validation_1-rmse:0.23440 +[12] validation_0-rmse:0.23940 validation_1-rmse:0.23096 +[13] validation_0-rmse:0.23630 validation_1-rmse:0.22764 +[14] validation_0-rmse:0.23385 validation_1-rmse:0.22440 +[15] validation_0-rmse:0.23099 validation_1-rmse:0.22128 +[16] validation_0-rmse:0.22865 validation_1-rmse:0.21801 +[17] validation_0-rmse:0.22620 validation_1-rmse:0.21515 +[18] validation_0-rmse:0.22375 validation_1-rmse:0.21210 +[19] validation_0-rmse:0.22142 validation_1-rmse:0.20925 +[20] validation_0-rmse:0.21927 validation_1-rmse:0.20663 +[21] validation_0-rmse:0.21720 validation_1-rmse:0.20416 +[22] validation_0-rmse:0.21528 validation_1-rmse:0.20170 +[23] validation_0-rmse:0.21330 validation_1-rmse:0.19913 +[24] validation_0-rmse:0.21136 validation_1-rmse:0.19693 +[25] validation_0-rmse:0.21002 validation_1-rmse:0.19438 +[26] validation_0-rmse:0.20807 validation_1-rmse:0.19222 +[27] validation_0-rmse:0.20636 validation_1-rmse:0.19016 +[28] validation_0-rmse:0.20439 validation_1-rmse:0.18763 +[29] validation_0-rmse:0.20276 validation_1-rmse:0.18559 +[30] validation_0-rmse:0.20114 validation_1-rmse:0.18380 +[31] validation_0-rmse:0.19965 validation_1-rmse:0.18163 +[32] validation_0-rmse:0.19833 validation_1-rmse:0.17955 +[33] validation_0-rmse:0.19688 validation_1-rmse:0.17782 +[34] validation_0-rmse:0.19558 validation_1-rmse:0.17614 +[35] validation_0-rmse:0.19420 validation_1-rmse:0.17451 +[36] validation_0-rmse:0.19297 validation_1-rmse:0.17293 +[37] validation_0-rmse:0.19169 validation_1-rmse:0.17111 +[38] validation_0-rmse:0.19038 validation_1-rmse:0.16943 +[39] validation_0-rmse:0.18941 validation_1-rmse:0.16798 +[40] validation_0-rmse:0.18828 validation_1-rmse:0.16657 +[41] validation_0-rmse:0.18724 validation_1-rmse:0.16485 +[42] validation_0-rmse:0.18620 validation_1-rmse:0.16347 +[43] validation_0-rmse:0.18525 validation_1-rmse:0.16204 +[44] validation_0-rmse:0.18429 validation_1-rmse:0.16073 +[45] validation_0-rmse:0.18324 validation_1-rmse:0.15951 +[46] validation_0-rmse:0.18250 validation_1-rmse:0.15797 +[47] validation_0-rmse:0.18157 validation_1-rmse:0.15682 +[48] validation_0-rmse:0.18069 validation_1-rmse:0.15566 +[49] validation_0-rmse:0.18002 validation_1-rmse:0.15440 +[50] validation_0-rmse:0.17914 validation_1-rmse:0.15322 +[51] validation_0-rmse:0.17842 validation_1-rmse:0.15220 +[52] validation_0-rmse:0.17756 validation_1-rmse:0.15107 +[53] validation_0-rmse:0.17668 validation_1-rmse:0.15007 +[54] validation_0-rmse:0.17596 validation_1-rmse:0.14866 +[55] validation_0-rmse:0.17525 validation_1-rmse:0.14775 +[56] validation_0-rmse:0.17467 validation_1-rmse:0.14653 +[57] validation_0-rmse:0.17390 validation_1-rmse:0.14564 +[58] validation_0-rmse:0.17326 validation_1-rmse:0.14478 +[59] validation_0-rmse:0.17273 validation_1-rmse:0.14356 +[60] validation_0-rmse:0.17218 validation_1-rmse:0.14269 +[61] validation_0-rmse:0.17157 validation_1-rmse:0.14186 +[62] validation_0-rmse:0.17120 validation_1-rmse:0.14083 +[63] validation_0-rmse:0.17069 validation_1-rmse:0.14002 +[64] validation_0-rmse:0.17012 validation_1-rmse:0.13912 +[65] validation_0-rmse:0.16942 validation_1-rmse:0.13834 +[66] validation_0-rmse:0.16914 validation_1-rmse:0.13720 +[67] validation_0-rmse:0.16856 validation_1-rmse:0.13648 +[68] validation_0-rmse:0.16800 validation_1-rmse:0.13569 +[69] validation_0-rmse:0.16796 validation_1-rmse:0.13472 +[70] validation_0-rmse:0.16737 validation_1-rmse:0.13405 +[71] validation_0-rmse:0.16686 validation_1-rmse:0.13342 +[72] validation_0-rmse:0.16639 validation_1-rmse:0.13270 +[73] validation_0-rmse:0.16648 validation_1-rmse:0.13149 +[74] validation_0-rmse:0.16609 validation_1-rmse:0.13086 +[75] validation_0-rmse:0.16560 validation_1-rmse:0.13025 +[76] validation_0-rmse:0.16530 validation_1-rmse:0.12925 +[77] validation_0-rmse:0.16492 validation_1-rmse:0.12824 +[78] validation_0-rmse:0.16451 validation_1-rmse:0.12770 +[79] validation_0-rmse:0.16414 validation_1-rmse:0.12710 +[80] validation_0-rmse:0.16377 validation_1-rmse:0.12654 +[81] validation_0-rmse:0.16338 validation_1-rmse:0.12595 +[82] validation_0-rmse:0.16317 validation_1-rmse:0.12490 +[83] validation_0-rmse:0.16249 validation_1-rmse:0.12361 +[84] validation_0-rmse:0.16217 validation_1-rmse:0.12307 +[85] validation_0-rmse:0.16178 validation_1-rmse:0.12255 +[86] validation_0-rmse:0.16149 validation_1-rmse:0.12206 +[87] validation_0-rmse:0.16113 validation_1-rmse:0.12155 +[88] validation_0-rmse:0.16049 validation_1-rmse:0.12061 +[89] validation_0-rmse:0.16008 validation_1-rmse:0.11990 +[90] validation_0-rmse:0.15955 validation_1-rmse:0.11882 +[91] validation_0-rmse:0.15927 validation_1-rmse:0.11842 +[92] validation_0-rmse:0.15891 validation_1-rmse:0.11796 +[93] validation_0-rmse:0.15880 validation_1-rmse:0.11730 +[94] validation_0-rmse:0.15829 validation_1-rmse:0.11631 +[95] validation_0-rmse:0.15809 validation_1-rmse:0.11584 +[96] validation_0-rmse:0.15778 validation_1-rmse:0.11544 +[97] validation_0-rmse:0.15763 validation_1-rmse:0.11504 +[98] validation_0-rmse:0.15724 validation_1-rmse:0.11438 +[99] validation_0-rmse:0.15694 validation_1-rmse:0.11396 +2025-04-29 01:56:05,520 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.77 secs) -------------------- +2025-04-29 01:56:05,521 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:06,027 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-03-12 00:00:00 to 2025-04-11 00:00:00, 11/11 trains +2025-04-29 01:56:06,027 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1744329600_prediction.feather +2025-04-29 01:56:06,037 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:56:06,045 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:56:06,046 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.024153 +1 0.003285 50.024153 +2 0.001898 50.024153 +3 0.000484 50.024153 +4 0.001688 50.024153 +2025-04-29 01:56:06,057 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:56:06,064 - FreqaiExampleStrategy - INFO - 目标列形状：(66770,) +2025-04-29 01:56:06,065 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.093162 +1 0.003285 50.093162 +2 0.001898 50.093162 +3 0.000484 50.093162 +4 0.001688 50.093162 +2025-04-29 01:56:06,070 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1744329600/cb_btc_1744329600 +2025-04-29 01:56:06,071 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:56:06,087 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:06,088 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-12 to 2025-04-10 -------------------- +2025-04-29 01:56:10,904 - datasieve.pipeline - INFO - DI tossed 2001 predictions for being too far from training data. +2025-04-29 01:56:10,907 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:56:10,907 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.32950 validation_1-rmse:0.29220 +[1] validation_0-rmse:0.32402 validation_1-rmse:0.28580 +[2] validation_0-rmse:0.31922 validation_1-rmse:0.27974 +[3] validation_0-rmse:0.31450 validation_1-rmse:0.27409 +[4] validation_0-rmse:0.30969 validation_1-rmse:0.26866 +[5] validation_0-rmse:0.30585 validation_1-rmse:0.26346 +[6] validation_0-rmse:0.30202 validation_1-rmse:0.25855 +[7] validation_0-rmse:0.29888 validation_1-rmse:0.25375 +[8] validation_0-rmse:0.29520 validation_1-rmse:0.24919 +[9] validation_0-rmse:0.29164 validation_1-rmse:0.24487 +[10] validation_0-rmse:0.28843 validation_1-rmse:0.24072 +[11] validation_0-rmse:0.28514 validation_1-rmse:0.23667 +[12] validation_0-rmse:0.28114 validation_1-rmse:0.23279 +[13] validation_0-rmse:0.27740 validation_1-rmse:0.22909 +[14] validation_0-rmse:0.27421 validation_1-rmse:0.22543 +[15] validation_0-rmse:0.27115 validation_1-rmse:0.22210 +[16] validation_0-rmse:0.26820 validation_1-rmse:0.21859 +[17] validation_0-rmse:0.26549 validation_1-rmse:0.21528 +[18] validation_0-rmse:0.26254 validation_1-rmse:0.21226 +[19] validation_0-rmse:0.25967 validation_1-rmse:0.20927 +[20] validation_0-rmse:0.25735 validation_1-rmse:0.20641 +[21] validation_0-rmse:0.25470 validation_1-rmse:0.20366 +[22] validation_0-rmse:0.25265 validation_1-rmse:0.20073 +[23] validation_0-rmse:0.25054 validation_1-rmse:0.19819 +[24] validation_0-rmse:0.24806 validation_1-rmse:0.19573 +[25] validation_0-rmse:0.24570 validation_1-rmse:0.19304 +[26] validation_0-rmse:0.24361 validation_1-rmse:0.19076 +[27] validation_0-rmse:0.24148 validation_1-rmse:0.18853 +[28] validation_0-rmse:0.24014 validation_1-rmse:0.18621 +[29] validation_0-rmse:0.23792 validation_1-rmse:0.18410 +[30] validation_0-rmse:0.23603 validation_1-rmse:0.18203 +[31] validation_0-rmse:0.23421 validation_1-rmse:0.17990 +[32] validation_0-rmse:0.23264 validation_1-rmse:0.17800 +[33] validation_0-rmse:0.23087 validation_1-rmse:0.17616 +[34] validation_0-rmse:0.22949 validation_1-rmse:0.17427 +[35] validation_0-rmse:0.22857 validation_1-rmse:0.17234 +[36] validation_0-rmse:0.22690 validation_1-rmse:0.17065 +[37] validation_0-rmse:0.22566 validation_1-rmse:0.16898 +[38] validation_0-rmse:0.22462 validation_1-rmse:0.16738 +[39] validation_0-rmse:0.22376 validation_1-rmse:0.16567 +[40] validation_0-rmse:0.22232 validation_1-rmse:0.16410 +[41] validation_0-rmse:0.22105 validation_1-rmse:0.16265 +[42] validation_0-rmse:0.22006 validation_1-rmse:0.16111 +[43] validation_0-rmse:0.21847 validation_1-rmse:0.15976 +[44] validation_0-rmse:0.21782 validation_1-rmse:0.15824 +[45] validation_0-rmse:0.21641 validation_1-rmse:0.15686 +[46] validation_0-rmse:0.21552 validation_1-rmse:0.15554 +[47] validation_0-rmse:0.21459 validation_1-rmse:0.15417 +[48] validation_0-rmse:0.21339 validation_1-rmse:0.15293 +[49] validation_0-rmse:0.21255 validation_1-rmse:0.15176 +[50] validation_0-rmse:0.21192 validation_1-rmse:0.15047 +[51] validation_0-rmse:0.21115 validation_1-rmse:0.14910 +[52] validation_0-rmse:0.21072 validation_1-rmse:0.14774 +[53] validation_0-rmse:0.20992 validation_1-rmse:0.14670 +[54] validation_0-rmse:0.20839 validation_1-rmse:0.14541 +[55] validation_0-rmse:0.20753 validation_1-rmse:0.14442 +[56] validation_0-rmse:0.20648 validation_1-rmse:0.14328 +[57] validation_0-rmse:0.20564 validation_1-rmse:0.14229 +[58] validation_0-rmse:0.20473 validation_1-rmse:0.14137 +[59] validation_0-rmse:0.20418 validation_1-rmse:0.14011 +[60] validation_0-rmse:0.20341 validation_1-rmse:0.13923 +[61] validation_0-rmse:0.20258 validation_1-rmse:0.13839 +[62] validation_0-rmse:0.20230 validation_1-rmse:0.13723 +[63] validation_0-rmse:0.20075 validation_1-rmse:0.13546 +[64] validation_0-rmse:0.20007 validation_1-rmse:0.13467 +[65] validation_0-rmse:0.19937 validation_1-rmse:0.13387 +[66] validation_0-rmse:0.19875 validation_1-rmse:0.13296 +[67] validation_0-rmse:0.19709 validation_1-rmse:0.13137 +[68] validation_0-rmse:0.19675 validation_1-rmse:0.13042 +[69] validation_0-rmse:0.19617 validation_1-rmse:0.12968 +[70] validation_0-rmse:0.19560 validation_1-rmse:0.12900 +[71] validation_0-rmse:0.19492 validation_1-rmse:0.12834 +[72] validation_0-rmse:0.19319 validation_1-rmse:0.12681 +[73] validation_0-rmse:0.19272 validation_1-rmse:0.12612 +[74] validation_0-rmse:0.19230 validation_1-rmse:0.12535 +[75] validation_0-rmse:0.19170 validation_1-rmse:0.12474 +[76] validation_0-rmse:0.19058 validation_1-rmse:0.12338 +[77] validation_0-rmse:0.19010 validation_1-rmse:0.12279 +[78] validation_0-rmse:0.18961 validation_1-rmse:0.12223 +[79] validation_0-rmse:0.18960 validation_1-rmse:0.12156 +[80] validation_0-rmse:0.18882 validation_1-rmse:0.12038 +[81] validation_0-rmse:0.18819 validation_1-rmse:0.11975 +[82] validation_0-rmse:0.18789 validation_1-rmse:0.11916 +[83] validation_0-rmse:0.18738 validation_1-rmse:0.11864 +[84] validation_0-rmse:0.18718 validation_1-rmse:0.11801 +[85] validation_0-rmse:0.18600 validation_1-rmse:0.11698 +[86] validation_0-rmse:0.18572 validation_1-rmse:0.11653 +[87] validation_0-rmse:0.18534 validation_1-rmse:0.11603 +[88] validation_0-rmse:0.18478 validation_1-rmse:0.11508 +[89] validation_0-rmse:0.18430 validation_1-rmse:0.11459 +[90] validation_0-rmse:0.18447 validation_1-rmse:0.11396 +[91] validation_0-rmse:0.18424 validation_1-rmse:0.11352 +[92] validation_0-rmse:0.18367 validation_1-rmse:0.11307 +[93] validation_0-rmse:0.18333 validation_1-rmse:0.11265 +[94] validation_0-rmse:0.18313 validation_1-rmse:0.11216 +[95] validation_0-rmse:0.18275 validation_1-rmse:0.11157 +[96] validation_0-rmse:0.18275 validation_1-rmse:0.11106 +[97] validation_0-rmse:0.18248 validation_1-rmse:0.11068 +[98] validation_0-rmse:0.18220 validation_1-rmse:0.11033 +[99] validation_0-rmse:0.18198 validation_1-rmse:0.10994 +2025-04-29 01:56:11,705 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.63 secs) -------------------- +2025-04-29 01:56:11,706 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:12,255 - FreqaiExampleStrategy - INFO - 动态参数：buy_rsi=39.26145316407591, sell_rsi=59.26145316407591, stoploss=-0.15, trailing_stop_positive=0.05 +2025-04-29 01:56:12,275 - FreqaiExampleStrategy - INFO - up_or_down 值统计： +up_or_down +1 33535 +0 33236 +2025-04-29 01:56:12,276 - FreqaiExampleStrategy - INFO - do_predict 值统计： +do_predict +0.0 35773 +1.0 30998 +2025-04-29 01:56:12,279 - FreqaiExampleStrategy - INFO - 处理交易对：SOL/USDT +2025-04-29 01:56:12,281 - freqtrade.freqai.freqai_interface - INFO - Training 11 timeranges +2025-04-29 01:56:12,282 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2024-12-02 00:00:00 to 2025-01-01 00:00:00, 1/11 trains +2025-04-29 01:56:12,283 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1735689600_prediction.feather +2025-04-29 01:56:12,334 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 5m to 8690 +2025-04-29 01:56:12,335 - freqtrade.data.dataprovider - INFO - Loading data for SOL/USDT 5m from 2024-12-01 19:50:00 to 2025-04-20 00:00:00 +2025-04-29 01:56:12,422 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 1h to 770 +2025-04-29 01:56:12,422 - freqtrade.data.dataprovider - INFO - Loading data for SOL/USDT 1h from 2024-11-29 22:00:00 to 2025-04-20 00:00:00 +2025-04-29 01:56:12,518 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 3m to 14450 +2025-04-29 01:56:12,519 - freqtrade.data.dataprovider - INFO - Loading data for BTC/USDT 3m from 2024-12-01 21:30:00 to 2025-04-20 00:00:00 +2025-04-29 01:56:13,040 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:13,046 - FreqaiExampleStrategy - INFO - 目标列形状：(14450,) +2025-04-29 01:56:13,047 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.58814 +1 0.003044 49.58814 +2 0.000465 49.58814 +3 -0.000380 49.58814 +4 0.002829 49.58814 +2025-04-29 01:56:13,052 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:13,057 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:56:13,059 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.68088 +1 0.003044 49.68088 +2 0.000465 49.68088 +3 -0.000380 49.68088 +4 0.002829 49.68088 +2025-04-29 01:56:13,066 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1735689600/cb_sol_1735689600 +2025-04-29 01:56:13,066 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:13,095 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:13,096 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-02 to 2024-12-31 -------------------- +2025-04-29 01:56:18,126 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:18,126 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.30164 validation_1-rmse:0.29585 +[1] validation_0-rmse:0.29609 validation_1-rmse:0.28921 +[2] validation_0-rmse:0.29103 validation_1-rmse:0.28298 +[3] validation_0-rmse:0.28604 validation_1-rmse:0.27706 +[4] validation_0-rmse:0.28108 validation_1-rmse:0.27129 +[5] validation_0-rmse:0.27670 validation_1-rmse:0.26609 +[6] validation_0-rmse:0.27234 validation_1-rmse:0.26092 +[7] validation_0-rmse:0.26874 validation_1-rmse:0.25593 +[8] validation_0-rmse:0.26461 validation_1-rmse:0.25118 +[9] validation_0-rmse:0.26074 validation_1-rmse:0.24677 +[10] validation_0-rmse:0.25745 validation_1-rmse:0.24239 +[11] validation_0-rmse:0.25460 validation_1-rmse:0.23832 +[12] validation_0-rmse:0.25121 validation_1-rmse:0.23441 +[13] validation_0-rmse:0.24825 validation_1-rmse:0.23068 +[14] validation_0-rmse:0.24580 validation_1-rmse:0.22694 +[15] validation_0-rmse:0.24286 validation_1-rmse:0.22346 +[16] validation_0-rmse:0.24051 validation_1-rmse:0.22006 +[17] validation_0-rmse:0.23821 validation_1-rmse:0.21690 +[18] validation_0-rmse:0.23549 validation_1-rmse:0.21383 +[19] validation_0-rmse:0.23335 validation_1-rmse:0.21087 +[20] validation_0-rmse:0.23089 validation_1-rmse:0.20804 +[21] validation_0-rmse:0.22918 validation_1-rmse:0.20505 +[22] validation_0-rmse:0.22716 validation_1-rmse:0.20240 +[23] validation_0-rmse:0.22562 validation_1-rmse:0.19981 +[24] validation_0-rmse:0.22385 validation_1-rmse:0.19723 +[25] validation_0-rmse:0.22201 validation_1-rmse:0.19473 +[26] validation_0-rmse:0.22016 validation_1-rmse:0.19245 +[27] validation_0-rmse:0.21834 validation_1-rmse:0.19024 +[28] validation_0-rmse:0.21671 validation_1-rmse:0.18789 +[29] validation_0-rmse:0.21493 validation_1-rmse:0.18579 +[30] validation_0-rmse:0.21385 validation_1-rmse:0.18351 +[31] validation_0-rmse:0.21216 validation_1-rmse:0.18156 +[32] validation_0-rmse:0.21088 validation_1-rmse:0.17941 +[33] validation_0-rmse:0.20953 validation_1-rmse:0.17754 +[34] validation_0-rmse:0.20805 validation_1-rmse:0.17575 +[35] validation_0-rmse:0.20648 validation_1-rmse:0.17399 +[36] validation_0-rmse:0.20515 validation_1-rmse:0.17220 +[37] validation_0-rmse:0.20382 validation_1-rmse:0.17031 +[38] validation_0-rmse:0.20257 validation_1-rmse:0.16871 +[39] validation_0-rmse:0.20125 validation_1-rmse:0.16718 +[40] validation_0-rmse:0.20005 validation_1-rmse:0.16574 +[41] validation_0-rmse:0.19885 validation_1-rmse:0.16415 +[42] validation_0-rmse:0.19789 validation_1-rmse:0.16270 +[43] validation_0-rmse:0.19680 validation_1-rmse:0.16130 +[44] validation_0-rmse:0.19564 validation_1-rmse:0.15993 +[45] validation_0-rmse:0.19480 validation_1-rmse:0.15854 +[46] validation_0-rmse:0.19376 validation_1-rmse:0.15728 +[47] validation_0-rmse:0.19290 validation_1-rmse:0.15568 +[48] validation_0-rmse:0.19223 validation_1-rmse:0.15445 +[49] validation_0-rmse:0.19129 validation_1-rmse:0.15330 +[50] validation_0-rmse:0.19035 validation_1-rmse:0.15194 +[51] validation_0-rmse:0.18948 validation_1-rmse:0.15082 +[52] validation_0-rmse:0.18882 validation_1-rmse:0.14945 +[53] validation_0-rmse:0.18801 validation_1-rmse:0.14840 +[54] validation_0-rmse:0.18707 validation_1-rmse:0.14736 +[55] validation_0-rmse:0.18637 validation_1-rmse:0.14635 +[56] validation_0-rmse:0.18571 validation_1-rmse:0.14542 +[57] validation_0-rmse:0.18497 validation_1-rmse:0.14413 +[58] validation_0-rmse:0.18443 validation_1-rmse:0.14297 +[59] validation_0-rmse:0.18375 validation_1-rmse:0.14203 +[60] validation_0-rmse:0.18319 validation_1-rmse:0.14111 +[61] validation_0-rmse:0.18266 validation_1-rmse:0.14030 +[62] validation_0-rmse:0.18185 validation_1-rmse:0.13914 +[63] validation_0-rmse:0.18145 validation_1-rmse:0.13831 +[64] validation_0-rmse:0.18135 validation_1-rmse:0.13720 +[65] validation_0-rmse:0.18075 validation_1-rmse:0.13643 +[66] validation_0-rmse:0.18020 validation_1-rmse:0.13560 +[67] validation_0-rmse:0.17951 validation_1-rmse:0.13485 +[68] validation_0-rmse:0.17888 validation_1-rmse:0.13414 +[69] validation_0-rmse:0.17850 validation_1-rmse:0.13343 +[70] validation_0-rmse:0.17798 validation_1-rmse:0.13224 +[71] validation_0-rmse:0.17751 validation_1-rmse:0.13133 +[72] validation_0-rmse:0.17711 validation_1-rmse:0.13062 +[73] validation_0-rmse:0.17701 validation_1-rmse:0.12966 +[74] validation_0-rmse:0.17648 validation_1-rmse:0.12872 +[75] validation_0-rmse:0.17611 validation_1-rmse:0.12806 +[76] validation_0-rmse:0.17573 validation_1-rmse:0.12732 +[77] validation_0-rmse:0.17528 validation_1-rmse:0.12664 +[78] validation_0-rmse:0.17478 validation_1-rmse:0.12605 +[79] validation_0-rmse:0.17432 validation_1-rmse:0.12518 +[80] validation_0-rmse:0.17391 validation_1-rmse:0.12466 +[81] validation_0-rmse:0.17358 validation_1-rmse:0.12398 +[82] validation_0-rmse:0.17315 validation_1-rmse:0.12342 +[83] validation_0-rmse:0.17260 validation_1-rmse:0.12276 +[84] validation_0-rmse:0.17220 validation_1-rmse:0.12222 +[85] validation_0-rmse:0.17182 validation_1-rmse:0.12176 +[86] validation_0-rmse:0.17152 validation_1-rmse:0.12124 +[87] validation_0-rmse:0.17103 validation_1-rmse:0.12046 +[88] validation_0-rmse:0.17085 validation_1-rmse:0.11974 +[89] validation_0-rmse:0.17053 validation_1-rmse:0.11930 +[90] validation_0-rmse:0.17018 validation_1-rmse:0.11888 +[91] validation_0-rmse:0.17011 validation_1-rmse:0.11810 +[92] validation_0-rmse:0.16980 validation_1-rmse:0.11762 +[93] validation_0-rmse:0.16956 validation_1-rmse:0.11689 +[94] validation_0-rmse:0.16923 validation_1-rmse:0.11641 +[95] validation_0-rmse:0.16912 validation_1-rmse:0.11579 +[96] validation_0-rmse:0.16878 validation_1-rmse:0.11530 +[97] validation_0-rmse:0.16857 validation_1-rmse:0.11489 +[98] validation_0-rmse:0.16824 validation_1-rmse:0.11442 +[99] validation_0-rmse:0.16824 validation_1-rmse:0.11403 +2025-04-29 01:56:19,586 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.52 secs) -------------------- +2025-04-29 01:56:19,587 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:20,174 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2024-12-12 00:00:00 to 2025-01-11 00:00:00, 2/11 trains +2025-04-29 01:56:20,175 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1736553600_prediction.feather +2025-04-29 01:56:20,179 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:20,185 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:56:20,186 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.68088 +1 0.003044 49.68088 +2 0.000465 49.68088 +3 -0.000380 49.68088 +4 0.002829 49.68088 +2025-04-29 01:56:20,192 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:20,197 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:56:20,199 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.97721 +1 0.003044 49.97721 +2 0.000465 49.97721 +3 -0.000380 49.97721 +4 0.002829 49.97721 +2025-04-29 01:56:20,204 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1736553600/cb_sol_1736553600 +2025-04-29 01:56:20,205 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:20,227 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:20,228 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-12 to 2025-01-10 -------------------- +2025-04-29 01:56:25,109 - datasieve.pipeline - INFO - DI tossed 5 predictions for being too far from training data. +2025-04-29 01:56:25,112 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:25,112 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.29597 validation_1-rmse:0.29016 +[1] validation_0-rmse:0.29075 validation_1-rmse:0.28391 +[2] validation_0-rmse:0.28602 validation_1-rmse:0.27798 +[3] validation_0-rmse:0.28062 validation_1-rmse:0.27213 +[4] validation_0-rmse:0.27647 validation_1-rmse:0.26682 +[5] validation_0-rmse:0.27188 validation_1-rmse:0.26144 +[6] validation_0-rmse:0.26781 validation_1-rmse:0.25655 +[7] validation_0-rmse:0.26412 validation_1-rmse:0.25180 +[8] validation_0-rmse:0.25994 validation_1-rmse:0.24709 +[9] validation_0-rmse:0.25649 validation_1-rmse:0.24277 +[10] validation_0-rmse:0.25332 validation_1-rmse:0.23850 +[11] validation_0-rmse:0.24999 validation_1-rmse:0.23452 +[12] validation_0-rmse:0.24687 validation_1-rmse:0.23072 +[13] validation_0-rmse:0.24432 validation_1-rmse:0.22694 +[14] validation_0-rmse:0.24128 validation_1-rmse:0.22341 +[15] validation_0-rmse:0.23869 validation_1-rmse:0.21969 +[16] validation_0-rmse:0.23628 validation_1-rmse:0.21635 +[17] validation_0-rmse:0.23354 validation_1-rmse:0.21326 +[18] validation_0-rmse:0.23123 validation_1-rmse:0.21007 +[19] validation_0-rmse:0.22919 validation_1-rmse:0.20707 +[20] validation_0-rmse:0.22705 validation_1-rmse:0.20418 +[21] validation_0-rmse:0.22505 validation_1-rmse:0.20149 +[22] validation_0-rmse:0.22285 validation_1-rmse:0.19887 +[23] validation_0-rmse:0.22084 validation_1-rmse:0.19631 +[24] validation_0-rmse:0.21877 validation_1-rmse:0.19389 +[25] validation_0-rmse:0.21748 validation_1-rmse:0.19133 +[26] validation_0-rmse:0.21557 validation_1-rmse:0.18870 +[27] validation_0-rmse:0.21374 validation_1-rmse:0.18648 +[28] validation_0-rmse:0.21183 validation_1-rmse:0.18432 +[29] validation_0-rmse:0.21047 validation_1-rmse:0.18209 +[30] validation_0-rmse:0.20873 validation_1-rmse:0.17990 +[31] validation_0-rmse:0.20717 validation_1-rmse:0.17795 +[32] validation_0-rmse:0.20564 validation_1-rmse:0.17599 +[33] validation_0-rmse:0.20428 validation_1-rmse:0.17421 +[34] validation_0-rmse:0.20290 validation_1-rmse:0.17229 +[35] validation_0-rmse:0.20161 validation_1-rmse:0.17047 +[36] validation_0-rmse:0.20018 validation_1-rmse:0.16878 +[37] validation_0-rmse:0.19923 validation_1-rmse:0.16688 +[38] validation_0-rmse:0.19796 validation_1-rmse:0.16534 +[39] validation_0-rmse:0.19668 validation_1-rmse:0.16355 +[40] validation_0-rmse:0.19543 validation_1-rmse:0.16204 +[41] validation_0-rmse:0.19441 validation_1-rmse:0.16062 +[42] validation_0-rmse:0.19344 validation_1-rmse:0.15910 +[43] validation_0-rmse:0.19256 validation_1-rmse:0.15759 +[44] validation_0-rmse:0.19154 validation_1-rmse:0.15625 +[45] validation_0-rmse:0.19048 validation_1-rmse:0.15494 +[46] validation_0-rmse:0.18937 validation_1-rmse:0.15366 +[47] validation_0-rmse:0.18865 validation_1-rmse:0.15236 +[48] validation_0-rmse:0.18784 validation_1-rmse:0.15112 +[49] validation_0-rmse:0.18704 validation_1-rmse:0.14998 +[50] validation_0-rmse:0.18625 validation_1-rmse:0.14874 +[51] validation_0-rmse:0.18541 validation_1-rmse:0.14763 +[52] validation_0-rmse:0.18456 validation_1-rmse:0.14659 +[53] validation_0-rmse:0.18383 validation_1-rmse:0.14530 +[54] validation_0-rmse:0.18315 validation_1-rmse:0.14420 +[55] validation_0-rmse:0.18234 validation_1-rmse:0.14321 +[56] validation_0-rmse:0.18181 validation_1-rmse:0.14206 +[57] validation_0-rmse:0.18109 validation_1-rmse:0.14106 +[58] validation_0-rmse:0.18033 validation_1-rmse:0.13996 +[59] validation_0-rmse:0.17964 validation_1-rmse:0.13905 +[60] validation_0-rmse:0.17921 validation_1-rmse:0.13820 +[61] validation_0-rmse:0.17865 validation_1-rmse:0.13731 +[62] validation_0-rmse:0.17795 validation_1-rmse:0.13648 +[63] validation_0-rmse:0.17737 validation_1-rmse:0.13559 +[64] validation_0-rmse:0.17680 validation_1-rmse:0.13483 +[65] validation_0-rmse:0.17628 validation_1-rmse:0.13408 +[66] validation_0-rmse:0.17588 validation_1-rmse:0.13303 +[67] validation_0-rmse:0.17530 validation_1-rmse:0.13228 +[68] validation_0-rmse:0.17478 validation_1-rmse:0.13153 +[69] validation_0-rmse:0.17439 validation_1-rmse:0.13081 +[70] validation_0-rmse:0.17401 validation_1-rmse:0.12991 +[71] validation_0-rmse:0.17347 validation_1-rmse:0.12911 +[72] validation_0-rmse:0.17304 validation_1-rmse:0.12838 +[73] validation_0-rmse:0.17254 validation_1-rmse:0.12774 +[74] validation_0-rmse:0.17207 validation_1-rmse:0.12656 +[75] validation_0-rmse:0.17185 validation_1-rmse:0.12571 +[76] validation_0-rmse:0.17126 validation_1-rmse:0.12512 +[77] validation_0-rmse:0.17096 validation_1-rmse:0.12447 +[78] validation_0-rmse:0.17064 validation_1-rmse:0.12381 +[79] validation_0-rmse:0.17024 validation_1-rmse:0.12300 +[80] validation_0-rmse:0.16989 validation_1-rmse:0.12244 +[81] validation_0-rmse:0.16955 validation_1-rmse:0.12180 +[82] validation_0-rmse:0.16924 validation_1-rmse:0.12129 +[83] validation_0-rmse:0.16931 validation_1-rmse:0.12037 +[84] validation_0-rmse:0.16888 validation_1-rmse:0.11970 +[85] validation_0-rmse:0.16845 validation_1-rmse:0.11914 +[86] validation_0-rmse:0.16809 validation_1-rmse:0.11840 +[87] validation_0-rmse:0.16766 validation_1-rmse:0.11760 +[88] validation_0-rmse:0.16741 validation_1-rmse:0.11714 +[89] validation_0-rmse:0.16707 validation_1-rmse:0.11667 +[90] validation_0-rmse:0.16683 validation_1-rmse:0.11592 +[91] validation_0-rmse:0.16643 validation_1-rmse:0.11537 +[92] validation_0-rmse:0.16621 validation_1-rmse:0.11455 +[93] validation_0-rmse:0.16611 validation_1-rmse:0.11396 +[94] validation_0-rmse:0.16587 validation_1-rmse:0.11350 +[95] validation_0-rmse:0.16563 validation_1-rmse:0.11308 +[96] validation_0-rmse:0.16535 validation_1-rmse:0.11237 +[97] validation_0-rmse:0.16487 validation_1-rmse:0.11173 +[98] validation_0-rmse:0.16461 validation_1-rmse:0.11133 +[99] validation_0-rmse:0.16437 validation_1-rmse:0.11096 +2025-04-29 01:56:26,510 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.30 secs) -------------------- +2025-04-29 01:56:26,511 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:27,072 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2024-12-22 00:00:00 to 2025-01-21 00:00:00, 3/11 trains +2025-04-29 01:56:27,073 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1737417600_prediction.feather +2025-04-29 01:56:27,079 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:27,085 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:56:27,086 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.97721 +1 0.003044 49.97721 +2 0.000465 49.97721 +3 -0.000380 49.97721 +4 0.002829 49.97721 +2025-04-29 01:56:27,094 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:27,100 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:56:27,102 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.941408 +1 0.003044 49.941408 +2 0.000465 49.941408 +3 -0.000380 49.941408 +4 0.002829 49.941408 +2025-04-29 01:56:27,108 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1737417600/cb_sol_1737417600 +2025-04-29 01:56:27,109 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:27,130 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:27,131 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-22 to 2025-01-20 -------------------- +2025-04-29 01:56:32,206 - datasieve.pipeline - INFO - DI tossed 1523 predictions for being too far from training data. +2025-04-29 01:56:32,209 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:32,210 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.30838 validation_1-rmse:0.28356 +[1] validation_0-rmse:0.30280 validation_1-rmse:0.27752 +[2] validation_0-rmse:0.29759 validation_1-rmse:0.27179 +[3] validation_0-rmse:0.29330 validation_1-rmse:0.26614 +[4] validation_0-rmse:0.28936 validation_1-rmse:0.26091 +[5] validation_0-rmse:0.28544 validation_1-rmse:0.25581 +[6] validation_0-rmse:0.28151 validation_1-rmse:0.25102 +[7] validation_0-rmse:0.27790 validation_1-rmse:0.24636 +[8] validation_0-rmse:0.27429 validation_1-rmse:0.24196 +[9] validation_0-rmse:0.27104 validation_1-rmse:0.23770 +[10] validation_0-rmse:0.26762 validation_1-rmse:0.23356 +[11] validation_0-rmse:0.26472 validation_1-rmse:0.22966 +[12] validation_0-rmse:0.26219 validation_1-rmse:0.22601 +[13] validation_0-rmse:0.25924 validation_1-rmse:0.22234 +[14] validation_0-rmse:0.25634 validation_1-rmse:0.21888 +[15] validation_0-rmse:0.25379 validation_1-rmse:0.21545 +[16] validation_0-rmse:0.25117 validation_1-rmse:0.21221 +[17] validation_0-rmse:0.24877 validation_1-rmse:0.20902 +[18] validation_0-rmse:0.24653 validation_1-rmse:0.20604 +[19] validation_0-rmse:0.24404 validation_1-rmse:0.20315 +[20] validation_0-rmse:0.24194 validation_1-rmse:0.20032 +[21] validation_0-rmse:0.23966 validation_1-rmse:0.19765 +[22] validation_0-rmse:0.23804 validation_1-rmse:0.19481 +[23] validation_0-rmse:0.23599 validation_1-rmse:0.19230 +[24] validation_0-rmse:0.23384 validation_1-rmse:0.18993 +[25] validation_0-rmse:0.23196 validation_1-rmse:0.18756 +[26] validation_0-rmse:0.23057 validation_1-rmse:0.18506 +[27] validation_0-rmse:0.22854 validation_1-rmse:0.18283 +[28] validation_0-rmse:0.22705 validation_1-rmse:0.18071 +[29] validation_0-rmse:0.22557 validation_1-rmse:0.17851 +[30] validation_0-rmse:0.22394 validation_1-rmse:0.17644 +[31] validation_0-rmse:0.22213 validation_1-rmse:0.17452 +[32] validation_0-rmse:0.22064 validation_1-rmse:0.17267 +[33] validation_0-rmse:0.21905 validation_1-rmse:0.17084 +[34] validation_0-rmse:0.21806 validation_1-rmse:0.16880 +[35] validation_0-rmse:0.21693 validation_1-rmse:0.16700 +[36] validation_0-rmse:0.21537 validation_1-rmse:0.16520 +[37] validation_0-rmse:0.21417 validation_1-rmse:0.16362 +[38] validation_0-rmse:0.21282 validation_1-rmse:0.16204 +[39] validation_0-rmse:0.21137 validation_1-rmse:0.16047 +[40] validation_0-rmse:0.20994 validation_1-rmse:0.15897 +[41] validation_0-rmse:0.20878 validation_1-rmse:0.15747 +[42] validation_0-rmse:0.20766 validation_1-rmse:0.15604 +[43] validation_0-rmse:0.20666 validation_1-rmse:0.15444 +[44] validation_0-rmse:0.20566 validation_1-rmse:0.15316 +[45] validation_0-rmse:0.20496 validation_1-rmse:0.15162 +[46] validation_0-rmse:0.20394 validation_1-rmse:0.15038 +[47] validation_0-rmse:0.20277 validation_1-rmse:0.14909 +[48] validation_0-rmse:0.20176 validation_1-rmse:0.14793 +[49] validation_0-rmse:0.20072 validation_1-rmse:0.14681 +[50] validation_0-rmse:0.20058 validation_1-rmse:0.14528 +[51] validation_0-rmse:0.19970 validation_1-rmse:0.14419 +[52] validation_0-rmse:0.19887 validation_1-rmse:0.14284 +[53] validation_0-rmse:0.19809 validation_1-rmse:0.14182 +[54] validation_0-rmse:0.19725 validation_1-rmse:0.14076 +[55] validation_0-rmse:0.19636 validation_1-rmse:0.13981 +[56] validation_0-rmse:0.19615 validation_1-rmse:0.13853 +[57] validation_0-rmse:0.19540 validation_1-rmse:0.13757 +[58] validation_0-rmse:0.19460 validation_1-rmse:0.13664 +[59] validation_0-rmse:0.19418 validation_1-rmse:0.13553 +[60] validation_0-rmse:0.19382 validation_1-rmse:0.13445 +[61] validation_0-rmse:0.19302 validation_1-rmse:0.13363 +[62] validation_0-rmse:0.19218 validation_1-rmse:0.13270 +[63] validation_0-rmse:0.19154 validation_1-rmse:0.13183 +[64] validation_0-rmse:0.19083 validation_1-rmse:0.13105 +[65] validation_0-rmse:0.19005 validation_1-rmse:0.13008 +[66] validation_0-rmse:0.18929 validation_1-rmse:0.12932 +[67] validation_0-rmse:0.18885 validation_1-rmse:0.12851 +[68] validation_0-rmse:0.18837 validation_1-rmse:0.12781 +[69] validation_0-rmse:0.18790 validation_1-rmse:0.12711 +[70] validation_0-rmse:0.18732 validation_1-rmse:0.12617 +[71] validation_0-rmse:0.18682 validation_1-rmse:0.12552 +[72] validation_0-rmse:0.18669 validation_1-rmse:0.12448 +[73] validation_0-rmse:0.18617 validation_1-rmse:0.12382 +[74] validation_0-rmse:0.18587 validation_1-rmse:0.12322 +[75] validation_0-rmse:0.18544 validation_1-rmse:0.12261 +[76] validation_0-rmse:0.18524 validation_1-rmse:0.12162 +[77] validation_0-rmse:0.18486 validation_1-rmse:0.12098 +[78] validation_0-rmse:0.18443 validation_1-rmse:0.12021 +[79] validation_0-rmse:0.18415 validation_1-rmse:0.11963 +[80] validation_0-rmse:0.18393 validation_1-rmse:0.11866 +[81] validation_0-rmse:0.18344 validation_1-rmse:0.11809 +[82] validation_0-rmse:0.18307 validation_1-rmse:0.11748 +[83] validation_0-rmse:0.18257 validation_1-rmse:0.11699 +[84] validation_0-rmse:0.18216 validation_1-rmse:0.11643 +[85] validation_0-rmse:0.18188 validation_1-rmse:0.11595 +[86] validation_0-rmse:0.18168 validation_1-rmse:0.11502 +[87] validation_0-rmse:0.18148 validation_1-rmse:0.11451 +[88] validation_0-rmse:0.18093 validation_1-rmse:0.11378 +[89] validation_0-rmse:0.18054 validation_1-rmse:0.11332 +[90] validation_0-rmse:0.18024 validation_1-rmse:0.11285 +[91] validation_0-rmse:0.17982 validation_1-rmse:0.11241 +[92] validation_0-rmse:0.17950 validation_1-rmse:0.11185 +[93] validation_0-rmse:0.17918 validation_1-rmse:0.11123 +[94] validation_0-rmse:0.17882 validation_1-rmse:0.11072 +[95] validation_0-rmse:0.17881 validation_1-rmse:0.10986 +[96] validation_0-rmse:0.17832 validation_1-rmse:0.10941 +[97] validation_0-rmse:0.17800 validation_1-rmse:0.10897 +[98] validation_0-rmse:0.17774 validation_1-rmse:0.10859 +[99] validation_0-rmse:0.17746 validation_1-rmse:0.10819 +2025-04-29 01:56:33,558 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.45 secs) -------------------- +2025-04-29 01:56:33,558 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:34,118 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-01 00:00:00 to 2025-01-31 00:00:00, 4/11 trains +2025-04-29 01:56:34,119 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1738281600_prediction.feather +2025-04-29 01:56:34,124 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:34,130 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:56:34,131 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.941408 +1 0.003044 49.941408 +2 0.000465 49.941408 +3 -0.000380 49.941408 +4 0.002829 49.941408 +2025-04-29 01:56:34,137 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:34,143 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:56:34,144 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.830756 +1 0.003044 49.830756 +2 0.000465 49.830756 +3 -0.000380 49.830756 +4 0.002829 49.830756 +2025-04-29 01:56:34,149 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1738281600/cb_sol_1738281600 +2025-04-29 01:56:34,150 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:34,173 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:34,173 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-01 to 2025-01-30 -------------------- +2025-04-29 01:56:39,271 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:39,271 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.29494 validation_1-rmse:0.28739 +[1] validation_0-rmse:0.28930 validation_1-rmse:0.28164 +[2] validation_0-rmse:0.28437 validation_1-rmse:0.27613 +[3] validation_0-rmse:0.27990 validation_1-rmse:0.27106 +[4] validation_0-rmse:0.27541 validation_1-rmse:0.26617 +[5] validation_0-rmse:0.27070 validation_1-rmse:0.26147 +[6] validation_0-rmse:0.26683 validation_1-rmse:0.25687 +[7] validation_0-rmse:0.26280 validation_1-rmse:0.25263 +[8] validation_0-rmse:0.25916 validation_1-rmse:0.24830 +[9] validation_0-rmse:0.25540 validation_1-rmse:0.24420 +[10] validation_0-rmse:0.25186 validation_1-rmse:0.24022 +[11] validation_0-rmse:0.24829 validation_1-rmse:0.23647 +[12] validation_0-rmse:0.24504 validation_1-rmse:0.23286 +[13] validation_0-rmse:0.24183 validation_1-rmse:0.22943 +[14] validation_0-rmse:0.23870 validation_1-rmse:0.22619 +[15] validation_0-rmse:0.23587 validation_1-rmse:0.22274 +[16] validation_0-rmse:0.23325 validation_1-rmse:0.21951 +[17] validation_0-rmse:0.23045 validation_1-rmse:0.21650 +[18] validation_0-rmse:0.22792 validation_1-rmse:0.21367 +[19] validation_0-rmse:0.22524 validation_1-rmse:0.21092 +[20] validation_0-rmse:0.22293 validation_1-rmse:0.20804 +[21] validation_0-rmse:0.22055 validation_1-rmse:0.20549 +[22] validation_0-rmse:0.21831 validation_1-rmse:0.20307 +[23] validation_0-rmse:0.21601 validation_1-rmse:0.20062 +[24] validation_0-rmse:0.21372 validation_1-rmse:0.19810 +[25] validation_0-rmse:0.21154 validation_1-rmse:0.19580 +[26] validation_0-rmse:0.20966 validation_1-rmse:0.19369 +[27] validation_0-rmse:0.20790 validation_1-rmse:0.19130 +[28] validation_0-rmse:0.20602 validation_1-rmse:0.18921 +[29] validation_0-rmse:0.20418 validation_1-rmse:0.18723 +[30] validation_0-rmse:0.20236 validation_1-rmse:0.18525 +[31] validation_0-rmse:0.20057 validation_1-rmse:0.18324 +[32] validation_0-rmse:0.19900 validation_1-rmse:0.18144 +[33] validation_0-rmse:0.19744 validation_1-rmse:0.17941 +[34] validation_0-rmse:0.19608 validation_1-rmse:0.17767 +[35] validation_0-rmse:0.19467 validation_1-rmse:0.17605 +[36] validation_0-rmse:0.19313 validation_1-rmse:0.17422 +[37] validation_0-rmse:0.19156 validation_1-rmse:0.17260 +[38] validation_0-rmse:0.19020 validation_1-rmse:0.17103 +[39] validation_0-rmse:0.18884 validation_1-rmse:0.16948 +[40] validation_0-rmse:0.18767 validation_1-rmse:0.16797 +[41] validation_0-rmse:0.18636 validation_1-rmse:0.16647 +[42] validation_0-rmse:0.18512 validation_1-rmse:0.16505 +[43] validation_0-rmse:0.18403 validation_1-rmse:0.16340 +[44] validation_0-rmse:0.18290 validation_1-rmse:0.16210 +[45] validation_0-rmse:0.18189 validation_1-rmse:0.16085 +[46] validation_0-rmse:0.18090 validation_1-rmse:0.15966 +[47] validation_0-rmse:0.17992 validation_1-rmse:0.15841 +[48] validation_0-rmse:0.17901 validation_1-rmse:0.15728 +[49] validation_0-rmse:0.17817 validation_1-rmse:0.15582 +[50] validation_0-rmse:0.17697 validation_1-rmse:0.15458 +[51] validation_0-rmse:0.17607 validation_1-rmse:0.15349 +[52] validation_0-rmse:0.17516 validation_1-rmse:0.15235 +[53] validation_0-rmse:0.17425 validation_1-rmse:0.15131 +[54] validation_0-rmse:0.17347 validation_1-rmse:0.15032 +[55] validation_0-rmse:0.17275 validation_1-rmse:0.14932 +[56] validation_0-rmse:0.17211 validation_1-rmse:0.14834 +[57] validation_0-rmse:0.17131 validation_1-rmse:0.14741 +[58] validation_0-rmse:0.17072 validation_1-rmse:0.14617 +[59] validation_0-rmse:0.16999 validation_1-rmse:0.14528 +[60] validation_0-rmse:0.16934 validation_1-rmse:0.14416 +[61] validation_0-rmse:0.16887 validation_1-rmse:0.14321 +[62] validation_0-rmse:0.16842 validation_1-rmse:0.14213 +[63] validation_0-rmse:0.16765 validation_1-rmse:0.14130 +[64] validation_0-rmse:0.16691 validation_1-rmse:0.14048 +[65] validation_0-rmse:0.16629 validation_1-rmse:0.13956 +[66] validation_0-rmse:0.16565 validation_1-rmse:0.13882 +[67] validation_0-rmse:0.16530 validation_1-rmse:0.13793 +[68] validation_0-rmse:0.16467 validation_1-rmse:0.13710 +[69] validation_0-rmse:0.16436 validation_1-rmse:0.13621 +[70] validation_0-rmse:0.16377 validation_1-rmse:0.13542 +[71] validation_0-rmse:0.16334 validation_1-rmse:0.13463 +[72] validation_0-rmse:0.16280 validation_1-rmse:0.13394 +[73] validation_0-rmse:0.16230 validation_1-rmse:0.13328 +[74] validation_0-rmse:0.16156 validation_1-rmse:0.13246 +[75] validation_0-rmse:0.16122 validation_1-rmse:0.13151 +[76] validation_0-rmse:0.16080 validation_1-rmse:0.13080 +[77] validation_0-rmse:0.16033 validation_1-rmse:0.13015 +[78] validation_0-rmse:0.15992 validation_1-rmse:0.12951 +[79] validation_0-rmse:0.15950 validation_1-rmse:0.12888 +[80] validation_0-rmse:0.15909 validation_1-rmse:0.12822 +[81] validation_0-rmse:0.15875 validation_1-rmse:0.12744 +[82] validation_0-rmse:0.15831 validation_1-rmse:0.12683 +[83] validation_0-rmse:0.15786 validation_1-rmse:0.12626 +[84] validation_0-rmse:0.15747 validation_1-rmse:0.12572 +[85] validation_0-rmse:0.15724 validation_1-rmse:0.12495 +[86] validation_0-rmse:0.15695 validation_1-rmse:0.12442 +[87] validation_0-rmse:0.15664 validation_1-rmse:0.12382 +[88] validation_0-rmse:0.15651 validation_1-rmse:0.12326 +[89] validation_0-rmse:0.15629 validation_1-rmse:0.12256 +[90] validation_0-rmse:0.15596 validation_1-rmse:0.12196 +[91] validation_0-rmse:0.15559 validation_1-rmse:0.12141 +[92] validation_0-rmse:0.15511 validation_1-rmse:0.12088 +[93] validation_0-rmse:0.15487 validation_1-rmse:0.12033 +[94] validation_0-rmse:0.15472 validation_1-rmse:0.11975 +[95] validation_0-rmse:0.15438 validation_1-rmse:0.11924 +[96] validation_0-rmse:0.15408 validation_1-rmse:0.11882 +[97] validation_0-rmse:0.15382 validation_1-rmse:0.11819 +[98] validation_0-rmse:0.15350 validation_1-rmse:0.11777 +[99] validation_0-rmse:0.15331 validation_1-rmse:0.11727 +2025-04-29 01:56:40,600 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.45 secs) -------------------- +2025-04-29 01:56:40,601 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:41,171 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-11 00:00:00 to 2025-02-10 00:00:00, 5/11 trains +2025-04-29 01:56:41,172 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1739145600_prediction.feather +2025-04-29 01:56:41,177 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:41,183 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:56:41,185 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.830756 +1 0.003044 49.830756 +2 0.000465 49.830756 +3 -0.000380 49.830756 +4 0.002829 49.830756 +2025-04-29 01:56:41,193 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:41,200 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:56:41,201 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.714422 +1 0.003044 49.714422 +2 0.000465 49.714422 +3 -0.000380 49.714422 +4 0.002829 49.714422 +2025-04-29 01:56:41,206 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1739145600/cb_sol_1739145600 +2025-04-29 01:56:41,207 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:41,228 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:41,229 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-11 to 2025-02-09 -------------------- +2025-04-29 01:56:46,277 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:46,278 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.29889 validation_1-rmse:0.30153 +[1] validation_0-rmse:0.29317 validation_1-rmse:0.29483 +[2] validation_0-rmse:0.28819 validation_1-rmse:0.28860 +[3] validation_0-rmse:0.28336 validation_1-rmse:0.28273 +[4] validation_0-rmse:0.27885 validation_1-rmse:0.27694 +[5] validation_0-rmse:0.27448 validation_1-rmse:0.27155 +[6] validation_0-rmse:0.27020 validation_1-rmse:0.26634 +[7] validation_0-rmse:0.26629 validation_1-rmse:0.26134 +[8] validation_0-rmse:0.26241 validation_1-rmse:0.25653 +[9] validation_0-rmse:0.25876 validation_1-rmse:0.25192 +[10] validation_0-rmse:0.25559 validation_1-rmse:0.24747 +[11] validation_0-rmse:0.25223 validation_1-rmse:0.24337 +[12] validation_0-rmse:0.24904 validation_1-rmse:0.23934 +[13] validation_0-rmse:0.24639 validation_1-rmse:0.23548 +[14] validation_0-rmse:0.24353 validation_1-rmse:0.23187 +[15] validation_0-rmse:0.24076 validation_1-rmse:0.22837 +[16] validation_0-rmse:0.23849 validation_1-rmse:0.22484 +[17] validation_0-rmse:0.23581 validation_1-rmse:0.22147 +[18] validation_0-rmse:0.23342 validation_1-rmse:0.21814 +[19] validation_0-rmse:0.23133 validation_1-rmse:0.21509 +[20] validation_0-rmse:0.22937 validation_1-rmse:0.21187 +[21] validation_0-rmse:0.22713 validation_1-rmse:0.20902 +[22] validation_0-rmse:0.22509 validation_1-rmse:0.20631 +[23] validation_0-rmse:0.22312 validation_1-rmse:0.20373 +[24] validation_0-rmse:0.22123 validation_1-rmse:0.20076 +[25] validation_0-rmse:0.21951 validation_1-rmse:0.19837 +[26] validation_0-rmse:0.21751 validation_1-rmse:0.19562 +[27] validation_0-rmse:0.21589 validation_1-rmse:0.19309 +[28] validation_0-rmse:0.21422 validation_1-rmse:0.19091 +[29] validation_0-rmse:0.21272 validation_1-rmse:0.18879 +[30] validation_0-rmse:0.21119 validation_1-rmse:0.18660 +[31] validation_0-rmse:0.20982 validation_1-rmse:0.18468 +[32] validation_0-rmse:0.20829 validation_1-rmse:0.18239 +[33] validation_0-rmse:0.20681 validation_1-rmse:0.18048 +[34] validation_0-rmse:0.20548 validation_1-rmse:0.17869 +[35] validation_0-rmse:0.20431 validation_1-rmse:0.17665 +[36] validation_0-rmse:0.20297 validation_1-rmse:0.17483 +[37] validation_0-rmse:0.20174 validation_1-rmse:0.17311 +[38] validation_0-rmse:0.20060 validation_1-rmse:0.17153 +[39] validation_0-rmse:0.19951 validation_1-rmse:0.16958 +[40] validation_0-rmse:0.19848 validation_1-rmse:0.16805 +[41] validation_0-rmse:0.19745 validation_1-rmse:0.16652 +[42] validation_0-rmse:0.19647 validation_1-rmse:0.16509 +[43] validation_0-rmse:0.19570 validation_1-rmse:0.16325 +[44] validation_0-rmse:0.19473 validation_1-rmse:0.16187 +[45] validation_0-rmse:0.19397 validation_1-rmse:0.16012 +[46] validation_0-rmse:0.19314 validation_1-rmse:0.15887 +[47] validation_0-rmse:0.19196 validation_1-rmse:0.15723 +[48] validation_0-rmse:0.19096 validation_1-rmse:0.15595 +[49] validation_0-rmse:0.19009 validation_1-rmse:0.15468 +[50] validation_0-rmse:0.18931 validation_1-rmse:0.15355 +[51] validation_0-rmse:0.18864 validation_1-rmse:0.15207 +[52] validation_0-rmse:0.18786 validation_1-rmse:0.15101 +[53] validation_0-rmse:0.18690 validation_1-rmse:0.14960 +[54] validation_0-rmse:0.18614 validation_1-rmse:0.14859 +[55] validation_0-rmse:0.18550 validation_1-rmse:0.14756 +[56] validation_0-rmse:0.18475 validation_1-rmse:0.14647 +[57] validation_0-rmse:0.18405 validation_1-rmse:0.14545 +[58] validation_0-rmse:0.18346 validation_1-rmse:0.14415 +[59] validation_0-rmse:0.18277 validation_1-rmse:0.14321 +[60] validation_0-rmse:0.18219 validation_1-rmse:0.14221 +[61] validation_0-rmse:0.18158 validation_1-rmse:0.14129 +[62] validation_0-rmse:0.18100 validation_1-rmse:0.14043 +[63] validation_0-rmse:0.18059 validation_1-rmse:0.13920 +[64] validation_0-rmse:0.17997 validation_1-rmse:0.13842 +[65] validation_0-rmse:0.17941 validation_1-rmse:0.13754 +[66] validation_0-rmse:0.17881 validation_1-rmse:0.13652 +[67] validation_0-rmse:0.17823 validation_1-rmse:0.13576 +[68] validation_0-rmse:0.17784 validation_1-rmse:0.13468 +[69] validation_0-rmse:0.17735 validation_1-rmse:0.13396 +[70] validation_0-rmse:0.17687 validation_1-rmse:0.13311 +[71] validation_0-rmse:0.17628 validation_1-rmse:0.13225 +[72] validation_0-rmse:0.17599 validation_1-rmse:0.13154 +[73] validation_0-rmse:0.17542 validation_1-rmse:0.13080 +[74] validation_0-rmse:0.17497 validation_1-rmse:0.13013 +[75] validation_0-rmse:0.17456 validation_1-rmse:0.12954 +[76] validation_0-rmse:0.17416 validation_1-rmse:0.12864 +[77] validation_0-rmse:0.17369 validation_1-rmse:0.12802 +[78] validation_0-rmse:0.17345 validation_1-rmse:0.12735 +[79] validation_0-rmse:0.17302 validation_1-rmse:0.12672 +[80] validation_0-rmse:0.17254 validation_1-rmse:0.12609 +[81] validation_0-rmse:0.17248 validation_1-rmse:0.12527 +[82] validation_0-rmse:0.17210 validation_1-rmse:0.12470 +[83] validation_0-rmse:0.17196 validation_1-rmse:0.12398 +[84] validation_0-rmse:0.17189 validation_1-rmse:0.12334 +[85] validation_0-rmse:0.17155 validation_1-rmse:0.12280 +[86] validation_0-rmse:0.17124 validation_1-rmse:0.12230 +[87] validation_0-rmse:0.17103 validation_1-rmse:0.12178 +[88] validation_0-rmse:0.17086 validation_1-rmse:0.12118 +[89] validation_0-rmse:0.17064 validation_1-rmse:0.12049 +[90] validation_0-rmse:0.17029 validation_1-rmse:0.11993 +[91] validation_0-rmse:0.16981 validation_1-rmse:0.11942 +[92] validation_0-rmse:0.16950 validation_1-rmse:0.11894 +[93] validation_0-rmse:0.16937 validation_1-rmse:0.11833 +[94] validation_0-rmse:0.16928 validation_1-rmse:0.11786 +[95] validation_0-rmse:0.16899 validation_1-rmse:0.11735 +[96] validation_0-rmse:0.16869 validation_1-rmse:0.11693 +[97] validation_0-rmse:0.16843 validation_1-rmse:0.11650 +[98] validation_0-rmse:0.16829 validation_1-rmse:0.11591 +[99] validation_0-rmse:0.16802 validation_1-rmse:0.11547 +2025-04-29 01:56:47,778 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.57 secs) -------------------- +2025-04-29 01:56:47,779 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:48,320 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-21 00:00:00 to 2025-02-20 00:00:00, 6/11 trains +2025-04-29 01:56:48,321 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1740009600_prediction.feather +2025-04-29 01:56:48,327 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:48,333 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:56:48,334 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.714422 +1 0.003044 49.714422 +2 0.000465 49.714422 +3 -0.000380 49.714422 +4 0.002829 49.714422 +2025-04-29 01:56:48,346 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:48,353 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:56:48,354 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.626186 +1 0.003044 49.626186 +2 0.000465 49.626186 +3 -0.000380 49.626186 +4 0.002829 49.626186 +2025-04-29 01:56:48,361 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1740009600/cb_sol_1740009600 +2025-04-29 01:56:48,361 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:48,383 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:48,383 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-21 to 2025-02-19 -------------------- +2025-04-29 01:56:53,532 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:53,533 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.29357 validation_1-rmse:0.28852 +[1] validation_0-rmse:0.28850 validation_1-rmse:0.28219 +[2] validation_0-rmse:0.28292 validation_1-rmse:0.27618 +[3] validation_0-rmse:0.27862 validation_1-rmse:0.27046 +[4] validation_0-rmse:0.27383 validation_1-rmse:0.26510 +[5] validation_0-rmse:0.27018 validation_1-rmse:0.25989 +[6] validation_0-rmse:0.26615 validation_1-rmse:0.25477 +[7] validation_0-rmse:0.26234 validation_1-rmse:0.25007 +[8] validation_0-rmse:0.25794 validation_1-rmse:0.24560 +[9] validation_0-rmse:0.25417 validation_1-rmse:0.24109 +[10] validation_0-rmse:0.25083 validation_1-rmse:0.23700 +[11] validation_0-rmse:0.24683 validation_1-rmse:0.23303 +[12] validation_0-rmse:0.24384 validation_1-rmse:0.22908 +[13] validation_0-rmse:0.24093 validation_1-rmse:0.22542 +[14] validation_0-rmse:0.23743 validation_1-rmse:0.22186 +[15] validation_0-rmse:0.23484 validation_1-rmse:0.21841 +[16] validation_0-rmse:0.23215 validation_1-rmse:0.21525 +[17] validation_0-rmse:0.22951 validation_1-rmse:0.21206 +[18] validation_0-rmse:0.22658 validation_1-rmse:0.20906 +[19] validation_0-rmse:0.22440 validation_1-rmse:0.20615 +[20] validation_0-rmse:0.22193 validation_1-rmse:0.20314 +[21] validation_0-rmse:0.22009 validation_1-rmse:0.20016 +[22] validation_0-rmse:0.21755 validation_1-rmse:0.19751 +[23] validation_0-rmse:0.21578 validation_1-rmse:0.19498 +[24] validation_0-rmse:0.21440 validation_1-rmse:0.19241 +[25] validation_0-rmse:0.21229 validation_1-rmse:0.19006 +[26] validation_0-rmse:0.21038 validation_1-rmse:0.18780 +[27] validation_0-rmse:0.20897 validation_1-rmse:0.18529 +[28] validation_0-rmse:0.20703 validation_1-rmse:0.18313 +[29] validation_0-rmse:0.20556 validation_1-rmse:0.18091 +[30] validation_0-rmse:0.20384 validation_1-rmse:0.17884 +[31] validation_0-rmse:0.20281 validation_1-rmse:0.17690 +[32] validation_0-rmse:0.20169 validation_1-rmse:0.17483 +[33] validation_0-rmse:0.20012 validation_1-rmse:0.17300 +[34] validation_0-rmse:0.19876 validation_1-rmse:0.17106 +[35] validation_0-rmse:0.19755 validation_1-rmse:0.16934 +[36] validation_0-rmse:0.19649 validation_1-rmse:0.16752 +[37] validation_0-rmse:0.19501 validation_1-rmse:0.16586 +[38] validation_0-rmse:0.19423 validation_1-rmse:0.16418 +[39] validation_0-rmse:0.19297 validation_1-rmse:0.16264 +[40] validation_0-rmse:0.19162 validation_1-rmse:0.16092 +[41] validation_0-rmse:0.19049 validation_1-rmse:0.15952 +[42] validation_0-rmse:0.18925 validation_1-rmse:0.15810 +[43] validation_0-rmse:0.18845 validation_1-rmse:0.15638 +[44] validation_0-rmse:0.18730 validation_1-rmse:0.15506 +[45] validation_0-rmse:0.18661 validation_1-rmse:0.15357 +[46] validation_0-rmse:0.18563 validation_1-rmse:0.15226 +[47] validation_0-rmse:0.18473 validation_1-rmse:0.15101 +[48] validation_0-rmse:0.18399 validation_1-rmse:0.14957 +[49] validation_0-rmse:0.18304 validation_1-rmse:0.14841 +[50] validation_0-rmse:0.18219 validation_1-rmse:0.14717 +[51] validation_0-rmse:0.18131 validation_1-rmse:0.14599 +[52] validation_0-rmse:0.18043 validation_1-rmse:0.14492 +[53] validation_0-rmse:0.17966 validation_1-rmse:0.14388 +[54] validation_0-rmse:0.17901 validation_1-rmse:0.14274 +[55] validation_0-rmse:0.17850 validation_1-rmse:0.14134 +[56] validation_0-rmse:0.17764 validation_1-rmse:0.14035 +[57] validation_0-rmse:0.17682 validation_1-rmse:0.13937 +[58] validation_0-rmse:0.17604 validation_1-rmse:0.13844 +[59] validation_0-rmse:0.17526 validation_1-rmse:0.13754 +[60] validation_0-rmse:0.17488 validation_1-rmse:0.13621 +[61] validation_0-rmse:0.17432 validation_1-rmse:0.13530 +[62] validation_0-rmse:0.17345 validation_1-rmse:0.13439 +[63] validation_0-rmse:0.17284 validation_1-rmse:0.13358 +[64] validation_0-rmse:0.17213 validation_1-rmse:0.13278 +[65] validation_0-rmse:0.17164 validation_1-rmse:0.13175 +[66] validation_0-rmse:0.17098 validation_1-rmse:0.13088 +[67] validation_0-rmse:0.17049 validation_1-rmse:0.13002 +[68] validation_0-rmse:0.17000 validation_1-rmse:0.12918 +[69] validation_0-rmse:0.16969 validation_1-rmse:0.12815 +[70] validation_0-rmse:0.16917 validation_1-rmse:0.12746 +[71] validation_0-rmse:0.16857 validation_1-rmse:0.12678 +[72] validation_0-rmse:0.16830 validation_1-rmse:0.12595 +[73] validation_0-rmse:0.16793 validation_1-rmse:0.12522 +[74] validation_0-rmse:0.16752 validation_1-rmse:0.12457 +[75] validation_0-rmse:0.16704 validation_1-rmse:0.12395 +[76] validation_0-rmse:0.16668 validation_1-rmse:0.12316 +[77] validation_0-rmse:0.16621 validation_1-rmse:0.12251 +[78] validation_0-rmse:0.16591 validation_1-rmse:0.12185 +[79] validation_0-rmse:0.16550 validation_1-rmse:0.12115 +[80] validation_0-rmse:0.16506 validation_1-rmse:0.12055 +[81] validation_0-rmse:0.16467 validation_1-rmse:0.12001 +[82] validation_0-rmse:0.16422 validation_1-rmse:0.11944 +[83] validation_0-rmse:0.16379 validation_1-rmse:0.11892 +[84] validation_0-rmse:0.16344 validation_1-rmse:0.11825 +[85] validation_0-rmse:0.16317 validation_1-rmse:0.11766 +[86] validation_0-rmse:0.16289 validation_1-rmse:0.11712 +[87] validation_0-rmse:0.16271 validation_1-rmse:0.11639 +[88] validation_0-rmse:0.16236 validation_1-rmse:0.11591 +[89] validation_0-rmse:0.16210 validation_1-rmse:0.11515 +[90] validation_0-rmse:0.16170 validation_1-rmse:0.11457 +[91] validation_0-rmse:0.16149 validation_1-rmse:0.11411 +[92] validation_0-rmse:0.16132 validation_1-rmse:0.11360 +[93] validation_0-rmse:0.16108 validation_1-rmse:0.11292 +[94] validation_0-rmse:0.16077 validation_1-rmse:0.11247 +[95] validation_0-rmse:0.16040 validation_1-rmse:0.11205 +[96] validation_0-rmse:0.16017 validation_1-rmse:0.11157 +[97] validation_0-rmse:0.15988 validation_1-rmse:0.11117 +[98] validation_0-rmse:0.15964 validation_1-rmse:0.11074 +[99] validation_0-rmse:0.15958 validation_1-rmse:0.11029 +2025-04-29 01:56:54,862 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.50 secs) -------------------- +2025-04-29 01:56:54,863 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:55,419 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-31 00:00:00 to 2025-03-02 00:00:00, 7/11 trains +2025-04-29 01:56:55,420 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1740873600_prediction.feather +2025-04-29 01:56:55,426 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:55,433 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:56:55,435 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.626186 +1 0.003044 49.626186 +2 0.000465 49.626186 +3 -0.000380 49.626186 +4 0.002829 49.626186 +2025-04-29 01:56:55,445 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:55,452 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:56:55,453 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.568812 +1 0.003044 49.568812 +2 0.000465 49.568812 +3 -0.000380 49.568812 +4 0.002829 49.568812 +2025-04-29 01:56:55,459 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1740873600/cb_sol_1740873600 +2025-04-29 01:56:55,459 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:55,481 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:55,482 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-31 to 2025-03-01 -------------------- +2025-04-29 01:57:00,566 - datasieve.pipeline - INFO - DI tossed 2417 predictions for being too far from training data. +2025-04-29 01:57:00,569 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:00,570 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.33058 validation_1-rmse:0.29214 +[1] validation_0-rmse:0.32414 validation_1-rmse:0.28558 +[2] validation_0-rmse:0.31832 validation_1-rmse:0.27962 +[3] validation_0-rmse:0.31280 validation_1-rmse:0.27380 +[4] validation_0-rmse:0.30679 validation_1-rmse:0.26829 +[5] validation_0-rmse:0.30182 validation_1-rmse:0.26306 +[6] validation_0-rmse:0.29686 validation_1-rmse:0.25797 +[7] validation_0-rmse:0.29291 validation_1-rmse:0.25323 +[8] validation_0-rmse:0.28868 validation_1-rmse:0.24871 +[9] validation_0-rmse:0.28559 validation_1-rmse:0.24437 +[10] validation_0-rmse:0.28262 validation_1-rmse:0.24018 +[11] validation_0-rmse:0.27890 validation_1-rmse:0.23606 +[12] validation_0-rmse:0.27663 validation_1-rmse:0.23225 +[13] validation_0-rmse:0.27306 validation_1-rmse:0.22870 +[14] validation_0-rmse:0.26948 validation_1-rmse:0.22493 +[15] validation_0-rmse:0.26663 validation_1-rmse:0.22157 +[16] validation_0-rmse:0.26427 validation_1-rmse:0.21817 +[17] validation_0-rmse:0.26195 validation_1-rmse:0.21492 +[18] validation_0-rmse:0.25856 validation_1-rmse:0.21177 +[19] validation_0-rmse:0.25606 validation_1-rmse:0.20861 +[20] validation_0-rmse:0.25343 validation_1-rmse:0.20580 +[21] validation_0-rmse:0.25243 validation_1-rmse:0.20301 +[22] validation_0-rmse:0.25066 validation_1-rmse:0.20027 +[23] validation_0-rmse:0.24864 validation_1-rmse:0.19761 +[24] validation_0-rmse:0.24630 validation_1-rmse:0.19522 +[25] validation_0-rmse:0.24491 validation_1-rmse:0.19283 +[26] validation_0-rmse:0.24339 validation_1-rmse:0.19036 +[27] validation_0-rmse:0.24108 validation_1-rmse:0.18818 +[28] validation_0-rmse:0.23976 validation_1-rmse:0.18592 +[29] validation_0-rmse:0.23882 validation_1-rmse:0.18348 +[30] validation_0-rmse:0.23676 validation_1-rmse:0.18142 +[31] validation_0-rmse:0.23520 validation_1-rmse:0.17945 +[32] validation_0-rmse:0.23395 validation_1-rmse:0.17754 +[33] validation_0-rmse:0.23229 validation_1-rmse:0.17545 +[34] validation_0-rmse:0.23073 validation_1-rmse:0.17360 +[35] validation_0-rmse:0.22951 validation_1-rmse:0.17182 +[36] validation_0-rmse:0.22806 validation_1-rmse:0.16995 +[37] validation_0-rmse:0.22713 validation_1-rmse:0.16834 +[38] validation_0-rmse:0.22541 validation_1-rmse:0.16668 +[39] validation_0-rmse:0.22393 validation_1-rmse:0.16509 +[40] validation_0-rmse:0.22282 validation_1-rmse:0.16343 +[41] validation_0-rmse:0.22168 validation_1-rmse:0.16185 +[42] validation_0-rmse:0.22085 validation_1-rmse:0.16046 +[43] validation_0-rmse:0.21991 validation_1-rmse:0.15907 +[44] validation_0-rmse:0.21833 validation_1-rmse:0.15756 +[45] validation_0-rmse:0.21710 validation_1-rmse:0.15618 +[46] validation_0-rmse:0.21619 validation_1-rmse:0.15490 +[47] validation_0-rmse:0.21518 validation_1-rmse:0.15345 +[48] validation_0-rmse:0.21402 validation_1-rmse:0.15221 +[49] validation_0-rmse:0.21305 validation_1-rmse:0.15086 +[50] validation_0-rmse:0.21229 validation_1-rmse:0.14968 +[51] validation_0-rmse:0.21119 validation_1-rmse:0.14854 +[52] validation_0-rmse:0.21019 validation_1-rmse:0.14745 +[53] validation_0-rmse:0.20924 validation_1-rmse:0.14637 +[54] validation_0-rmse:0.20982 validation_1-rmse:0.14517 +[55] validation_0-rmse:0.20888 validation_1-rmse:0.14405 +[56] validation_0-rmse:0.20806 validation_1-rmse:0.14305 +[57] validation_0-rmse:0.20822 validation_1-rmse:0.14169 +[58] validation_0-rmse:0.20741 validation_1-rmse:0.14071 +[59] validation_0-rmse:0.20663 validation_1-rmse:0.13976 +[60] validation_0-rmse:0.20602 validation_1-rmse:0.13882 +[61] validation_0-rmse:0.20523 validation_1-rmse:0.13776 +[62] validation_0-rmse:0.20558 validation_1-rmse:0.13689 +[63] validation_0-rmse:0.20501 validation_1-rmse:0.13605 +[64] validation_0-rmse:0.20348 validation_1-rmse:0.13462 +[65] validation_0-rmse:0.20273 validation_1-rmse:0.13382 +[66] validation_0-rmse:0.20203 validation_1-rmse:0.13306 +[67] validation_0-rmse:0.20166 validation_1-rmse:0.13228 +[68] validation_0-rmse:0.20002 validation_1-rmse:0.13102 +[69] validation_0-rmse:0.19928 validation_1-rmse:0.13021 +[70] validation_0-rmse:0.19870 validation_1-rmse:0.12946 +[71] validation_0-rmse:0.19830 validation_1-rmse:0.12876 +[72] validation_0-rmse:0.19814 validation_1-rmse:0.12801 +[73] validation_0-rmse:0.19798 validation_1-rmse:0.12711 +[74] validation_0-rmse:0.19746 validation_1-rmse:0.12649 +[75] validation_0-rmse:0.19701 validation_1-rmse:0.12588 +[76] validation_0-rmse:0.19555 validation_1-rmse:0.12467 +[77] validation_0-rmse:0.19514 validation_1-rmse:0.12407 +[78] validation_0-rmse:0.19468 validation_1-rmse:0.12347 +[79] validation_0-rmse:0.19439 validation_1-rmse:0.12277 +[80] validation_0-rmse:0.19473 validation_1-rmse:0.12220 +[81] validation_0-rmse:0.19448 validation_1-rmse:0.12154 +[82] validation_0-rmse:0.19418 validation_1-rmse:0.12086 +[83] validation_0-rmse:0.19370 validation_1-rmse:0.12030 +[84] validation_0-rmse:0.19346 validation_1-rmse:0.11976 +[85] validation_0-rmse:0.19322 validation_1-rmse:0.11879 +[86] validation_0-rmse:0.19282 validation_1-rmse:0.11819 +[87] validation_0-rmse:0.19226 validation_1-rmse:0.11770 +[88] validation_0-rmse:0.19187 validation_1-rmse:0.11719 +[89] validation_0-rmse:0.19145 validation_1-rmse:0.11671 +[90] validation_0-rmse:0.19134 validation_1-rmse:0.11619 +[91] validation_0-rmse:0.19030 validation_1-rmse:0.11531 +[92] validation_0-rmse:0.18998 validation_1-rmse:0.11487 +[93] validation_0-rmse:0.18945 validation_1-rmse:0.11445 +[94] validation_0-rmse:0.18919 validation_1-rmse:0.11395 +[95] validation_0-rmse:0.18862 validation_1-rmse:0.11324 +[96] validation_0-rmse:0.18824 validation_1-rmse:0.11283 +[97] validation_0-rmse:0.18778 validation_1-rmse:0.11225 +[98] validation_0-rmse:0.18755 validation_1-rmse:0.11186 +[99] validation_0-rmse:0.18742 validation_1-rmse:0.11149 +2025-04-29 01:57:02,441 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.98 secs) -------------------- +2025-04-29 01:57:02,442 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:02,968 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-02-10 00:00:00 to 2025-03-12 00:00:00, 8/11 trains +2025-04-29 01:57:02,968 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1741737600_prediction.feather +2025-04-29 01:57:02,980 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:02,987 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:57:02,989 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.568812 +1 0.003044 49.568812 +2 0.000465 49.568812 +3 -0.000380 49.568812 +4 0.002829 49.568812 +2025-04-29 01:57:03,001 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:03,007 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:57:03,009 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.623338 +1 0.003044 49.623338 +2 0.000465 49.623338 +3 -0.000380 49.623338 +4 0.002829 49.623338 +2025-04-29 01:57:03,014 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1741737600/cb_sol_1741737600 +2025-04-29 01:57:03,015 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:03,042 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:03,042 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-10 to 2025-03-11 -------------------- +2025-04-29 01:57:08,138 - datasieve.pipeline - INFO - DI tossed 3 predictions for being too far from training data. +2025-04-29 01:57:08,141 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:08,141 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.25025 validation_1-rmse:0.24842 +[1] validation_0-rmse:0.24557 validation_1-rmse:0.24302 +[2] validation_0-rmse:0.24132 validation_1-rmse:0.23806 +[3] validation_0-rmse:0.23733 validation_1-rmse:0.23332 +[4] validation_0-rmse:0.23376 validation_1-rmse:0.22859 +[5] validation_0-rmse:0.23049 validation_1-rmse:0.22444 +[6] validation_0-rmse:0.22702 validation_1-rmse:0.22025 +[7] validation_0-rmse:0.22380 validation_1-rmse:0.21631 +[8] validation_0-rmse:0.22066 validation_1-rmse:0.21250 +[9] validation_0-rmse:0.21772 validation_1-rmse:0.20892 +[10] validation_0-rmse:0.21473 validation_1-rmse:0.20536 +[11] validation_0-rmse:0.21219 validation_1-rmse:0.20211 +[12] validation_0-rmse:0.20968 validation_1-rmse:0.19897 +[13] validation_0-rmse:0.20730 validation_1-rmse:0.19597 +[14] validation_0-rmse:0.20552 validation_1-rmse:0.19281 +[15] validation_0-rmse:0.20361 validation_1-rmse:0.18992 +[16] validation_0-rmse:0.20165 validation_1-rmse:0.18721 +[17] validation_0-rmse:0.19948 validation_1-rmse:0.18463 +[18] validation_0-rmse:0.19807 validation_1-rmse:0.18193 +[19] validation_0-rmse:0.19703 validation_1-rmse:0.17939 +[20] validation_0-rmse:0.19569 validation_1-rmse:0.17683 +[21] validation_0-rmse:0.19388 validation_1-rmse:0.17462 +[22] validation_0-rmse:0.19219 validation_1-rmse:0.17240 +[23] validation_0-rmse:0.19062 validation_1-rmse:0.17026 +[24] validation_0-rmse:0.18933 validation_1-rmse:0.16813 +[25] validation_0-rmse:0.18829 validation_1-rmse:0.16598 +[26] validation_0-rmse:0.18704 validation_1-rmse:0.16411 +[27] validation_0-rmse:0.18563 validation_1-rmse:0.16221 +[28] validation_0-rmse:0.18446 validation_1-rmse:0.16034 +[29] validation_0-rmse:0.18316 validation_1-rmse:0.15841 +[30] validation_0-rmse:0.18192 validation_1-rmse:0.15674 +[31] validation_0-rmse:0.18091 validation_1-rmse:0.15479 +[32] validation_0-rmse:0.18003 validation_1-rmse:0.15312 +[33] validation_0-rmse:0.17886 validation_1-rmse:0.15150 +[34] validation_0-rmse:0.17786 validation_1-rmse:0.14997 +[35] validation_0-rmse:0.17692 validation_1-rmse:0.14855 +[36] validation_0-rmse:0.17613 validation_1-rmse:0.14709 +[37] validation_0-rmse:0.17547 validation_1-rmse:0.14549 +[38] validation_0-rmse:0.17467 validation_1-rmse:0.14404 +[39] validation_0-rmse:0.17393 validation_1-rmse:0.14267 +[40] validation_0-rmse:0.17348 validation_1-rmse:0.14118 +[41] validation_0-rmse:0.17258 validation_1-rmse:0.13993 +[42] validation_0-rmse:0.17168 validation_1-rmse:0.13871 +[43] validation_0-rmse:0.17077 validation_1-rmse:0.13757 +[44] validation_0-rmse:0.17015 validation_1-rmse:0.13621 +[45] validation_0-rmse:0.16924 validation_1-rmse:0.13509 +[46] validation_0-rmse:0.16833 validation_1-rmse:0.13401 +[47] validation_0-rmse:0.16756 validation_1-rmse:0.13297 +[48] validation_0-rmse:0.16717 validation_1-rmse:0.13198 +[49] validation_0-rmse:0.16664 validation_1-rmse:0.13081 +[50] validation_0-rmse:0.16615 validation_1-rmse:0.12979 +[51] validation_0-rmse:0.16541 validation_1-rmse:0.12879 +[52] validation_0-rmse:0.16478 validation_1-rmse:0.12767 +[53] validation_0-rmse:0.16408 validation_1-rmse:0.12675 +[54] validation_0-rmse:0.16363 validation_1-rmse:0.12571 +[55] validation_0-rmse:0.16320 validation_1-rmse:0.12485 +[56] validation_0-rmse:0.16253 validation_1-rmse:0.12398 +[57] validation_0-rmse:0.16192 validation_1-rmse:0.12307 +[58] validation_0-rmse:0.16149 validation_1-rmse:0.12229 +[59] validation_0-rmse:0.16137 validation_1-rmse:0.12128 +[60] validation_0-rmse:0.16117 validation_1-rmse:0.12045 +[61] validation_0-rmse:0.16064 validation_1-rmse:0.11966 +[62] validation_0-rmse:0.16050 validation_1-rmse:0.11890 +[63] validation_0-rmse:0.16003 validation_1-rmse:0.11809 +[64] validation_0-rmse:0.15969 validation_1-rmse:0.11739 +[65] validation_0-rmse:0.15922 validation_1-rmse:0.11661 +[66] validation_0-rmse:0.15868 validation_1-rmse:0.11577 +[67] validation_0-rmse:0.15830 validation_1-rmse:0.11509 +[68] validation_0-rmse:0.15789 validation_1-rmse:0.11446 +[69] validation_0-rmse:0.15733 validation_1-rmse:0.11372 +[70] validation_0-rmse:0.15694 validation_1-rmse:0.11307 +[71] validation_0-rmse:0.15692 validation_1-rmse:0.11224 +[72] validation_0-rmse:0.15659 validation_1-rmse:0.11166 +[73] validation_0-rmse:0.15634 validation_1-rmse:0.11111 +[74] validation_0-rmse:0.15595 validation_1-rmse:0.11056 +[75] validation_0-rmse:0.15579 validation_1-rmse:0.10985 +[76] validation_0-rmse:0.15543 validation_1-rmse:0.10903 +[77] validation_0-rmse:0.15500 validation_1-rmse:0.10848 +[78] validation_0-rmse:0.15499 validation_1-rmse:0.10778 +[79] validation_0-rmse:0.15471 validation_1-rmse:0.10721 +[80] validation_0-rmse:0.15442 validation_1-rmse:0.10666 +[81] validation_0-rmse:0.15416 validation_1-rmse:0.10608 +[82] validation_0-rmse:0.15388 validation_1-rmse:0.10560 +[83] validation_0-rmse:0.15368 validation_1-rmse:0.10498 +[84] validation_0-rmse:0.15346 validation_1-rmse:0.10449 +[85] validation_0-rmse:0.15329 validation_1-rmse:0.10392 +[86] validation_0-rmse:0.15302 validation_1-rmse:0.10347 +[87] validation_0-rmse:0.15270 validation_1-rmse:0.10303 +[88] validation_0-rmse:0.15259 validation_1-rmse:0.10258 +[89] validation_0-rmse:0.15269 validation_1-rmse:0.10204 +[90] validation_0-rmse:0.15239 validation_1-rmse:0.10159 +[91] validation_0-rmse:0.15204 validation_1-rmse:0.10116 +[92] validation_0-rmse:0.15175 validation_1-rmse:0.10070 +[93] validation_0-rmse:0.15167 validation_1-rmse:0.10017 +[94] validation_0-rmse:0.15154 validation_1-rmse:0.09982 +[95] validation_0-rmse:0.15122 validation_1-rmse:0.09932 +[96] validation_0-rmse:0.15119 validation_1-rmse:0.09880 +[97] validation_0-rmse:0.15112 validation_1-rmse:0.09842 +[98] validation_0-rmse:0.15095 validation_1-rmse:0.09807 +[99] validation_0-rmse:0.15075 validation_1-rmse:0.09770 +2025-04-29 01:57:09,614 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.60 secs) -------------------- +2025-04-29 01:57:09,615 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:10,150 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-02-20 00:00:00 to 2025-03-22 00:00:00, 9/11 trains +2025-04-29 01:57:10,151 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1742601600_prediction.feather +2025-04-29 01:57:10,159 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:10,167 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:57:10,168 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.623338 +1 0.003044 49.623338 +2 0.000465 49.623338 +3 -0.000380 49.623338 +4 0.002829 49.623338 +2025-04-29 01:57:10,181 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:10,188 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:57:10,190 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.644115 +1 0.003044 49.644115 +2 0.000465 49.644115 +3 -0.000380 49.644115 +4 0.002829 49.644115 +2025-04-29 01:57:10,195 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1742601600/cb_sol_1742601600 +2025-04-29 01:57:10,196 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:10,218 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:10,218 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-20 to 2025-03-21 -------------------- +2025-04-29 01:57:15,185 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:15,186 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.24126 validation_1-rmse:0.24985 +[1] validation_0-rmse:0.23710 validation_1-rmse:0.24457 +[2] validation_0-rmse:0.23323 validation_1-rmse:0.23968 +[3] validation_0-rmse:0.22960 validation_1-rmse:0.23491 +[4] validation_0-rmse:0.22600 validation_1-rmse:0.23038 +[5] validation_0-rmse:0.22255 validation_1-rmse:0.22616 +[6] validation_0-rmse:0.21946 validation_1-rmse:0.22213 +[7] validation_0-rmse:0.21640 validation_1-rmse:0.21827 +[8] validation_0-rmse:0.21381 validation_1-rmse:0.21453 +[9] validation_0-rmse:0.21110 validation_1-rmse:0.21092 +[10] validation_0-rmse:0.20854 validation_1-rmse:0.20742 +[11] validation_0-rmse:0.20586 validation_1-rmse:0.20418 +[12] validation_0-rmse:0.20373 validation_1-rmse:0.20097 +[13] validation_0-rmse:0.20156 validation_1-rmse:0.19779 +[14] validation_0-rmse:0.19934 validation_1-rmse:0.19493 +[15] validation_0-rmse:0.19739 validation_1-rmse:0.19211 +[16] validation_0-rmse:0.19537 validation_1-rmse:0.18929 +[17] validation_0-rmse:0.19333 validation_1-rmse:0.18671 +[18] validation_0-rmse:0.19163 validation_1-rmse:0.18396 +[19] validation_0-rmse:0.18975 validation_1-rmse:0.18157 +[20] validation_0-rmse:0.18799 validation_1-rmse:0.17903 +[21] validation_0-rmse:0.18612 validation_1-rmse:0.17673 +[22] validation_0-rmse:0.18451 validation_1-rmse:0.17454 +[23] validation_0-rmse:0.18299 validation_1-rmse:0.17225 +[24] validation_0-rmse:0.18150 validation_1-rmse:0.17025 +[25] validation_0-rmse:0.18016 validation_1-rmse:0.16803 +[26] validation_0-rmse:0.17866 validation_1-rmse:0.16614 +[27] validation_0-rmse:0.17732 validation_1-rmse:0.16429 +[28] validation_0-rmse:0.17619 validation_1-rmse:0.16247 +[29] validation_0-rmse:0.17494 validation_1-rmse:0.16080 +[30] validation_0-rmse:0.17391 validation_1-rmse:0.15889 +[31] validation_0-rmse:0.17282 validation_1-rmse:0.15724 +[32] validation_0-rmse:0.17156 validation_1-rmse:0.15548 +[33] validation_0-rmse:0.17054 validation_1-rmse:0.15393 +[34] validation_0-rmse:0.16943 validation_1-rmse:0.15244 +[35] validation_0-rmse:0.16841 validation_1-rmse:0.15088 +[36] validation_0-rmse:0.16736 validation_1-rmse:0.14950 +[37] validation_0-rmse:0.16647 validation_1-rmse:0.14797 +[38] validation_0-rmse:0.16544 validation_1-rmse:0.14641 +[39] validation_0-rmse:0.16454 validation_1-rmse:0.14508 +[40] validation_0-rmse:0.16357 validation_1-rmse:0.14380 +[41] validation_0-rmse:0.16266 validation_1-rmse:0.14261 +[42] validation_0-rmse:0.16198 validation_1-rmse:0.14134 +[43] validation_0-rmse:0.16105 validation_1-rmse:0.14019 +[44] validation_0-rmse:0.16046 validation_1-rmse:0.13896 +[45] validation_0-rmse:0.15963 validation_1-rmse:0.13773 +[46] validation_0-rmse:0.15899 validation_1-rmse:0.13662 +[47] validation_0-rmse:0.15822 validation_1-rmse:0.13555 +[48] validation_0-rmse:0.15757 validation_1-rmse:0.13452 +[49] validation_0-rmse:0.15688 validation_1-rmse:0.13322 +[50] validation_0-rmse:0.15627 validation_1-rmse:0.13206 +[51] validation_0-rmse:0.15558 validation_1-rmse:0.13110 +[52] validation_0-rmse:0.15493 validation_1-rmse:0.13017 +[53] validation_0-rmse:0.15429 validation_1-rmse:0.12924 +[54] validation_0-rmse:0.15365 validation_1-rmse:0.12838 +[55] validation_0-rmse:0.15303 validation_1-rmse:0.12741 +[56] validation_0-rmse:0.15258 validation_1-rmse:0.12653 +[57] validation_0-rmse:0.15202 validation_1-rmse:0.12569 +[58] validation_0-rmse:0.15142 validation_1-rmse:0.12478 +[59] validation_0-rmse:0.15106 validation_1-rmse:0.12392 +[60] validation_0-rmse:0.15049 validation_1-rmse:0.12297 +[61] validation_0-rmse:0.14990 validation_1-rmse:0.12223 +[62] validation_0-rmse:0.14932 validation_1-rmse:0.12144 +[63] validation_0-rmse:0.14876 validation_1-rmse:0.12071 +[64] validation_0-rmse:0.14826 validation_1-rmse:0.12000 +[65] validation_0-rmse:0.14788 validation_1-rmse:0.11931 +[66] validation_0-rmse:0.14753 validation_1-rmse:0.11842 +[67] validation_0-rmse:0.14714 validation_1-rmse:0.11776 +[68] validation_0-rmse:0.14665 validation_1-rmse:0.11706 +[69] validation_0-rmse:0.14655 validation_1-rmse:0.11614 +[70] validation_0-rmse:0.14616 validation_1-rmse:0.11556 +[71] validation_0-rmse:0.14579 validation_1-rmse:0.11478 +[72] validation_0-rmse:0.14533 validation_1-rmse:0.11418 +[73] validation_0-rmse:0.14491 validation_1-rmse:0.11358 +[74] validation_0-rmse:0.14448 validation_1-rmse:0.11300 +[75] validation_0-rmse:0.14446 validation_1-rmse:0.11235 +[76] validation_0-rmse:0.14414 validation_1-rmse:0.11173 +[77] validation_0-rmse:0.14371 validation_1-rmse:0.11116 +[78] validation_0-rmse:0.14344 validation_1-rmse:0.11066 +[79] validation_0-rmse:0.14321 validation_1-rmse:0.10996 +[80] validation_0-rmse:0.14280 validation_1-rmse:0.10942 +[81] validation_0-rmse:0.14250 validation_1-rmse:0.10885 +[82] validation_0-rmse:0.14222 validation_1-rmse:0.10837 +[83] validation_0-rmse:0.14184 validation_1-rmse:0.10787 +[84] validation_0-rmse:0.14140 validation_1-rmse:0.10731 +[85] validation_0-rmse:0.14114 validation_1-rmse:0.10683 +[86] validation_0-rmse:0.14100 validation_1-rmse:0.10625 +[87] validation_0-rmse:0.14077 validation_1-rmse:0.10574 +[88] validation_0-rmse:0.14048 validation_1-rmse:0.10534 +[89] validation_0-rmse:0.14010 validation_1-rmse:0.10485 +[90] validation_0-rmse:0.13990 validation_1-rmse:0.10443 +[91] validation_0-rmse:0.13956 validation_1-rmse:0.10400 +[92] validation_0-rmse:0.13949 validation_1-rmse:0.10341 +[93] validation_0-rmse:0.13930 validation_1-rmse:0.10298 +[94] validation_0-rmse:0.13905 validation_1-rmse:0.10254 +[95] validation_0-rmse:0.13884 validation_1-rmse:0.10211 +[96] validation_0-rmse:0.13867 validation_1-rmse:0.10167 +[97] validation_0-rmse:0.13859 validation_1-rmse:0.10114 +[98] validation_0-rmse:0.13839 validation_1-rmse:0.10078 +[99] validation_0-rmse:0.13818 validation_1-rmse:0.10038 +2025-04-29 01:57:16,538 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.34 secs) -------------------- +2025-04-29 01:57:16,539 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:17,068 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-03-02 00:00:00 to 2025-04-01 00:00:00, 10/11 trains +2025-04-29 01:57:17,069 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1743465600_prediction.feather +2025-04-29 01:57:17,084 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:17,092 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:57:17,094 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.644115 +1 0.003044 49.644115 +2 0.000465 49.644115 +3 -0.000380 49.644115 +4 0.002829 49.644115 +2025-04-29 01:57:17,108 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:17,115 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:57:17,117 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.601082 +1 0.003044 49.601082 +2 0.000465 49.601082 +3 -0.000380 49.601082 +4 0.002829 49.601082 +2025-04-29 01:57:17,124 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1743465600/cb_sol_1743465600 +2025-04-29 01:57:17,125 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:17,151 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:17,151 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-02 to 2025-03-31 -------------------- +2025-04-29 01:57:22,430 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:22,430 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.23717 validation_1-rmse:0.24954 +[1] validation_0-rmse:0.23311 validation_1-rmse:0.24432 +[2] validation_0-rmse:0.22894 validation_1-rmse:0.23928 +[3] validation_0-rmse:0.22483 validation_1-rmse:0.23452 +[4] validation_0-rmse:0.22141 validation_1-rmse:0.23005 +[5] validation_0-rmse:0.21750 validation_1-rmse:0.22575 +[6] validation_0-rmse:0.21419 validation_1-rmse:0.22161 +[7] validation_0-rmse:0.21074 validation_1-rmse:0.21764 +[8] validation_0-rmse:0.20776 validation_1-rmse:0.21374 +[9] validation_0-rmse:0.20479 validation_1-rmse:0.21020 +[10] validation_0-rmse:0.20193 validation_1-rmse:0.20664 +[11] validation_0-rmse:0.19915 validation_1-rmse:0.20326 +[12] validation_0-rmse:0.19683 validation_1-rmse:0.20013 +[13] validation_0-rmse:0.19459 validation_1-rmse:0.19705 +[14] validation_0-rmse:0.19243 validation_1-rmse:0.19415 +[15] validation_0-rmse:0.19013 validation_1-rmse:0.19115 +[16] validation_0-rmse:0.18828 validation_1-rmse:0.18836 +[17] validation_0-rmse:0.18621 validation_1-rmse:0.18557 +[18] validation_0-rmse:0.18402 validation_1-rmse:0.18302 +[19] validation_0-rmse:0.18198 validation_1-rmse:0.18050 +[20] validation_0-rmse:0.18015 validation_1-rmse:0.17803 +[21] validation_0-rmse:0.17857 validation_1-rmse:0.17575 +[22] validation_0-rmse:0.17681 validation_1-rmse:0.17350 +[23] validation_0-rmse:0.17537 validation_1-rmse:0.17132 +[24] validation_0-rmse:0.17377 validation_1-rmse:0.16919 +[25] validation_0-rmse:0.17225 validation_1-rmse:0.16720 +[26] validation_0-rmse:0.17072 validation_1-rmse:0.16529 +[27] validation_0-rmse:0.16931 validation_1-rmse:0.16310 +[28] validation_0-rmse:0.16784 validation_1-rmse:0.16126 +[29] validation_0-rmse:0.16650 validation_1-rmse:0.15940 +[30] validation_0-rmse:0.16512 validation_1-rmse:0.15771 +[31] validation_0-rmse:0.16392 validation_1-rmse:0.15605 +[32] validation_0-rmse:0.16287 validation_1-rmse:0.15428 +[33] validation_0-rmse:0.16159 validation_1-rmse:0.15277 +[34] validation_0-rmse:0.16033 validation_1-rmse:0.15125 +[35] validation_0-rmse:0.15910 validation_1-rmse:0.14974 +[36] validation_0-rmse:0.15821 validation_1-rmse:0.14832 +[37] validation_0-rmse:0.15733 validation_1-rmse:0.14664 +[38] validation_0-rmse:0.15624 validation_1-rmse:0.14525 +[39] validation_0-rmse:0.15518 validation_1-rmse:0.14395 +[40] validation_0-rmse:0.15451 validation_1-rmse:0.14267 +[41] validation_0-rmse:0.15396 validation_1-rmse:0.14127 +[42] validation_0-rmse:0.15309 validation_1-rmse:0.14006 +[43] validation_0-rmse:0.15219 validation_1-rmse:0.13890 +[44] validation_0-rmse:0.15156 validation_1-rmse:0.13749 +[45] validation_0-rmse:0.15061 validation_1-rmse:0.13637 +[46] validation_0-rmse:0.14982 validation_1-rmse:0.13528 +[47] validation_0-rmse:0.14918 validation_1-rmse:0.13414 +[48] validation_0-rmse:0.14840 validation_1-rmse:0.13312 +[49] validation_0-rmse:0.14802 validation_1-rmse:0.13212 +[50] validation_0-rmse:0.14738 validation_1-rmse:0.13089 +[51] validation_0-rmse:0.14671 validation_1-rmse:0.12994 +[52] validation_0-rmse:0.14604 validation_1-rmse:0.12894 +[53] validation_0-rmse:0.14534 validation_1-rmse:0.12802 +[54] validation_0-rmse:0.14464 validation_1-rmse:0.12718 +[55] validation_0-rmse:0.14423 validation_1-rmse:0.12625 +[56] validation_0-rmse:0.14371 validation_1-rmse:0.12531 +[57] validation_0-rmse:0.14321 validation_1-rmse:0.12446 +[58] validation_0-rmse:0.14279 validation_1-rmse:0.12346 +[59] validation_0-rmse:0.14234 validation_1-rmse:0.12257 +[60] validation_0-rmse:0.14194 validation_1-rmse:0.12181 +[61] validation_0-rmse:0.14176 validation_1-rmse:0.12077 +[62] validation_0-rmse:0.14120 validation_1-rmse:0.12003 +[63] validation_0-rmse:0.14073 validation_1-rmse:0.11932 +[64] validation_0-rmse:0.14023 validation_1-rmse:0.11862 +[65] validation_0-rmse:0.14001 validation_1-rmse:0.11791 +[66] validation_0-rmse:0.13966 validation_1-rmse:0.11720 +[67] validation_0-rmse:0.13920 validation_1-rmse:0.11644 +[68] validation_0-rmse:0.13872 validation_1-rmse:0.11560 +[69] validation_0-rmse:0.13831 validation_1-rmse:0.11494 +[70] validation_0-rmse:0.13808 validation_1-rmse:0.11425 +[71] validation_0-rmse:0.13762 validation_1-rmse:0.11348 +[72] validation_0-rmse:0.13725 validation_1-rmse:0.11284 +[73] validation_0-rmse:0.13681 validation_1-rmse:0.11225 +[74] validation_0-rmse:0.13629 validation_1-rmse:0.11165 +[75] validation_0-rmse:0.13595 validation_1-rmse:0.11109 +[76] validation_0-rmse:0.13585 validation_1-rmse:0.11023 +[77] validation_0-rmse:0.13541 validation_1-rmse:0.10972 +[78] validation_0-rmse:0.13505 validation_1-rmse:0.10920 +[79] validation_0-rmse:0.13465 validation_1-rmse:0.10861 +[80] validation_0-rmse:0.13433 validation_1-rmse:0.10810 +[81] validation_0-rmse:0.13409 validation_1-rmse:0.10744 +[82] validation_0-rmse:0.13377 validation_1-rmse:0.10695 +[83] validation_0-rmse:0.13353 validation_1-rmse:0.10641 +[84] validation_0-rmse:0.13337 validation_1-rmse:0.10588 +[85] validation_0-rmse:0.13329 validation_1-rmse:0.10533 +[86] validation_0-rmse:0.13296 validation_1-rmse:0.10488 +[87] validation_0-rmse:0.13264 validation_1-rmse:0.10442 +[88] validation_0-rmse:0.13247 validation_1-rmse:0.10394 +[89] validation_0-rmse:0.13216 validation_1-rmse:0.10351 +[90] validation_0-rmse:0.13188 validation_1-rmse:0.10297 +[91] validation_0-rmse:0.13145 validation_1-rmse:0.10203 +[92] validation_0-rmse:0.13122 validation_1-rmse:0.10157 +[93] validation_0-rmse:0.13102 validation_1-rmse:0.10118 +[94] validation_0-rmse:0.13060 validation_1-rmse:0.10033 +[95] validation_0-rmse:0.13033 validation_1-rmse:0.09981 +[96] validation_0-rmse:0.13016 validation_1-rmse:0.09933 +[97] validation_0-rmse:0.12995 validation_1-rmse:0.09894 +[98] validation_0-rmse:0.12972 validation_1-rmse:0.09860 +[99] validation_0-rmse:0.12954 validation_1-rmse:0.09825 +2025-04-29 01:57:23,725 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.60 secs) -------------------- +2025-04-29 01:57:23,726 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:24,305 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-03-12 00:00:00 to 2025-04-11 00:00:00, 11/11 trains +2025-04-29 01:57:24,305 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1744329600_prediction.feather +2025-04-29 01:57:24,318 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:24,325 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:57:24,327 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.601082 +1 0.003044 49.601082 +2 0.000465 49.601082 +3 -0.000380 49.601082 +4 0.002829 49.601082 +2025-04-29 01:57:24,337 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:24,345 - FreqaiExampleStrategy - INFO - 目标列形状：(66770,) +2025-04-29 01:57:24,346 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.729824 +1 0.003044 49.729824 +2 0.000465 49.729824 +3 -0.000380 49.729824 +4 0.002829 49.729824 +2025-04-29 01:57:24,352 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1744329600/cb_sol_1744329600 +2025-04-29 01:57:24,353 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:24,376 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:24,376 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-12 to 2025-04-10 -------------------- +2025-04-29 01:57:29,392 - datasieve.pipeline - INFO - DI tossed 1948 predictions for being too far from training data. +2025-04-29 01:57:29,396 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:29,396 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.30616 validation_1-rmse:0.27906 +[1] validation_0-rmse:0.30021 validation_1-rmse:0.27322 +[2] validation_0-rmse:0.29443 validation_1-rmse:0.26757 +[3] validation_0-rmse:0.28911 validation_1-rmse:0.26205 +[4] validation_0-rmse:0.28365 validation_1-rmse:0.25699 +[5] validation_0-rmse:0.27823 validation_1-rmse:0.25219 +[6] validation_0-rmse:0.27295 validation_1-rmse:0.24748 +[7] validation_0-rmse:0.26797 validation_1-rmse:0.24295 +[8] validation_0-rmse:0.26320 validation_1-rmse:0.23854 +[9] validation_0-rmse:0.25898 validation_1-rmse:0.23437 +[10] validation_0-rmse:0.25517 validation_1-rmse:0.23021 +[11] validation_0-rmse:0.25113 validation_1-rmse:0.22639 +[12] validation_0-rmse:0.24762 validation_1-rmse:0.22270 +[13] validation_0-rmse:0.24393 validation_1-rmse:0.21915 +[14] validation_0-rmse:0.24169 validation_1-rmse:0.21579 +[15] validation_0-rmse:0.23898 validation_1-rmse:0.21236 +[16] validation_0-rmse:0.23539 validation_1-rmse:0.20924 +[17] validation_0-rmse:0.23364 validation_1-rmse:0.20621 +[18] validation_0-rmse:0.23062 validation_1-rmse:0.20322 +[19] validation_0-rmse:0.22764 validation_1-rmse:0.20024 +[20] validation_0-rmse:0.22488 validation_1-rmse:0.19731 +[21] validation_0-rmse:0.22211 validation_1-rmse:0.19445 +[22] validation_0-rmse:0.21952 validation_1-rmse:0.19188 +[23] validation_0-rmse:0.21699 validation_1-rmse:0.18935 +[24] validation_0-rmse:0.21549 validation_1-rmse:0.18686 +[25] validation_0-rmse:0.21310 validation_1-rmse:0.18454 +[26] validation_0-rmse:0.21118 validation_1-rmse:0.18198 +[27] validation_0-rmse:0.20904 validation_1-rmse:0.17979 +[28] validation_0-rmse:0.20726 validation_1-rmse:0.17755 +[29] validation_0-rmse:0.20511 validation_1-rmse:0.17547 +[30] validation_0-rmse:0.20336 validation_1-rmse:0.17335 +[31] validation_0-rmse:0.20172 validation_1-rmse:0.17144 +[32] validation_0-rmse:0.19983 validation_1-rmse:0.16961 +[33] validation_0-rmse:0.19794 validation_1-rmse:0.16759 +[34] validation_0-rmse:0.19658 validation_1-rmse:0.16581 +[35] validation_0-rmse:0.19492 validation_1-rmse:0.16409 +[36] validation_0-rmse:0.19347 validation_1-rmse:0.16229 +[37] validation_0-rmse:0.19225 validation_1-rmse:0.16064 +[38] validation_0-rmse:0.19083 validation_1-rmse:0.15877 +[39] validation_0-rmse:0.18921 validation_1-rmse:0.15720 +[40] validation_0-rmse:0.18766 validation_1-rmse:0.15572 +[41] validation_0-rmse:0.18652 validation_1-rmse:0.15414 +[42] validation_0-rmse:0.18519 validation_1-rmse:0.15277 +[43] validation_0-rmse:0.18396 validation_1-rmse:0.15125 +[44] validation_0-rmse:0.18264 validation_1-rmse:0.14968 +[45] validation_0-rmse:0.18134 validation_1-rmse:0.14841 +[46] validation_0-rmse:0.18026 validation_1-rmse:0.14717 +[47] validation_0-rmse:0.17900 validation_1-rmse:0.14594 +[48] validation_0-rmse:0.17815 validation_1-rmse:0.14460 +[49] validation_0-rmse:0.17713 validation_1-rmse:0.14344 +[50] validation_0-rmse:0.17609 validation_1-rmse:0.14232 +[51] validation_0-rmse:0.17502 validation_1-rmse:0.14112 +[52] validation_0-rmse:0.17414 validation_1-rmse:0.13991 +[53] validation_0-rmse:0.17317 validation_1-rmse:0.13889 +[54] validation_0-rmse:0.17267 validation_1-rmse:0.13770 +[55] validation_0-rmse:0.17175 validation_1-rmse:0.13665 +[56] validation_0-rmse:0.17087 validation_1-rmse:0.13573 +[57] validation_0-rmse:0.17001 validation_1-rmse:0.13483 +[58] validation_0-rmse:0.16920 validation_1-rmse:0.13384 +[59] validation_0-rmse:0.16869 validation_1-rmse:0.13280 +[60] validation_0-rmse:0.16790 validation_1-rmse:0.13189 +[61] validation_0-rmse:0.16689 validation_1-rmse:0.13093 +[62] validation_0-rmse:0.16600 validation_1-rmse:0.13007 +[63] validation_0-rmse:0.16548 validation_1-rmse:0.12921 +[64] validation_0-rmse:0.16482 validation_1-rmse:0.12837 +[65] validation_0-rmse:0.16397 validation_1-rmse:0.12747 +[66] validation_0-rmse:0.16316 validation_1-rmse:0.12669 +[67] validation_0-rmse:0.16267 validation_1-rmse:0.12587 +[68] validation_0-rmse:0.16204 validation_1-rmse:0.12501 +[69] validation_0-rmse:0.16159 validation_1-rmse:0.12422 +[70] validation_0-rmse:0.16090 validation_1-rmse:0.12354 +[71] validation_0-rmse:0.16026 validation_1-rmse:0.12282 +[72] validation_0-rmse:0.15986 validation_1-rmse:0.12206 +[73] validation_0-rmse:0.15919 validation_1-rmse:0.12129 +[74] validation_0-rmse:0.15875 validation_1-rmse:0.12061 +[75] validation_0-rmse:0.15829 validation_1-rmse:0.11966 +[76] validation_0-rmse:0.15790 validation_1-rmse:0.11864 +[77] validation_0-rmse:0.15732 validation_1-rmse:0.11802 +[78] validation_0-rmse:0.15696 validation_1-rmse:0.11739 +[79] validation_0-rmse:0.15615 validation_1-rmse:0.11660 +[80] validation_0-rmse:0.15556 validation_1-rmse:0.11593 +[81] validation_0-rmse:0.15516 validation_1-rmse:0.11531 +[82] validation_0-rmse:0.15466 validation_1-rmse:0.11437 +[83] validation_0-rmse:0.15422 validation_1-rmse:0.11383 +[84] validation_0-rmse:0.15382 validation_1-rmse:0.11332 +[85] validation_0-rmse:0.15350 validation_1-rmse:0.11244 +[86] validation_0-rmse:0.15310 validation_1-rmse:0.11180 +[87] validation_0-rmse:0.15277 validation_1-rmse:0.11119 +[88] validation_0-rmse:0.15228 validation_1-rmse:0.11060 +[89] validation_0-rmse:0.15192 validation_1-rmse:0.11011 +[90] validation_0-rmse:0.15144 validation_1-rmse:0.10956 +[91] validation_0-rmse:0.15092 validation_1-rmse:0.10913 +[92] validation_0-rmse:0.15058 validation_1-rmse:0.10847 +[93] validation_0-rmse:0.15017 validation_1-rmse:0.10803 +[94] validation_0-rmse:0.14984 validation_1-rmse:0.10702 +[95] validation_0-rmse:0.14967 validation_1-rmse:0.10629 +[96] validation_0-rmse:0.14914 validation_1-rmse:0.10587 +[97] validation_0-rmse:0.14882 validation_1-rmse:0.10545 +[98] validation_0-rmse:0.14853 validation_1-rmse:0.10454 +[99] validation_0-rmse:0.14837 validation_1-rmse:0.10398 +2025-04-29 01:57:30,474 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.12 secs) -------------------- +2025-04-29 01:57:30,475 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:31,077 - FreqaiExampleStrategy - INFO - 动态参数：buy_rsi=50.0, sell_rsi=70.0, stoploss=-0.15, trailing_stop_positive=0.05 +2025-04-29 01:57:31,096 - FreqaiExampleStrategy - INFO - up_or_down 值统计： +up_or_down +0 33825 +1 32946 +2025-04-29 01:57:31,097 - FreqaiExampleStrategy - INFO - do_predict 值统计： +do_predict +0.0 36730 +1.0 30041 +2025-04-29 01:57:31,105 - freqtrade.optimize.backtesting - INFO - Backtesting with data from 2025-01-01 00:00:00 up to 2025-04-20 00:00:00 (109 days). +2025-04-29 01:57:31,109 - FreqaiExampleStrategy - ERROR - MACD 或 MACD 信号列缺失，无法生成买入信号。尝试重新计算 MACD 列。 +2025-04-29 01:57:31,111 - FreqaiExampleStrategy - INFO - MACD 列已成功重新计算。 +2025-04-29 01:57:31,193 - FreqaiExampleStrategy - ERROR - MACD 或 MACD 信号列缺失，无法生成买入信号。尝试重新计算 MACD 列。 +2025-04-29 01:57:31,195 - FreqaiExampleStrategy - INFO - MACD 列已成功重新计算。 +2025-04-29 01:57:33,776 - freqtrade.misc - INFO - dumping json to "/freqtrade/user_data/backtest_results/backtest-result-2025-04-29_01-57-33.meta.json" +Result for strategy FreqaiExampleStrategy + BACKTESTING REPORT +┏━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Pair ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ BTC/USDT │ 38 │ -0.39 │ -22.029 │ -2.2 │ 22:13:00 │ 5 32 1 13.2 │ +│ SOL/USDT │ 44 │ -1.94 │ -128.236 │ -12.82 │ 16:35:00 │ 12 26 6 27.3 │ +│ TOTAL │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└──────────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┘ + LEFT OPEN TRADES REPORT +┏━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Pair ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ TOTAL │ 0 │ 0.0 │ 0.000 │ 0.0 │ 0:00 │ 0 0 0 0 │ +└───────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┘ + ENTER TAG STATS +┏━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Enter Tag ┃ Entries ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ long │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +│ TOTAL │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└───────────┴─────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┘ + EXIT REASON STATS +┏━━━━━━━━━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Exit Reason ┃ Exits ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━━━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ roi │ 75 │ 0.07 │ 7.926 │ 0.79 │ 14:48:00 │ 17 58 0 100 │ +│ trailing_stop_loss │ 7 │ -15.04 │ -158.191 │ -15.82 │ 2 days, 18:13:00 │ 0 0 7 0 │ +│ TOTAL │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└────────────────────┴───────┴──────────────┴─────────────────┴──────────────┴──────────────────┴────────────────────────┘ + MIXED TAG STATS +┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Enter Tag ┃ Exit Reason ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ ('long', 'roi') │ │ 75 │ 0.07 │ 7.926 │ 0.79 │ 14:48:00 │ 17 58 0 100 │ +│ ('long', 'trailing_stop_loss') │ │ 7 │ -15.04 │ -158.191 │ -15.82 │ 2 days, 18:13:00 │ 0 0 7 0 │ +│ TOTAL │ │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└────────────────────────────────┴─────────────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────────┴────────────────────────┘ + SUMMARY METRICS +┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┓ +┃ Metric ┃ Value ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━┩ +│ Backtesting from │ 2025-01-01 00:00:00 │ +│ Backtesting to │ 2025-04-20 00:00:00 │ +│ Trading Mode │ Spot │ +│ Max open trades │ 2 │ +│ │ │ +│ Total/Daily Avg Trades │ 82 / 0.75 │ +│ Starting balance │ 1000 USDT │ +│ Final balance │ 849.735 USDT │ +│ Absolute profit │ -150.265 USDT │ +│ Total profit % │ -15.03% │ +│ CAGR % │ -42.03% │ +│ Sortino │ -252.56 │ +│ Sharpe │ -4.15 │ +│ Calmar │ -17.48 │ +│ SQN │ -2.60 │ +│ Profit factor │ 0.05 │ +│ Expectancy (Ratio) │ -1.83 (-0.79) │ +│ Avg. daily profit % │ -0.14% │ +│ Avg. stake amount │ 150 USDT │ +│ Total trade volume │ 24523.15 USDT │ +│ │ │ +│ Best Pair │ BTC/USDT -2.20% │ +│ Worst Pair │ SOL/USDT -12.82% │ +│ Best trade │ SOL/USDT 0.90% │ +│ Worst trade │ SOL/USDT -15.19% │ +│ Best day │ 1.76 USDT │ +│ Worst day │ -22.827 USDT │ +│ Days win/draw/lose │ 14 / 80 / 7 │ +│ Avg. Duration Winners │ 0:55:00 │ +│ Avg. Duration Loser │ 2 days, 18:13:00 │ +│ Max Consecutive Wins / Loss │ 2 / 16 │ +│ Rejected Entry signals │ 0 │ +│ Entry/Exit Timeouts │ 0 / 0 │ +│ │ │ +│ Min balance │ 849.735 USDT │ +│ Max balance │ 1000.508 USDT │ +│ Max % of account underwater │ 15.07% │ +│ Absolute Drawdown (Account) │ 15.07% │ +│ Absolute Drawdown │ 150.773 USDT │ +│ Drawdown high │ 0.508 USDT │ +│ Drawdown low │ -150.265 USDT │ +│ Drawdown Start │ 2025-01-06 19:48:00 │ +│ Drawdown End │ 2025-04-06 23:15:00 │ +│ Market change │ -26.79% │ +└─────────────────────────────┴─────────────────────┘ + +Backtested 2025-01-01 00:00:00 -> 2025-04-20 00:00:00 | Max open trades : 2 + STRATEGY SUMMARY +┏━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Strategy ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ Drawdown ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━┩ +│ FreqaiExampleStrategy │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ 150.773 USDT 15.07% │ +└───────────────────────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┴──────────────────────┘ diff --git a/freqtrade/templates/FreqaiExampleHybridStrategy.py b/freqtrade/templates/FreqaiExampleHybridStrategy.py deleted file mode 100644 index 908c4b17..00000000 --- a/freqtrade/templates/FreqaiExampleHybridStrategy.py +++ /dev/null @@ -1,320 +0,0 @@ -import logging - -import numpy as np # noqa -import pandas as pd # noqa -import talib.abstract as ta -from pandas import DataFrame -from technical import qtpylib - -from freqtrade.strategy import IntParameter, IStrategy, merge_informative_pair # noqa - - -logger = logging.getLogger(__name__) - - -class FreqaiExampleHybridStrategy(IStrategy): - """ - Example of a hybrid FreqAI strat, designed to illustrate how a user may employ - FreqAI to bolster a typical Freqtrade strategy. - - Launching this strategy would be: - - freqtrade trade --strategy FreqaiExampleHybridStrategy --strategy-path freqtrade/templates - --freqaimodel CatboostClassifier --config config_examples/config_freqai.example.json - - or the user simply adds this to their config: - - "freqai": { - "enabled": true, - "purge_old_models": 2, - "train_period_days": 15, - "identifier": "unique-id", - "feature_parameters": { - "include_timeframes": [ - "3m", - "15m", - "1h" - ], - "include_corr_pairlist": [ - "BTC/USDT", - "ETH/USDT" - ], - "label_period_candles": 20, - "include_shifted_candles": 2, - "DI_threshold": 0.9, - "weight_factor": 0.9, - "principal_component_analysis": false, - "use_SVM_to_remove_outliers": true, - "indicator_periods_candles": [10, 20] - }, - "data_split_parameters": { - "test_size": 0, - "random_state": 1 - }, - "model_training_parameters": { - "n_estimators": 800 - } - }, - - Thanks to @smarmau and @johanvulgt for developing and sharing the strategy. - """ - - minimal_roi = { - # "120": 0.0, # exit after 120 minutes at break even - "60": 0.01, - "30": 0.02, - "0": 0.04, - } - - plot_config = { - "main_plot": { - "tema": {}, - }, - "subplots": { - "MACD": { - "macd": {"color": "blue"}, - "macdsignal": {"color": "orange"}, - }, - "RSI": { - "rsi": {"color": "red"}, - }, - "Up_or_down": { - "&s-up_or_down": {"color": "green"}, - }, - }, - } - - process_only_new_candles = True - stoploss = -0.05 - use_exit_signal = True - startup_candle_count: int = 30 - can_short = True - - # Hyperoptable parameters - buy_rsi = IntParameter(low=1, high=50, default=30, space="buy", optimize=True, load=True) - sell_rsi = IntParameter(low=50, high=100, default=70, space="sell", optimize=True, load=True) - short_rsi = IntParameter(low=51, high=100, default=70, space="sell", optimize=True, load=True) - exit_short_rsi = IntParameter(low=1, high=50, default=30, space="buy", optimize=True, load=True) - - def feature_engineering_expand_all( - self, dataframe: DataFrame, period: int, metadata: dict, **kwargs - ) -> DataFrame: - """ - *Only functional with FreqAI enabled strategies* - This function will automatically expand the defined features on the config defined - `indicator_periods_candles`, `include_timeframes`, `include_shifted_candles`, and - `include_corr_pairs`. In other words, a single feature defined in this function - will automatically expand to a total of - `indicator_periods_candles` * `include_timeframes` * `include_shifted_candles` * - `include_corr_pairs` numbers of features added to the model. - - All features must be prepended with `%` to be recognized by FreqAI internals. - - More details on how these config defined parameters accelerate feature engineering - in the documentation at: - - https://www.freqtrade.io/en/latest/freqai-parameter-table/#feature-parameters - - https://www.freqtrade.io/en/latest/freqai-feature-engineering/#defining-the-features - - :param dataframe: strategy dataframe which will receive the features - :param period: period of the indicator - usage example: - :param metadata: metadata of current pair - dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period) - """ - - dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period) - dataframe["%-mfi-period"] = ta.MFI(dataframe, timeperiod=period) - dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period) - dataframe["%-sma-period"] = ta.SMA(dataframe, timeperiod=period) - dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period) - - bollinger = qtpylib.bollinger_bands( - qtpylib.typical_price(dataframe), window=period, stds=2.2 - ) - dataframe["bb_lowerband-period"] = bollinger["lower"] - dataframe["bb_middleband-period"] = bollinger["mid"] - dataframe["bb_upperband-period"] = bollinger["upper"] - - dataframe["%-bb_width-period"] = ( - dataframe["bb_upperband-period"] - dataframe["bb_lowerband-period"] - ) / dataframe["bb_middleband-period"] - dataframe["%-close-bb_lower-period"] = dataframe["close"] / dataframe["bb_lowerband-period"] - - dataframe["%-roc-period"] = ta.ROC(dataframe, timeperiod=period) - - dataframe["%-relative_volume-period"] = ( - dataframe["volume"] / dataframe["volume"].rolling(period).mean() - ) - - return dataframe - - def feature_engineering_expand_basic( - self, dataframe: DataFrame, metadata: dict, **kwargs - ) -> DataFrame: - """ - *Only functional with FreqAI enabled strategies* - This function will automatically expand the defined features on the config defined - `include_timeframes`, `include_shifted_candles`, and `include_corr_pairs`. - In other words, a single feature defined in this function - will automatically expand to a total of - `include_timeframes` * `include_shifted_candles` * `include_corr_pairs` - numbers of features added to the model. - - Features defined here will *not* be automatically duplicated on user defined - `indicator_periods_candles` - - All features must be prepended with `%` to be recognized by FreqAI internals. - - More details on how these config defined parameters accelerate feature engineering - in the documentation at: - - https://www.freqtrade.io/en/latest/freqai-parameter-table/#feature-parameters - - https://www.freqtrade.io/en/latest/freqai-feature-engineering/#defining-the-features - - :param dataframe: strategy dataframe which will receive the features - :param metadata: metadata of current pair - dataframe["%-pct-change"] = dataframe["close"].pct_change() - dataframe["%-ema-200"] = ta.EMA(dataframe, timeperiod=200) - """ - dataframe["%-pct-change"] = dataframe["close"].pct_change() - dataframe["%-raw_volume"] = dataframe["volume"] - dataframe["%-raw_price"] = dataframe["close"] - return dataframe - - def feature_engineering_standard( - self, dataframe: DataFrame, metadata: dict, **kwargs - ) -> DataFrame: - """ - *Only functional with FreqAI enabled strategies* - This optional function will be called once with the dataframe of the base timeframe. - This is the final function to be called, which means that the dataframe entering this - function will contain all the features and columns created by all other - freqai_feature_engineering_* functions. - - This function is a good place to do custom exotic feature extractions (e.g. tsfresh). - This function is a good place for any feature that should not be auto-expanded upon - (e.g. day of the week). - - All features must be prepended with `%` to be recognized by FreqAI internals. - - More details about feature engineering available: - - https://www.freqtrade.io/en/latest/freqai-feature-engineering - - :param dataframe: strategy dataframe which will receive the features - :param metadata: metadata of current pair - usage example: dataframe["%-day_of_week"] = (dataframe["date"].dt.dayofweek + 1) / 7 - """ - dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek - dataframe["%-hour_of_day"] = dataframe["date"].dt.hour - return dataframe - - def set_freqai_targets(self, dataframe: DataFrame, metadata: dict, **kwargs) -> DataFrame: - """ - *Only functional with FreqAI enabled strategies* - Required function to set the targets for the model. - All targets must be prepended with `&` to be recognized by the FreqAI internals. - - More details about feature engineering available: - - https://www.freqtrade.io/en/latest/freqai-feature-engineering - - :param dataframe: strategy dataframe which will receive the targets - :param metadata: metadata of current pair - usage example: dataframe["&-target"] = dataframe["close"].shift(-1) / dataframe["close"] - """ - self.freqai.class_names = ["down", "up"] - dataframe["&s-up_or_down"] = np.where( - dataframe["close"].shift(-50) > dataframe["close"], "up", "down" - ) - - return dataframe - - def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame: # noqa: C901 - # User creates their own custom strat here. Present example is a supertrend - # based strategy. - - dataframe = self.freqai.start(dataframe, metadata, self) - - # TA indicators to combine with the Freqai targets - # RSI - dataframe["rsi"] = ta.RSI(dataframe) - - # Bollinger Bands - bollinger = qtpylib.bollinger_bands(qtpylib.typical_price(dataframe), window=20, stds=2) - dataframe["bb_lowerband"] = bollinger["lower"] - dataframe["bb_middleband"] = bollinger["mid"] - dataframe["bb_upperband"] = bollinger["upper"] - dataframe["bb_percent"] = (dataframe["close"] - dataframe["bb_lowerband"]) / ( - dataframe["bb_upperband"] - dataframe["bb_lowerband"] - ) - dataframe["bb_width"] = (dataframe["bb_upperband"] - dataframe["bb_lowerband"]) / dataframe[ - "bb_middleband" - ] - - # TEMA - Triple Exponential Moving Average - dataframe["tema"] = ta.TEMA(dataframe, timeperiod=9) - - return dataframe - - def populate_entry_trend(self, df: DataFrame, metadata: dict) -> DataFrame: - df.loc[ - ( - # Signal: RSI crosses above 30 - (qtpylib.crossed_above(df["rsi"], self.buy_rsi.value)) - & (df["tema"] <= df["bb_middleband"]) # Guard: tema below BB middle - & (df["tema"] > df["tema"].shift(1)) # Guard: tema is raising - & (df["volume"] > 0) # Make sure Volume is not 0 - & (df["do_predict"] == 1) # Make sure Freqai is confident in the prediction - & - # Only enter trade if Freqai thinks the trend is in this direction - (df["&s-up_or_down"] == "up") - ), - "enter_long", - ] = 1 - - df.loc[ - ( - # Signal: RSI crosses above 70 - (qtpylib.crossed_above(df["rsi"], self.short_rsi.value)) - & (df["tema"] > df["bb_middleband"]) # Guard: tema above BB middle - & (df["tema"] < df["tema"].shift(1)) # Guard: tema is falling - & (df["volume"] > 0) # Make sure Volume is not 0 - & (df["do_predict"] == 1) # Make sure Freqai is confident in the prediction - & - # Only enter trade if Freqai thinks the trend is in this direction - (df["&s-up_or_down"] == "down") - ), - "enter_short", - ] = 1 - - return df - - def populate_exit_trend(self, df: DataFrame, metadata: dict) -> DataFrame: - df.loc[ - ( - # Signal: RSI crosses above 70 - (qtpylib.crossed_above(df["rsi"], self.sell_rsi.value)) - & (df["tema"] > df["bb_middleband"]) # Guard: tema above BB middle - & (df["tema"] < df["tema"].shift(1)) # Guard: tema is falling - & (df["volume"] > 0) # Make sure Volume is not 0 - ), - "exit_long", - ] = 1 - - df.loc[ - ( - # Signal: RSI crosses above 30 - (qtpylib.crossed_above(df["rsi"], self.exit_short_rsi.value)) - & - # Guard: tema below BB middle - (df["tema"] <= df["bb_middleband"]) - & (df["tema"] > df["tema"].shift(1)) # Guard: tema is raising - & (df["volume"] > 0) # Make sure Volume is not 0 - ), - "exit_short", - ] = 1 - - return df diff --git a/freqtrade/templates/FreqaiExampleStrategy.json b/freqtrade/templates/FreqaiExampleStrategy.json new file mode 100644 index 00000000..98ffab5a --- /dev/null +++ b/freqtrade/templates/FreqaiExampleStrategy.json @@ -0,0 +1,32 @@ +{ + "strategy_name": "FreqaiExampleStrategy", + "params": { + "max_open_trades": { + "max_open_trades": 4 + }, + "buy": { + "buy_rsi": 39.92672300850069 + }, + "sell": { + "sell_rsi": 69.92672300850069 + }, + "protection": {}, + "roi": { + "0": 0.163, + "8": 0.049, + "16": 0.007, + "66": 0 + }, + "stoploss": { + "stoploss": -0.251 + }, + "trailing": { + "trailing_stop": true, + "trailing_stop_positive": 0.055, + "trailing_stop_positive_offset": 0.11699999999999999, + "trailing_only_offset_is_reached": true + } + }, + "ft_stratparam_v": 1, + "export_time": "2025-05-17 10:15:19.962889+00:00" +} \ No newline at end of file diff --git a/freqtrade/templates/FreqaiExampleStrategy.py b/freqtrade/templates/FreqaiExampleStrategy.py index a627b1ef..c620a9a6 100644 --- a/freqtrade/templates/FreqaiExampleStrategy.py +++ b/freqtrade/templates/FreqaiExampleStrategy.py @@ -1,293 +1,277 @@ import logging +import numpy as np from functools import reduce - import talib.abstract as ta from pandas import DataFrame from technical import qtpylib - -from freqtrade.strategy import IStrategy - +from freqtrade.strategy import IStrategy, IntParameter, DecimalParameter logger = logging.getLogger(__name__) - class FreqaiExampleStrategy(IStrategy): - """ - Example strategy showing how the user connects their own - IFreqaiModel to the strategy. + minimal_roi = { + 0: 0.135, + 9: 0.052, + 15: 0.007, + 60: 0 + } + stoploss = -0.263 + trailing_stop = True + trailing_stop_positive = 0.324 + trailing_stop_positive_offset = 0.411 + trailing_only_offset_is_reached = False + max_open_trades = 4 + process_only_new_candles = True + use_exit_signal = True + startup_candle_count: int = 40 + can_short = False - Warning! This is a showcase of functionality, - which means that it is designed to show various functions of FreqAI - and it runs on all computers. We use this showcase to help users - understand how to build a strategy, and we use it as a benchmark - to help debug possible problems. + buy_rsi = IntParameter(low=10, high=50, default=30, space="buy", optimize=False, load=True) + sell_rsi = IntParameter(low=50, high=90, default=70, space="sell", optimize=False, load=True) + roi_0 = DecimalParameter(low=0.01, high=0.2, default=0.135, space="roi", optimize=True, load=True) + roi_15 = DecimalParameter(low=0.005, high=0.1, default=0.052, space="roi", optimize=True, load=True) + roi_30 = DecimalParameter(low=0.001, high=0.05, default=0.007, space="roi", optimize=True, load=True) + stoploss_param = DecimalParameter(low=-0.35, high=-0.1, default=-0.263, space="stoploss", optimize=True, load=True) + trailing_stop_positive_param = DecimalParameter(low=0.1, high=0.5, default=0.324, space="trailing", optimize=True, load=True) + trailing_stop_positive_offset_param = DecimalParameter(low=0.2, high=0.6, default=0.411, space="trailing", optimize=True, load=True) - This means this is *not* meant to be run live in production. - """ - - minimal_roi = {"0": 0.1, "240": -1} + freqai_info = { + "model": "LightGBMRegressor", + "feature_parameters": { + "include_timeframes": ["5m", "15m", "1h"], + "include_corr_pairlist": [], + "label_period_candles": 12, + "include_shifted_candles": 3, + }, + "data_split_parameters": { + "test_size": 0.2, + "shuffle": False, + }, + "model_training_parameters": { + "n_estimators": 200, + "learning_rate": 0.05, + "num_leaves": 31, + "verbose": -1, + }, + } plot_config = { "main_plot": {}, "subplots": { - "&-s_close": {"&-s_close": {"color": "blue"}}, - "do_predict": { - "do_predict": {"color": "brown"}, - }, + "&-buy_rsi": {"&-buy_rsi": {"color": "green"}}, + "&-sell_rsi": {"&-sell_rsi": {"color": "red"}}, + "&-stoploss": {"&-stoploss": {"color": "purple"}}, + "&-roi_0": {"&-roi_0": {"color": "orange"}}, + "do_predict": {"do_predict": {"color": "brown"}}, }, } - process_only_new_candles = True - stoploss = -0.05 - use_exit_signal = True - # this is the maximum period fed to talib (timeframe independent) - startup_candle_count: int = 40 - can_short = False - - def feature_engineering_expand_all( - self, dataframe: DataFrame, period: int, metadata: dict, **kwargs - ) -> DataFrame: - """ - *Only functional with FreqAI enabled strategies* - This function will automatically expand the defined features on the config defined - `indicator_periods_candles`, `include_timeframes`, `include_shifted_candles`, and - `include_corr_pairs`. In other words, a single feature defined in this function - will automatically expand to a total of - `indicator_periods_candles` * `include_timeframes` * `include_shifted_candles` * - `include_corr_pairs` numbers of features added to the model. - - All features must be prepended with `%` to be recognized by FreqAI internals. - - Access metadata such as the current pair/timeframe with: - - `metadata["pair"]` `metadata["tf"]` - - More details on how these config defined parameters accelerate feature engineering - in the documentation at: - - https://www.freqtrade.io/en/latest/freqai-parameter-table/#feature-parameters - - https://www.freqtrade.io/en/latest/freqai-feature-engineering/#defining-the-features - - :param dataframe: strategy dataframe which will receive the features - :param period: period of the indicator - usage example: - :param metadata: metadata of current pair - dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period) - """ - + def feature_engineering_expand_all(self, dataframe: DataFrame, period: int, metadata: dict, **kwargs) -> DataFrame: dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period) dataframe["%-mfi-period"] = ta.MFI(dataframe, timeperiod=period) - dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period) dataframe["%-sma-period"] = ta.SMA(dataframe, timeperiod=period) dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period) - - bollinger = qtpylib.bollinger_bands( - qtpylib.typical_price(dataframe), window=period, stds=2.2 - ) + dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period) + bollinger = qtpylib.bollinger_bands(qtpylib.typical_price(dataframe), window=period, stds=2.2) dataframe["bb_lowerband-period"] = bollinger["lower"] dataframe["bb_middleband-period"] = bollinger["mid"] dataframe["bb_upperband-period"] = bollinger["upper"] - dataframe["%-bb_width-period"] = ( dataframe["bb_upperband-period"] - dataframe["bb_lowerband-period"] ) / dataframe["bb_middleband-period"] dataframe["%-close-bb_lower-period"] = dataframe["close"] / dataframe["bb_lowerband-period"] - dataframe["%-roc-period"] = ta.ROC(dataframe, timeperiod=period) - dataframe["%-relative_volume-period"] = ( dataframe["volume"] / dataframe["volume"].rolling(period).mean() ) - + dataframe = dataframe.replace([np.inf, -np.inf], 0) + dataframe = dataframe.ffill() + dataframe = dataframe.fillna(0) return dataframe - def feature_engineering_expand_basic( - self, dataframe: DataFrame, metadata: dict, **kwargs - ) -> DataFrame: - """ - *Only functional with FreqAI enabled strategies* - This function will automatically expand the defined features on the config defined - `include_timeframes`, `include_shifted_candles`, and `include_corr_pairs`. - In other words, a single feature defined in this function - will automatically expand to a total of - `include_timeframes` * `include_shifted_candles` * `include_corr_pairs` - numbers of features added to the model. - - Features defined here will *not* be automatically duplicated on user defined - `indicator_periods_candles` - - All features must be prepended with `%` to be recognized by FreqAI internals. - - Access metadata such as the current pair/timeframe with: - - `metadata["pair"]` `metadata["tf"]` - - More details on how these config defined parameters accelerate feature engineering - in the documentation at: - - https://www.freqtrade.io/en/latest/freqai-parameter-table/#feature-parameters - - https://www.freqtrade.io/en/latest/freqai-feature-engineering/#defining-the-features - - :param dataframe: strategy dataframe which will receive the features - :param metadata: metadata of current pair - dataframe["%-pct-change"] = dataframe["close"].pct_change() - dataframe["%-ema-200"] = ta.EMA(dataframe, timeperiod=200) - """ + def feature_engineering_expand_basic(self, dataframe: DataFrame, metadata: dict, **kwargs) -> DataFrame: dataframe["%-pct-change"] = dataframe["close"].pct_change() dataframe["%-raw_volume"] = dataframe["volume"] dataframe["%-raw_price"] = dataframe["close"] + dataframe = dataframe.replace([np.inf, -np.inf], 0) + dataframe = dataframe.ffill() + dataframe = dataframe.fillna(0) return dataframe - def feature_engineering_standard( - self, dataframe: DataFrame, metadata: dict, **kwargs - ) -> DataFrame: - """ - *Only functional with FreqAI enabled strategies* - This optional function will be called once with the dataframe of the base timeframe. - This is the final function to be called, which means that the dataframe entering this - function will contain all the features and columns created by all other - freqai_feature_engineering_* functions. - - This function is a good place to do custom exotic feature extractions (e.g. tsfresh). - This function is a good place for any feature that should not be auto-expanded upon - (e.g. day of the week). - - All features must be prepended with `%` to be recognized by FreqAI internals. - - Access metadata such as the current pair with: - - `metadata["pair"]` - - More details about feature engineering available: - - https://www.freqtrade.io/en/latest/freqai-feature-engineering - - :param dataframe: strategy dataframe which will receive the features - :param metadata: metadata of current pair - usage example: dataframe["%-day_of_week"] = (dataframe["date"].dt.dayofweek + 1) / 7 - """ + def feature_engineering_standard(self, dataframe: DataFrame, metadata: dict, **kwargs) -> DataFrame: + if len(dataframe["close"]) < 20: + logger.warning(f"数据不足 {len(dataframe)} 根 K 线，%-volatility 可能不完整") dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek dataframe["%-hour_of_day"] = dataframe["date"].dt.hour + dataframe["%-volatility"] = dataframe["close"].pct_change().rolling(20, min_periods=1).std() + dataframe["%-volatility"] = dataframe["%-volatility"].replace([np.inf, -np.inf], 0) + dataframe["%-volatility"] = dataframe["%-volatility"].ffill() + dataframe["%-volatility"] = dataframe["%-volatility"].fillna(0) return dataframe def set_freqai_targets(self, dataframe: DataFrame, metadata: dict, **kwargs) -> DataFrame: - """ - *Only functional with FreqAI enabled strategies* - Required function to set the targets for the model. - All targets must be prepended with `&` to be recognized by the FreqAI internals. + logger.info(f"设置 FreqAI 目标，交易对：{metadata['pair']}") + if "close" not in dataframe.columns: + logger.error("数据框缺少必要的 'close' 列") + raise ValueError("数据框缺少必要的 'close' 列") - Access metadata such as the current pair with: + try: + label_period = self.freqai_info["feature_parameters"]["label_period_candles"] + if "%-volatility" not in dataframe.columns: + logger.warning("缺少 %-volatility 列，强制重新生成") + dataframe["%-volatility"] = dataframe["close"].pct_change().rolling(20, min_periods=1).std() + dataframe["%-volatility"] = dataframe["%-volatility"].replace([np.inf, -np.inf], 0) + dataframe["%-volatility"] = dataframe["%-volatility"].ffill() + dataframe["%-volatility"] = dataframe["%-volatility"].fillna(0) - `metadata["pair"]` + dataframe["&-buy_rsi"] = ta.RSI(dataframe, timeperiod=14) + dataframe["&-buy_rsi"] = dataframe["&-buy_rsi"].shift(-label_period).ffill().bfill() - More details about feature engineering available: - - https://www.freqtrade.io/en/latest/freqai-feature-engineering - - :param dataframe: strategy dataframe which will receive the targets - :param metadata: metadata of current pair - usage example: dataframe["&-target"] = dataframe["close"].shift(-1) / dataframe["close"] - """ - dataframe["&-s_close"] = ( - dataframe["close"] - .shift(-self.freqai_info["feature_parameters"]["label_period_candles"]) - .rolling(self.freqai_info["feature_parameters"]["label_period_candles"]) - .mean() - / dataframe["close"] - - 1 - ) - - # Classifiers are typically set up with strings as targets: - # df['&s-up_or_down'] = np.where( df["close"].shift(-100) > - # df["close"], 'up', 'down') - - # If user wishes to use multiple targets, they can add more by - # appending more columns with '&'. User should keep in mind that multi targets - # requires a multioutput prediction model such as - # freqai/prediction_models/CatboostRegressorMultiTarget.py, - # freqtrade trade --freqaimodel CatboostRegressorMultiTarget - - # df["&-s_range"] = ( - # df["close"] - # .shift(-self.freqai_info["feature_parameters"]["label_period_candles"]) - # .rolling(self.freqai_info["feature_parameters"]["label_period_candles"]) - # .max() - # - - # df["close"] - # .shift(-self.freqai_info["feature_parameters"]["label_period_candles"]) - # .rolling(self.freqai_info["feature_parameters"]["label_period_candles"]) - # .min() - # ) + for col in ["&-buy_rsi", "%-volatility"]: + dataframe[col] = dataframe[col].replace([np.inf, -np.inf], 0) + dataframe[col] = dataframe[col].ffill() + dataframe[col] = dataframe[col].fillna(0) + if dataframe[col].isna().any(): + logger.warning(f"目标列 {col} 仍包含 NaN，数据预览：\n{dataframe[col].tail(10)}") + except Exception as e: + logger.error(f"创建 FreqAI 目标失败：{str(e)}") + raise + logger.info(f"目标列预览：\n{dataframe[['&-buy_rsi']].head().to_string()}") return dataframe def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame: - # All indicators must be populated by feature_engineering_*() functions - - # the model will return all labels created by user in `set_freqai_targets()` - # (& appended targets), an indication of whether or not the prediction should be accepted, - # the target mean/std values for each of the labels created by user in - # `set_freqai_targets()` for each training period. - + logger.info(f"处理交易对：{metadata['pair']}") + logger.debug(f"输入特征列：{list(dataframe.columns)}") dataframe = self.freqai.start(dataframe, metadata, self) + logger.debug(f"FreqAI 输出特征列：{list(dataframe.columns)}") + + dataframe["rsi"] = ta.RSI(dataframe, timeperiod=14) + bollinger = qtpylib.bollinger_bands(qtpylib.typical_price(dataframe), window=20, stds=2) + dataframe["bb_lowerband"] = bollinger["lower"] + dataframe["bb_middleband"] = bollinger["mid"] + dataframe["bb_upperband"] = bollinger["upper"] + dataframe["tema"] = ta.TEMA(dataframe, timeperiod=9) + + label_period = self.freqai_info["feature_parameters"]["label_period_candles"] + dataframe["up_or_down"] = np.where( + dataframe["close"].shift(-label_period) > dataframe["close"], 1, 0 + ) + + if "&-buy_rsi" in dataframe.columns: + if "%-volatility" not in dataframe.columns: + logger.warning("缺少 %-volatility 列，强制重新生成") + dataframe["%-volatility"] = dataframe["close"].pct_change().rolling(20, min_periods=1).std() + dataframe["%-volatility"] = dataframe["%-volatility"].replace([np.inf, -np.inf], 0) + dataframe["%-volatility"] = dataframe["%-volatility"].ffill() + dataframe["%-volatility"] = dataframe["%-volatility"].fillna(0) + + dataframe["&-sell_rsi"] = dataframe["&-buy_rsi"] + 30 + dataframe["&-stoploss"] = self.stoploss - (dataframe["%-volatility"] * 5).clip(-0.05, 0.05) + dataframe["&-roi_0"] = (dataframe["close"].shift(-label_period) / dataframe["close"] - 1).clip(0, 0.2) + + for col in ["&-buy_rsi", "&-sell_rsi", "&-stoploss", "&-roi_0"]: + dataframe[col] = dataframe[col].replace([np.inf, -np.inf], 0) + dataframe[col] = dataframe[col].ffill() + dataframe[col] = dataframe[col].fillna(0) + + dataframe["buy_rsi_pred"] = dataframe["&-buy_rsi"].rolling(5).mean().clip(10, 50) + dataframe["sell_rsi_pred"] = dataframe["&-sell_rsi"].rolling(5).mean().clip(50, 90) + dataframe["stoploss_pred"] = dataframe["&-stoploss"].clip(-0.35, -0.1) + dataframe["roi_0_pred"] = dataframe["&-roi_0"].clip(0.01, 0.2) + + for col in ["buy_rsi_pred", "sell_rsi_pred", "stoploss_pred", "roi_0_pred"]: + if dataframe[col].isna().any(): + logger.warning(f"列 {col} 包含 NaN，填充为默认值") + dataframe[col] = dataframe[col].ffill() + dataframe[col] = dataframe[col].fillna(dataframe[col].mean()) + + dataframe["trailing_stop_positive"] = (dataframe["roi_0_pred"] * 0.5).clip(0.01, 0.3) + dataframe["trailing_stop_positive_offset"] = (dataframe["roi_0_pred"] * 0.75).clip(0.02, 0.4) + + self.buy_rsi.value = float(dataframe["buy_rsi_pred"].iloc[-1]) + self.sell_rsi.value = float(dataframe["sell_rsi_pred"].iloc[-1]) + self.stoploss = float(self.stoploss_param.value) + self.minimal_roi = { + 0: float(self.roi_0.value), + 15: float(self.roi_15.value), + 30: float(self.roi_30.value), + 60: 0 + } + self.trailing_stop_positive = float(self.trailing_stop_positive_param.value) + self.trailing_stop_positive_offset = float(self.trailing_stop_positive_offset_param.value) + + logger.info(f"动态参数：buy_rsi={self.buy_rsi.value}, sell_rsi={self.sell_rsi.value}, " + f"stoploss={self.stoploss}, trailing_stop_positive={self.trailing_stop_positive}") + else: + logger.warning(f"&-buy_rsi 列缺失，跳过 FreqAI 预测逻辑，检查 freqai.start 输出") + + dataframe = dataframe.replace([np.inf, -np.inf], 0) + dataframe = dataframe.ffill() + dataframe = dataframe.fillna(0) + + logger.info(f"up_or_down 值统计：\n{dataframe['up_or_down'].value_counts().to_string()}") + logger.info(f"do_predict 值统计：\n{dataframe['do_predict'].value_counts().to_string()}") + logger.debug(f"最终特征列：{list(dataframe.columns)}") return dataframe def populate_entry_trend(self, df: DataFrame, metadata: dict) -> DataFrame: enter_long_conditions = [ + qtpylib.crossed_above(df["rsi"], df["buy_rsi_pred"]), + df["tema"] > df["tema"].shift(1), + df["volume"] > 0, df["do_predict"] == 1, - df["&-s_close"] > 0.01, + df["up_or_down"] == 1 ] - if enter_long_conditions: df.loc[ - reduce(lambda x, y: x & y, enter_long_conditions), ["enter_long", "enter_tag"] + reduce(lambda x, y: x & y, enter_long_conditions), + ["enter_long", "enter_tag"] ] = (1, "long") - - enter_short_conditions = [ - df["do_predict"] == 1, - df["&-s_close"] < -0.01, - ] - - if enter_short_conditions: - df.loc[ - reduce(lambda x, y: x & y, enter_short_conditions), ["enter_short", "enter_tag"] - ] = (1, "short") - return df def populate_exit_trend(self, df: DataFrame, metadata: dict) -> DataFrame: - exit_long_conditions = [df["do_predict"] == 1, df["&-s_close"] < 0] + exit_long_conditions = [ + qtpylib.crossed_above(df["rsi"], df["sell_rsi_pred"]), + (df["close"] < df["close"].shift(1) * 0.97), + df["volume"] > 0, + df["do_predict"] == 1, + df["up_or_down"] == 0 + ] if exit_long_conditions: - df.loc[reduce(lambda x, y: x & y, exit_long_conditions), "exit_long"] = 1 - - exit_short_conditions = [df["do_predict"] == 1, df["&-s_close"] > 0] - if exit_short_conditions: - df.loc[reduce(lambda x, y: x & y, exit_short_conditions), "exit_short"] = 1 - + df.loc[ + reduce(lambda x, y: x & y, exit_long_conditions), + "exit_long" + ] = 1 return df def confirm_trade_entry( - self, - pair: str, - order_type: str, - amount: float, - rate: float, - time_in_force: str, - current_time, - entry_tag, - side: str, - **kwargs, + self, pair: str, order_type: str, amount: float, rate: float, + time_in_force: str, current_time, entry_tag, side: str, **kwargs ) -> bool: - df, _ = self.dp.get_analyzed_dataframe(pair, self.timeframe) - last_candle = df.iloc[-1].squeeze() - - if side == "long": - if rate > (last_candle["close"] * (1 + 0.0025)): - return False - else: - if rate < (last_candle["close"] * (1 - 0.0025)): + try: + df, _ = self.dp.get_analyzed_dataframe(pair, self.timeframe) + if df is None or df.empty: + logger.warning(f"无法获取 {pair} 的分析数据，拒绝交易") return False - return True + last_candle = df.iloc[-1].squeeze() + if "close" not in last_candle or np.isnan(last_candle["close"]): + logger.warning(f"{pair} 的最新 K 线缺少有效 close 价格，拒绝交易") + return False + + if side == "long": + max_rate = last_candle["close"] * (1 + 0.0025) # 0.25% 滑点阈值 + if rate > max_rate: + logger.debug(f"拒绝 {pair} 的买入，价格 {rate} 超过最大允许价格 {max_rate}") + return False + elif side == "short": + logger.warning(f"{pair} 尝试做空，但策略不支持做空 (can_short={self.can_short})") + return False + + logger.debug(f"确认 {pair} 的交易：side={side}, rate={rate}, close={last_candle['close']}") + return True + except Exception as e: + logger.error(f"确认 {pair} 交易时出错：{str(e)}") + return False diff --git a/freqtrade/templates/TheForceV7.json b/freqtrade/templates/TheForceV7.json new file mode 100644 index 00000000..fcc51e13 --- /dev/null +++ b/freqtrade/templates/TheForceV7.json @@ -0,0 +1,34 @@ +{ + "strategy_name": "TheForceV7", + "params": { + "max_open_trades": { + "max_open_trades": 3 + }, + "buy": { + "adx_buy": 25, + "atr_ratio": 0.005 + }, + "sell": { + "ema_fast_period": 7, + "rsi_sell": 60 + }, + "protection": {}, + "roi": { + "0": 0.23399999999999999, + "32": 0.06, + "91": 0.026, + "195": 0 + }, + "stoploss": { + "stoploss": -0.108 + }, + "trailing": { + "trailing_stop": true, + "trailing_stop_positive": 0.054, + "trailing_stop_positive_offset": 0.12, + "trailing_only_offset_is_reached": false + } + }, + "ft_stratparam_v": 1, + "export_time": "2025-05-17 17:07:27.574446+00:00" +} \ No newline at end of file diff --git a/freqtrade/templates/TheForceV7.py b/freqtrade/templates/TheForceV7.py new file mode 100644 index 00000000..6baa2499 --- /dev/null +++ b/freqtrade/templates/TheForceV7.py @@ -0,0 +1,193 @@ +from freqtrade.strategy import IStrategy +from pandas import DataFrame +import talib.abstract as ta +from typing import Dict, List, Optional, Union +from freqtrade.persistence import Trade +from freqtrade.strategy import CategoricalParameter, DecimalParameter, IntParameter +from datetime import datetime + +class TheForceV7(IStrategy): + # 基础参数 + timeframe = '5m' + use_exit_signal = True + exit_profit_only = False + ignore_roi_if_entry_signal = False + + # # Hyperopt 参数 + # stoploss = DecimalParameter( + # low=-0.3, high=-0.1, default=-0.233, decimals=3, space='`stoploss' + # ) + # profit_threshold_multiplier = DecimalParameter( + # low=0.1, high=1.0, default=0.5, decimals=3, space='stoploss' + # ) + # trailing_stop_multiplier = DecimalParameter( + # low=0.5, high=3.0, default=1.5, decimals=3, space='stoploss' + # ) + + # Hyperopt 参数 + stoploss = DecimalParameter(low=-0.3, high=-0.1, default=-0.233, decimals=3, space='stoploss') + profit_threshold_multiplier = DecimalParameter(low=0.2, high=1.0, default=0.5, decimals=3, space='stoploss') # 扩大范围 + trailing_stop_multiplier = DecimalParameter(low=0.8, high=3.0, default=1.5, decimals=3, space='stoploss') # 扩大范围 + + # Hyperopt 参数 + stoploss = DecimalParameter(-0.3, -0.05, default=-0.15, decimals=3, space='stoploss') + profit_threshold_multiplier = DecimalParameter(0.8, 3.0, default=1.5, decimals=3, space='stoploss') + trailing_stop_multiplier = DecimalParameter(1.5, 6.0, default=3.0, decimals=3, space='stoploss') + adx_buy = DecimalParameter(15, 35, default=25, decimals=0, space='buy') + atr_ratio = DecimalParameter(0.002, 0.01, default=0.005, decimals=3, space='buy') + rsi_sell = DecimalParameter(50, 70, default=60, decimals=0, space='sell') + ema_fast_period = IntParameter(3, 10, default=7, space='sell') + + + @property + def protections(self): + return [ + { + "method": "CooldownPeriod", + "stop_duration_candles": 5 # 卖出后禁止再次买入的K线数 + }, + { + "method": "MaxDrawdown", + "lookback_period_candles": 48, + "trade_limit": 20, + "stop_duration_candles": 4, + "max_allowed_drawdown": 0.2 # 最大允许回撤 20% + }, + { + "method": "StoplossGuard", + "lookback_period_candles": 24, + "trade_limit": 4, # 在 lookback 内最多触发几次止损 + "stop_duration_candles": 2, # 锁定多少根 K 线 + "only_per_pair": False # 是否按币种统计 + }, + { + "method": "LowProfitPairs", + "lookback_period_candles": 6, + "trade_limit": 2, + "stop_duration_candles": 60, + "required_profit": 0.02 + }, + { + "method": "LowProfitPairs", + "lookback_period_candles": 24, + "trade_limit": 4, + "stop_duration_candles": 2, + "required_profit": 0.01 + } + + ] + + def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + # Calculate ATR (14-period, consistent with your code) + + # Store the latest ATR in metadata for the pair + + dataframe['ema200c'] = ta.EMA(dataframe['close'], timeperiod=200) + dataframe['ema50c'] = ta.EMA(dataframe['close'], timeperiod=50) + dataframe['ema20c'] = ta.EMA(dataframe['close'], timeperiod=20) + dataframe['rsi7'] = ta.RSI(dataframe['close'], timeperiod=7) + macd = ta.MACD(dataframe['close']) + dataframe['macd'] = macd[0] + dataframe['macdsignal'] = macd[1] + stoch = ta.STOCH(dataframe['high'], dataframe['low'], dataframe['close'], fastk_period=14, slowk_period=3, slowd_period=3) + dataframe['slowk'] = stoch[0] + dataframe['slowd'] = stoch[1] + dataframe['volvar'] = dataframe['volume'].rolling(window=20).mean() + + dataframe['atr'] = ta.ATR(dataframe, timeperiod=14) + dataframe['adx'] = ta.ADX(dataframe, timeperiod=14) + dataframe['rsi'] = ta.RSI(dataframe, timeperiod=14) + for period in [self.ema_fast_period.value, 21, 50]: + dataframe[f'ema_{period}'] = ta.EMA(dataframe, timeperiod=period) + metadata['latest_atr'] = dataframe['atr'].iloc[-1] + metadata['latest_adx'] = dataframe['adx'].iloc[-1] + + return dataframe + + def crossover(self, series1: DataFrame, series2: DataFrame) -> DataFrame: + """Detects when series1 crosses above series2.""" + return (series1 > series2) & (series1.shift(1) <= series2.shift(1)) + + def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + dataframe.loc[ + (dataframe['close'] > dataframe['ema200c']) & # Relaxed trend + (dataframe['close'] > dataframe['ema50c']) & # Short-term trend + (dataframe['rsi7'] < 50) & # Relaxed RSI + (dataframe['macd'] > 0) & # Relaxed MACD + (dataframe['volume'] > dataframe['volvar'] * 0.5) & # Relaxed volume + (dataframe['adx'] > 21), # Trend strength + 'enter_long' + ] = 1 + + return dataframe + + def populate_exit_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + dataframe.loc[ + ( + (dataframe['slowk'] > 65) | (dataframe['slowd'] > 65) | # Relaxed STOCH + (dataframe['rsi7'] > 70) # Overbought + ) & + (dataframe['close'] < dataframe['ema20c']) & # Trend reversal + (self.crossover(dataframe['macdsignal'], dataframe['macd'])) & # Custom crossover + (dataframe['macd'] < 0), # Downtrend + 'exit_long' + ] = 1 + + return dataframe + + def custom_stoploss(self, pair: str, trade: Trade, current_time: datetime, current_rate: float, current_profit: float, after_fill: bool, **kwargs) -> Optional[float]: + atr = kwargs.get('metadata', {}).get('latest_atr', 0.01 * current_rate) + adx = kwargs.get('metadata', {}).get('latest_adx', 0) + atr_percent = atr / current_rate + profit_threshold = float(self.profit_threshold_multiplier.value) * atr_percent + trailing_stop_distance = float(self.trailing_stop_multiplier.value) * atr_percent + trade_duration = (current_time - trade.open_date).total_seconds() / 3600 + + # 动态调整 + if trade_duration < 3: # 3小时内放宽 + profit_threshold *= 1.5 # 提高触发门槛 + trailing_stop_distance *= 1.5 # 放宽止损距离 + if adx > 35: # 强趋势 + trailing_stop_distance *= 0.5 # 紧跟趋势 + elif adx < 20: # 震荡市场 + trailing_stop_distance *= 2.0 # 放宽止损 + + # ATR 追踪止损 + if adx > 35 and after_fill and current_profit > profit_threshold: + return -trailing_stop_distance + # 固定止损 + elif trade_duration > 1.5 or adx < 20 or current_profit < -0.015: # 1.5小时，震荡，亏损>1.5% + return float(self.stoploss) + return -0.05 # 默认止损收紧 + + @staticmethod + def hyperopt_loss_function(results: DataFrame, trade_count: int, min_date: datetime, max_date: datetime, config: Dict, processed: Dict[str, DataFrame], *args, **kwargs) -> float: + total_profit = results['profit_abs'].sum() + win_rate = len(results[results['profit_abs'] > 0]) / trade_count if trade_count > 0 else 0 + avg_duration = results['trade_duration'].mean() / 60 # 分钟 + loss = -total_profit * win_rate * (1 / (avg_duration + 1)) + return loss + + def custom_stake_amount(self, pair: str, current_time: datetime, current_rate: float, + proposed_stake: float, min_stake: float, max_stake: float, + leverage: float, entry_tag: Optional[str], side: str, + **kwargs) -> float: + dataframe, _ = self.dp.get_analyzed_dataframe(pair, self.timeframe) + if dataframe.empty: + return proposed_stake + + atr = ta.ATR(dataframe, timeperiod=28).iloc[-1] + price_std = dataframe['close'].std() + combined_volatility = atr + price_std + + base_stake = self.wallets.get_total_stake_amount() * 0.0333 # 3.33% risk + base_stake = min(base_stake, 50.0) # Cap at 50 USDT + + risk_factor = 1.0 + if combined_volatility > current_rate * 0.03: # High volatility + risk_factor = 0.3 if pair in ['SOL/USDT', 'OKB/USDT'] else 0.5 + elif combined_volatility < current_rate * 0.01: # Low volatility + risk_factor = 1.2 if pair in ['BTC/USDT', 'ETH/USDT'] else 1.0 + + return base_stake * risk_factor + diff --git a/freqtrade/templates/base_config.json.j2 b/freqtrade/templates/base_config.json.j2 deleted file mode 100644 index 86a717a4..00000000 --- a/freqtrade/templates/base_config.json.j2 +++ /dev/null @@ -1,69 +0,0 @@ -{%set volume_pairlist = '{ - "method": "VolumePairList", - "number_assets": 20, - "sort_key": "quoteVolume", - "min_value": 0, - "refresh_period": 1800 - }' %} -{ - "$schema": "https://schema.freqtrade.io/schema.json", - "max_open_trades": {{ max_open_trades }}, - "stake_currency": "{{ stake_currency }}", - "stake_amount": {{ stake_amount }}, - "tradable_balance_ratio": 0.99, -{{- ('\n "fiat_display_currency": "' + fiat_display_currency + '",') if fiat_display_currency else ''}} -{{- ('\n "timeframe": "' + timeframe + '",') if timeframe else '' }} - "dry_run": {{ dry_run | lower }}, - "dry_run_wallet": 1000, - "cancel_open_orders_on_exit": false, - "trading_mode": "{{ trading_mode }}", - "margin_mode": "{{ margin_mode }}", - "unfilledtimeout": { - "entry": 10, - "exit": 10, - "exit_timeout_count": 0, - "unit": "minutes" - }, - "entry_pricing": { - "price_side": "same", - "use_order_book": true, - "order_book_top": 1, - "price_last_balance": 0.0, - "check_depth_of_market": { - "enabled": false, - "bids_to_ask_delta": 1 - } - }, - "exit_pricing":{ - "price_side": "same", - "use_order_book": true, - "order_book_top": 1 - }, - {{ exchange | indent(4) }}, - "pairlists": [ - {{ volume_pairlist }} - ], - "telegram": { - "enabled": {{ telegram | lower }}, - "token": "{{ telegram_token }}", - "chat_id": "{{ telegram_chat_id }}" - }, - "api_server": { - "enabled": {{ api_server | lower }}, - "listen_ip_address": "{{ api_server_listen_addr | default("127.0.0.1", true) }}", - "listen_port": 8080, - "verbosity": "error", - "enable_openapi": false, - "jwt_secret_key": "{{ api_server_jwt_key }}", - "ws_token": "{{ api_server_ws_token }}", - "CORS_origins": [], - "username": "{{ api_server_username }}", - "password": "{{ api_server_password }}" - }, - "bot_name": "freqtrade", - "initial_state": "running", - "force_entry_enable": false, - "internals": { - "process_throttle_secs": 5 - } -} diff --git a/freqtrade/templates/base_strategy.py.j2 b/freqtrade/templates/base_strategy.py.j2 deleted file mode 100644 index fe577826..00000000 --- a/freqtrade/templates/base_strategy.py.j2 +++ /dev/null @@ -1,179 +0,0 @@ -# pragma pylint: disable=missing-docstring, invalid-name, pointless-string-statement -# flake8: noqa: F401 -# isort: skip_file -# --- Do not remove these imports --- -import numpy as np -import pandas as pd -from datetime import datetime, timedelta, timezone -from pandas import DataFrame -from typing import Dict, Optional, Union, Tuple - -from freqtrade.strategy import ( - IStrategy, - Trade, - Order, - PairLocks, - informative, # @informative decorator - # Hyperopt Parameters - BooleanParameter, - CategoricalParameter, - DecimalParameter, - IntParameter, - RealParameter, - # timeframe helpers - timeframe_to_minutes, - timeframe_to_next_date, - timeframe_to_prev_date, - # Strategy helper functions - merge_informative_pair, - stoploss_from_absolute, - stoploss_from_open, -) - -# -------------------------------- -# Add your lib to import here -import talib.abstract as ta -import pandas_ta as pta -from technical import qtpylib - - -class {{ strategy }}(IStrategy): - """ - This is a strategy template to get you started. - More information in https://www.freqtrade.io/en/latest/strategy-customization/ - - You can: - :return: a Dataframe with all mandatory indicators for the strategies - - Rename the class name (Do not forget to update class_name) - - Add any methods you want to build your strategy - - Add any lib you need to build your strategy - - You must keep: - - the lib in the section "Do not remove these libs" - - the methods: populate_indicators, populate_entry_trend, populate_exit_trend - You should keep: - - timeframe, minimal_roi, stoploss, trailing_* - """ - # Strategy interface version - allow new iterations of the strategy interface. - # Check the documentation or the Sample strategy to get the latest version. - INTERFACE_VERSION = 3 - - # Optimal timeframe for the strategy. - timeframe = "5m" - - # Can this strategy go short? - can_short: bool = False - - # Minimal ROI designed for the strategy. - # This attribute will be overridden if the config file contains "minimal_roi". - minimal_roi = { - "60": 0.01, - "30": 0.02, - "0": 0.04 - } - - # Optimal stoploss designed for the strategy. - # This attribute will be overridden if the config file contains "stoploss". - stoploss = -0.10 - - # Trailing stoploss - trailing_stop = False - # trailing_only_offset_is_reached = False - # trailing_stop_positive = 0.01 - # trailing_stop_positive_offset = 0.0 # Disabled / not configured - - # Run "populate_indicators()" only for new candle. - process_only_new_candles = True - - # These values can be overridden in the config. - use_exit_signal = True - exit_profit_only = False - ignore_roi_if_entry_signal = False - - # Number of candles the strategy requires before producing valid signals - startup_candle_count: int = 30 - - # Strategy parameters - buy_rsi = IntParameter(10, 40, default=30, space="buy") - sell_rsi = IntParameter(60, 90, default=70, space="sell") - - {{- attributes | indent(4) }} - {{- plot_config | indent(4) }} - - def informative_pairs(self): - """ - Define additional, informative pair/interval combinations to be cached from the exchange. - These pair/interval combinations are non-tradeable, unless they are part - of the whitelist as well. - For more information, please consult the documentation - :return: List of tuples in the format (pair, interval) - Sample: return [("ETH/USDT", "5m"), - ("BTC/USDT", "15m"), - ] - """ - return [] - - def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame: - """ - Adds several different TA indicators to the given DataFrame - - Performance Note: For the best performance be frugal on the number of indicators - you are using. Let uncomment only the indicator you are using in your strategies - or your hyperopt configuration, otherwise you will waste your memory and CPU usage. - :param dataframe: Dataframe with data from the exchange - :param metadata: Additional information, like the currently traded pair - :return: a Dataframe with all mandatory indicators for the strategies - """ - {{- indicators | indent(8) }} - - return dataframe - - def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame: - """ - Based on TA indicators, populates the entry signal for the given dataframe - :param dataframe: DataFrame - :param metadata: Additional information, like the currently traded pair - :return: DataFrame with entry columns populated - """ - dataframe.loc[ - ( - {{ buy_trend | indent(16) }} - (dataframe["volume"] > 0) # Make sure Volume is not 0 - ), - "enter_long"] = 1 - # Uncomment to use shorts (Only used in futures/margin mode. Check the documentation for more info) - """ - dataframe.loc[ - ( - {{ sell_trend | indent(16) }} - (dataframe['volume'] > 0) # Make sure Volume is not 0 - ), - 'enter_short'] = 1 - """ - - return dataframe - - def populate_exit_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame: - """ - Based on TA indicators, populates the exit signal for the given dataframe - :param dataframe: DataFrame - :param metadata: Additional information, like the currently traded pair - :return: DataFrame with exit columns populated - """ - dataframe.loc[ - ( - {{ sell_trend | indent(16) }} - (dataframe["volume"] > 0) # Make sure Volume is not 0 - ), - "exit_long"] = 1 - # Uncomment to use shorts (Only used in futures/margin mode. Check the documentation for more info) - """ - dataframe.loc[ - ( - {{ buy_trend | indent(16) }} - (dataframe['volume'] > 0) # Make sure Volume is not 0 - ), - 'exit_short'] = 1 - """ - return dataframe - {{- additional_methods | indent(4) }} diff --git a/freqtrade/templates/freqaiprimer.json b/freqtrade/templates/freqaiprimer.json new file mode 100644 index 00000000..e29d2fa2 --- /dev/null +++ b/freqtrade/templates/freqaiprimer.json @@ -0,0 +1,32 @@ +{ + "strategy_name": "FreqaiPrimer", + "params": { + "max_open_trades": { + "max_open_trades": 4 + }, + "buy": { + "buy_rsi": 45.2500884290867 + }, + "sell": { + "sell_rsi": 75.2500884290867 + }, + "protection": {}, + "roi": { + "0": 0.20400000000000001, + "18": 0.07100000000000001, + "47": 0.03, + "102": 0 + }, + "stoploss": { + "stoploss": -0.07 + }, + "trailing": { + "trailing_stop": true, + "trailing_stop_positive": 0.237, + "trailing_stop_positive_offset": 0.267, + "trailing_only_offset_is_reached": false + } + }, + "ft_stratparam_v": 1, + "export_time": "2025-05-17 11:42:41.193338+00:00" +} \ No newline at end of file diff --git a/freqtrade/templates/freqaiprimer.py b/freqtrade/templates/freqaiprimer.py new file mode 100644 index 00000000..0a7d5b43 --- /dev/null +++ b/freqtrade/templates/freqaiprimer.py @@ -0,0 +1,279 @@ +import logging +import numpy as np +from functools import reduce +import talib.abstract as ta +from pandas import DataFrame +from technical import qtpylib +from freqtrade.strategy import IStrategy, IntParameter, DecimalParameter + +logger = logging.getLogger(__name__) + +class FreqaiPrimer(IStrategy): + minimal_roi = { + 0: 0.135, + 9: 0.052, + 15: 0.007, + 60: 0 + } + stoploss = -0.263 + trailing_stop = True + trailing_stop_positive = 0.324 + trailing_stop_positive_offset = 0.411 + trailing_only_offset_is_reached = False + max_open_trades = 4 + process_only_new_candles = True + use_exit_signal = True + startup_candle_count: int = 40 + can_short = False + + buy_rsi = IntParameter(low=10, high=50, default=30, space="buy", optimize=False, load=True) + sell_rsi = IntParameter(low=50, high=90, default=70, space="sell", optimize=False, load=True) + roi_0 = DecimalParameter(low=0.01, high=0.2, default=0.135, space="roi", optimize=True, load=True) + roi_15 = DecimalParameter(low=0.005, high=0.1, default=0.052, space="roi", optimize=True, load=True) + roi_30 = DecimalParameter(low=0.001, high=0.05, default=0.007, space="roi", optimize=True, load=True) + stoploss_param = DecimalParameter(low=-0.35, high=-0.1, default=-0.263, space="stoploss", optimize=True, load=True) + trailing_stop_positive_param = DecimalParameter(low=0.1, high=0.5, default=0.324, space="trailing", optimize=True, load=True) + trailing_stop_positive_offset_param = DecimalParameter(low=0.2, high=0.6, default=0.411, space="trailing", optimize=True, load=True) + + freqai_info = { + "model": "LightGBMRegressor", + "feature_parameters": { + "include_timeframes": ["5m", "15m", "1h"], + "include_corr_pairlist": [], + "label_period_candles": 12, + "include_shifted_candles": 3, + }, + "data_split_parameters": { + "test_size": 0.2, + "shuffle": False, + }, + "model_training_parameters": { + "n_estimators": 200, + "learning_rate": 0.05, + "num_leaves": 31, + "verbose": -1, + }, + } + + plot_config = { + "main_plot": {}, + "subplots": { + "&-buy_rsi": {"&-buy_rsi": {"color": "green"}}, + "&-sell_rsi": {"&-sell_rsi": {"color": "red"}}, + "&-stoploss": {"&-stoploss": {"color": "purple"}}, + "&-roi_0": {"&-roi_0": {"color": "orange"}}, + "do_predict": {"do_predict": {"color": "brown"}}, + }, + } + + def feature_engineering_expand_all(self, dataframe: DataFrame, period: int, metadata: dict, **kwargs) -> DataFrame: + dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period) + dataframe["%-mfi-period"] = ta.MFI(dataframe, timeperiod=period) + dataframe["%-sma-period"] = ta.SMA(dataframe, timeperiod=period) + dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period) + dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period) + bollinger = qtpylib.bollinger_bands(qtpylib.typical_price(dataframe), window=period, stds=2.2) + dataframe["bb_lowerband-period"] = bollinger["lower"] + dataframe["bb_middleband-period"] = bollinger["mid"] + dataframe["bb_upperband-period"] = bollinger["upper"] + dataframe["%-bb_width-period"] = ( + dataframe["bb_upperband-period"] - dataframe["bb_lowerband-period"] + ) / dataframe["bb_middleband-period"] + dataframe["%-close-bb_lower-period"] = dataframe["close"] / dataframe["bb_lowerband-period"] + dataframe["%-roc-period"] = ta.ROC(dataframe, timeperiod=period) + dataframe["%-relative_volume-period"] = ( + dataframe["volume"] / dataframe["volume"].rolling(period).mean() + ) + dataframe = dataframe.replace([np.inf, -np.inf], 0) + dataframe = dataframe.ffill() + dataframe = dataframe.fillna(0) + return dataframe + + def feature_engineering_expand_basic(self, dataframe: DataFrame, metadata: dict, **kwargs) -> DataFrame: + dataframe["%-pct-change"] = dataframe["close"].pct_change() + dataframe["%-raw_volume"] = dataframe["volume"] + dataframe["%-raw_price"] = dataframe["close"] + dataframe = dataframe.replace([np.inf, -np.inf], 0) + dataframe = dataframe.ffill() + dataframe = dataframe.fillna(0) + return dataframe + + def feature_engineering_standard(self, dataframe: DataFrame, metadata: dict, **kwargs) -> DataFrame: + if len(dataframe["close"]) < 20: + logger.warning(f"数据不足 {len(dataframe)} 根 K 线，%-volatility 可能不完整") + dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek + dataframe["%-hour_of_day"] = dataframe["date"].dt.hour + dataframe["%-volatility"] = dataframe["close"].pct_change().rolling(20, min_periods=1).std() + dataframe["%-volatility"] = dataframe["%-volatility"].replace([np.inf, -np.inf], 0) + dataframe["%-volatility"] = dataframe["%-volatility"].ffill() + dataframe["%-volatility"] = dataframe["%-volatility"].fillna(0) + return dataframe + + def set_freqai_targets(self, dataframe: DataFrame, metadata: dict, **kwargs) -> DataFrame: + logger.info(f"设置 FreqAI 目标，交易对：{metadata['pair']}") + if "close" not in dataframe.columns: + logger.error("数据框缺少必要的 'close' 列") + raise ValueError("数据框缺少必要的 'close' 列") + + try: + label_period = self.freqai_info["feature_parameters"]["label_period_candles"] + if "%-volatility" not in dataframe.columns: + logger.warning("缺少 %-volatility 列，强制重新生成") + dataframe["%-volatility"] = dataframe["close"].pct_change().rolling(20, min_periods=1).std() + dataframe["%-volatility"] = dataframe["%-volatility"].replace([np.inf, -np.inf], 0) + dataframe["%-volatility"] = dataframe["%-volatility"].ffill() + dataframe["%-volatility"] = dataframe["%-volatility"].fillna(0) + +# 移除 shift(-label_period)，改为使用当前及过去的数据 + dataframe["&-buy_rsi"] = ta.RSI(dataframe, timeperiod=14) + dataframe["&-buy_rsi"] = dataframe["&-buy_rsi"].rolling(window=label_period).mean().ffill().bfill() + + for col in ["&-buy_rsi", "%-volatility"]: + dataframe[col] = dataframe[col].replace([np.inf, -np.inf], 0) + dataframe[col] = dataframe[col].ffill() + dataframe[col] = dataframe[col].fillna(0) + if dataframe[col].isna().any(): + logger.warning(f"目标列 {col} 仍包含 NaN，数据预览：\n{dataframe[col].tail(10)}") + except Exception as e: + logger.error(f"创建 FreqAI 目标失败：{str(e)}") + raise + + logger.info(f"目标列预览：\n{dataframe[['&-buy_rsi']].head().to_string()}") + return dataframe + + def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + logger.info(f"处理交易对：{metadata['pair']}") + logger.debug(f"输入特征列：{list(dataframe.columns)}") + dataframe = self.freqai.start(dataframe, metadata, self) + logger.debug(f"FreqAI 输出特征列：{list(dataframe.columns)}") + + dataframe["rsi"] = ta.RSI(dataframe, timeperiod=14) + bollinger = qtpylib.bollinger_bands(qtpylib.typical_price(dataframe), window=20, stds=2) + dataframe["bb_lowerband"] = bollinger["lower"] + dataframe["bb_middleband"] = bollinger["mid"] + dataframe["bb_upperband"] = bollinger["upper"] + dataframe["tema"] = ta.TEMA(dataframe, timeperiod=9) + + label_period = self.freqai_info["feature_parameters"]["label_period_candles"] +# 使用滚动窗口而非未来函数来生成 up_or_down 列 + dataframe["up_or_down"] = np.where( + dataframe["close"].rolling(window=label_period).mean() > dataframe["close"], 1, 0 + ) + + if "&-buy_rsi" in dataframe.columns: + if "%-volatility" not in dataframe.columns: + logger.warning("缺少 %-volatility 列，强制重新生成") + dataframe["%-volatility"] = dataframe["close"].pct_change().rolling(20, min_periods=1).std() + dataframe["%-volatility"] = dataframe["%-volatility"].replace([np.inf, -np.inf], 0) + dataframe["%-volatility"] = dataframe["%-volatility"].ffill() + dataframe["%-volatility"] = dataframe["%-volatility"].fillna(0) + + dataframe["&-sell_rsi"] = dataframe["&-buy_rsi"] + 30 + dataframe["&-stoploss"] = self.stoploss - (dataframe["%-volatility"] * 5).clip(-0.05, 0.05) + dataframe["&-roi_0"] = (dataframe["close"].rolling(window=label_period).mean() / dataframe["close"] - 1).clip(0, 0.2) + + for col in ["&-buy_rsi", "&-sell_rsi", "&-stoploss", "&-roi_0"]: + dataframe[col] = dataframe[col].replace([np.inf, -np.inf], 0) + dataframe[col] = dataframe[col].ffill() + dataframe[col] = dataframe[col].fillna(0) + + dataframe["buy_rsi_pred"] = dataframe["&-buy_rsi"].rolling(5).mean().clip(10, 50) + dataframe["sell_rsi_pred"] = dataframe["&-sell_rsi"].rolling(5).mean().clip(50, 90) + dataframe["stoploss_pred"] = dataframe["&-stoploss"].clip(-0.35, -0.1) + dataframe["roi_0_pred"] = dataframe["&-roi_0"].clip(0.01, 0.2) + + for col in ["buy_rsi_pred", "sell_rsi_pred", "stoploss_pred", "roi_0_pred"]: + if dataframe[col].isna().any(): + logger.warning(f"列 {col} 包含 NaN，填充为默认值") + dataframe[col] = dataframe[col].ffill() + dataframe[col] = dataframe[col].fillna(dataframe[col].mean()) + + dataframe["trailing_stop_positive"] = (dataframe["roi_0_pred"] * 0.5).clip(0.01, 0.3) + dataframe["trailing_stop_positive_offset"] = (dataframe["roi_0_pred"] * 0.75).clip(0.02, 0.4) + + self.buy_rsi.value = float(dataframe["buy_rsi_pred"].iloc[-1]) + self.sell_rsi.value = float(dataframe["sell_rsi_pred"].iloc[-1]) + self.stoploss = float(self.stoploss_param.value) + self.minimal_roi = { + 0: float(self.roi_0.value), + 15: float(self.roi_15.value), + 30: float(self.roi_30.value), + 60: 0 + } + self.trailing_stop_positive = float(self.trailing_stop_positive_param.value) + self.trailing_stop_positive_offset = float(self.trailing_stop_positive_offset_param.value) + + logger.info(f"动态参数：buy_rsi={self.buy_rsi.value}, sell_rsi={self.sell_rsi.value}, " + f"stoploss={self.stoploss}, trailing_stop_positive={self.trailing_stop_positive}") + else: + logger.warning(f"&-buy_rsi 列缺失，跳过 FreqAI 预测逻辑，检查 freqai.start 输出") + + dataframe = dataframe.replace([np.inf, -np.inf], 0) + dataframe = dataframe.ffill() + dataframe = dataframe.fillna(0) + + logger.info(f"up_or_down 值统计：\n{dataframe['up_or_down'].value_counts().to_string()}") + logger.info(f"do_predict 值统计：\n{dataframe['do_predict'].value_counts().to_string()}") + logger.debug(f"最终特征列：{list(dataframe.columns)}") + + return dataframe + + def populate_entry_trend(self, df: DataFrame, metadata: dict) -> DataFrame: + enter_long_conditions = [ + qtpylib.crossed_above(df["rsi"], df["buy_rsi_pred"]), + df["tema"] > df["tema"].shift(1), + df["volume"] > 0, + df["do_predict"] == 1, + df["up_or_down"] == 1 + ] + if enter_long_conditions: + df.loc[ + reduce(lambda x, y: x & y, enter_long_conditions), + ["enter_long", "enter_tag"] + ] = (1, "long") + return df + + def populate_exit_trend(self, df: DataFrame, metadata: dict) -> DataFrame: + exit_long_conditions = [ + qtpylib.crossed_above(df["rsi"], df["sell_rsi_pred"]), + (df["close"] < df["close"].shift(1) * 0.97), + df["volume"] > 0, + df["do_predict"] == 1, + df["up_or_down"] == 0 + ] + if exit_long_conditions: + df.loc[ + reduce(lambda x, y: x & y, exit_long_conditions), + "exit_long" + ] = 1 + return df + + def confirm_trade_entry( + self, pair: str, order_type: str, amount: float, rate: float, + time_in_force: str, current_time, entry_tag, side: str, **kwargs + ) -> bool: + try: + df, _ = self.dp.get_analyzed_dataframe(pair, self.timeframe) + if df is None or df.empty: + logger.warning(f"无法获取 {pair} 的分析数据，拒绝交易") + return False + + last_candle = df.iloc[-1].squeeze() + if "close" not in last_candle or np.isnan(last_candle["close"]): + logger.warning(f"{pair} 的最新 K 线缺少有效 close 价格，拒绝交易") + return False + + if side == "long": + max_rate = last_candle["close"] * (1 + 0.0025) # 0.25% 滑点阈值 + if rate > max_rate: + logger.debug(f"拒绝 {pair} 的买入，价格 {rate} 超过最大允许价格 {max_rate}") + return False + elif side == "short": + logger.warning(f"{pair} 尝试做空，但策略不支持做空 (can_short={self.can_short})") + return False + + logger.debug(f"确认 {pair} 的交易：side={side}, rate={rate}, close={last_candle['close']}") + return True + except Exception as e: + logger.error(f"确认 {pair} 交易时出错：{str(e)}") + return False diff --git a/freqtrade/templates/sample_hyperopt_loss.py b/freqtrade/templates/sample_hyperopt_loss.py deleted file mode 100644 index 20a348f2..00000000 --- a/freqtrade/templates/sample_hyperopt_loss.py +++ /dev/null @@ -1,57 +0,0 @@ -from datetime import datetime -from math import exp - -from pandas import DataFrame - -from freqtrade.constants import Config -from freqtrade.optimize.hyperopt import IHyperOptLoss - - -# Define some constants: - -# set TARGET_TRADES to suit your number concurrent trades so its realistic -# to the number of days -TARGET_TRADES = 600 -# This is assumed to be expected avg profit * expected trade count. -# For example, for 0.35% avg per trade (or 0.0035 as ratio) and 1100 trades, -# self.expected_max_profit = 3.85 -# Check that the reported Σ% values do not exceed this! -# Note, this is ratio. 3.85 stated above means 385Σ%. -EXPECTED_MAX_PROFIT = 3.0 - -# max average trade duration in minutes -# if eval ends with higher value, we consider it a failed eval -MAX_ACCEPTED_TRADE_DURATION = 300 - - -class SampleHyperOptLoss(IHyperOptLoss): - """ - Defines the default loss function for hyperopt - This is intended to give you some inspiration for your own loss function. - - The Function needs to return a number (float) - which becomes smaller for better backtest - results. - """ - - @staticmethod - def hyperopt_loss_function( - results: DataFrame, - trade_count: int, - min_date: datetime, - max_date: datetime, - config: Config, - processed: dict[str, DataFrame], - *args, - **kwargs, - ) -> float: - """ - Objective function, returns smaller number for better results - """ - total_profit = results["profit_ratio"].sum() - trade_duration = results["trade_duration"].mean() - - trade_loss = 1 - 0.25 * exp(-((trade_count - TARGET_TRADES) ** 2) / 10**5.8) - profit_loss = max(0, 1 - total_profit / EXPECTED_MAX_PROFIT) - duration_loss = 0.4 * min(trade_duration / MAX_ACCEPTED_TRADE_DURATION, 1) - result = trade_loss + profit_loss + duration_loss - return result diff --git a/freqtrade/templates/sample_strategy.py b/freqtrade/templates/sample_strategy.py deleted file mode 100644 index 75a0fe38..00000000 --- a/freqtrade/templates/sample_strategy.py +++ /dev/null @@ -1,426 +0,0 @@ -# pragma pylint: disable=missing-docstring, invalid-name, pointless-string-statement -# flake8: noqa: F401 -# isort: skip_file -# --- Do not remove these imports --- -import numpy as np -import pandas as pd -from datetime import datetime, timedelta, timezone -from pandas import DataFrame -from typing import Optional, Union - -from freqtrade.strategy import ( - IStrategy, - Trade, - Order, - PairLocks, - informative, # @informative decorator - # Hyperopt Parameters - BooleanParameter, - CategoricalParameter, - DecimalParameter, - IntParameter, - RealParameter, - # timeframe helpers - timeframe_to_minutes, - timeframe_to_next_date, - timeframe_to_prev_date, - # Strategy helper functions - merge_informative_pair, - stoploss_from_absolute, - stoploss_from_open, -) - -# -------------------------------- -# Add your lib to import here -import talib.abstract as ta -from technical import qtpylib - - -# This class is a sample. Feel free to customize it. -class SampleStrategy(IStrategy): - """ - This is a sample strategy to inspire you. - More information in https://www.freqtrade.io/en/latest/strategy-customization/ - - You can: - :return: a Dataframe with all mandatory indicators for the strategies - - Rename the class name (Do not forget to update class_name) - - Add any methods you want to build your strategy - - Add any lib you need to build your strategy - - You must keep: - - the lib in the section "Do not remove these libs" - - the methods: populate_indicators, populate_entry_trend, populate_exit_trend - You should keep: - - timeframe, minimal_roi, stoploss, trailing_* - """ - - # Strategy interface version - allow new iterations of the strategy interface. - # Check the documentation or the Sample strategy to get the latest version. - INTERFACE_VERSION = 3 - - # Can this strategy go short? - can_short: bool = False - - # Minimal ROI designed for the strategy. - # This attribute will be overridden if the config file contains "minimal_roi". - minimal_roi = { - # "120": 0.0, # exit after 120 minutes at break even - "60": 0.01, - "30": 0.02, - "0": 0.04, - } - - # Optimal stoploss designed for the strategy. - # This attribute will be overridden if the config file contains "stoploss". - stoploss = -0.10 - - # Trailing stoploss - trailing_stop = False - # trailing_only_offset_is_reached = False - # trailing_stop_positive = 0.01 - # trailing_stop_positive_offset = 0.0 # Disabled / not configured - - # Optimal timeframe for the strategy. - timeframe = "5m" - - # Run "populate_indicators()" only for new candle. - process_only_new_candles = True - - # These values can be overridden in the config. - use_exit_signal = True - exit_profit_only = False - ignore_roi_if_entry_signal = False - - # Hyperoptable parameters - buy_rsi = IntParameter(low=1, high=50, default=30, space="buy", optimize=True, load=True) - sell_rsi = IntParameter(low=50, high=100, default=70, space="sell", optimize=True, load=True) - short_rsi = IntParameter(low=51, high=100, default=70, space="sell", optimize=True, load=True) - exit_short_rsi = IntParameter(low=1, high=50, default=30, space="buy", optimize=True, load=True) - - # Number of candles the strategy requires before producing valid signals - startup_candle_count: int = 200 - - # Optional order type mapping. - order_types = { - "entry": "limit", - "exit": "limit", - "stoploss": "market", - "stoploss_on_exchange": False, - } - - # Optional order time in force. - order_time_in_force = {"entry": "GTC", "exit": "GTC"} - - plot_config = { - "main_plot": { - "tema": {}, - "sar": {"color": "white"}, - }, - "subplots": { - "MACD": { - "macd": {"color": "blue"}, - "macdsignal": {"color": "orange"}, - }, - "RSI": { - "rsi": {"color": "red"}, - }, - }, - } - - def informative_pairs(self): - """ - Define additional, informative pair/interval combinations to be cached from the exchange. - These pair/interval combinations are non-tradeable, unless they are part - of the whitelist as well. - For more information, please consult the documentation - :return: List of tuples in the format (pair, interval) - Sample: return [("ETH/USDT", "5m"), - ("BTC/USDT", "15m"), - ] - """ - return [] - - def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame: - """ - Adds several different TA indicators to the given DataFrame - - Performance Note: For the best performance be frugal on the number of indicators - you are using. Let uncomment only the indicator you are using in your strategies - or your hyperopt configuration, otherwise you will waste your memory and CPU usage. - :param dataframe: Dataframe with data from the exchange - :param metadata: Additional information, like the currently traded pair - :return: a Dataframe with all mandatory indicators for the strategies - """ - - # Momentum Indicators - # ------------------------------------ - - # ADX - dataframe["adx"] = ta.ADX(dataframe) - - # # Plus Directional Indicator / Movement - # dataframe['plus_dm'] = ta.PLUS_DM(dataframe) - # dataframe['plus_di'] = ta.PLUS_DI(dataframe) - - # # Minus Directional Indicator / Movement - # dataframe['minus_dm'] = ta.MINUS_DM(dataframe) - # dataframe['minus_di'] = ta.MINUS_DI(dataframe) - - # # Aroon, Aroon Oscillator - # aroon = ta.AROON(dataframe) - # dataframe['aroonup'] = aroon['aroonup'] - # dataframe['aroondown'] = aroon['aroondown'] - # dataframe['aroonosc'] = ta.AROONOSC(dataframe) - - # # Awesome Oscillator - # dataframe['ao'] = qtpylib.awesome_oscillator(dataframe) - - # # Keltner Channel - # keltner = qtpylib.keltner_channel(dataframe) - # dataframe["kc_upperband"] = keltner["upper"] - # dataframe["kc_lowerband"] = keltner["lower"] - # dataframe["kc_middleband"] = keltner["mid"] - # dataframe["kc_percent"] = ( - # (dataframe["close"] - dataframe["kc_lowerband"]) / - # (dataframe["kc_upperband"] - dataframe["kc_lowerband"]) - # ) - # dataframe["kc_width"] = ( - # (dataframe["kc_upperband"] - dataframe["kc_lowerband"]) / dataframe["kc_middleband"] - # ) - - # # Ultimate Oscillator - # dataframe['uo'] = ta.ULTOSC(dataframe) - - # # Commodity Channel Index: values [Oversold:-100, Overbought:100] - # dataframe['cci'] = ta.CCI(dataframe) - - # RSI - dataframe["rsi"] = ta.RSI(dataframe) - - # # Inverse Fisher transform on RSI: values [-1.0, 1.0] (https://goo.gl/2JGGoy) - # rsi = 0.1 * (dataframe['rsi'] - 50) - # dataframe['fisher_rsi'] = (np.exp(2 * rsi) - 1) / (np.exp(2 * rsi) + 1) - - # # Inverse Fisher transform on RSI normalized: values [0.0, 100.0] (https://goo.gl/2JGGoy) - # dataframe['fisher_rsi_norma'] = 50 * (dataframe['fisher_rsi'] + 1) - - # # Stochastic Slow - # stoch = ta.STOCH(dataframe) - # dataframe['slowd'] = stoch['slowd'] - # dataframe['slowk'] = stoch['slowk'] - - # Stochastic Fast - stoch_fast = ta.STOCHF(dataframe) - dataframe["fastd"] = stoch_fast["fastd"] - dataframe["fastk"] = stoch_fast["fastk"] - - # # Stochastic RSI - # Please read https://github.com/freqtrade/freqtrade/issues/2961 before using this. - # STOCHRSI is NOT aligned with tradingview, which may result in non-expected results. - # stoch_rsi = ta.STOCHRSI(dataframe) - # dataframe['fastd_rsi'] = stoch_rsi['fastd'] - # dataframe['fastk_rsi'] = stoch_rsi['fastk'] - - # MACD - macd = ta.MACD(dataframe) - dataframe["macd"] = macd["macd"] - dataframe["macdsignal"] = macd["macdsignal"] - dataframe["macdhist"] = macd["macdhist"] - - # MFI - dataframe["mfi"] = ta.MFI(dataframe) - - # # ROC - # dataframe['roc'] = ta.ROC(dataframe) - - # Overlap Studies - # ------------------------------------ - - # Bollinger Bands - bollinger = qtpylib.bollinger_bands(qtpylib.typical_price(dataframe), window=20, stds=2) - dataframe["bb_lowerband"] = bollinger["lower"] - dataframe["bb_middleband"] = bollinger["mid"] - dataframe["bb_upperband"] = bollinger["upper"] - dataframe["bb_percent"] = (dataframe["close"] - dataframe["bb_lowerband"]) / ( - dataframe["bb_upperband"] - dataframe["bb_lowerband"] - ) - dataframe["bb_width"] = (dataframe["bb_upperband"] - dataframe["bb_lowerband"]) / dataframe[ - "bb_middleband" - ] - - # Bollinger Bands - Weighted (EMA based instead of SMA) - # weighted_bollinger = qtpylib.weighted_bollinger_bands( - # qtpylib.typical_price(dataframe), window=20, stds=2 - # ) - # dataframe["wbb_upperband"] = weighted_bollinger["upper"] - # dataframe["wbb_lowerband"] = weighted_bollinger["lower"] - # dataframe["wbb_middleband"] = weighted_bollinger["mid"] - # dataframe["wbb_percent"] = ( - # (dataframe["close"] - dataframe["wbb_lowerband"]) / - # (dataframe["wbb_upperband"] - dataframe["wbb_lowerband"]) - # ) - # dataframe["wbb_width"] = ( - # (dataframe["wbb_upperband"] - dataframe["wbb_lowerband"]) / - # dataframe["wbb_middleband"] - # ) - - # # EMA - Exponential Moving Average - # dataframe['ema3'] = ta.EMA(dataframe, timeperiod=3) - # dataframe['ema5'] = ta.EMA(dataframe, timeperiod=5) - # dataframe['ema10'] = ta.EMA(dataframe, timeperiod=10) - # dataframe['ema21'] = ta.EMA(dataframe, timeperiod=21) - # dataframe['ema50'] = ta.EMA(dataframe, timeperiod=50) - # dataframe['ema100'] = ta.EMA(dataframe, timeperiod=100) - - # # SMA - Simple Moving Average - # dataframe['sma3'] = ta.SMA(dataframe, timeperiod=3) - # dataframe['sma5'] = ta.SMA(dataframe, timeperiod=5) - # dataframe['sma10'] = ta.SMA(dataframe, timeperiod=10) - # dataframe['sma21'] = ta.SMA(dataframe, timeperiod=21) - # dataframe['sma50'] = ta.SMA(dataframe, timeperiod=50) - # dataframe['sma100'] = ta.SMA(dataframe, timeperiod=100) - - # Parabolic SAR - dataframe["sar"] = ta.SAR(dataframe) - - # TEMA - Triple Exponential Moving Average - dataframe["tema"] = ta.TEMA(dataframe, timeperiod=9) - - # Cycle Indicator - # ------------------------------------ - # Hilbert Transform Indicator - SineWave - hilbert = ta.HT_SINE(dataframe) - dataframe["htsine"] = hilbert["sine"] - dataframe["htleadsine"] = hilbert["leadsine"] - - # Pattern Recognition - Bullish candlestick patterns - # ------------------------------------ - # # Hammer: values [0, 100] - # dataframe['CDLHAMMER'] = ta.CDLHAMMER(dataframe) - # # Inverted Hammer: values [0, 100] - # dataframe['CDLINVERTEDHAMMER'] = ta.CDLINVERTEDHAMMER(dataframe) - # # Dragonfly Doji: values [0, 100] - # dataframe['CDLDRAGONFLYDOJI'] = ta.CDLDRAGONFLYDOJI(dataframe) - # # Piercing Line: values [0, 100] - # dataframe['CDLPIERCING'] = ta.CDLPIERCING(dataframe) # values [0, 100] - # # Morningstar: values [0, 100] - # dataframe['CDLMORNINGSTAR'] = ta.CDLMORNINGSTAR(dataframe) # values [0, 100] - # # Three White Soldiers: values [0, 100] - # dataframe['CDL3WHITESOLDIERS'] = ta.CDL3WHITESOLDIERS(dataframe) # values [0, 100] - - # Pattern Recognition - Bearish candlestick patterns - # ------------------------------------ - # # Hanging Man: values [0, 100] - # dataframe['CDLHANGINGMAN'] = ta.CDLHANGINGMAN(dataframe) - # # Shooting Star: values [0, 100] - # dataframe['CDLSHOOTINGSTAR'] = ta.CDLSHOOTINGSTAR(dataframe) - # # Gravestone Doji: values [0, 100] - # dataframe['CDLGRAVESTONEDOJI'] = ta.CDLGRAVESTONEDOJI(dataframe) - # # Dark Cloud Cover: values [0, 100] - # dataframe['CDLDARKCLOUDCOVER'] = ta.CDLDARKCLOUDCOVER(dataframe) - # # Evening Doji Star: values [0, 100] - # dataframe['CDLEVENINGDOJISTAR'] = ta.CDLEVENINGDOJISTAR(dataframe) - # # Evening Star: values [0, 100] - # dataframe['CDLEVENINGSTAR'] = ta.CDLEVENINGSTAR(dataframe) - - # Pattern Recognition - Bullish/Bearish candlestick patterns - # ------------------------------------ - # # Three Line Strike: values [0, -100, 100] - # dataframe['CDL3LINESTRIKE'] = ta.CDL3LINESTRIKE(dataframe) - # # Spinning Top: values [0, -100, 100] - # dataframe['CDLSPINNINGTOP'] = ta.CDLSPINNINGTOP(dataframe) # values [0, -100, 100] - # # Engulfing: values [0, -100, 100] - # dataframe['CDLENGULFING'] = ta.CDLENGULFING(dataframe) # values [0, -100, 100] - # # Harami: values [0, -100, 100] - # dataframe['CDLHARAMI'] = ta.CDLHARAMI(dataframe) # values [0, -100, 100] - # # Three Outside Up/Down: values [0, -100, 100] - # dataframe['CDL3OUTSIDE'] = ta.CDL3OUTSIDE(dataframe) # values [0, -100, 100] - # # Three Inside Up/Down: values [0, -100, 100] - # dataframe['CDL3INSIDE'] = ta.CDL3INSIDE(dataframe) # values [0, -100, 100] - - # # Chart type - # # ------------------------------------ - # # Heikin Ashi Strategy - # heikinashi = qtpylib.heikinashi(dataframe) - # dataframe['ha_open'] = heikinashi['open'] - # dataframe['ha_close'] = heikinashi['close'] - # dataframe['ha_high'] = heikinashi['high'] - # dataframe['ha_low'] = heikinashi['low'] - - # Retrieve best bid and best ask from the orderbook - # ------------------------------------ - """ - # first check if dataprovider is available - if self.dp: - if self.dp.runmode.value in ('live', 'dry_run'): - ob = self.dp.orderbook(metadata['pair'], 1) - dataframe['best_bid'] = ob['bids'][0][0] - dataframe['best_ask'] = ob['asks'][0][0] - """ - - return dataframe - - def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame: - """ - Based on TA indicators, populates the entry signal for the given dataframe - :param dataframe: DataFrame - :param metadata: Additional information, like the currently traded pair - :return: DataFrame with entry columns populated - """ - dataframe.loc[ - ( - # Signal: RSI crosses above 30 - (qtpylib.crossed_above(dataframe["rsi"], self.buy_rsi.value)) - & (dataframe["tema"] <= dataframe["bb_middleband"]) # Guard: tema below BB middle - & (dataframe["tema"] > dataframe["tema"].shift(1)) # Guard: tema is raising - & (dataframe["volume"] > 0) # Make sure Volume is not 0 - ), - "enter_long", - ] = 1 - - dataframe.loc[ - ( - # Signal: RSI crosses above 70 - (qtpylib.crossed_above(dataframe["rsi"], self.short_rsi.value)) - & (dataframe["tema"] > dataframe["bb_middleband"]) # Guard: tema above BB middle - & (dataframe["tema"] < dataframe["tema"].shift(1)) # Guard: tema is falling - & (dataframe["volume"] > 0) # Make sure Volume is not 0 - ), - "enter_short", - ] = 1 - - return dataframe - - def populate_exit_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame: - """ - Based on TA indicators, populates the exit signal for the given dataframe - :param dataframe: DataFrame - :param metadata: Additional information, like the currently traded pair - :return: DataFrame with exit columns populated - """ - dataframe.loc[ - ( - # Signal: RSI crosses above 70 - (qtpylib.crossed_above(dataframe["rsi"], self.sell_rsi.value)) - & (dataframe["tema"] > dataframe["bb_middleband"]) # Guard: tema above BB middle - & (dataframe["tema"] < dataframe["tema"].shift(1)) # Guard: tema is falling - & (dataframe["volume"] > 0) # Make sure Volume is not 0 - ), - "exit_long", - ] = 1 - - dataframe.loc[ - ( - # Signal: RSI crosses above 30 - (qtpylib.crossed_above(dataframe["rsi"], self.exit_short_rsi.value)) - & - # Guard: tema below BB middle - (dataframe["tema"] <= dataframe["bb_middleband"]) - & (dataframe["tema"] > dataframe["tema"].shift(1)) # Guard: tema is raising - & (dataframe["volume"] > 0) # Make sure Volume is not 0 - ), - "exit_short", - ] = 1 - - return dataframe diff --git a/freqtrade/templates/strategy_analysis_example.ipynb b/freqtrade/templates/strategy_analysis_example.ipynb deleted file mode 100644 index c81a76f7..00000000 --- a/freqtrade/templates/strategy_analysis_example.ipynb +++ /dev/null @@ -1,480 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "# Strategy analysis example\n", - "\n", - "Debugging a strategy can be time-consuming. Freqtrade offers helper functions to visualize raw data.\n", - "The following assumes you work with SampleStrategy, data for 5m timeframe from Binance and have downloaded them into the data directory in the default location.\n", - "Please follow the [documentation](https://www.freqtrade.io/en/stable/data-download/) for more details." - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Setup\n", - "\n", - "### Change Working directory to repository root" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "import os\n", - "from pathlib import Path\n", - "\n", - "\n", - "# Change directory\n", - "# Modify this cell to insure that the output shows the correct path.\n", - "# Define all paths relative to the project root shown in the cell output\n", - "project_root = \"somedir/freqtrade\"\n", - "i = 0\n", - "try:\n", - " os.chdir(project_root)\n", - " if not Path(\"LICENSE\").is_file():\n", - " i = 0\n", - " while i < 4 and (not Path(\"LICENSE\").is_file()):\n", - " os.chdir(Path(Path.cwd(), \"../\"))\n", - " i += 1\n", - " project_root = Path.cwd()\n", - "except FileNotFoundError:\n", - " print(\"Please define the project root relative to the current directory\")\n", - "print(Path.cwd())" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Configure Freqtrade environment" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "from freqtrade.configuration import Configuration\n", - "\n", - "\n", - "# Customize these according to your needs.\n", - "\n", - "# Initialize empty configuration object\n", - "config = Configuration.from_files([])\n", - "# Optionally (recommended), use existing configuration file\n", - "# config = Configuration.from_files([\"user_data/config.json\"])\n", - "\n", - "# Define some constants\n", - "config[\"timeframe\"] = \"5m\"\n", - "# Name of the strategy class\n", - "config[\"strategy\"] = \"SampleStrategy\"\n", - "# Location of the data\n", - "data_location = config[\"datadir\"]\n", - "# Pair to analyze - Only use one pair here\n", - "pair = \"BTC/USDT\"" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Load data using values set above\n", - "from freqtrade.data.history import load_pair_history\n", - "from freqtrade.enums import CandleType\n", - "\n", - "\n", - "candles = load_pair_history(\n", - " datadir=data_location,\n", - " timeframe=config[\"timeframe\"],\n", - " pair=pair,\n", - " data_format=\"json\", # Make sure to update this to your data\n", - " candle_type=CandleType.SPOT,\n", - ")\n", - "\n", - "# Confirm success\n", - "print(f\"Loaded {len(candles)} rows of data for {pair} from {data_location}\")\n", - "candles.head()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Load and run strategy\n", - "* Rerun each time the strategy file is changed" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Load strategy using values set above\n", - "from freqtrade.data.dataprovider import DataProvider\n", - "from freqtrade.resolvers import StrategyResolver\n", - "\n", - "\n", - "strategy = StrategyResolver.load_strategy(config)\n", - "strategy.dp = DataProvider(config, None, None)\n", - "strategy.ft_bot_start()\n", - "\n", - "# Generate buy/sell signals using strategy\n", - "df = strategy.analyze_ticker(candles, {\"pair\": pair})\n", - "df.tail()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Display the trade details\n", - "\n", - "* Note that using `data.head()` would also work, however most indicators have some \"startup\" data at the top of the dataframe.\n", - "* Some possible problems\n", - " * Columns with NaN values at the end of the dataframe\n", - " * Columns used in `crossed*()` functions with completely different units\n", - "* Comparison with full backtest\n", - " * having 200 buy signals as output for one pair from `analyze_ticker()` does not necessarily mean that 200 trades will be made during backtesting.\n", - " * Assuming you use only one condition such as, `df['rsi'] < 30` as buy condition, this will generate multiple \"buy\" signals for each pair in sequence (until rsi returns > 29). The bot will only buy on the first of these signals (and also only if a trade-slot (\"max_open_trades\") is still available), or on one of the middle signals, as soon as a \"slot\" becomes available. \n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Report results\n", - "print(f\"Generated {df['enter_long'].sum()} entry signals\")\n", - "data = df.set_index(\"date\", drop=False)\n", - "data.tail()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Load existing objects into a Jupyter notebook\n", - "\n", - "The following cells assume that you have already generated data using the cli. \n", - "They will allow you to drill deeper into your results, and perform analysis which otherwise would make the output very difficult to digest due to information overload." - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Load backtest results to pandas dataframe\n", - "\n", - "Analyze a trades dataframe (also used below for plotting)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "from freqtrade.data.btanalysis import load_backtest_data, load_backtest_stats\n", - "\n", - "\n", - "# if backtest_dir points to a directory, it'll automatically load the last backtest file.\n", - "backtest_dir = config[\"user_data_dir\"] / \"backtest_results\"\n", - "# backtest_dir can also point to a specific file\n", - "# backtest_dir = (\n", - "# config[\"user_data_dir\"] / \"backtest_results/backtest-result-2020-07-01_20-04-22.json\"\n", - "# )" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# You can get the full backtest statistics by using the following command.\n", - "# This contains all information used to generate the backtest result.\n", - "stats = load_backtest_stats(backtest_dir)\n", - "\n", - "strategy = \"SampleStrategy\"\n", - "# All statistics are available per strategy, so if `--strategy-list` was used during backtest,\n", - "# this will be reflected here as well.\n", - "# Example usages:\n", - "print(stats[\"strategy\"][strategy][\"results_per_pair\"])\n", - "# Get pairlist used for this backtest\n", - "print(stats[\"strategy\"][strategy][\"pairlist\"])\n", - "# Get market change (average change of all pairs from start to end of the backtest period)\n", - "print(stats[\"strategy\"][strategy][\"market_change\"])\n", - "# Maximum drawdown ()\n", - "print(stats[\"strategy\"][strategy][\"max_drawdown_abs\"])\n", - "# Maximum drawdown start and end\n", - "print(stats[\"strategy\"][strategy][\"drawdown_start\"])\n", - "print(stats[\"strategy\"][strategy][\"drawdown_end\"])\n", - "\n", - "\n", - "# Get strategy comparison (only relevant if multiple strategies were compared)\n", - "print(stats[\"strategy_comparison\"])" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Load backtested trades as dataframe\n", - "trades = load_backtest_data(backtest_dir)\n", - "\n", - "# Show value-counts per pair\n", - "trades.groupby(\"pair\")[\"exit_reason\"].value_counts()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Plotting daily profit / equity line" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Plotting equity line (starting with 0 on day 1 and adding daily profit for each backtested day)\n", - "\n", - "import pandas as pd\n", - "import plotly.express as px\n", - "\n", - "from freqtrade.configuration import Configuration\n", - "from freqtrade.data.btanalysis import load_backtest_stats\n", - "\n", - "\n", - "# strategy = 'SampleStrategy'\n", - "# config = Configuration.from_files([\"user_data/config.json\"])\n", - "# backtest_dir = config[\"user_data_dir\"] / \"backtest_results\"\n", - "\n", - "stats = load_backtest_stats(backtest_dir)\n", - "strategy_stats = stats[\"strategy\"][strategy]\n", - "\n", - "df = pd.DataFrame(columns=[\"dates\", \"equity\"], data=strategy_stats[\"daily_profit\"])\n", - "df[\"equity_daily\"] = df[\"equity\"].cumsum()\n", - "\n", - "fig = px.line(df, x=\"dates\", y=\"equity_daily\")\n", - "fig.show()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Load live trading results into a pandas dataframe\n", - "\n", - "In case you did already some trading and want to analyze your performance" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "from freqtrade.data.btanalysis import load_trades_from_db\n", - "\n", - "\n", - "# Fetch trades from database\n", - "trades = load_trades_from_db(\"sqlite:///tradesv3.sqlite\")\n", - "\n", - "# Display results\n", - "trades.groupby(\"pair\")[\"exit_reason\"].value_counts()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Analyze the loaded trades for trade parallelism\n", - "This can be useful to find the best `max_open_trades` parameter, when used with backtesting in conjunction with a very high `max_open_trades` setting.\n", - "\n", - "`analyze_trade_parallelism()` returns a timeseries dataframe with an \"open_trades\" column, specifying the number of open trades for each candle." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "from freqtrade.data.btanalysis import analyze_trade_parallelism\n", - "\n", - "\n", - "# Analyze the above\n", - "parallel_trades = analyze_trade_parallelism(trades, \"5m\")\n", - "\n", - "parallel_trades.plot()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Plot results\n", - "\n", - "Freqtrade offers interactive plotting capabilities based on plotly." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "from freqtrade.plot.plotting import generate_candlestick_graph\n", - "\n", - "\n", - "# Limit graph period to keep plotly quick and reactive\n", - "\n", - "# Filter trades to one pair\n", - "trades_red = trades.loc[trades[\"pair\"] == pair]\n", - "\n", - "data_red = data[\"2019-06-01\":\"2019-06-10\"]\n", - "# Generate candlestick graph\n", - "graph = generate_candlestick_graph(\n", - " pair=pair,\n", - " data=data_red,\n", - " trades=trades_red,\n", - " indicators1=[\"sma20\", \"ema50\", \"ema55\"],\n", - " indicators2=[\"rsi\", \"macd\", \"macdsignal\", \"macdhist\"],\n", - ")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Show graph inline\n", - "# graph.show()\n", - "\n", - "# Render graph in a separate window\n", - "graph.show(renderer=\"browser\")" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Plot average profit per trade as distribution graph" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "import plotly.figure_factory as ff\n", - "\n", - "\n", - "hist_data = [trades.profit_ratio]\n", - "group_labels = [\"profit_ratio\"] # name of the dataset\n", - "\n", - "fig = ff.create_distplot(hist_data, group_labels, bin_size=0.01)\n", - "fig.show()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Feel free to submit an issue or Pull Request enhancing this document if you would like to share ideas on how to best analyze the data." - ] - } - ], - "metadata": { - "file_extension": ".py", - "kernelspec": { - "display_name": "Python 3.9.7 64-bit", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.11.4" - }, - "mimetype": "text/x-python", - "name": "python", - "npconvert_exporter": "python", - "pygments_lexer": "ipython3", - "toc": { - "base_numbering": 1, - "nav_menu": {}, - "number_sections": true, - "sideBar": true, - "skip_h1_title": false, - "title_cell": "Table of Contents", - "title_sidebar": "Contents", - "toc_cell": false, - "toc_position": {}, - "toc_section_display": true, - "toc_window_display": false - }, - "varInspector": { - "cols": { - "lenName": 16, - "lenType": 16, - "lenVar": 40 - }, - "kernels_config": { - "python": { - "delete_cmd_postfix": "", - "delete_cmd_prefix": "del ", - "library": "var_list.py", - "varRefreshCmd": "print(var_dic_list())" - }, - "r": { - "delete_cmd_postfix": ") ", - "delete_cmd_prefix": "rm(", - "library": "var_list.r", - "varRefreshCmd": "cat(var_dic_list()) " - } - }, - "types_to_exclude": [ - "module", - "function", - "builtin_function_or_method", - "instance", - "_Feature" - ], - "window_display": false - }, - "version": 3, - "vscode": { - "interpreter": { - "hash": "675f32a300d6d26767470181ad0b11dd4676bcce7ed1dd2ffe2fbc370c95fc7c" - } - } - }, - "nbformat": 4, - "nbformat_minor": 4 -} diff --git a/freqtrade_utf8.log b/freqtrade_utf8.log new file mode 100644 index 00000000..4aaafe69 --- /dev/null +++ b/freqtrade_utf8.log @@ -0,0 +1,3066 @@ +Creating freqtrade_freqtrade_run ... +Creating freqtrade_freqtrade_run ... done +2025-04-29 01:54:55,246 - freqtrade - INFO - freqtrade 2025.3 +2025-04-29 01:54:55,464 - numexpr.utils - INFO - NumExpr defaulting to 12 threads. +2025-04-29 01:54:56,878 - freqtrade.configuration.load_config - INFO - Using config: /freqtrade/config_examples/config_freqai.okx.json ... +2025-04-29 01:54:56,879 - freqtrade.configuration.load_config - INFO - Using config: /freqtrade/templates/FreqaiExampleStrategy.json ... +2025-04-29 01:54:56,881 - freqtrade.loggers - INFO - Enabling colorized output. +2025-04-29 01:54:56,881 - root - INFO - Logfile configured +2025-04-29 01:54:56,882 - freqtrade.loggers - INFO - Verbosity set to 0 +2025-04-29 01:54:56,882 - freqtrade.configuration.configuration - INFO - Using additional Strategy lookup path: /freqtrade/templates +2025-04-29 01:54:56,883 - freqtrade.configuration.configuration - INFO - Using max_open_trades: 4 ... +2025-04-29 01:54:56,883 - freqtrade.configuration.configuration - INFO - Parameter --timerange detected: 20250101-20250420 ... +2025-04-29 01:54:56,907 - freqtrade.configuration.configuration - INFO - Using user-data directory: /freqtrade/user_data ... +2025-04-29 01:54:56,908 - freqtrade.configuration.configuration - INFO - Using data directory: /freqtrade/user_data/data/okx ... +2025-04-29 01:54:56,908 - freqtrade.configuration.configuration - INFO - Parameter --cache=none detected ... +2025-04-29 01:54:56,908 - freqtrade.configuration.configuration - INFO - Filter trades by timerange: 20250101-20250420 +2025-04-29 01:54:56,909 - freqtrade.configuration.configuration - INFO - Using freqaimodel class name: XGBoostRegressor +2025-04-29 01:54:56,910 - freqtrade.exchange.check_exchange - INFO - Checking exchange... +2025-04-29 01:54:56,916 - freqtrade.exchange.check_exchange - INFO - Exchange "okx" is officially supported by the Freqtrade development team. +2025-04-29 01:54:56,916 - freqtrade.configuration.configuration - INFO - Using pairlist from configuration. +2025-04-29 01:54:56,917 - freqtrade.configuration.config_validation - INFO - Validating configuration ... +2025-04-29 01:54:56,919 - freqtrade.commands.optimize_commands - INFO - Starting freqtrade in Backtesting mode +2025-04-29 01:54:56,919 - freqtrade.exchange.exchange - INFO - Instance is running with dry_run enabled +2025-04-29 01:54:56,920 - freqtrade.exchange.exchange - INFO - Using CCXT 4.4.69 +2025-04-29 01:54:56,920 - freqtrade.exchange.exchange - INFO - Applying additional ccxt config: {'enableRateLimit': True, 'rateLimit': 500, 'options': {'defaultType': 'spot'}} +2025-04-29 01:54:56,925 - freqtrade.exchange.exchange - INFO - Applying additional ccxt config: {'enableRateLimit': True, 'rateLimit': 500, 'options': {'defaultType': 'spot'}, 'timeout': 20000} +2025-04-29 01:54:56,931 - freqtrade.exchange.exchange - INFO - Using Exchange "OKX" +2025-04-29 01:54:59,471 - freqtrade.resolvers.exchange_resolver - INFO - Using resolved exchange 'Okx'... +2025-04-29 01:54:59,491 - freqtrade.resolvers.iresolver - INFO - Using resolved strategy FreqaiExampleStrategy from '/freqtrade/templates/FreqaiExampleStrategy.py'... +2025-04-29 01:54:59,491 - freqtrade.strategy.hyper - INFO - Loading parameters from file /freqtrade/templates/FreqaiExampleStrategy.json +2025-04-29 01:54:59,492 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'timeframe' with value in config file: 3m. +2025-04-29 01:54:59,492 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'stoploss' with value in config file: -0.05. +2025-04-29 01:54:59,493 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'stake_currency' with value in config file: USDT. +2025-04-29 01:54:59,493 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'stake_amount' with value in config file: 150. +2025-04-29 01:54:59,493 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'startup_candle_count' with value in config file: 30. +2025-04-29 01:54:59,494 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'unfilledtimeout' with value in config file: {'entry': 5, 'exit': 15, 'exit_timeout_count': 0, 'unit': +'minutes'}. +2025-04-29 01:54:59,494 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'max_open_trades' with value in config file: 4. +2025-04-29 01:54:59,494 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using minimal_roi: {'0': 0.132, '8': 0.047, '14': 0.007, '60': 0} +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using timeframe: 3m +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using stoploss: -0.05 +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_stop: True +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_stop_positive: 0.01 +2025-04-29 01:54:59,496 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_stop_positive_offset: 0.02 +2025-04-29 01:54:59,496 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_only_offset_is_reached: False +2025-04-29 01:54:59,496 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using use_custom_stoploss: False +2025-04-29 01:54:59,497 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using process_only_new_candles: True +2025-04-29 01:54:59,497 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using order_types: {'entry': 'limit', 'exit': 'limit', 'stoploss': 'limit', 'stoploss_on_exchange': False, +'stoploss_on_exchange_interval': 60} +2025-04-29 01:54:59,497 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using order_time_in_force: {'entry': 'GTC', 'exit': 'GTC'} +2025-04-29 01:54:59,498 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using stake_currency: USDT +2025-04-29 01:54:59,498 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using stake_amount: 150 +2025-04-29 01:54:59,498 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using startup_candle_count: 30 +2025-04-29 01:54:59,499 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using unfilledtimeout: {'entry': 5, 'exit': 15, 'exit_timeout_count': 0, 'unit': 'minutes'} +2025-04-29 01:54:59,499 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using use_exit_signal: True +2025-04-29 01:54:59,499 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using exit_profit_only: False +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using ignore_roi_if_entry_signal: False +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using exit_profit_offset: 0.0 +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using disable_dataframe_checks: False +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using ignore_buying_expired_candle_after: 0 +2025-04-29 01:54:59,501 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using position_adjustment_enable: False +2025-04-29 01:54:59,501 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using max_entry_position_adjustment: -1 +2025-04-29 01:54:59,501 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using max_open_trades: 4 +2025-04-29 01:54:59,502 - freqtrade.configuration.config_validation - INFO - Validating configuration ... +2025-04-29 01:54:59,505 - freqtrade.resolvers.iresolver - INFO - Using resolved pairlist StaticPairList from '/freqtrade/freqtrade/plugins/pairlist/StaticPairList.py'... +2025-04-29 01:54:59,512 - freqtrade.optimize.backtesting - INFO - Using fee 0.1500% - worst case fee from exchange (lowest tier). +2025-04-29 01:54:59,512 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 3m to 14450 +2025-04-29 01:54:59,513 - freqtrade.data.history.history_utils - INFO - Using indicator startup period: 14450 ... +2025-04-29 01:54:59,672 - freqtrade.optimize.backtesting - INFO - Loading data from 2024-12-01 21:30:00 up to 2025-04-20 00:00:00 (139 days). +2025-04-29 01:54:59,672 - freqtrade.optimize.backtesting - INFO - Dataload complete. Calculating indicators +2025-04-29 01:54:59,673 - freqtrade.optimize.backtesting - INFO - Running backtesting for Strategy FreqaiExampleStrategy +2025-04-29 01:55:01,274 - matplotlib.font_manager - INFO - generated new fontManager +2025-04-29 01:55:01,489 - freqtrade.resolvers.iresolver - INFO - Using resolved freqaimodel XGBoostRegressor from '/freqtrade/freqtrade/freqai/prediction_models/XGBoostRegressor.py'... +2025-04-29 01:55:01,490 - freqtrade.freqai.data_drawer - INFO - Could not find existing datadrawer, starting from scratch +2025-04-29 01:55:01,491 - freqtrade.freqai.data_drawer - INFO - Could not find existing historic_predictions, starting from scratch +2025-04-29 01:55:01,491 - freqtrade.freqai.freqai_interface - INFO - Set fresh train queue from whitelist. Queue: ['BTC/USDT', 'SOL/USDT'] +2025-04-29 01:55:01,492 - freqtrade.strategy.hyper - INFO - Strategy Parameter: buy_rsi = 39.92672300850069 +2025-04-29 01:55:01,492 - freqtrade.strategy.hyper - INFO - Strategy Parameter: sell_rsi = 69.92672300850067 +2025-04-29 01:55:01,493 - freqtrade.strategy.hyper - INFO - No params for protection found, using default values. +2025-04-29 01:55:01,498 - FreqaiExampleStrategy - INFO - 处理交易对：BTC/USDT +2025-04-29 01:55:01,500 - freqtrade.freqai.freqai_interface - INFO - Training 11 timeranges +2025-04-29 01:55:01,501 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2024-12-02 00:00:00 to 2025-01-01 00:00:00, 1/11 trains +2025-04-29 01:55:01,502 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1735689600_prediction.feather +2025-04-29 01:55:01,602 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 5m to 8690 +2025-04-29 01:55:01,603 - freqtrade.data.dataprovider - INFO - Loading data for BTC/USDT 5m from 2024-12-01 19:50:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:01,705 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 1h to 770 +2025-04-29 01:55:01,706 - freqtrade.data.dataprovider - INFO - Loading data for BTC/USDT 1h from 2024-11-29 22:00:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:01,814 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 3m to 14450 +2025-04-29 01:55:01,815 - freqtrade.data.dataprovider - INFO - Loading data for ETH/USDT 3m from 2024-12-01 21:30:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:01,942 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 5m to 8690 +2025-04-29 01:55:01,943 - freqtrade.data.dataprovider - INFO - Loading data for ETH/USDT 5m from 2024-12-01 19:50:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:02,037 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 1h to 770 +2025-04-29 01:55:02,038 - freqtrade.data.dataprovider - INFO - Loading data for ETH/USDT 1h from 2024-11-29 22:00:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:02,113 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:02,118 - FreqaiExampleStrategy - INFO - 目标列形状：(14450,) +2025-04-29 01:55:02,121 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.152831 +1 0.003285 50.152831 +2 0.001898 50.152831 +3 0.000484 50.152831 +4 0.001688 50.152831 +2025-04-29 01:55:02,123 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:02,129 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:55:02,130 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.202701 +1 0.003285 50.202701 +2 0.001898 50.202701 +3 0.000484 50.202701 +4 0.001688 50.202701 +2025-04-29 01:55:02,134 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1735689600/cb_btc_1735689600 +2025-04-29 01:55:02,135 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:02,151 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:02,152 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-02 to 2024-12-31 -------------------- +2025-04-29 01:55:07,277 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:07,278 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.24624 validation_1-rmse:0.26036 +[1] validation_0-rmse:0.24176 validation_1-rmse:0.25460 +[2] validation_0-rmse:0.23782 validation_1-rmse:0.24904 +[3] validation_0-rmse:0.23408 validation_1-rmse:0.24381 +[4] validation_0-rmse:0.23057 validation_1-rmse:0.23882 +[5] validation_0-rmse:0.22701 validation_1-rmse:0.23409 +[6] validation_0-rmse:0.22400 validation_1-rmse:0.22962 +[7] validation_0-rmse:0.22088 validation_1-rmse:0.22533 +[8] validation_0-rmse:0.21817 validation_1-rmse:0.22130 +[9] validation_0-rmse:0.21491 validation_1-rmse:0.21740 +[10] validation_0-rmse:0.21265 validation_1-rmse:0.21347 +[11] validation_0-rmse:0.20982 validation_1-rmse:0.20978 +[12] validation_0-rmse:0.20747 validation_1-rmse:0.20640 +[13] validation_0-rmse:0.20512 validation_1-rmse:0.20299 +[14] validation_0-rmse:0.20280 validation_1-rmse:0.19966 +[15] validation_0-rmse:0.20012 validation_1-rmse:0.19656 +[16] validation_0-rmse:0.19785 validation_1-rmse:0.19346 +[17] validation_0-rmse:0.19572 validation_1-rmse:0.19054 +[18] validation_0-rmse:0.19400 validation_1-rmse:0.18759 +[19] validation_0-rmse:0.19164 validation_1-rmse:0.18488 +[20] validation_0-rmse:0.18956 validation_1-rmse:0.18205 +[21] validation_0-rmse:0.18746 validation_1-rmse:0.17951 +[22] validation_0-rmse:0.18593 validation_1-rmse:0.17696 +[23] validation_0-rmse:0.18395 validation_1-rmse:0.17465 +[24] validation_0-rmse:0.18249 validation_1-rmse:0.17217 +[25] validation_0-rmse:0.18084 validation_1-rmse:0.16993 +[26] validation_0-rmse:0.17928 validation_1-rmse:0.16771 +[27] validation_0-rmse:0.17776 validation_1-rmse:0.16571 +[28] validation_0-rmse:0.17652 validation_1-rmse:0.16356 +[29] validation_0-rmse:0.17499 validation_1-rmse:0.16166 +[30] validation_0-rmse:0.17371 validation_1-rmse:0.15983 +[31] validation_0-rmse:0.17243 validation_1-rmse:0.15792 +[32] validation_0-rmse:0.17110 validation_1-rmse:0.15628 +[33] validation_0-rmse:0.16996 validation_1-rmse:0.15433 +[34] validation_0-rmse:0.16884 validation_1-rmse:0.15277 +[35] validation_0-rmse:0.16785 validation_1-rmse:0.15090 +[36] validation_0-rmse:0.16682 validation_1-rmse:0.14942 +[37] validation_0-rmse:0.16559 validation_1-rmse:0.14774 +[38] validation_0-rmse:0.16459 validation_1-rmse:0.14628 +[39] validation_0-rmse:0.16356 validation_1-rmse:0.14466 +[40] validation_0-rmse:0.16250 validation_1-rmse:0.14330 +[41] validation_0-rmse:0.16153 validation_1-rmse:0.14201 +[42] validation_0-rmse:0.16059 validation_1-rmse:0.14075 +[43] validation_0-rmse:0.15986 validation_1-rmse:0.13938 +[44] validation_0-rmse:0.15908 validation_1-rmse:0.13822 +[45] validation_0-rmse:0.15810 validation_1-rmse:0.13687 +[46] validation_0-rmse:0.15733 validation_1-rmse:0.13577 +[47] validation_0-rmse:0.15655 validation_1-rmse:0.13458 +[48] validation_0-rmse:0.15580 validation_1-rmse:0.13355 +[49] validation_0-rmse:0.15512 validation_1-rmse:0.13228 +[50] validation_0-rmse:0.15434 validation_1-rmse:0.13121 +[51] validation_0-rmse:0.15363 validation_1-rmse:0.13030 +[52] validation_0-rmse:0.15294 validation_1-rmse:0.12937 +[53] validation_0-rmse:0.15243 validation_1-rmse:0.12818 +[54] validation_0-rmse:0.15170 validation_1-rmse:0.12720 +[55] validation_0-rmse:0.15096 validation_1-rmse:0.12632 +[56] validation_0-rmse:0.15035 validation_1-rmse:0.12538 +[57] validation_0-rmse:0.14977 validation_1-rmse:0.12453 +[58] validation_0-rmse:0.14914 validation_1-rmse:0.12363 +[59] validation_0-rmse:0.14867 validation_1-rmse:0.12263 +[60] validation_0-rmse:0.14819 validation_1-rmse:0.12183 +[61] validation_0-rmse:0.14763 validation_1-rmse:0.12108 +[62] validation_0-rmse:0.14706 validation_1-rmse:0.12035 +[63] validation_0-rmse:0.14648 validation_1-rmse:0.11946 +[64] validation_0-rmse:0.14601 validation_1-rmse:0.11876 +[65] validation_0-rmse:0.14553 validation_1-rmse:0.11808 +[66] validation_0-rmse:0.14506 validation_1-rmse:0.11742 +[67] validation_0-rmse:0.14469 validation_1-rmse:0.11671 +[68] validation_0-rmse:0.14422 validation_1-rmse:0.11604 +[69] validation_0-rmse:0.14381 validation_1-rmse:0.11543 +[70] validation_0-rmse:0.14337 validation_1-rmse:0.11485 +[71] validation_0-rmse:0.14294 validation_1-rmse:0.11398 +[72] validation_0-rmse:0.14260 validation_1-rmse:0.11335 +[73] validation_0-rmse:0.14223 validation_1-rmse:0.11278 +[74] validation_0-rmse:0.14190 validation_1-rmse:0.11225 +[75] validation_0-rmse:0.14144 validation_1-rmse:0.11143 +[76] validation_0-rmse:0.14098 validation_1-rmse:0.11052 +[77] validation_0-rmse:0.14062 validation_1-rmse:0.10998 +[78] validation_0-rmse:0.14029 validation_1-rmse:0.10953 +[79] validation_0-rmse:0.13993 validation_1-rmse:0.10888 +[80] validation_0-rmse:0.13958 validation_1-rmse:0.10839 +[81] validation_0-rmse:0.13918 validation_1-rmse:0.10767 +[82] validation_0-rmse:0.13897 validation_1-rmse:0.10720 +[83] validation_0-rmse:0.13864 validation_1-rmse:0.10669 +[84] validation_0-rmse:0.13836 validation_1-rmse:0.10620 +[85] validation_0-rmse:0.13810 validation_1-rmse:0.10573 +[86] validation_0-rmse:0.13782 validation_1-rmse:0.10526 +[87] validation_0-rmse:0.13756 validation_1-rmse:0.10458 +[88] validation_0-rmse:0.13736 validation_1-rmse:0.10420 +[89] validation_0-rmse:0.13708 validation_1-rmse:0.10383 +[90] validation_0-rmse:0.13685 validation_1-rmse:0.10343 +[91] validation_0-rmse:0.13658 validation_1-rmse:0.10298 +[92] validation_0-rmse:0.13646 validation_1-rmse:0.10231 +[93] validation_0-rmse:0.13615 validation_1-rmse:0.10190 +[94] validation_0-rmse:0.13589 validation_1-rmse:0.10154 +[95] validation_0-rmse:0.13572 validation_1-rmse:0.10095 +[96] validation_0-rmse:0.13550 validation_1-rmse:0.10058 +[97] validation_0-rmse:0.13530 validation_1-rmse:0.10026 +[98] validation_0-rmse:0.13513 validation_1-rmse:0.09995 +[99] validation_0-rmse:0.13480 validation_1-rmse:0.09950 +2025-04-29 01:55:08,221 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (6.09 secs) -------------------- +2025-04-29 01:55:08,222 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:08,903 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2024-12-12 00:00:00 to 2025-01-11 00:00:00, 2/11 trains +2025-04-29 01:55:08,904 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1736553600_prediction.feather +2025-04-29 01:55:08,907 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:08,912 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:55:08,914 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.202701 +1 0.003285 50.202701 +2 0.001898 50.202701 +3 0.000484 50.202701 +4 0.001688 50.202701 +2025-04-29 01:55:08,917 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:08,924 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:55:08,925 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.367593 +1 0.003285 50.367593 +2 0.001898 50.367593 +3 0.000484 50.367593 +4 0.001688 50.367593 +2025-04-29 01:55:08,929 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1736553600/cb_btc_1736553600 +2025-04-29 01:55:08,930 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:08,946 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:08,947 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-12 to 2025-01-10 -------------------- +2025-04-29 01:55:13,908 - datasieve.pipeline - INFO - DI tossed 5 predictions for being too far from training data. +2025-04-29 01:55:13,911 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:13,912 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.26037 validation_1-rmse:0.25324 +[1] validation_0-rmse:0.25572 validation_1-rmse:0.24787 +[2] validation_0-rmse:0.25117 validation_1-rmse:0.24281 +[3] validation_0-rmse:0.24697 validation_1-rmse:0.23802 +[4] validation_0-rmse:0.24328 validation_1-rmse:0.23332 +[5] validation_0-rmse:0.23939 validation_1-rmse:0.22905 +[6] validation_0-rmse:0.23522 validation_1-rmse:0.22484 +[7] validation_0-rmse:0.23148 validation_1-rmse:0.22085 +[8] validation_0-rmse:0.22873 validation_1-rmse:0.21697 +[9] validation_0-rmse:0.22519 validation_1-rmse:0.21317 +[10] validation_0-rmse:0.22206 validation_1-rmse:0.20963 +[11] validation_0-rmse:0.21866 validation_1-rmse:0.20626 +[12] validation_0-rmse:0.21563 validation_1-rmse:0.20296 +[13] validation_0-rmse:0.21313 validation_1-rmse:0.19956 +[14] validation_0-rmse:0.21062 validation_1-rmse:0.19636 +[15] validation_0-rmse:0.20808 validation_1-rmse:0.19339 +[16] validation_0-rmse:0.20570 validation_1-rmse:0.19058 +[17] validation_0-rmse:0.20318 validation_1-rmse:0.18781 +[18] validation_0-rmse:0.20113 validation_1-rmse:0.18518 +[19] validation_0-rmse:0.19934 validation_1-rmse:0.18248 +[20] validation_0-rmse:0.19735 validation_1-rmse:0.18006 +[21] validation_0-rmse:0.19541 validation_1-rmse:0.17744 +[22] validation_0-rmse:0.19336 validation_1-rmse:0.17517 +[23] validation_0-rmse:0.19145 validation_1-rmse:0.17301 +[24] validation_0-rmse:0.18989 validation_1-rmse:0.17058 +[25] validation_0-rmse:0.18782 validation_1-rmse:0.16854 +[26] validation_0-rmse:0.18634 validation_1-rmse:0.16625 +[27] validation_0-rmse:0.18471 validation_1-rmse:0.16430 +[28] validation_0-rmse:0.18312 validation_1-rmse:0.16236 +[29] validation_0-rmse:0.18157 validation_1-rmse:0.16053 +[30] validation_0-rmse:0.17991 validation_1-rmse:0.15849 +[31] validation_0-rmse:0.17839 validation_1-rmse:0.15677 +[32] validation_0-rmse:0.17693 validation_1-rmse:0.15498 +[33] validation_0-rmse:0.17574 validation_1-rmse:0.15336 +[34] validation_0-rmse:0.17469 validation_1-rmse:0.15168 +[35] validation_0-rmse:0.17352 validation_1-rmse:0.15015 +[36] validation_0-rmse:0.17228 validation_1-rmse:0.14868 +[37] validation_0-rmse:0.17127 validation_1-rmse:0.14692 +[38] validation_0-rmse:0.17030 validation_1-rmse:0.14553 +[39] validation_0-rmse:0.16926 validation_1-rmse:0.14420 +[40] validation_0-rmse:0.16821 validation_1-rmse:0.14297 +[41] validation_0-rmse:0.16740 validation_1-rmse:0.14144 +[42] validation_0-rmse:0.16647 validation_1-rmse:0.14020 +[43] validation_0-rmse:0.16548 validation_1-rmse:0.13903 +[44] validation_0-rmse:0.16440 validation_1-rmse:0.13765 +[45] validation_0-rmse:0.16353 validation_1-rmse:0.13652 +[46] validation_0-rmse:0.16269 validation_1-rmse:0.13522 +[47] validation_0-rmse:0.16193 validation_1-rmse:0.13419 +[48] validation_0-rmse:0.16114 validation_1-rmse:0.13311 +[49] validation_0-rmse:0.16043 validation_1-rmse:0.13214 +[50] validation_0-rmse:0.15971 validation_1-rmse:0.13090 +[51] validation_0-rmse:0.15909 validation_1-rmse:0.12992 +[52] validation_0-rmse:0.15834 validation_1-rmse:0.12899 +[53] validation_0-rmse:0.15763 validation_1-rmse:0.12809 +[54] validation_0-rmse:0.15697 validation_1-rmse:0.12724 +[55] validation_0-rmse:0.15631 validation_1-rmse:0.12637 +[56] validation_0-rmse:0.15553 validation_1-rmse:0.12535 +[57] validation_0-rmse:0.15494 validation_1-rmse:0.12456 +[58] validation_0-rmse:0.15452 validation_1-rmse:0.12352 +[59] validation_0-rmse:0.15396 validation_1-rmse:0.12273 +[60] validation_0-rmse:0.15334 validation_1-rmse:0.12196 +[61] validation_0-rmse:0.15274 validation_1-rmse:0.12123 +[62] validation_0-rmse:0.15221 validation_1-rmse:0.12048 +[63] validation_0-rmse:0.15176 validation_1-rmse:0.11953 +[64] validation_0-rmse:0.15133 validation_1-rmse:0.11887 +[65] validation_0-rmse:0.15080 validation_1-rmse:0.11796 +[66] validation_0-rmse:0.15035 validation_1-rmse:0.11734 +[67] validation_0-rmse:0.14995 validation_1-rmse:0.11667 +[68] validation_0-rmse:0.14954 validation_1-rmse:0.11616 +[69] validation_0-rmse:0.14916 validation_1-rmse:0.11535 +[70] validation_0-rmse:0.14887 validation_1-rmse:0.11469 +[71] validation_0-rmse:0.14854 validation_1-rmse:0.11408 +[72] validation_0-rmse:0.14811 validation_1-rmse:0.11334 +[73] validation_0-rmse:0.14766 validation_1-rmse:0.11278 +[74] validation_0-rmse:0.14738 validation_1-rmse:0.11231 +[75] validation_0-rmse:0.14697 validation_1-rmse:0.11184 +[76] validation_0-rmse:0.14663 validation_1-rmse:0.11108 +[77] validation_0-rmse:0.14635 validation_1-rmse:0.11058 +[78] validation_0-rmse:0.14591 validation_1-rmse:0.10984 +[79] validation_0-rmse:0.14561 validation_1-rmse:0.10929 +[80] validation_0-rmse:0.14529 validation_1-rmse:0.10875 +[81] validation_0-rmse:0.14510 validation_1-rmse:0.10826 +[82] validation_0-rmse:0.14471 validation_1-rmse:0.10772 +[83] validation_0-rmse:0.14444 validation_1-rmse:0.10725 +[84] validation_0-rmse:0.14420 validation_1-rmse:0.10652 +[85] validation_0-rmse:0.14393 validation_1-rmse:0.10608 +[86] validation_0-rmse:0.14371 validation_1-rmse:0.10567 +[87] validation_0-rmse:0.14342 validation_1-rmse:0.10528 +[88] validation_0-rmse:0.14314 validation_1-rmse:0.10483 +[89] validation_0-rmse:0.14307 validation_1-rmse:0.10439 +[90] validation_0-rmse:0.14273 validation_1-rmse:0.10395 +[91] validation_0-rmse:0.14237 validation_1-rmse:0.10353 +[92] validation_0-rmse:0.14210 validation_1-rmse:0.10318 +[93] validation_0-rmse:0.14186 validation_1-rmse:0.10279 +[94] validation_0-rmse:0.14175 validation_1-rmse:0.10234 +[95] validation_0-rmse:0.14153 validation_1-rmse:0.10204 +[96] validation_0-rmse:0.14142 validation_1-rmse:0.10160 +[97] validation_0-rmse:0.14124 validation_1-rmse:0.10126 +[98] validation_0-rmse:0.14102 validation_1-rmse:0.10068 +[99] validation_0-rmse:0.14079 validation_1-rmse:0.10036 +2025-04-29 01:55:14,692 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.76 secs) -------------------- +2025-04-29 01:55:14,693 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:15,250 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2024-12-22 00:00:00 to 2025-01-21 00:00:00, 3/11 trains +2025-04-29 01:55:15,250 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1737417600_prediction.feather +2025-04-29 01:55:15,254 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:15,261 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:55:15,262 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.367593 +1 0.003285 50.367593 +2 0.001898 50.367593 +3 0.000484 50.367593 +4 0.001688 50.367593 +2025-04-29 01:55:15,268 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:15,275 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:55:15,276 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.305589 +1 0.003285 50.305589 +2 0.001898 50.305589 +3 0.000484 50.305589 +4 0.001688 50.305589 +2025-04-29 01:55:15,281 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1737417600/cb_btc_1737417600 +2025-04-29 01:55:15,281 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:15,297 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:15,298 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-22 to 2025-01-20 -------------------- +2025-04-29 01:55:20,324 - datasieve.pipeline - INFO - DI tossed 1622 predictions for being too far from training data. +2025-04-29 01:55:20,327 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:20,327 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.25769 validation_1-rmse:0.25549 +[1] validation_0-rmse:0.25314 validation_1-rmse:0.24986 +[2] validation_0-rmse:0.24864 validation_1-rmse:0.24456 +[3] validation_0-rmse:0.24486 validation_1-rmse:0.23955 +[4] validation_0-rmse:0.24144 validation_1-rmse:0.23480 +[5] validation_0-rmse:0.23803 validation_1-rmse:0.23024 +[6] validation_0-rmse:0.23468 validation_1-rmse:0.22599 +[7] validation_0-rmse:0.23134 validation_1-rmse:0.22162 +[8] validation_0-rmse:0.22843 validation_1-rmse:0.21773 +[9] validation_0-rmse:0.22560 validation_1-rmse:0.21396 +[10] validation_0-rmse:0.22402 validation_1-rmse:0.21023 +[11] validation_0-rmse:0.22155 validation_1-rmse:0.20680 +[12] validation_0-rmse:0.21899 validation_1-rmse:0.20342 +[13] validation_0-rmse:0.21654 validation_1-rmse:0.20029 +[14] validation_0-rmse:0.21431 validation_1-rmse:0.19719 +[15] validation_0-rmse:0.21282 validation_1-rmse:0.19411 +[16] validation_0-rmse:0.21076 validation_1-rmse:0.19117 +[17] validation_0-rmse:0.20882 validation_1-rmse:0.18835 +[18] validation_0-rmse:0.20695 validation_1-rmse:0.18547 +[19] validation_0-rmse:0.20538 validation_1-rmse:0.18292 +[20] validation_0-rmse:0.20345 validation_1-rmse:0.18038 +[21] validation_0-rmse:0.20148 validation_1-rmse:0.17799 +[22] validation_0-rmse:0.19991 validation_1-rmse:0.17569 +[23] validation_0-rmse:0.19832 validation_1-rmse:0.17350 +[24] validation_0-rmse:0.19658 validation_1-rmse:0.17096 +[25] validation_0-rmse:0.19474 validation_1-rmse:0.16879 +[26] validation_0-rmse:0.19292 validation_1-rmse:0.16665 +[27] validation_0-rmse:0.19134 validation_1-rmse:0.16470 +[28] validation_0-rmse:0.19034 validation_1-rmse:0.16253 +[29] validation_0-rmse:0.18882 validation_1-rmse:0.16068 +[30] validation_0-rmse:0.18736 validation_1-rmse:0.15892 +[31] validation_0-rmse:0.18605 validation_1-rmse:0.15690 +[32] validation_0-rmse:0.18481 validation_1-rmse:0.15521 +[33] validation_0-rmse:0.18346 validation_1-rmse:0.15356 +[34] validation_0-rmse:0.18222 validation_1-rmse:0.15188 +[35] validation_0-rmse:0.18095 validation_1-rmse:0.15028 +[36] validation_0-rmse:0.18015 validation_1-rmse:0.14857 +[37] validation_0-rmse:0.17915 validation_1-rmse:0.14713 +[38] validation_0-rmse:0.17817 validation_1-rmse:0.14573 +[39] validation_0-rmse:0.17723 validation_1-rmse:0.14437 +[40] validation_0-rmse:0.17619 validation_1-rmse:0.14308 +[41] validation_0-rmse:0.17509 validation_1-rmse:0.14176 +[42] validation_0-rmse:0.17407 validation_1-rmse:0.14047 +[43] validation_0-rmse:0.17340 validation_1-rmse:0.13921 +[44] validation_0-rmse:0.17245 validation_1-rmse:0.13806 +[45] validation_0-rmse:0.17212 validation_1-rmse:0.13685 +[46] validation_0-rmse:0.17133 validation_1-rmse:0.13577 +[47] validation_0-rmse:0.17064 validation_1-rmse:0.13451 +[48] validation_0-rmse:0.17004 validation_1-rmse:0.13331 +[49] validation_0-rmse:0.16941 validation_1-rmse:0.13222 +[50] validation_0-rmse:0.16858 validation_1-rmse:0.13123 +[51] validation_0-rmse:0.16786 validation_1-rmse:0.13007 +[52] validation_0-rmse:0.16718 validation_1-rmse:0.12912 +[53] validation_0-rmse:0.16651 validation_1-rmse:0.12806 +[54] validation_0-rmse:0.16592 validation_1-rmse:0.12709 +[55] validation_0-rmse:0.16542 validation_1-rmse:0.12604 +[56] validation_0-rmse:0.16479 validation_1-rmse:0.12523 +[57] validation_0-rmse:0.16426 validation_1-rmse:0.12439 +[58] validation_0-rmse:0.16363 validation_1-rmse:0.12352 +[59] validation_0-rmse:0.16325 validation_1-rmse:0.12263 +[60] validation_0-rmse:0.16289 validation_1-rmse:0.12173 +[61] validation_0-rmse:0.16226 validation_1-rmse:0.12099 +[62] validation_0-rmse:0.16176 validation_1-rmse:0.12010 +[63] validation_0-rmse:0.16144 validation_1-rmse:0.11936 +[64] validation_0-rmse:0.16088 validation_1-rmse:0.11862 +[65] validation_0-rmse:0.16030 validation_1-rmse:0.11786 +[66] validation_0-rmse:0.15991 validation_1-rmse:0.11714 +[67] validation_0-rmse:0.15947 validation_1-rmse:0.11640 +[68] validation_0-rmse:0.15912 validation_1-rmse:0.11574 +[69] validation_0-rmse:0.15874 validation_1-rmse:0.11507 +[70] validation_0-rmse:0.15837 validation_1-rmse:0.11430 +[71] validation_0-rmse:0.15798 validation_1-rmse:0.11365 +[72] validation_0-rmse:0.15763 validation_1-rmse:0.11305 +[73] validation_0-rmse:0.15713 validation_1-rmse:0.11250 +[74] validation_0-rmse:0.15648 validation_1-rmse:0.11177 +[75] validation_0-rmse:0.15619 validation_1-rmse:0.11122 +[76] validation_0-rmse:0.15593 validation_1-rmse:0.11066 +[77] validation_0-rmse:0.15562 validation_1-rmse:0.11007 +[78] validation_0-rmse:0.15519 validation_1-rmse:0.10953 +[79] validation_0-rmse:0.15500 validation_1-rmse:0.10883 +[80] validation_0-rmse:0.15461 validation_1-rmse:0.10835 +[81] validation_0-rmse:0.15417 validation_1-rmse:0.10780 +[82] validation_0-rmse:0.15393 validation_1-rmse:0.10742 +[83] validation_0-rmse:0.15395 validation_1-rmse:0.10634 +[84] validation_0-rmse:0.15359 validation_1-rmse:0.10588 +[85] validation_0-rmse:0.15315 validation_1-rmse:0.10539 +[86] validation_0-rmse:0.15315 validation_1-rmse:0.10440 +[87] validation_0-rmse:0.15278 validation_1-rmse:0.10400 +[88] validation_0-rmse:0.15239 validation_1-rmse:0.10353 +[89] validation_0-rmse:0.15200 validation_1-rmse:0.10310 +[90] validation_0-rmse:0.15182 validation_1-rmse:0.10245 +[91] validation_0-rmse:0.15175 validation_1-rmse:0.10182 +[92] validation_0-rmse:0.15139 validation_1-rmse:0.10138 +[93] validation_0-rmse:0.15105 validation_1-rmse:0.10095 +[94] validation_0-rmse:0.15091 validation_1-rmse:0.10056 +[95] validation_0-rmse:0.15088 validation_1-rmse:0.09964 +[96] validation_0-rmse:0.15065 validation_1-rmse:0.09927 +[97] validation_0-rmse:0.15036 validation_1-rmse:0.09888 +[98] validation_0-rmse:0.15021 validation_1-rmse:0.09852 +[99] validation_0-rmse:0.15004 validation_1-rmse:0.09815 +2025-04-29 01:55:21,007 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.73 secs) -------------------- +2025-04-29 01:55:21,008 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:21,504 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-01 00:00:00 to 2025-01-31 00:00:00, 4/11 trains +2025-04-29 01:55:21,505 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1738281600_prediction.feather +2025-04-29 01:55:21,510 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:21,516 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:55:21,517 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.305589 +1 0.003285 50.305589 +2 0.001898 50.305589 +3 0.000484 50.305589 +4 0.001688 50.305589 +2025-04-29 01:55:21,522 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:21,528 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:55:21,529 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.168798 +1 0.003285 50.168798 +2 0.001898 50.168798 +3 0.000484 50.168798 +4 0.001688 50.168798 +2025-04-29 01:55:21,533 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1738281600/cb_btc_1738281600 +2025-04-29 01:55:21,534 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:21,550 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:21,550 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-01 to 2025-01-30 -------------------- +2025-04-29 01:55:26,605 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:26,606 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.25046 validation_1-rmse:0.26128 +[1] validation_0-rmse:0.24588 validation_1-rmse:0.25570 +[2] validation_0-rmse:0.24156 validation_1-rmse:0.25047 +[3] validation_0-rmse:0.23757 validation_1-rmse:0.24551 +[4] validation_0-rmse:0.23411 validation_1-rmse:0.24075 +[5] validation_0-rmse:0.23029 validation_1-rmse:0.23637 +[6] validation_0-rmse:0.22707 validation_1-rmse:0.23199 +[7] validation_0-rmse:0.22405 validation_1-rmse:0.22801 +[8] validation_0-rmse:0.22083 validation_1-rmse:0.22420 +[9] validation_0-rmse:0.21768 validation_1-rmse:0.22038 +[10] validation_0-rmse:0.21473 validation_1-rmse:0.21674 +[11] validation_0-rmse:0.21187 validation_1-rmse:0.21322 +[12] validation_0-rmse:0.20911 validation_1-rmse:0.20996 +[13] validation_0-rmse:0.20669 validation_1-rmse:0.20679 +[14] validation_0-rmse:0.20441 validation_1-rmse:0.20366 +[15] validation_0-rmse:0.20250 validation_1-rmse:0.20054 +[16] validation_0-rmse:0.20017 validation_1-rmse:0.19757 +[17] validation_0-rmse:0.19804 validation_1-rmse:0.19490 +[18] validation_0-rmse:0.19618 validation_1-rmse:0.19221 +[19] validation_0-rmse:0.19404 validation_1-rmse:0.18954 +[20] validation_0-rmse:0.19209 validation_1-rmse:0.18666 +[21] validation_0-rmse:0.19014 validation_1-rmse:0.18430 +[22] validation_0-rmse:0.18845 validation_1-rmse:0.18197 +[23] validation_0-rmse:0.18653 validation_1-rmse:0.17972 +[24] validation_0-rmse:0.18468 validation_1-rmse:0.17722 +[25] validation_0-rmse:0.18325 validation_1-rmse:0.17491 +[26] validation_0-rmse:0.18152 validation_1-rmse:0.17284 +[27] validation_0-rmse:0.17999 validation_1-rmse:0.17092 +[28] validation_0-rmse:0.17846 validation_1-rmse:0.16892 +[29] validation_0-rmse:0.17696 validation_1-rmse:0.16709 +[30] validation_0-rmse:0.17558 validation_1-rmse:0.16510 +[31] validation_0-rmse:0.17418 validation_1-rmse:0.16335 +[32] validation_0-rmse:0.17293 validation_1-rmse:0.16161 +[33] validation_0-rmse:0.17159 validation_1-rmse:0.16003 +[34] validation_0-rmse:0.17030 validation_1-rmse:0.15831 +[35] validation_0-rmse:0.16907 validation_1-rmse:0.15681 +[36] validation_0-rmse:0.16796 validation_1-rmse:0.15513 +[37] validation_0-rmse:0.16690 validation_1-rmse:0.15349 +[38] validation_0-rmse:0.16580 validation_1-rmse:0.15204 +[39] validation_0-rmse:0.16492 validation_1-rmse:0.15050 +[40] validation_0-rmse:0.16383 validation_1-rmse:0.14918 +[41] validation_0-rmse:0.16281 validation_1-rmse:0.14788 +[42] validation_0-rmse:0.16176 validation_1-rmse:0.14660 +[43] validation_0-rmse:0.16082 validation_1-rmse:0.14516 +[44] validation_0-rmse:0.15990 validation_1-rmse:0.14395 +[45] validation_0-rmse:0.15891 validation_1-rmse:0.14281 +[46] validation_0-rmse:0.15797 validation_1-rmse:0.14168 +[47] validation_0-rmse:0.15712 validation_1-rmse:0.14040 +[48] validation_0-rmse:0.15632 validation_1-rmse:0.13933 +[49] validation_0-rmse:0.15542 validation_1-rmse:0.13821 +[50] validation_0-rmse:0.15458 validation_1-rmse:0.13705 +[51] validation_0-rmse:0.15404 validation_1-rmse:0.13583 +[52] validation_0-rmse:0.15334 validation_1-rmse:0.13483 +[53] validation_0-rmse:0.15256 validation_1-rmse:0.13387 +[54] validation_0-rmse:0.15190 validation_1-rmse:0.13290 +[55] validation_0-rmse:0.15122 validation_1-rmse:0.13174 +[56] validation_0-rmse:0.15065 validation_1-rmse:0.13080 +[57] validation_0-rmse:0.15006 validation_1-rmse:0.12993 +[58] validation_0-rmse:0.14955 validation_1-rmse:0.12897 +[59] validation_0-rmse:0.14893 validation_1-rmse:0.12814 +[60] validation_0-rmse:0.14843 validation_1-rmse:0.12735 +[61] validation_0-rmse:0.14789 validation_1-rmse:0.12642 +[62] validation_0-rmse:0.14718 validation_1-rmse:0.12561 +[63] validation_0-rmse:0.14659 validation_1-rmse:0.12486 +[64] validation_0-rmse:0.14600 validation_1-rmse:0.12397 +[65] validation_0-rmse:0.14547 validation_1-rmse:0.12324 +[66] validation_0-rmse:0.14499 validation_1-rmse:0.12255 +[67] validation_0-rmse:0.14451 validation_1-rmse:0.12188 +[68] validation_0-rmse:0.14393 validation_1-rmse:0.12114 +[69] validation_0-rmse:0.14346 validation_1-rmse:0.12048 +[70] validation_0-rmse:0.14293 validation_1-rmse:0.11974 +[71] validation_0-rmse:0.14256 validation_1-rmse:0.11893 +[72] validation_0-rmse:0.14212 validation_1-rmse:0.11830 +[73] validation_0-rmse:0.14177 validation_1-rmse:0.11748 +[74] validation_0-rmse:0.14134 validation_1-rmse:0.11686 +[75] validation_0-rmse:0.14101 validation_1-rmse:0.11609 +[76] validation_0-rmse:0.14060 validation_1-rmse:0.11536 +[77] validation_0-rmse:0.14020 validation_1-rmse:0.11484 +[78] validation_0-rmse:0.13983 validation_1-rmse:0.11412 +[79] validation_0-rmse:0.13951 validation_1-rmse:0.11357 +[80] validation_0-rmse:0.13928 validation_1-rmse:0.11273 +[81] validation_0-rmse:0.13889 validation_1-rmse:0.11221 +[82] validation_0-rmse:0.13855 validation_1-rmse:0.11166 +[83] validation_0-rmse:0.13824 validation_1-rmse:0.11114 +[84] validation_0-rmse:0.13808 validation_1-rmse:0.11050 +[85] validation_0-rmse:0.13767 validation_1-rmse:0.10998 +[86] validation_0-rmse:0.13731 validation_1-rmse:0.10947 +[87] validation_0-rmse:0.13716 validation_1-rmse:0.10876 +[88] validation_0-rmse:0.13678 validation_1-rmse:0.10832 +[89] validation_0-rmse:0.13659 validation_1-rmse:0.10782 +[90] validation_0-rmse:0.13629 validation_1-rmse:0.10736 +[91] validation_0-rmse:0.13600 validation_1-rmse:0.10662 +[92] validation_0-rmse:0.13577 validation_1-rmse:0.10613 +[93] validation_0-rmse:0.13541 validation_1-rmse:0.10565 +[94] validation_0-rmse:0.13534 validation_1-rmse:0.10501 +[95] validation_0-rmse:0.13511 validation_1-rmse:0.10453 +[96] validation_0-rmse:0.13483 validation_1-rmse:0.10401 +[97] validation_0-rmse:0.13455 validation_1-rmse:0.10362 +[98] validation_0-rmse:0.13425 validation_1-rmse:0.10323 +[99] validation_0-rmse:0.13402 validation_1-rmse:0.10289 +2025-04-29 01:55:27,556 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (6.02 secs) -------------------- +2025-04-29 01:55:27,557 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:28,076 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-11 00:00:00 to 2025-02-10 00:00:00, 5/11 trains +2025-04-29 01:55:28,077 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1739145600_prediction.feather +2025-04-29 01:55:28,081 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:28,088 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:55:28,089 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.168798 +1 0.003285 50.168798 +2 0.001898 50.168798 +3 0.000484 50.168798 +4 0.001688 50.168798 +2025-04-29 01:55:28,094 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:28,100 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:55:28,102 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.167897 +1 0.003285 50.167897 +2 0.001898 50.167897 +3 0.000484 50.167897 +4 0.001688 50.167897 +2025-04-29 01:55:28,106 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1739145600/cb_btc_1739145600 +2025-04-29 01:55:28,107 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:28,123 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:28,124 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-11 to 2025-02-09 -------------------- +2025-04-29 01:55:33,123 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:33,124 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.26428 validation_1-rmse:0.27464 +[1] validation_0-rmse:0.25911 validation_1-rmse:0.26865 +[2] validation_0-rmse:0.25427 validation_1-rmse:0.26296 +[3] validation_0-rmse:0.24970 validation_1-rmse:0.25748 +[4] validation_0-rmse:0.24525 validation_1-rmse:0.25222 +[5] validation_0-rmse:0.24140 validation_1-rmse:0.24725 +[6] validation_0-rmse:0.23748 validation_1-rmse:0.24264 +[7] validation_0-rmse:0.23368 validation_1-rmse:0.23792 +[8] validation_0-rmse:0.23022 validation_1-rmse:0.23363 +[9] validation_0-rmse:0.22695 validation_1-rmse:0.22945 +[10] validation_0-rmse:0.22381 validation_1-rmse:0.22543 +[11] validation_0-rmse:0.22105 validation_1-rmse:0.22154 +[12] validation_0-rmse:0.21818 validation_1-rmse:0.21797 +[13] validation_0-rmse:0.21526 validation_1-rmse:0.21430 +[14] validation_0-rmse:0.21284 validation_1-rmse:0.21101 +[15] validation_0-rmse:0.21034 validation_1-rmse:0.20769 +[16] validation_0-rmse:0.20802 validation_1-rmse:0.20438 +[17] validation_0-rmse:0.20590 validation_1-rmse:0.20136 +[18] validation_0-rmse:0.20386 validation_1-rmse:0.19837 +[19] validation_0-rmse:0.20219 validation_1-rmse:0.19549 +[20] validation_0-rmse:0.20037 validation_1-rmse:0.19283 +[21] validation_0-rmse:0.19826 validation_1-rmse:0.19005 +[22] validation_0-rmse:0.19657 validation_1-rmse:0.18750 +[23] validation_0-rmse:0.19525 validation_1-rmse:0.18498 +[24] validation_0-rmse:0.19373 validation_1-rmse:0.18267 +[25] validation_0-rmse:0.19197 validation_1-rmse:0.18037 +[26] validation_0-rmse:0.19063 validation_1-rmse:0.17799 +[27] validation_0-rmse:0.18897 validation_1-rmse:0.17587 +[28] validation_0-rmse:0.18765 validation_1-rmse:0.17382 +[29] validation_0-rmse:0.18608 validation_1-rmse:0.17185 +[30] validation_0-rmse:0.18456 validation_1-rmse:0.16992 +[31] validation_0-rmse:0.18340 validation_1-rmse:0.16793 +[32] validation_0-rmse:0.18206 validation_1-rmse:0.16616 +[33] validation_0-rmse:0.18077 validation_1-rmse:0.16437 +[34] validation_0-rmse:0.17960 validation_1-rmse:0.16270 +[35] validation_0-rmse:0.17857 validation_1-rmse:0.16105 +[36] validation_0-rmse:0.17748 validation_1-rmse:0.15925 +[37] validation_0-rmse:0.17649 validation_1-rmse:0.15762 +[38] validation_0-rmse:0.17540 validation_1-rmse:0.15611 +[39] validation_0-rmse:0.17427 validation_1-rmse:0.15469 +[40] validation_0-rmse:0.17312 validation_1-rmse:0.15301 +[41] validation_0-rmse:0.17217 validation_1-rmse:0.15169 +[42] validation_0-rmse:0.17119 validation_1-rmse:0.15037 +[43] validation_0-rmse:0.17030 validation_1-rmse:0.14910 +[44] validation_0-rmse:0.16939 validation_1-rmse:0.14786 +[45] validation_0-rmse:0.16851 validation_1-rmse:0.14660 +[46] validation_0-rmse:0.16793 validation_1-rmse:0.14518 +[47] validation_0-rmse:0.16760 validation_1-rmse:0.14365 +[48] validation_0-rmse:0.16674 validation_1-rmse:0.14258 +[49] validation_0-rmse:0.16588 validation_1-rmse:0.14152 +[50] validation_0-rmse:0.16505 validation_1-rmse:0.14051 +[51] validation_0-rmse:0.16437 validation_1-rmse:0.13919 +[52] validation_0-rmse:0.16361 validation_1-rmse:0.13818 +[53] validation_0-rmse:0.16290 validation_1-rmse:0.13715 +[54] validation_0-rmse:0.16217 validation_1-rmse:0.13621 +[55] validation_0-rmse:0.16207 validation_1-rmse:0.13493 +[56] validation_0-rmse:0.16153 validation_1-rmse:0.13395 +[57] validation_0-rmse:0.16077 validation_1-rmse:0.13302 +[58] validation_0-rmse:0.16021 validation_1-rmse:0.13218 +[59] validation_0-rmse:0.15972 validation_1-rmse:0.13117 +[60] validation_0-rmse:0.15954 validation_1-rmse:0.13003 +[61] validation_0-rmse:0.15896 validation_1-rmse:0.12926 +[62] validation_0-rmse:0.15849 validation_1-rmse:0.12848 +[63] validation_0-rmse:0.15801 validation_1-rmse:0.12770 +[64] validation_0-rmse:0.15737 validation_1-rmse:0.12678 +[65] validation_0-rmse:0.15736 validation_1-rmse:0.12578 +[66] validation_0-rmse:0.15684 validation_1-rmse:0.12506 +[67] validation_0-rmse:0.15638 validation_1-rmse:0.12437 +[68] validation_0-rmse:0.15618 validation_1-rmse:0.12336 +[69] validation_0-rmse:0.15581 validation_1-rmse:0.12269 +[70] validation_0-rmse:0.15537 validation_1-rmse:0.12205 +[71] validation_0-rmse:0.15534 validation_1-rmse:0.12117 +[72] validation_0-rmse:0.15485 validation_1-rmse:0.12049 +[73] validation_0-rmse:0.15465 validation_1-rmse:0.11968 +[74] validation_0-rmse:0.15430 validation_1-rmse:0.11906 +[75] validation_0-rmse:0.15386 validation_1-rmse:0.11840 +[76] validation_0-rmse:0.15353 validation_1-rmse:0.11781 +[77] validation_0-rmse:0.15354 validation_1-rmse:0.11697 +[78] validation_0-rmse:0.15325 validation_1-rmse:0.11630 +[79] validation_0-rmse:0.15282 validation_1-rmse:0.11572 +[80] validation_0-rmse:0.15239 validation_1-rmse:0.11514 +[81] validation_0-rmse:0.15226 validation_1-rmse:0.11431 +[82] validation_0-rmse:0.15189 validation_1-rmse:0.11381 +[83] validation_0-rmse:0.15171 validation_1-rmse:0.11316 +[84] validation_0-rmse:0.15136 validation_1-rmse:0.11270 +[85] validation_0-rmse:0.15112 validation_1-rmse:0.11212 +[86] validation_0-rmse:0.15112 validation_1-rmse:0.11140 +[87] validation_0-rmse:0.15074 validation_1-rmse:0.11094 +[88] validation_0-rmse:0.15048 validation_1-rmse:0.11035 +[89] validation_0-rmse:0.15026 validation_1-rmse:0.10983 +[90] validation_0-rmse:0.14989 validation_1-rmse:0.10938 +[91] validation_0-rmse:0.14955 validation_1-rmse:0.10893 +[92] validation_0-rmse:0.14955 validation_1-rmse:0.10815 +[93] validation_0-rmse:0.14933 validation_1-rmse:0.10765 +[94] validation_0-rmse:0.14908 validation_1-rmse:0.10711 +[95] validation_0-rmse:0.14889 validation_1-rmse:0.10668 +[96] validation_0-rmse:0.14853 validation_1-rmse:0.10627 +[97] validation_0-rmse:0.14853 validation_1-rmse:0.10553 +[98] validation_0-rmse:0.14835 validation_1-rmse:0.10513 +[99] validation_0-rmse:0.14818 validation_1-rmse:0.10475 +2025-04-29 01:55:33,929 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.82 secs) -------------------- +2025-04-29 01:55:33,930 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:34,433 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-21 00:00:00 to 2025-02-20 00:00:00, 6/11 trains +2025-04-29 01:55:34,434 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1740009600_prediction.feather +2025-04-29 01:55:34,440 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:34,447 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:55:34,448 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.167897 +1 0.003285 50.167897 +2 0.001898 50.167897 +3 0.000484 50.167897 +4 0.001688 50.167897 +2025-04-29 01:55:34,453 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:34,459 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:55:34,461 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.107698 +1 0.003285 50.107698 +2 0.001898 50.107698 +3 0.000484 50.107698 +4 0.001688 50.107698 +2025-04-29 01:55:34,465 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1740009600/cb_btc_1740009600 +2025-04-29 01:55:34,466 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:34,482 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:34,483 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-21 to 2025-02-19 -------------------- +2025-04-29 01:55:39,369 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:39,370 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.27166 validation_1-rmse:0.27726 +[1] validation_0-rmse:0.26708 validation_1-rmse:0.27112 +[2] validation_0-rmse:0.26297 validation_1-rmse:0.26523 +[3] validation_0-rmse:0.25865 validation_1-rmse:0.25959 +[4] validation_0-rmse:0.25494 validation_1-rmse:0.25419 +[5] validation_0-rmse:0.25100 validation_1-rmse:0.24913 +[6] validation_0-rmse:0.24763 validation_1-rmse:0.24437 +[7] validation_0-rmse:0.24441 validation_1-rmse:0.23970 +[8] validation_0-rmse:0.24110 validation_1-rmse:0.23527 +[9] validation_0-rmse:0.23801 validation_1-rmse:0.23102 +[10] validation_0-rmse:0.23492 validation_1-rmse:0.22691 +[11] validation_0-rmse:0.23229 validation_1-rmse:0.22297 +[12] validation_0-rmse:0.22956 validation_1-rmse:0.21923 +[13] validation_0-rmse:0.22707 validation_1-rmse:0.21564 +[14] validation_0-rmse:0.22482 validation_1-rmse:0.21221 +[15] validation_0-rmse:0.22237 validation_1-rmse:0.20891 +[16] validation_0-rmse:0.22030 validation_1-rmse:0.20557 +[17] validation_0-rmse:0.21784 validation_1-rmse:0.20243 +[18] validation_0-rmse:0.21591 validation_1-rmse:0.19949 +[19] validation_0-rmse:0.21399 validation_1-rmse:0.19664 +[20] validation_0-rmse:0.21182 validation_1-rmse:0.19378 +[21] validation_0-rmse:0.20992 validation_1-rmse:0.19110 +[22] validation_0-rmse:0.20821 validation_1-rmse:0.18850 +[23] validation_0-rmse:0.20621 validation_1-rmse:0.18597 +[24] validation_0-rmse:0.20490 validation_1-rmse:0.18353 +[25] validation_0-rmse:0.20318 validation_1-rmse:0.18126 +[26] validation_0-rmse:0.20168 validation_1-rmse:0.17896 +[27] validation_0-rmse:0.19992 validation_1-rmse:0.17679 +[28] validation_0-rmse:0.19865 validation_1-rmse:0.17458 +[29] validation_0-rmse:0.19722 validation_1-rmse:0.17257 +[30] validation_0-rmse:0.19571 validation_1-rmse:0.17039 +[31] validation_0-rmse:0.19429 validation_1-rmse:0.16855 +[32] validation_0-rmse:0.19285 validation_1-rmse:0.16664 +[33] validation_0-rmse:0.19141 validation_1-rmse:0.16488 +[34] validation_0-rmse:0.19022 validation_1-rmse:0.16312 +[35] validation_0-rmse:0.18904 validation_1-rmse:0.16145 +[36] validation_0-rmse:0.18832 validation_1-rmse:0.15973 +[37] validation_0-rmse:0.18723 validation_1-rmse:0.15815 +[38] validation_0-rmse:0.18610 validation_1-rmse:0.15653 +[39] validation_0-rmse:0.18504 validation_1-rmse:0.15503 +[40] validation_0-rmse:0.18402 validation_1-rmse:0.15358 +[41] validation_0-rmse:0.18333 validation_1-rmse:0.15193 +[42] validation_0-rmse:0.18213 validation_1-rmse:0.15058 +[43] validation_0-rmse:0.18176 validation_1-rmse:0.14922 +[44] validation_0-rmse:0.18093 validation_1-rmse:0.14792 +[45] validation_0-rmse:0.18017 validation_1-rmse:0.14667 +[46] validation_0-rmse:0.17928 validation_1-rmse:0.14537 +[47] validation_0-rmse:0.17858 validation_1-rmse:0.14420 +[48] validation_0-rmse:0.17770 validation_1-rmse:0.14306 +[49] validation_0-rmse:0.17695 validation_1-rmse:0.14199 +[50] validation_0-rmse:0.17613 validation_1-rmse:0.14094 +[51] validation_0-rmse:0.17545 validation_1-rmse:0.13979 +[52] validation_0-rmse:0.17490 validation_1-rmse:0.13874 +[53] validation_0-rmse:0.17452 validation_1-rmse:0.13755 +[54] validation_0-rmse:0.17383 validation_1-rmse:0.13663 +[55] validation_0-rmse:0.17327 validation_1-rmse:0.13568 +[56] validation_0-rmse:0.17255 validation_1-rmse:0.13477 +[57] validation_0-rmse:0.17192 validation_1-rmse:0.13382 +[58] validation_0-rmse:0.17138 validation_1-rmse:0.13277 +[59] validation_0-rmse:0.17074 validation_1-rmse:0.13188 +[60] validation_0-rmse:0.17026 validation_1-rmse:0.13089 +[61] validation_0-rmse:0.16969 validation_1-rmse:0.13010 +[62] validation_0-rmse:0.16932 validation_1-rmse:0.12904 +[63] validation_0-rmse:0.16888 validation_1-rmse:0.12818 +[64] validation_0-rmse:0.16849 validation_1-rmse:0.12745 +[65] validation_0-rmse:0.16802 validation_1-rmse:0.12639 +[66] validation_0-rmse:0.16747 validation_1-rmse:0.12567 +[67] validation_0-rmse:0.16710 validation_1-rmse:0.12496 +[68] validation_0-rmse:0.16672 validation_1-rmse:0.12426 +[69] validation_0-rmse:0.16635 validation_1-rmse:0.12331 +[70] validation_0-rmse:0.16597 validation_1-rmse:0.12267 +[71] validation_0-rmse:0.16554 validation_1-rmse:0.12196 +[72] validation_0-rmse:0.16522 validation_1-rmse:0.12121 +[73] validation_0-rmse:0.16481 validation_1-rmse:0.12054 +[74] validation_0-rmse:0.16442 validation_1-rmse:0.11996 +[75] validation_0-rmse:0.16409 validation_1-rmse:0.11939 +[76] validation_0-rmse:0.16375 validation_1-rmse:0.11878 +[77] validation_0-rmse:0.16275 validation_1-rmse:0.11753 +[78] validation_0-rmse:0.16248 validation_1-rmse:0.11692 +[79] validation_0-rmse:0.16215 validation_1-rmse:0.11619 +[80] validation_0-rmse:0.16187 validation_1-rmse:0.11564 +[81] validation_0-rmse:0.16150 validation_1-rmse:0.11493 +[82] validation_0-rmse:0.16123 validation_1-rmse:0.11438 +[83] validation_0-rmse:0.16109 validation_1-rmse:0.11358 +[84] validation_0-rmse:0.16065 validation_1-rmse:0.11304 +[85] validation_0-rmse:0.16038 validation_1-rmse:0.11256 +[86] validation_0-rmse:0.16022 validation_1-rmse:0.11205 +[87] validation_0-rmse:0.16007 validation_1-rmse:0.11158 +[88] validation_0-rmse:0.15945 validation_1-rmse:0.11054 +[89] validation_0-rmse:0.15912 validation_1-rmse:0.11008 +[90] validation_0-rmse:0.15894 validation_1-rmse:0.10937 +[91] validation_0-rmse:0.15868 validation_1-rmse:0.10886 +[92] validation_0-rmse:0.15845 validation_1-rmse:0.10844 +[93] validation_0-rmse:0.15817 validation_1-rmse:0.10803 +[94] validation_0-rmse:0.15789 validation_1-rmse:0.10758 +[95] validation_0-rmse:0.15772 validation_1-rmse:0.10721 +[96] validation_0-rmse:0.15763 validation_1-rmse:0.10676 +[97] validation_0-rmse:0.15751 validation_1-rmse:0.10609 +[98] validation_0-rmse:0.15731 validation_1-rmse:0.10574 +[99] validation_0-rmse:0.15738 validation_1-rmse:0.10531 +2025-04-29 01:55:40,266 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.80 secs) -------------------- +2025-04-29 01:55:40,267 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:40,801 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-31 00:00:00 to 2025-03-02 00:00:00, 7/11 trains +2025-04-29 01:55:40,802 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1740873600_prediction.feather +2025-04-29 01:55:40,807 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:40,814 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:55:40,816 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.107698 +1 0.003285 50.107698 +2 0.001898 50.107698 +3 0.000484 50.107698 +4 0.001688 50.107698 +2025-04-29 01:55:40,821 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:40,827 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:55:40,829 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079166 +1 0.003285 50.079166 +2 0.001898 50.079166 +3 0.000484 50.079166 +4 0.001688 50.079166 +2025-04-29 01:55:40,833 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1740873600/cb_btc_1740873600 +2025-04-29 01:55:40,834 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:40,849 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:40,850 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-31 to 2025-03-01 -------------------- +2025-04-29 01:55:45,643 - datasieve.pipeline - INFO - DI tossed 2275 predictions for being too far from training data. +2025-04-29 01:55:45,646 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:45,647 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.27618 validation_1-rmse:0.28955 +[1] validation_0-rmse:0.27005 validation_1-rmse:0.28323 +[2] validation_0-rmse:0.26414 validation_1-rmse:0.27722 +[3] validation_0-rmse:0.25897 validation_1-rmse:0.27161 +[4] validation_0-rmse:0.25425 validation_1-rmse:0.26622 +[5] validation_0-rmse:0.24886 validation_1-rmse:0.26100 +[6] validation_0-rmse:0.24522 validation_1-rmse:0.25606 +[7] validation_0-rmse:0.24137 validation_1-rmse:0.25132 +[8] validation_0-rmse:0.23765 validation_1-rmse:0.24687 +[9] validation_0-rmse:0.23323 validation_1-rmse:0.24254 +[10] validation_0-rmse:0.22900 validation_1-rmse:0.23827 +[11] validation_0-rmse:0.22588 validation_1-rmse:0.23450 +[12] validation_0-rmse:0.22228 validation_1-rmse:0.23055 +[13] validation_0-rmse:0.21872 validation_1-rmse:0.22698 +[14] validation_0-rmse:0.21492 validation_1-rmse:0.22348 +[15] validation_0-rmse:0.21329 validation_1-rmse:0.22011 +[16] validation_0-rmse:0.21024 validation_1-rmse:0.21686 +[17] validation_0-rmse:0.20823 validation_1-rmse:0.21380 +[18] validation_0-rmse:0.20544 validation_1-rmse:0.21075 +[19] validation_0-rmse:0.20415 validation_1-rmse:0.20787 +[20] validation_0-rmse:0.20143 validation_1-rmse:0.20515 +[21] validation_0-rmse:0.19917 validation_1-rmse:0.20247 +[22] validation_0-rmse:0.19745 validation_1-rmse:0.19994 +[23] validation_0-rmse:0.19508 validation_1-rmse:0.19746 +[24] validation_0-rmse:0.19300 validation_1-rmse:0.19490 +[25] validation_0-rmse:0.19085 validation_1-rmse:0.19254 +[26] validation_0-rmse:0.18898 validation_1-rmse:0.19031 +[27] validation_0-rmse:0.18720 validation_1-rmse:0.18794 +[28] validation_0-rmse:0.18503 validation_1-rmse:0.18584 +[29] validation_0-rmse:0.18314 validation_1-rmse:0.18382 +[30] validation_0-rmse:0.18132 validation_1-rmse:0.18164 +[31] validation_0-rmse:0.17984 validation_1-rmse:0.17967 +[32] validation_0-rmse:0.17818 validation_1-rmse:0.17779 +[33] validation_0-rmse:0.17637 validation_1-rmse:0.17572 +[34] validation_0-rmse:0.17473 validation_1-rmse:0.17399 +[35] validation_0-rmse:0.17338 validation_1-rmse:0.17229 +[36] validation_0-rmse:0.17253 validation_1-rmse:0.17055 +[37] validation_0-rmse:0.17149 validation_1-rmse:0.16883 +[38] validation_0-rmse:0.17030 validation_1-rmse:0.16730 +[39] validation_0-rmse:0.16950 validation_1-rmse:0.16556 +[40] validation_0-rmse:0.16815 validation_1-rmse:0.16412 +[41] validation_0-rmse:0.16704 validation_1-rmse:0.16268 +[42] validation_0-rmse:0.16617 validation_1-rmse:0.16128 +[43] validation_0-rmse:0.16542 validation_1-rmse:0.15970 +[44] validation_0-rmse:0.16438 validation_1-rmse:0.15840 +[45] validation_0-rmse:0.16356 validation_1-rmse:0.15692 +[46] validation_0-rmse:0.16239 validation_1-rmse:0.15574 +[47] validation_0-rmse:0.16153 validation_1-rmse:0.15456 +[48] validation_0-rmse:0.16076 validation_1-rmse:0.15314 +[49] validation_0-rmse:0.15998 validation_1-rmse:0.15201 +[50] validation_0-rmse:0.15946 validation_1-rmse:0.15084 +[51] validation_0-rmse:0.15891 validation_1-rmse:0.14954 +[52] validation_0-rmse:0.15834 validation_1-rmse:0.14847 +[53] validation_0-rmse:0.15764 validation_1-rmse:0.14722 +[54] validation_0-rmse:0.15707 validation_1-rmse:0.14623 +[55] validation_0-rmse:0.15653 validation_1-rmse:0.14527 +[56] validation_0-rmse:0.15583 validation_1-rmse:0.14434 +[57] validation_0-rmse:0.15549 validation_1-rmse:0.14329 +[58] validation_0-rmse:0.15507 validation_1-rmse:0.14241 +[59] validation_0-rmse:0.15468 validation_1-rmse:0.14053 +[60] validation_0-rmse:0.15398 validation_1-rmse:0.13968 +[61] validation_0-rmse:0.15390 validation_1-rmse:0.13864 +[62] validation_0-rmse:0.15360 validation_1-rmse:0.13783 +[63] validation_0-rmse:0.15368 validation_1-rmse:0.13704 +[64] validation_0-rmse:0.15338 validation_1-rmse:0.13624 +[65] validation_0-rmse:0.15273 validation_1-rmse:0.13551 +[66] validation_0-rmse:0.15238 validation_1-rmse:0.13451 +[67] validation_0-rmse:0.15212 validation_1-rmse:0.13290 +[68] validation_0-rmse:0.15191 validation_1-rmse:0.13217 +[69] validation_0-rmse:0.15138 validation_1-rmse:0.13143 +[70] validation_0-rmse:0.15090 validation_1-rmse:0.13071 +[71] validation_0-rmse:0.15082 validation_1-rmse:0.13001 +[72] validation_0-rmse:0.14988 validation_1-rmse:0.12847 +[73] validation_0-rmse:0.14953 validation_1-rmse:0.12783 +[74] validation_0-rmse:0.14924 validation_1-rmse:0.12709 +[75] validation_0-rmse:0.14926 validation_1-rmse:0.12578 +[76] validation_0-rmse:0.14903 validation_1-rmse:0.12499 +[77] validation_0-rmse:0.14851 validation_1-rmse:0.12435 +[78] validation_0-rmse:0.14808 validation_1-rmse:0.12368 +[79] validation_0-rmse:0.14768 validation_1-rmse:0.12305 +[80] validation_0-rmse:0.14741 validation_1-rmse:0.12217 +[81] validation_0-rmse:0.14712 validation_1-rmse:0.12165 +[82] validation_0-rmse:0.14696 validation_1-rmse:0.12110 +[83] validation_0-rmse:0.14686 validation_1-rmse:0.12045 +[84] validation_0-rmse:0.14648 validation_1-rmse:0.11984 +[85] validation_0-rmse:0.14623 validation_1-rmse:0.11923 +[86] validation_0-rmse:0.14606 validation_1-rmse:0.11869 +[87] validation_0-rmse:0.14583 validation_1-rmse:0.11754 +[88] validation_0-rmse:0.14572 validation_1-rmse:0.11710 +[89] validation_0-rmse:0.14537 validation_1-rmse:0.11660 +[90] validation_0-rmse:0.14510 validation_1-rmse:0.11614 +[91] validation_0-rmse:0.14516 validation_1-rmse:0.11514 +[92] validation_0-rmse:0.14480 validation_1-rmse:0.11455 +[93] validation_0-rmse:0.14475 validation_1-rmse:0.11414 +[94] validation_0-rmse:0.14443 validation_1-rmse:0.11374 +[95] validation_0-rmse:0.14409 validation_1-rmse:0.11331 +[96] validation_0-rmse:0.14391 validation_1-rmse:0.11240 +[97] validation_0-rmse:0.14303 validation_1-rmse:0.11154 +[98] validation_0-rmse:0.14274 validation_1-rmse:0.11114 +[99] validation_0-rmse:0.14246 validation_1-rmse:0.11071 +2025-04-29 01:55:46,544 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.71 secs) -------------------- +2025-04-29 01:55:46,544 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:47,092 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-02-10 00:00:00 to 2025-03-12 00:00:00, 8/11 trains +2025-04-29 01:55:47,092 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1741737600_prediction.feather +2025-04-29 01:55:47,100 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:47,107 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:55:47,109 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079166 +1 0.003285 50.079166 +2 0.001898 50.079166 +3 0.000484 50.079166 +4 0.001688 50.079166 +2025-04-29 01:55:47,115 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:47,122 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:55:47,123 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.102027 +1 0.003285 50.102027 +2 0.001898 50.102027 +3 0.000484 50.102027 +4 0.001688 50.102027 +2025-04-29 01:55:47,128 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1741737600/cb_btc_1741737600 +2025-04-29 01:55:47,129 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:47,145 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:47,145 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-10 to 2025-03-11 -------------------- +2025-04-29 01:55:51,987 - datasieve.pipeline - INFO - DI tossed 18 predictions for being too far from training data. +2025-04-29 01:55:51,989 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:51,989 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.26738 validation_1-rmse:0.26816 +[1] validation_0-rmse:0.26268 validation_1-rmse:0.26258 +[2] validation_0-rmse:0.25808 validation_1-rmse:0.25725 +[3] validation_0-rmse:0.25395 validation_1-rmse:0.25212 +[4] validation_0-rmse:0.24987 validation_1-rmse:0.24723 +[5] validation_0-rmse:0.24633 validation_1-rmse:0.24263 +[6] validation_0-rmse:0.24308 validation_1-rmse:0.23814 +[7] validation_0-rmse:0.23959 validation_1-rmse:0.23402 +[8] validation_0-rmse:0.23612 validation_1-rmse:0.22977 +[9] validation_0-rmse:0.23322 validation_1-rmse:0.22577 +[10] validation_0-rmse:0.23012 validation_1-rmse:0.22207 +[11] validation_0-rmse:0.22730 validation_1-rmse:0.21843 +[12] validation_0-rmse:0.22453 validation_1-rmse:0.21489 +[13] validation_0-rmse:0.22236 validation_1-rmse:0.21145 +[14] validation_0-rmse:0.22000 validation_1-rmse:0.20841 +[15] validation_0-rmse:0.21744 validation_1-rmse:0.20529 +[16] validation_0-rmse:0.21556 validation_1-rmse:0.20225 +[17] validation_0-rmse:0.21331 validation_1-rmse:0.19932 +[18] validation_0-rmse:0.21171 validation_1-rmse:0.19643 +[19] validation_0-rmse:0.21051 validation_1-rmse:0.19382 +[20] validation_0-rmse:0.20880 validation_1-rmse:0.19128 +[21] validation_0-rmse:0.20711 validation_1-rmse:0.18854 +[22] validation_0-rmse:0.20538 validation_1-rmse:0.18612 +[23] validation_0-rmse:0.20350 validation_1-rmse:0.18381 +[24] validation_0-rmse:0.20234 validation_1-rmse:0.18144 +[25] validation_0-rmse:0.20081 validation_1-rmse:0.17917 +[26] validation_0-rmse:0.19918 validation_1-rmse:0.17714 +[27] validation_0-rmse:0.19804 validation_1-rmse:0.17496 +[28] validation_0-rmse:0.19662 validation_1-rmse:0.17304 +[29] validation_0-rmse:0.19580 validation_1-rmse:0.17082 +[30] validation_0-rmse:0.19454 validation_1-rmse:0.16901 +[31] validation_0-rmse:0.19331 validation_1-rmse:0.16691 +[32] validation_0-rmse:0.19234 validation_1-rmse:0.16517 +[33] validation_0-rmse:0.19118 validation_1-rmse:0.16354 +[34] validation_0-rmse:0.19024 validation_1-rmse:0.16175 +[35] validation_0-rmse:0.18915 validation_1-rmse:0.16020 +[36] validation_0-rmse:0.18823 validation_1-rmse:0.15865 +[37] validation_0-rmse:0.18756 validation_1-rmse:0.15712 +[38] validation_0-rmse:0.18698 validation_1-rmse:0.15541 +[39] validation_0-rmse:0.18643 validation_1-rmse:0.15395 +[40] validation_0-rmse:0.18562 validation_1-rmse:0.15265 +[41] validation_0-rmse:0.18516 validation_1-rmse:0.15124 +[42] validation_0-rmse:0.18421 validation_1-rmse:0.14979 +[43] validation_0-rmse:0.18360 validation_1-rmse:0.14850 +[44] validation_0-rmse:0.18275 validation_1-rmse:0.14733 +[45] validation_0-rmse:0.18253 validation_1-rmse:0.14597 +[46] validation_0-rmse:0.18183 validation_1-rmse:0.14470 +[47] validation_0-rmse:0.18111 validation_1-rmse:0.14361 +[48] validation_0-rmse:0.18060 validation_1-rmse:0.14243 +[49] validation_0-rmse:0.18001 validation_1-rmse:0.14134 +[50] validation_0-rmse:0.17953 validation_1-rmse:0.14030 +[51] validation_0-rmse:0.17899 validation_1-rmse:0.13927 +[52] validation_0-rmse:0.17830 validation_1-rmse:0.13817 +[53] validation_0-rmse:0.17770 validation_1-rmse:0.13720 +[54] validation_0-rmse:0.17702 validation_1-rmse:0.13629 +[55] validation_0-rmse:0.17650 validation_1-rmse:0.13531 +[56] validation_0-rmse:0.17625 validation_1-rmse:0.13440 +[57] validation_0-rmse:0.17580 validation_1-rmse:0.13352 +[58] validation_0-rmse:0.17530 validation_1-rmse:0.13268 +[59] validation_0-rmse:0.17486 validation_1-rmse:0.13166 +[60] validation_0-rmse:0.17438 validation_1-rmse:0.13071 +[61] validation_0-rmse:0.17387 validation_1-rmse:0.12991 +[62] validation_0-rmse:0.17356 validation_1-rmse:0.12914 +[63] validation_0-rmse:0.17311 validation_1-rmse:0.12839 +[64] validation_0-rmse:0.17265 validation_1-rmse:0.12767 +[65] validation_0-rmse:0.17209 validation_1-rmse:0.12682 +[66] validation_0-rmse:0.17197 validation_1-rmse:0.12595 +[67] validation_0-rmse:0.17157 validation_1-rmse:0.12506 +[68] validation_0-rmse:0.17131 validation_1-rmse:0.12439 +[69] validation_0-rmse:0.17088 validation_1-rmse:0.12371 +[70] validation_0-rmse:0.17038 validation_1-rmse:0.12298 +[71] validation_0-rmse:0.17009 validation_1-rmse:0.12235 +[72] validation_0-rmse:0.16979 validation_1-rmse:0.12172 +[73] validation_0-rmse:0.16934 validation_1-rmse:0.12118 +[74] validation_0-rmse:0.16902 validation_1-rmse:0.12050 +[75] validation_0-rmse:0.16881 validation_1-rmse:0.11988 +[76] validation_0-rmse:0.16846 validation_1-rmse:0.11928 +[77] validation_0-rmse:0.16809 validation_1-rmse:0.11846 +[78] validation_0-rmse:0.16774 validation_1-rmse:0.11791 +[79] validation_0-rmse:0.16745 validation_1-rmse:0.11738 +[80] validation_0-rmse:0.16717 validation_1-rmse:0.11683 +[81] validation_0-rmse:0.16702 validation_1-rmse:0.11599 +[82] validation_0-rmse:0.16677 validation_1-rmse:0.11535 +[83] validation_0-rmse:0.16649 validation_1-rmse:0.11468 +[84] validation_0-rmse:0.16605 validation_1-rmse:0.11415 +[85] validation_0-rmse:0.16591 validation_1-rmse:0.11350 +[86] validation_0-rmse:0.16560 validation_1-rmse:0.11303 +[87] validation_0-rmse:0.16531 validation_1-rmse:0.11259 +[88] validation_0-rmse:0.16504 validation_1-rmse:0.11185 +[89] validation_0-rmse:0.16485 validation_1-rmse:0.11134 +[90] validation_0-rmse:0.16463 validation_1-rmse:0.11083 +[91] validation_0-rmse:0.16436 validation_1-rmse:0.11041 +[92] validation_0-rmse:0.16412 validation_1-rmse:0.10988 +[93] validation_0-rmse:0.16388 validation_1-rmse:0.10942 +[94] validation_0-rmse:0.16391 validation_1-rmse:0.10881 +[95] validation_0-rmse:0.16357 validation_1-rmse:0.10838 +[96] validation_0-rmse:0.16358 validation_1-rmse:0.10796 +[97] validation_0-rmse:0.16338 validation_1-rmse:0.10756 +[98] validation_0-rmse:0.16339 validation_1-rmse:0.10688 +[99] validation_0-rmse:0.16321 validation_1-rmse:0.10649 +2025-04-29 01:55:52,741 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.61 secs) -------------------- +2025-04-29 01:55:52,742 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:53,285 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-02-20 00:00:00 to 2025-03-22 00:00:00, 9/11 trains +2025-04-29 01:55:53,286 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1742601600_prediction.feather +2025-04-29 01:55:53,291 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:53,298 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:55:53,300 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.102027 +1 0.003285 50.102027 +2 0.001898 50.102027 +3 0.000484 50.102027 +4 0.001688 50.102027 +2025-04-29 01:55:53,309 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:53,316 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:55:53,318 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079967 +1 0.003285 50.079967 +2 0.001898 50.079967 +3 0.000484 50.079967 +4 0.001688 50.079967 +2025-04-29 01:55:53,322 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1742601600/cb_btc_1742601600 +2025-04-29 01:55:53,323 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:53,339 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:53,340 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-20 to 2025-03-21 -------------------- +2025-04-29 01:55:58,184 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:58,185 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.26992 validation_1-rmse:0.26756 +[1] validation_0-rmse:0.26551 validation_1-rmse:0.26201 +[2] validation_0-rmse:0.26111 validation_1-rmse:0.25656 +[3] validation_0-rmse:0.25690 validation_1-rmse:0.25154 +[4] validation_0-rmse:0.25291 validation_1-rmse:0.24683 +[5] validation_0-rmse:0.24933 validation_1-rmse:0.24228 +[6] validation_0-rmse:0.24598 validation_1-rmse:0.23796 +[7] validation_0-rmse:0.24252 validation_1-rmse:0.23392 +[8] validation_0-rmse:0.23953 validation_1-rmse:0.22978 +[9] validation_0-rmse:0.23634 validation_1-rmse:0.22592 +[10] validation_0-rmse:0.23330 validation_1-rmse:0.22229 +[11] validation_0-rmse:0.23059 validation_1-rmse:0.21875 +[12] validation_0-rmse:0.22799 validation_1-rmse:0.21546 +[13] validation_0-rmse:0.22565 validation_1-rmse:0.21212 +[14] validation_0-rmse:0.22329 validation_1-rmse:0.20904 +[15] validation_0-rmse:0.22111 validation_1-rmse:0.20604 +[16] validation_0-rmse:0.21894 validation_1-rmse:0.20318 +[17] validation_0-rmse:0.21715 validation_1-rmse:0.20021 +[18] validation_0-rmse:0.21499 validation_1-rmse:0.19735 +[19] validation_0-rmse:0.21283 validation_1-rmse:0.19480 +[20] validation_0-rmse:0.21109 validation_1-rmse:0.19209 +[21] validation_0-rmse:0.20904 validation_1-rmse:0.18969 +[22] validation_0-rmse:0.20762 validation_1-rmse:0.18718 +[23] validation_0-rmse:0.20580 validation_1-rmse:0.18498 +[24] validation_0-rmse:0.20434 validation_1-rmse:0.18262 +[25] validation_0-rmse:0.20267 validation_1-rmse:0.18048 +[26] validation_0-rmse:0.20106 validation_1-rmse:0.17844 +[27] validation_0-rmse:0.19945 validation_1-rmse:0.17647 +[28] validation_0-rmse:0.19813 validation_1-rmse:0.17443 +[29] validation_0-rmse:0.19669 validation_1-rmse:0.17264 +[30] validation_0-rmse:0.19541 validation_1-rmse:0.17054 +[31] validation_0-rmse:0.19401 validation_1-rmse:0.16881 +[32] validation_0-rmse:0.19263 validation_1-rmse:0.16719 +[33] validation_0-rmse:0.19134 validation_1-rmse:0.16560 +[34] validation_0-rmse:0.18996 validation_1-rmse:0.16365 +[35] validation_0-rmse:0.18864 validation_1-rmse:0.16211 +[36] validation_0-rmse:0.18752 validation_1-rmse:0.16069 +[37] validation_0-rmse:0.18652 validation_1-rmse:0.15898 +[38] validation_0-rmse:0.18540 validation_1-rmse:0.15751 +[39] validation_0-rmse:0.18429 validation_1-rmse:0.15616 +[40] validation_0-rmse:0.18317 validation_1-rmse:0.15475 +[41] validation_0-rmse:0.18215 validation_1-rmse:0.15324 +[42] validation_0-rmse:0.18119 validation_1-rmse:0.15199 +[43] validation_0-rmse:0.18008 validation_1-rmse:0.15057 +[44] validation_0-rmse:0.17926 validation_1-rmse:0.14942 +[45] validation_0-rmse:0.17841 validation_1-rmse:0.14813 +[46] validation_0-rmse:0.17755 validation_1-rmse:0.14700 +[47] validation_0-rmse:0.17672 validation_1-rmse:0.14572 +[48] validation_0-rmse:0.17586 validation_1-rmse:0.14466 +[49] validation_0-rmse:0.17511 validation_1-rmse:0.14354 +[50] validation_0-rmse:0.17440 validation_1-rmse:0.14236 +[51] validation_0-rmse:0.17354 validation_1-rmse:0.14130 +[52] validation_0-rmse:0.17281 validation_1-rmse:0.14035 +[53] validation_0-rmse:0.17210 validation_1-rmse:0.13942 +[54] validation_0-rmse:0.17136 validation_1-rmse:0.13843 +[55] validation_0-rmse:0.17045 validation_1-rmse:0.13715 +[56] validation_0-rmse:0.16971 validation_1-rmse:0.13629 +[57] validation_0-rmse:0.16900 validation_1-rmse:0.13511 +[58] validation_0-rmse:0.16834 validation_1-rmse:0.13426 +[59] validation_0-rmse:0.16763 validation_1-rmse:0.13323 +[60] validation_0-rmse:0.16702 validation_1-rmse:0.13242 +[61] validation_0-rmse:0.16639 validation_1-rmse:0.13164 +[62] validation_0-rmse:0.16586 validation_1-rmse:0.13079 +[63] validation_0-rmse:0.16527 validation_1-rmse:0.13006 +[64] validation_0-rmse:0.16458 validation_1-rmse:0.12914 +[65] validation_0-rmse:0.16396 validation_1-rmse:0.12841 +[66] validation_0-rmse:0.16332 validation_1-rmse:0.12742 +[67] validation_0-rmse:0.16290 validation_1-rmse:0.12665 +[68] validation_0-rmse:0.16248 validation_1-rmse:0.12584 +[69] validation_0-rmse:0.16192 validation_1-rmse:0.12503 +[70] validation_0-rmse:0.16128 validation_1-rmse:0.12435 +[71] validation_0-rmse:0.16078 validation_1-rmse:0.12371 +[72] validation_0-rmse:0.16032 validation_1-rmse:0.12311 +[73] validation_0-rmse:0.15998 validation_1-rmse:0.12241 +[74] validation_0-rmse:0.15959 validation_1-rmse:0.12184 +[75] validation_0-rmse:0.15922 validation_1-rmse:0.12121 +[76] validation_0-rmse:0.15877 validation_1-rmse:0.12064 +[77] validation_0-rmse:0.15830 validation_1-rmse:0.11981 +[78] validation_0-rmse:0.15791 validation_1-rmse:0.11927 +[79] validation_0-rmse:0.15751 validation_1-rmse:0.11859 +[80] validation_0-rmse:0.15716 validation_1-rmse:0.11795 +[81] validation_0-rmse:0.15680 validation_1-rmse:0.11740 +[82] validation_0-rmse:0.15624 validation_1-rmse:0.11683 +[83] validation_0-rmse:0.15578 validation_1-rmse:0.11632 +[84] validation_0-rmse:0.15553 validation_1-rmse:0.11586 +[85] validation_0-rmse:0.15471 validation_1-rmse:0.11513 +[86] validation_0-rmse:0.15444 validation_1-rmse:0.11465 +[87] validation_0-rmse:0.15417 validation_1-rmse:0.11406 +[88] validation_0-rmse:0.15387 validation_1-rmse:0.11359 +[89] validation_0-rmse:0.15359 validation_1-rmse:0.11319 +[90] validation_0-rmse:0.15332 validation_1-rmse:0.11269 +[91] validation_0-rmse:0.15301 validation_1-rmse:0.11221 +[92] validation_0-rmse:0.15258 validation_1-rmse:0.11176 +[93] validation_0-rmse:0.15231 validation_1-rmse:0.11135 +[94] validation_0-rmse:0.15202 validation_1-rmse:0.11093 +[95] validation_0-rmse:0.15185 validation_1-rmse:0.11041 +[96] validation_0-rmse:0.15173 validation_1-rmse:0.11000 +[97] validation_0-rmse:0.15150 validation_1-rmse:0.10961 +[98] validation_0-rmse:0.15114 validation_1-rmse:0.10917 +[99] validation_0-rmse:0.15096 validation_1-rmse:0.10882 +2025-04-29 01:55:59,097 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.77 secs) -------------------- +2025-04-29 01:55:59,098 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:59,706 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-03-02 00:00:00 to 2025-04-01 00:00:00, 10/11 trains +2025-04-29 01:55:59,706 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1743465600_prediction.feather +2025-04-29 01:55:59,715 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:59,723 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:55:59,725 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079967 +1 0.003285 50.079967 +2 0.001898 50.079967 +3 0.000484 50.079967 +4 0.001688 50.079967 +2025-04-29 01:55:59,732 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:59,739 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:55:59,741 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.024153 +1 0.003285 50.024153 +2 0.001898 50.024153 +3 0.000484 50.024153 +4 0.001688 50.024153 +2025-04-29 01:55:59,745 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1743465600/cb_btc_1743465600 +2025-04-29 01:55:59,746 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:59,762 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:59,762 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-02 to 2025-03-31 -------------------- +2025-04-29 01:56:04,571 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:56:04,571 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.28468 validation_1-rmse:0.28491 +[1] validation_0-rmse:0.27961 validation_1-rmse:0.27914 +[2] validation_0-rmse:0.27524 validation_1-rmse:0.27370 +[3] validation_0-rmse:0.27054 validation_1-rmse:0.26858 +[4] validation_0-rmse:0.26601 validation_1-rmse:0.26362 +[5] validation_0-rmse:0.26219 validation_1-rmse:0.25896 +[6] validation_0-rmse:0.25814 validation_1-rmse:0.25450 +[7] validation_0-rmse:0.25500 validation_1-rmse:0.25026 +[8] validation_0-rmse:0.25145 validation_1-rmse:0.24602 +[9] validation_0-rmse:0.24843 validation_1-rmse:0.24213 +[10] validation_0-rmse:0.24527 validation_1-rmse:0.23824 +[11] validation_0-rmse:0.24238 validation_1-rmse:0.23440 +[12] validation_0-rmse:0.23940 validation_1-rmse:0.23096 +[13] validation_0-rmse:0.23630 validation_1-rmse:0.22764 +[14] validation_0-rmse:0.23385 validation_1-rmse:0.22440 +[15] validation_0-rmse:0.23099 validation_1-rmse:0.22128 +[16] validation_0-rmse:0.22865 validation_1-rmse:0.21801 +[17] validation_0-rmse:0.22620 validation_1-rmse:0.21515 +[18] validation_0-rmse:0.22375 validation_1-rmse:0.21210 +[19] validation_0-rmse:0.22142 validation_1-rmse:0.20925 +[20] validation_0-rmse:0.21927 validation_1-rmse:0.20663 +[21] validation_0-rmse:0.21720 validation_1-rmse:0.20416 +[22] validation_0-rmse:0.21528 validation_1-rmse:0.20170 +[23] validation_0-rmse:0.21330 validation_1-rmse:0.19913 +[24] validation_0-rmse:0.21136 validation_1-rmse:0.19693 +[25] validation_0-rmse:0.21002 validation_1-rmse:0.19438 +[26] validation_0-rmse:0.20807 validation_1-rmse:0.19222 +[27] validation_0-rmse:0.20636 validation_1-rmse:0.19016 +[28] validation_0-rmse:0.20439 validation_1-rmse:0.18763 +[29] validation_0-rmse:0.20276 validation_1-rmse:0.18559 +[30] validation_0-rmse:0.20114 validation_1-rmse:0.18380 +[31] validation_0-rmse:0.19965 validation_1-rmse:0.18163 +[32] validation_0-rmse:0.19833 validation_1-rmse:0.17955 +[33] validation_0-rmse:0.19688 validation_1-rmse:0.17782 +[34] validation_0-rmse:0.19558 validation_1-rmse:0.17614 +[35] validation_0-rmse:0.19420 validation_1-rmse:0.17451 +[36] validation_0-rmse:0.19297 validation_1-rmse:0.17293 +[37] validation_0-rmse:0.19169 validation_1-rmse:0.17111 +[38] validation_0-rmse:0.19038 validation_1-rmse:0.16943 +[39] validation_0-rmse:0.18941 validation_1-rmse:0.16798 +[40] validation_0-rmse:0.18828 validation_1-rmse:0.16657 +[41] validation_0-rmse:0.18724 validation_1-rmse:0.16485 +[42] validation_0-rmse:0.18620 validation_1-rmse:0.16347 +[43] validation_0-rmse:0.18525 validation_1-rmse:0.16204 +[44] validation_0-rmse:0.18429 validation_1-rmse:0.16073 +[45] validation_0-rmse:0.18324 validation_1-rmse:0.15951 +[46] validation_0-rmse:0.18250 validation_1-rmse:0.15797 +[47] validation_0-rmse:0.18157 validation_1-rmse:0.15682 +[48] validation_0-rmse:0.18069 validation_1-rmse:0.15566 +[49] validation_0-rmse:0.18002 validation_1-rmse:0.15440 +[50] validation_0-rmse:0.17914 validation_1-rmse:0.15322 +[51] validation_0-rmse:0.17842 validation_1-rmse:0.15220 +[52] validation_0-rmse:0.17756 validation_1-rmse:0.15107 +[53] validation_0-rmse:0.17668 validation_1-rmse:0.15007 +[54] validation_0-rmse:0.17596 validation_1-rmse:0.14866 +[55] validation_0-rmse:0.17525 validation_1-rmse:0.14775 +[56] validation_0-rmse:0.17467 validation_1-rmse:0.14653 +[57] validation_0-rmse:0.17390 validation_1-rmse:0.14564 +[58] validation_0-rmse:0.17326 validation_1-rmse:0.14478 +[59] validation_0-rmse:0.17273 validation_1-rmse:0.14356 +[60] validation_0-rmse:0.17218 validation_1-rmse:0.14269 +[61] validation_0-rmse:0.17157 validation_1-rmse:0.14186 +[62] validation_0-rmse:0.17120 validation_1-rmse:0.14083 +[63] validation_0-rmse:0.17069 validation_1-rmse:0.14002 +[64] validation_0-rmse:0.17012 validation_1-rmse:0.13912 +[65] validation_0-rmse:0.16942 validation_1-rmse:0.13834 +[66] validation_0-rmse:0.16914 validation_1-rmse:0.13720 +[67] validation_0-rmse:0.16856 validation_1-rmse:0.13648 +[68] validation_0-rmse:0.16800 validation_1-rmse:0.13569 +[69] validation_0-rmse:0.16796 validation_1-rmse:0.13472 +[70] validation_0-rmse:0.16737 validation_1-rmse:0.13405 +[71] validation_0-rmse:0.16686 validation_1-rmse:0.13342 +[72] validation_0-rmse:0.16639 validation_1-rmse:0.13270 +[73] validation_0-rmse:0.16648 validation_1-rmse:0.13149 +[74] validation_0-rmse:0.16609 validation_1-rmse:0.13086 +[75] validation_0-rmse:0.16560 validation_1-rmse:0.13025 +[76] validation_0-rmse:0.16530 validation_1-rmse:0.12925 +[77] validation_0-rmse:0.16492 validation_1-rmse:0.12824 +[78] validation_0-rmse:0.16451 validation_1-rmse:0.12770 +[79] validation_0-rmse:0.16414 validation_1-rmse:0.12710 +[80] validation_0-rmse:0.16377 validation_1-rmse:0.12654 +[81] validation_0-rmse:0.16338 validation_1-rmse:0.12595 +[82] validation_0-rmse:0.16317 validation_1-rmse:0.12490 +[83] validation_0-rmse:0.16249 validation_1-rmse:0.12361 +[84] validation_0-rmse:0.16217 validation_1-rmse:0.12307 +[85] validation_0-rmse:0.16178 validation_1-rmse:0.12255 +[86] validation_0-rmse:0.16149 validation_1-rmse:0.12206 +[87] validation_0-rmse:0.16113 validation_1-rmse:0.12155 +[88] validation_0-rmse:0.16049 validation_1-rmse:0.12061 +[89] validation_0-rmse:0.16008 validation_1-rmse:0.11990 +[90] validation_0-rmse:0.15955 validation_1-rmse:0.11882 +[91] validation_0-rmse:0.15927 validation_1-rmse:0.11842 +[92] validation_0-rmse:0.15891 validation_1-rmse:0.11796 +[93] validation_0-rmse:0.15880 validation_1-rmse:0.11730 +[94] validation_0-rmse:0.15829 validation_1-rmse:0.11631 +[95] validation_0-rmse:0.15809 validation_1-rmse:0.11584 +[96] validation_0-rmse:0.15778 validation_1-rmse:0.11544 +[97] validation_0-rmse:0.15763 validation_1-rmse:0.11504 +[98] validation_0-rmse:0.15724 validation_1-rmse:0.11438 +[99] validation_0-rmse:0.15694 validation_1-rmse:0.11396 +2025-04-29 01:56:05,520 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.77 secs) -------------------- +2025-04-29 01:56:05,521 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:06,027 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-03-12 00:00:00 to 2025-04-11 00:00:00, 11/11 trains +2025-04-29 01:56:06,027 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1744329600_prediction.feather +2025-04-29 01:56:06,037 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:56:06,045 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:56:06,046 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.024153 +1 0.003285 50.024153 +2 0.001898 50.024153 +3 0.000484 50.024153 +4 0.001688 50.024153 +2025-04-29 01:56:06,057 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:56:06,064 - FreqaiExampleStrategy - INFO - 目标列形状：(66770,) +2025-04-29 01:56:06,065 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.093162 +1 0.003285 50.093162 +2 0.001898 50.093162 +3 0.000484 50.093162 +4 0.001688 50.093162 +2025-04-29 01:56:06,070 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1744329600/cb_btc_1744329600 +2025-04-29 01:56:06,071 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:56:06,087 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:06,088 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-12 to 2025-04-10 -------------------- +2025-04-29 01:56:10,904 - datasieve.pipeline - INFO - DI tossed 2001 predictions for being too far from training data. +2025-04-29 01:56:10,907 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:56:10,907 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.32950 validation_1-rmse:0.29220 +[1] validation_0-rmse:0.32402 validation_1-rmse:0.28580 +[2] validation_0-rmse:0.31922 validation_1-rmse:0.27974 +[3] validation_0-rmse:0.31450 validation_1-rmse:0.27409 +[4] validation_0-rmse:0.30969 validation_1-rmse:0.26866 +[5] validation_0-rmse:0.30585 validation_1-rmse:0.26346 +[6] validation_0-rmse:0.30202 validation_1-rmse:0.25855 +[7] validation_0-rmse:0.29888 validation_1-rmse:0.25375 +[8] validation_0-rmse:0.29520 validation_1-rmse:0.24919 +[9] validation_0-rmse:0.29164 validation_1-rmse:0.24487 +[10] validation_0-rmse:0.28843 validation_1-rmse:0.24072 +[11] validation_0-rmse:0.28514 validation_1-rmse:0.23667 +[12] validation_0-rmse:0.28114 validation_1-rmse:0.23279 +[13] validation_0-rmse:0.27740 validation_1-rmse:0.22909 +[14] validation_0-rmse:0.27421 validation_1-rmse:0.22543 +[15] validation_0-rmse:0.27115 validation_1-rmse:0.22210 +[16] validation_0-rmse:0.26820 validation_1-rmse:0.21859 +[17] validation_0-rmse:0.26549 validation_1-rmse:0.21528 +[18] validation_0-rmse:0.26254 validation_1-rmse:0.21226 +[19] validation_0-rmse:0.25967 validation_1-rmse:0.20927 +[20] validation_0-rmse:0.25735 validation_1-rmse:0.20641 +[21] validation_0-rmse:0.25470 validation_1-rmse:0.20366 +[22] validation_0-rmse:0.25265 validation_1-rmse:0.20073 +[23] validation_0-rmse:0.25054 validation_1-rmse:0.19819 +[24] validation_0-rmse:0.24806 validation_1-rmse:0.19573 +[25] validation_0-rmse:0.24570 validation_1-rmse:0.19304 +[26] validation_0-rmse:0.24361 validation_1-rmse:0.19076 +[27] validation_0-rmse:0.24148 validation_1-rmse:0.18853 +[28] validation_0-rmse:0.24014 validation_1-rmse:0.18621 +[29] validation_0-rmse:0.23792 validation_1-rmse:0.18410 +[30] validation_0-rmse:0.23603 validation_1-rmse:0.18203 +[31] validation_0-rmse:0.23421 validation_1-rmse:0.17990 +[32] validation_0-rmse:0.23264 validation_1-rmse:0.17800 +[33] validation_0-rmse:0.23087 validation_1-rmse:0.17616 +[34] validation_0-rmse:0.22949 validation_1-rmse:0.17427 +[35] validation_0-rmse:0.22857 validation_1-rmse:0.17234 +[36] validation_0-rmse:0.22690 validation_1-rmse:0.17065 +[37] validation_0-rmse:0.22566 validation_1-rmse:0.16898 +[38] validation_0-rmse:0.22462 validation_1-rmse:0.16738 +[39] validation_0-rmse:0.22376 validation_1-rmse:0.16567 +[40] validation_0-rmse:0.22232 validation_1-rmse:0.16410 +[41] validation_0-rmse:0.22105 validation_1-rmse:0.16265 +[42] validation_0-rmse:0.22006 validation_1-rmse:0.16111 +[43] validation_0-rmse:0.21847 validation_1-rmse:0.15976 +[44] validation_0-rmse:0.21782 validation_1-rmse:0.15824 +[45] validation_0-rmse:0.21641 validation_1-rmse:0.15686 +[46] validation_0-rmse:0.21552 validation_1-rmse:0.15554 +[47] validation_0-rmse:0.21459 validation_1-rmse:0.15417 +[48] validation_0-rmse:0.21339 validation_1-rmse:0.15293 +[49] validation_0-rmse:0.21255 validation_1-rmse:0.15176 +[50] validation_0-rmse:0.21192 validation_1-rmse:0.15047 +[51] validation_0-rmse:0.21115 validation_1-rmse:0.14910 +[52] validation_0-rmse:0.21072 validation_1-rmse:0.14774 +[53] validation_0-rmse:0.20992 validation_1-rmse:0.14670 +[54] validation_0-rmse:0.20839 validation_1-rmse:0.14541 +[55] validation_0-rmse:0.20753 validation_1-rmse:0.14442 +[56] validation_0-rmse:0.20648 validation_1-rmse:0.14328 +[57] validation_0-rmse:0.20564 validation_1-rmse:0.14229 +[58] validation_0-rmse:0.20473 validation_1-rmse:0.14137 +[59] validation_0-rmse:0.20418 validation_1-rmse:0.14011 +[60] validation_0-rmse:0.20341 validation_1-rmse:0.13923 +[61] validation_0-rmse:0.20258 validation_1-rmse:0.13839 +[62] validation_0-rmse:0.20230 validation_1-rmse:0.13723 +[63] validation_0-rmse:0.20075 validation_1-rmse:0.13546 +[64] validation_0-rmse:0.20007 validation_1-rmse:0.13467 +[65] validation_0-rmse:0.19937 validation_1-rmse:0.13387 +[66] validation_0-rmse:0.19875 validation_1-rmse:0.13296 +[67] validation_0-rmse:0.19709 validation_1-rmse:0.13137 +[68] validation_0-rmse:0.19675 validation_1-rmse:0.13042 +[69] validation_0-rmse:0.19617 validation_1-rmse:0.12968 +[70] validation_0-rmse:0.19560 validation_1-rmse:0.12900 +[71] validation_0-rmse:0.19492 validation_1-rmse:0.12834 +[72] validation_0-rmse:0.19319 validation_1-rmse:0.12681 +[73] validation_0-rmse:0.19272 validation_1-rmse:0.12612 +[74] validation_0-rmse:0.19230 validation_1-rmse:0.12535 +[75] validation_0-rmse:0.19170 validation_1-rmse:0.12474 +[76] validation_0-rmse:0.19058 validation_1-rmse:0.12338 +[77] validation_0-rmse:0.19010 validation_1-rmse:0.12279 +[78] validation_0-rmse:0.18961 validation_1-rmse:0.12223 +[79] validation_0-rmse:0.18960 validation_1-rmse:0.12156 +[80] validation_0-rmse:0.18882 validation_1-rmse:0.12038 +[81] validation_0-rmse:0.18819 validation_1-rmse:0.11975 +[82] validation_0-rmse:0.18789 validation_1-rmse:0.11916 +[83] validation_0-rmse:0.18738 validation_1-rmse:0.11864 +[84] validation_0-rmse:0.18718 validation_1-rmse:0.11801 +[85] validation_0-rmse:0.18600 validation_1-rmse:0.11698 +[86] validation_0-rmse:0.18572 validation_1-rmse:0.11653 +[87] validation_0-rmse:0.18534 validation_1-rmse:0.11603 +[88] validation_0-rmse:0.18478 validation_1-rmse:0.11508 +[89] validation_0-rmse:0.18430 validation_1-rmse:0.11459 +[90] validation_0-rmse:0.18447 validation_1-rmse:0.11396 +[91] validation_0-rmse:0.18424 validation_1-rmse:0.11352 +[92] validation_0-rmse:0.18367 validation_1-rmse:0.11307 +[93] validation_0-rmse:0.18333 validation_1-rmse:0.11265 +[94] validation_0-rmse:0.18313 validation_1-rmse:0.11216 +[95] validation_0-rmse:0.18275 validation_1-rmse:0.11157 +[96] validation_0-rmse:0.18275 validation_1-rmse:0.11106 +[97] validation_0-rmse:0.18248 validation_1-rmse:0.11068 +[98] validation_0-rmse:0.18220 validation_1-rmse:0.11033 +[99] validation_0-rmse:0.18198 validation_1-rmse:0.10994 +2025-04-29 01:56:11,705 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.63 secs) -------------------- +2025-04-29 01:56:11,706 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:12,255 - FreqaiExampleStrategy - INFO - 动态参数：buy_rsi=39.26145316407591, sell_rsi=59.26145316407591, stoploss=-0.15, trailing_stop_positive=0.05 +2025-04-29 01:56:12,275 - FreqaiExampleStrategy - INFO - up_or_down 值统计： +up_or_down +1 33535 +0 33236 +2025-04-29 01:56:12,276 - FreqaiExampleStrategy - INFO - do_predict 值统计： +do_predict +0.0 35773 +1.0 30998 +2025-04-29 01:56:12,279 - FreqaiExampleStrategy - INFO - 处理交易对：SOL/USDT +2025-04-29 01:56:12,281 - freqtrade.freqai.freqai_interface - INFO - Training 11 timeranges +2025-04-29 01:56:12,282 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2024-12-02 00:00:00 to 2025-01-01 00:00:00, 1/11 trains +2025-04-29 01:56:12,283 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1735689600_prediction.feather +2025-04-29 01:56:12,334 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 5m to 8690 +2025-04-29 01:56:12,335 - freqtrade.data.dataprovider - INFO - Loading data for SOL/USDT 5m from 2024-12-01 19:50:00 to 2025-04-20 00:00:00 +2025-04-29 01:56:12,422 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 1h to 770 +2025-04-29 01:56:12,422 - freqtrade.data.dataprovider - INFO - Loading data for SOL/USDT 1h from 2024-11-29 22:00:00 to 2025-04-20 00:00:00 +2025-04-29 01:56:12,518 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 3m to 14450 +2025-04-29 01:56:12,519 - freqtrade.data.dataprovider - INFO - Loading data for BTC/USDT 3m from 2024-12-01 21:30:00 to 2025-04-20 00:00:00 +2025-04-29 01:56:13,040 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:13,046 - FreqaiExampleStrategy - INFO - 目标列形状：(14450,) +2025-04-29 01:56:13,047 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.58814 +1 0.003044 49.58814 +2 0.000465 49.58814 +3 -0.000380 49.58814 +4 0.002829 49.58814 +2025-04-29 01:56:13,052 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:13,057 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:56:13,059 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.68088 +1 0.003044 49.68088 +2 0.000465 49.68088 +3 -0.000380 49.68088 +4 0.002829 49.68088 +2025-04-29 01:56:13,066 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1735689600/cb_sol_1735689600 +2025-04-29 01:56:13,066 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:13,095 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:13,096 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-02 to 2024-12-31 -------------------- +2025-04-29 01:56:18,126 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:18,126 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.30164 validation_1-rmse:0.29585 +[1] validation_0-rmse:0.29609 validation_1-rmse:0.28921 +[2] validation_0-rmse:0.29103 validation_1-rmse:0.28298 +[3] validation_0-rmse:0.28604 validation_1-rmse:0.27706 +[4] validation_0-rmse:0.28108 validation_1-rmse:0.27129 +[5] validation_0-rmse:0.27670 validation_1-rmse:0.26609 +[6] validation_0-rmse:0.27234 validation_1-rmse:0.26092 +[7] validation_0-rmse:0.26874 validation_1-rmse:0.25593 +[8] validation_0-rmse:0.26461 validation_1-rmse:0.25118 +[9] validation_0-rmse:0.26074 validation_1-rmse:0.24677 +[10] validation_0-rmse:0.25745 validation_1-rmse:0.24239 +[11] validation_0-rmse:0.25460 validation_1-rmse:0.23832 +[12] validation_0-rmse:0.25121 validation_1-rmse:0.23441 +[13] validation_0-rmse:0.24825 validation_1-rmse:0.23068 +[14] validation_0-rmse:0.24580 validation_1-rmse:0.22694 +[15] validation_0-rmse:0.24286 validation_1-rmse:0.22346 +[16] validation_0-rmse:0.24051 validation_1-rmse:0.22006 +[17] validation_0-rmse:0.23821 validation_1-rmse:0.21690 +[18] validation_0-rmse:0.23549 validation_1-rmse:0.21383 +[19] validation_0-rmse:0.23335 validation_1-rmse:0.21087 +[20] validation_0-rmse:0.23089 validation_1-rmse:0.20804 +[21] validation_0-rmse:0.22918 validation_1-rmse:0.20505 +[22] validation_0-rmse:0.22716 validation_1-rmse:0.20240 +[23] validation_0-rmse:0.22562 validation_1-rmse:0.19981 +[24] validation_0-rmse:0.22385 validation_1-rmse:0.19723 +[25] validation_0-rmse:0.22201 validation_1-rmse:0.19473 +[26] validation_0-rmse:0.22016 validation_1-rmse:0.19245 +[27] validation_0-rmse:0.21834 validation_1-rmse:0.19024 +[28] validation_0-rmse:0.21671 validation_1-rmse:0.18789 +[29] validation_0-rmse:0.21493 validation_1-rmse:0.18579 +[30] validation_0-rmse:0.21385 validation_1-rmse:0.18351 +[31] validation_0-rmse:0.21216 validation_1-rmse:0.18156 +[32] validation_0-rmse:0.21088 validation_1-rmse:0.17941 +[33] validation_0-rmse:0.20953 validation_1-rmse:0.17754 +[34] validation_0-rmse:0.20805 validation_1-rmse:0.17575 +[35] validation_0-rmse:0.20648 validation_1-rmse:0.17399 +[36] validation_0-rmse:0.20515 validation_1-rmse:0.17220 +[37] validation_0-rmse:0.20382 validation_1-rmse:0.17031 +[38] validation_0-rmse:0.20257 validation_1-rmse:0.16871 +[39] validation_0-rmse:0.20125 validation_1-rmse:0.16718 +[40] validation_0-rmse:0.20005 validation_1-rmse:0.16574 +[41] validation_0-rmse:0.19885 validation_1-rmse:0.16415 +[42] validation_0-rmse:0.19789 validation_1-rmse:0.16270 +[43] validation_0-rmse:0.19680 validation_1-rmse:0.16130 +[44] validation_0-rmse:0.19564 validation_1-rmse:0.15993 +[45] validation_0-rmse:0.19480 validation_1-rmse:0.15854 +[46] validation_0-rmse:0.19376 validation_1-rmse:0.15728 +[47] validation_0-rmse:0.19290 validation_1-rmse:0.15568 +[48] validation_0-rmse:0.19223 validation_1-rmse:0.15445 +[49] validation_0-rmse:0.19129 validation_1-rmse:0.15330 +[50] validation_0-rmse:0.19035 validation_1-rmse:0.15194 +[51] validation_0-rmse:0.18948 validation_1-rmse:0.15082 +[52] validation_0-rmse:0.18882 validation_1-rmse:0.14945 +[53] validation_0-rmse:0.18801 validation_1-rmse:0.14840 +[54] validation_0-rmse:0.18707 validation_1-rmse:0.14736 +[55] validation_0-rmse:0.18637 validation_1-rmse:0.14635 +[56] validation_0-rmse:0.18571 validation_1-rmse:0.14542 +[57] validation_0-rmse:0.18497 validation_1-rmse:0.14413 +[58] validation_0-rmse:0.18443 validation_1-rmse:0.14297 +[59] validation_0-rmse:0.18375 validation_1-rmse:0.14203 +[60] validation_0-rmse:0.18319 validation_1-rmse:0.14111 +[61] validation_0-rmse:0.18266 validation_1-rmse:0.14030 +[62] validation_0-rmse:0.18185 validation_1-rmse:0.13914 +[63] validation_0-rmse:0.18145 validation_1-rmse:0.13831 +[64] validation_0-rmse:0.18135 validation_1-rmse:0.13720 +[65] validation_0-rmse:0.18075 validation_1-rmse:0.13643 +[66] validation_0-rmse:0.18020 validation_1-rmse:0.13560 +[67] validation_0-rmse:0.17951 validation_1-rmse:0.13485 +[68] validation_0-rmse:0.17888 validation_1-rmse:0.13414 +[69] validation_0-rmse:0.17850 validation_1-rmse:0.13343 +[70] validation_0-rmse:0.17798 validation_1-rmse:0.13224 +[71] validation_0-rmse:0.17751 validation_1-rmse:0.13133 +[72] validation_0-rmse:0.17711 validation_1-rmse:0.13062 +[73] validation_0-rmse:0.17701 validation_1-rmse:0.12966 +[74] validation_0-rmse:0.17648 validation_1-rmse:0.12872 +[75] validation_0-rmse:0.17611 validation_1-rmse:0.12806 +[76] validation_0-rmse:0.17573 validation_1-rmse:0.12732 +[77] validation_0-rmse:0.17528 validation_1-rmse:0.12664 +[78] validation_0-rmse:0.17478 validation_1-rmse:0.12605 +[79] validation_0-rmse:0.17432 validation_1-rmse:0.12518 +[80] validation_0-rmse:0.17391 validation_1-rmse:0.12466 +[81] validation_0-rmse:0.17358 validation_1-rmse:0.12398 +[82] validation_0-rmse:0.17315 validation_1-rmse:0.12342 +[83] validation_0-rmse:0.17260 validation_1-rmse:0.12276 +[84] validation_0-rmse:0.17220 validation_1-rmse:0.12222 +[85] validation_0-rmse:0.17182 validation_1-rmse:0.12176 +[86] validation_0-rmse:0.17152 validation_1-rmse:0.12124 +[87] validation_0-rmse:0.17103 validation_1-rmse:0.12046 +[88] validation_0-rmse:0.17085 validation_1-rmse:0.11974 +[89] validation_0-rmse:0.17053 validation_1-rmse:0.11930 +[90] validation_0-rmse:0.17018 validation_1-rmse:0.11888 +[91] validation_0-rmse:0.17011 validation_1-rmse:0.11810 +[92] validation_0-rmse:0.16980 validation_1-rmse:0.11762 +[93] validation_0-rmse:0.16956 validation_1-rmse:0.11689 +[94] validation_0-rmse:0.16923 validation_1-rmse:0.11641 +[95] validation_0-rmse:0.16912 validation_1-rmse:0.11579 +[96] validation_0-rmse:0.16878 validation_1-rmse:0.11530 +[97] validation_0-rmse:0.16857 validation_1-rmse:0.11489 +[98] validation_0-rmse:0.16824 validation_1-rmse:0.11442 +[99] validation_0-rmse:0.16824 validation_1-rmse:0.11403 +2025-04-29 01:56:19,586 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.52 secs) -------------------- +2025-04-29 01:56:19,587 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:20,174 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2024-12-12 00:00:00 to 2025-01-11 00:00:00, 2/11 trains +2025-04-29 01:56:20,175 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1736553600_prediction.feather +2025-04-29 01:56:20,179 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:20,185 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:56:20,186 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.68088 +1 0.003044 49.68088 +2 0.000465 49.68088 +3 -0.000380 49.68088 +4 0.002829 49.68088 +2025-04-29 01:56:20,192 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:20,197 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:56:20,199 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.97721 +1 0.003044 49.97721 +2 0.000465 49.97721 +3 -0.000380 49.97721 +4 0.002829 49.97721 +2025-04-29 01:56:20,204 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1736553600/cb_sol_1736553600 +2025-04-29 01:56:20,205 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:20,227 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:20,228 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-12 to 2025-01-10 -------------------- +2025-04-29 01:56:25,109 - datasieve.pipeline - INFO - DI tossed 5 predictions for being too far from training data. +2025-04-29 01:56:25,112 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:25,112 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.29597 validation_1-rmse:0.29016 +[1] validation_0-rmse:0.29075 validation_1-rmse:0.28391 +[2] validation_0-rmse:0.28602 validation_1-rmse:0.27798 +[3] validation_0-rmse:0.28062 validation_1-rmse:0.27213 +[4] validation_0-rmse:0.27647 validation_1-rmse:0.26682 +[5] validation_0-rmse:0.27188 validation_1-rmse:0.26144 +[6] validation_0-rmse:0.26781 validation_1-rmse:0.25655 +[7] validation_0-rmse:0.26412 validation_1-rmse:0.25180 +[8] validation_0-rmse:0.25994 validation_1-rmse:0.24709 +[9] validation_0-rmse:0.25649 validation_1-rmse:0.24277 +[10] validation_0-rmse:0.25332 validation_1-rmse:0.23850 +[11] validation_0-rmse:0.24999 validation_1-rmse:0.23452 +[12] validation_0-rmse:0.24687 validation_1-rmse:0.23072 +[13] validation_0-rmse:0.24432 validation_1-rmse:0.22694 +[14] validation_0-rmse:0.24128 validation_1-rmse:0.22341 +[15] validation_0-rmse:0.23869 validation_1-rmse:0.21969 +[16] validation_0-rmse:0.23628 validation_1-rmse:0.21635 +[17] validation_0-rmse:0.23354 validation_1-rmse:0.21326 +[18] validation_0-rmse:0.23123 validation_1-rmse:0.21007 +[19] validation_0-rmse:0.22919 validation_1-rmse:0.20707 +[20] validation_0-rmse:0.22705 validation_1-rmse:0.20418 +[21] validation_0-rmse:0.22505 validation_1-rmse:0.20149 +[22] validation_0-rmse:0.22285 validation_1-rmse:0.19887 +[23] validation_0-rmse:0.22084 validation_1-rmse:0.19631 +[24] validation_0-rmse:0.21877 validation_1-rmse:0.19389 +[25] validation_0-rmse:0.21748 validation_1-rmse:0.19133 +[26] validation_0-rmse:0.21557 validation_1-rmse:0.18870 +[27] validation_0-rmse:0.21374 validation_1-rmse:0.18648 +[28] validation_0-rmse:0.21183 validation_1-rmse:0.18432 +[29] validation_0-rmse:0.21047 validation_1-rmse:0.18209 +[30] validation_0-rmse:0.20873 validation_1-rmse:0.17990 +[31] validation_0-rmse:0.20717 validation_1-rmse:0.17795 +[32] validation_0-rmse:0.20564 validation_1-rmse:0.17599 +[33] validation_0-rmse:0.20428 validation_1-rmse:0.17421 +[34] validation_0-rmse:0.20290 validation_1-rmse:0.17229 +[35] validation_0-rmse:0.20161 validation_1-rmse:0.17047 +[36] validation_0-rmse:0.20018 validation_1-rmse:0.16878 +[37] validation_0-rmse:0.19923 validation_1-rmse:0.16688 +[38] validation_0-rmse:0.19796 validation_1-rmse:0.16534 +[39] validation_0-rmse:0.19668 validation_1-rmse:0.16355 +[40] validation_0-rmse:0.19543 validation_1-rmse:0.16204 +[41] validation_0-rmse:0.19441 validation_1-rmse:0.16062 +[42] validation_0-rmse:0.19344 validation_1-rmse:0.15910 +[43] validation_0-rmse:0.19256 validation_1-rmse:0.15759 +[44] validation_0-rmse:0.19154 validation_1-rmse:0.15625 +[45] validation_0-rmse:0.19048 validation_1-rmse:0.15494 +[46] validation_0-rmse:0.18937 validation_1-rmse:0.15366 +[47] validation_0-rmse:0.18865 validation_1-rmse:0.15236 +[48] validation_0-rmse:0.18784 validation_1-rmse:0.15112 +[49] validation_0-rmse:0.18704 validation_1-rmse:0.14998 +[50] validation_0-rmse:0.18625 validation_1-rmse:0.14874 +[51] validation_0-rmse:0.18541 validation_1-rmse:0.14763 +[52] validation_0-rmse:0.18456 validation_1-rmse:0.14659 +[53] validation_0-rmse:0.18383 validation_1-rmse:0.14530 +[54] validation_0-rmse:0.18315 validation_1-rmse:0.14420 +[55] validation_0-rmse:0.18234 validation_1-rmse:0.14321 +[56] validation_0-rmse:0.18181 validation_1-rmse:0.14206 +[57] validation_0-rmse:0.18109 validation_1-rmse:0.14106 +[58] validation_0-rmse:0.18033 validation_1-rmse:0.13996 +[59] validation_0-rmse:0.17964 validation_1-rmse:0.13905 +[60] validation_0-rmse:0.17921 validation_1-rmse:0.13820 +[61] validation_0-rmse:0.17865 validation_1-rmse:0.13731 +[62] validation_0-rmse:0.17795 validation_1-rmse:0.13648 +[63] validation_0-rmse:0.17737 validation_1-rmse:0.13559 +[64] validation_0-rmse:0.17680 validation_1-rmse:0.13483 +[65] validation_0-rmse:0.17628 validation_1-rmse:0.13408 +[66] validation_0-rmse:0.17588 validation_1-rmse:0.13303 +[67] validation_0-rmse:0.17530 validation_1-rmse:0.13228 +[68] validation_0-rmse:0.17478 validation_1-rmse:0.13153 +[69] validation_0-rmse:0.17439 validation_1-rmse:0.13081 +[70] validation_0-rmse:0.17401 validation_1-rmse:0.12991 +[71] validation_0-rmse:0.17347 validation_1-rmse:0.12911 +[72] validation_0-rmse:0.17304 validation_1-rmse:0.12838 +[73] validation_0-rmse:0.17254 validation_1-rmse:0.12774 +[74] validation_0-rmse:0.17207 validation_1-rmse:0.12656 +[75] validation_0-rmse:0.17185 validation_1-rmse:0.12571 +[76] validation_0-rmse:0.17126 validation_1-rmse:0.12512 +[77] validation_0-rmse:0.17096 validation_1-rmse:0.12447 +[78] validation_0-rmse:0.17064 validation_1-rmse:0.12381 +[79] validation_0-rmse:0.17024 validation_1-rmse:0.12300 +[80] validation_0-rmse:0.16989 validation_1-rmse:0.12244 +[81] validation_0-rmse:0.16955 validation_1-rmse:0.12180 +[82] validation_0-rmse:0.16924 validation_1-rmse:0.12129 +[83] validation_0-rmse:0.16931 validation_1-rmse:0.12037 +[84] validation_0-rmse:0.16888 validation_1-rmse:0.11970 +[85] validation_0-rmse:0.16845 validation_1-rmse:0.11914 +[86] validation_0-rmse:0.16809 validation_1-rmse:0.11840 +[87] validation_0-rmse:0.16766 validation_1-rmse:0.11760 +[88] validation_0-rmse:0.16741 validation_1-rmse:0.11714 +[89] validation_0-rmse:0.16707 validation_1-rmse:0.11667 +[90] validation_0-rmse:0.16683 validation_1-rmse:0.11592 +[91] validation_0-rmse:0.16643 validation_1-rmse:0.11537 +[92] validation_0-rmse:0.16621 validation_1-rmse:0.11455 +[93] validation_0-rmse:0.16611 validation_1-rmse:0.11396 +[94] validation_0-rmse:0.16587 validation_1-rmse:0.11350 +[95] validation_0-rmse:0.16563 validation_1-rmse:0.11308 +[96] validation_0-rmse:0.16535 validation_1-rmse:0.11237 +[97] validation_0-rmse:0.16487 validation_1-rmse:0.11173 +[98] validation_0-rmse:0.16461 validation_1-rmse:0.11133 +[99] validation_0-rmse:0.16437 validation_1-rmse:0.11096 +2025-04-29 01:56:26,510 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.30 secs) -------------------- +2025-04-29 01:56:26,511 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:27,072 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2024-12-22 00:00:00 to 2025-01-21 00:00:00, 3/11 trains +2025-04-29 01:56:27,073 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1737417600_prediction.feather +2025-04-29 01:56:27,079 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:27,085 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:56:27,086 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.97721 +1 0.003044 49.97721 +2 0.000465 49.97721 +3 -0.000380 49.97721 +4 0.002829 49.97721 +2025-04-29 01:56:27,094 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:27,100 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:56:27,102 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.941408 +1 0.003044 49.941408 +2 0.000465 49.941408 +3 -0.000380 49.941408 +4 0.002829 49.941408 +2025-04-29 01:56:27,108 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1737417600/cb_sol_1737417600 +2025-04-29 01:56:27,109 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:27,130 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:27,131 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-22 to 2025-01-20 -------------------- +2025-04-29 01:56:32,206 - datasieve.pipeline - INFO - DI tossed 1523 predictions for being too far from training data. +2025-04-29 01:56:32,209 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:32,210 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.30838 validation_1-rmse:0.28356 +[1] validation_0-rmse:0.30280 validation_1-rmse:0.27752 +[2] validation_0-rmse:0.29759 validation_1-rmse:0.27179 +[3] validation_0-rmse:0.29330 validation_1-rmse:0.26614 +[4] validation_0-rmse:0.28936 validation_1-rmse:0.26091 +[5] validation_0-rmse:0.28544 validation_1-rmse:0.25581 +[6] validation_0-rmse:0.28151 validation_1-rmse:0.25102 +[7] validation_0-rmse:0.27790 validation_1-rmse:0.24636 +[8] validation_0-rmse:0.27429 validation_1-rmse:0.24196 +[9] validation_0-rmse:0.27104 validation_1-rmse:0.23770 +[10] validation_0-rmse:0.26762 validation_1-rmse:0.23356 +[11] validation_0-rmse:0.26472 validation_1-rmse:0.22966 +[12] validation_0-rmse:0.26219 validation_1-rmse:0.22601 +[13] validation_0-rmse:0.25924 validation_1-rmse:0.22234 +[14] validation_0-rmse:0.25634 validation_1-rmse:0.21888 +[15] validation_0-rmse:0.25379 validation_1-rmse:0.21545 +[16] validation_0-rmse:0.25117 validation_1-rmse:0.21221 +[17] validation_0-rmse:0.24877 validation_1-rmse:0.20902 +[18] validation_0-rmse:0.24653 validation_1-rmse:0.20604 +[19] validation_0-rmse:0.24404 validation_1-rmse:0.20315 +[20] validation_0-rmse:0.24194 validation_1-rmse:0.20032 +[21] validation_0-rmse:0.23966 validation_1-rmse:0.19765 +[22] validation_0-rmse:0.23804 validation_1-rmse:0.19481 +[23] validation_0-rmse:0.23599 validation_1-rmse:0.19230 +[24] validation_0-rmse:0.23384 validation_1-rmse:0.18993 +[25] validation_0-rmse:0.23196 validation_1-rmse:0.18756 +[26] validation_0-rmse:0.23057 validation_1-rmse:0.18506 +[27] validation_0-rmse:0.22854 validation_1-rmse:0.18283 +[28] validation_0-rmse:0.22705 validation_1-rmse:0.18071 +[29] validation_0-rmse:0.22557 validation_1-rmse:0.17851 +[30] validation_0-rmse:0.22394 validation_1-rmse:0.17644 +[31] validation_0-rmse:0.22213 validation_1-rmse:0.17452 +[32] validation_0-rmse:0.22064 validation_1-rmse:0.17267 +[33] validation_0-rmse:0.21905 validation_1-rmse:0.17084 +[34] validation_0-rmse:0.21806 validation_1-rmse:0.16880 +[35] validation_0-rmse:0.21693 validation_1-rmse:0.16700 +[36] validation_0-rmse:0.21537 validation_1-rmse:0.16520 +[37] validation_0-rmse:0.21417 validation_1-rmse:0.16362 +[38] validation_0-rmse:0.21282 validation_1-rmse:0.16204 +[39] validation_0-rmse:0.21137 validation_1-rmse:0.16047 +[40] validation_0-rmse:0.20994 validation_1-rmse:0.15897 +[41] validation_0-rmse:0.20878 validation_1-rmse:0.15747 +[42] validation_0-rmse:0.20766 validation_1-rmse:0.15604 +[43] validation_0-rmse:0.20666 validation_1-rmse:0.15444 +[44] validation_0-rmse:0.20566 validation_1-rmse:0.15316 +[45] validation_0-rmse:0.20496 validation_1-rmse:0.15162 +[46] validation_0-rmse:0.20394 validation_1-rmse:0.15038 +[47] validation_0-rmse:0.20277 validation_1-rmse:0.14909 +[48] validation_0-rmse:0.20176 validation_1-rmse:0.14793 +[49] validation_0-rmse:0.20072 validation_1-rmse:0.14681 +[50] validation_0-rmse:0.20058 validation_1-rmse:0.14528 +[51] validation_0-rmse:0.19970 validation_1-rmse:0.14419 +[52] validation_0-rmse:0.19887 validation_1-rmse:0.14284 +[53] validation_0-rmse:0.19809 validation_1-rmse:0.14182 +[54] validation_0-rmse:0.19725 validation_1-rmse:0.14076 +[55] validation_0-rmse:0.19636 validation_1-rmse:0.13981 +[56] validation_0-rmse:0.19615 validation_1-rmse:0.13853 +[57] validation_0-rmse:0.19540 validation_1-rmse:0.13757 +[58] validation_0-rmse:0.19460 validation_1-rmse:0.13664 +[59] validation_0-rmse:0.19418 validation_1-rmse:0.13553 +[60] validation_0-rmse:0.19382 validation_1-rmse:0.13445 +[61] validation_0-rmse:0.19302 validation_1-rmse:0.13363 +[62] validation_0-rmse:0.19218 validation_1-rmse:0.13270 +[63] validation_0-rmse:0.19154 validation_1-rmse:0.13183 +[64] validation_0-rmse:0.19083 validation_1-rmse:0.13105 +[65] validation_0-rmse:0.19005 validation_1-rmse:0.13008 +[66] validation_0-rmse:0.18929 validation_1-rmse:0.12932 +[67] validation_0-rmse:0.18885 validation_1-rmse:0.12851 +[68] validation_0-rmse:0.18837 validation_1-rmse:0.12781 +[69] validation_0-rmse:0.18790 validation_1-rmse:0.12711 +[70] validation_0-rmse:0.18732 validation_1-rmse:0.12617 +[71] validation_0-rmse:0.18682 validation_1-rmse:0.12552 +[72] validation_0-rmse:0.18669 validation_1-rmse:0.12448 +[73] validation_0-rmse:0.18617 validation_1-rmse:0.12382 +[74] validation_0-rmse:0.18587 validation_1-rmse:0.12322 +[75] validation_0-rmse:0.18544 validation_1-rmse:0.12261 +[76] validation_0-rmse:0.18524 validation_1-rmse:0.12162 +[77] validation_0-rmse:0.18486 validation_1-rmse:0.12098 +[78] validation_0-rmse:0.18443 validation_1-rmse:0.12021 +[79] validation_0-rmse:0.18415 validation_1-rmse:0.11963 +[80] validation_0-rmse:0.18393 validation_1-rmse:0.11866 +[81] validation_0-rmse:0.18344 validation_1-rmse:0.11809 +[82] validation_0-rmse:0.18307 validation_1-rmse:0.11748 +[83] validation_0-rmse:0.18257 validation_1-rmse:0.11699 +[84] validation_0-rmse:0.18216 validation_1-rmse:0.11643 +[85] validation_0-rmse:0.18188 validation_1-rmse:0.11595 +[86] validation_0-rmse:0.18168 validation_1-rmse:0.11502 +[87] validation_0-rmse:0.18148 validation_1-rmse:0.11451 +[88] validation_0-rmse:0.18093 validation_1-rmse:0.11378 +[89] validation_0-rmse:0.18054 validation_1-rmse:0.11332 +[90] validation_0-rmse:0.18024 validation_1-rmse:0.11285 +[91] validation_0-rmse:0.17982 validation_1-rmse:0.11241 +[92] validation_0-rmse:0.17950 validation_1-rmse:0.11185 +[93] validation_0-rmse:0.17918 validation_1-rmse:0.11123 +[94] validation_0-rmse:0.17882 validation_1-rmse:0.11072 +[95] validation_0-rmse:0.17881 validation_1-rmse:0.10986 +[96] validation_0-rmse:0.17832 validation_1-rmse:0.10941 +[97] validation_0-rmse:0.17800 validation_1-rmse:0.10897 +[98] validation_0-rmse:0.17774 validation_1-rmse:0.10859 +[99] validation_0-rmse:0.17746 validation_1-rmse:0.10819 +2025-04-29 01:56:33,558 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.45 secs) -------------------- +2025-04-29 01:56:33,558 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:34,118 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-01 00:00:00 to 2025-01-31 00:00:00, 4/11 trains +2025-04-29 01:56:34,119 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1738281600_prediction.feather +2025-04-29 01:56:34,124 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:34,130 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:56:34,131 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.941408 +1 0.003044 49.941408 +2 0.000465 49.941408 +3 -0.000380 49.941408 +4 0.002829 49.941408 +2025-04-29 01:56:34,137 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:34,143 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:56:34,144 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.830756 +1 0.003044 49.830756 +2 0.000465 49.830756 +3 -0.000380 49.830756 +4 0.002829 49.830756 +2025-04-29 01:56:34,149 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1738281600/cb_sol_1738281600 +2025-04-29 01:56:34,150 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:34,173 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:34,173 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-01 to 2025-01-30 -------------------- +2025-04-29 01:56:39,271 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:39,271 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.29494 validation_1-rmse:0.28739 +[1] validation_0-rmse:0.28930 validation_1-rmse:0.28164 +[2] validation_0-rmse:0.28437 validation_1-rmse:0.27613 +[3] validation_0-rmse:0.27990 validation_1-rmse:0.27106 +[4] validation_0-rmse:0.27541 validation_1-rmse:0.26617 +[5] validation_0-rmse:0.27070 validation_1-rmse:0.26147 +[6] validation_0-rmse:0.26683 validation_1-rmse:0.25687 +[7] validation_0-rmse:0.26280 validation_1-rmse:0.25263 +[8] validation_0-rmse:0.25916 validation_1-rmse:0.24830 +[9] validation_0-rmse:0.25540 validation_1-rmse:0.24420 +[10] validation_0-rmse:0.25186 validation_1-rmse:0.24022 +[11] validation_0-rmse:0.24829 validation_1-rmse:0.23647 +[12] validation_0-rmse:0.24504 validation_1-rmse:0.23286 +[13] validation_0-rmse:0.24183 validation_1-rmse:0.22943 +[14] validation_0-rmse:0.23870 validation_1-rmse:0.22619 +[15] validation_0-rmse:0.23587 validation_1-rmse:0.22274 +[16] validation_0-rmse:0.23325 validation_1-rmse:0.21951 +[17] validation_0-rmse:0.23045 validation_1-rmse:0.21650 +[18] validation_0-rmse:0.22792 validation_1-rmse:0.21367 +[19] validation_0-rmse:0.22524 validation_1-rmse:0.21092 +[20] validation_0-rmse:0.22293 validation_1-rmse:0.20804 +[21] validation_0-rmse:0.22055 validation_1-rmse:0.20549 +[22] validation_0-rmse:0.21831 validation_1-rmse:0.20307 +[23] validation_0-rmse:0.21601 validation_1-rmse:0.20062 +[24] validation_0-rmse:0.21372 validation_1-rmse:0.19810 +[25] validation_0-rmse:0.21154 validation_1-rmse:0.19580 +[26] validation_0-rmse:0.20966 validation_1-rmse:0.19369 +[27] validation_0-rmse:0.20790 validation_1-rmse:0.19130 +[28] validation_0-rmse:0.20602 validation_1-rmse:0.18921 +[29] validation_0-rmse:0.20418 validation_1-rmse:0.18723 +[30] validation_0-rmse:0.20236 validation_1-rmse:0.18525 +[31] validation_0-rmse:0.20057 validation_1-rmse:0.18324 +[32] validation_0-rmse:0.19900 validation_1-rmse:0.18144 +[33] validation_0-rmse:0.19744 validation_1-rmse:0.17941 +[34] validation_0-rmse:0.19608 validation_1-rmse:0.17767 +[35] validation_0-rmse:0.19467 validation_1-rmse:0.17605 +[36] validation_0-rmse:0.19313 validation_1-rmse:0.17422 +[37] validation_0-rmse:0.19156 validation_1-rmse:0.17260 +[38] validation_0-rmse:0.19020 validation_1-rmse:0.17103 +[39] validation_0-rmse:0.18884 validation_1-rmse:0.16948 +[40] validation_0-rmse:0.18767 validation_1-rmse:0.16797 +[41] validation_0-rmse:0.18636 validation_1-rmse:0.16647 +[42] validation_0-rmse:0.18512 validation_1-rmse:0.16505 +[43] validation_0-rmse:0.18403 validation_1-rmse:0.16340 +[44] validation_0-rmse:0.18290 validation_1-rmse:0.16210 +[45] validation_0-rmse:0.18189 validation_1-rmse:0.16085 +[46] validation_0-rmse:0.18090 validation_1-rmse:0.15966 +[47] validation_0-rmse:0.17992 validation_1-rmse:0.15841 +[48] validation_0-rmse:0.17901 validation_1-rmse:0.15728 +[49] validation_0-rmse:0.17817 validation_1-rmse:0.15582 +[50] validation_0-rmse:0.17697 validation_1-rmse:0.15458 +[51] validation_0-rmse:0.17607 validation_1-rmse:0.15349 +[52] validation_0-rmse:0.17516 validation_1-rmse:0.15235 +[53] validation_0-rmse:0.17425 validation_1-rmse:0.15131 +[54] validation_0-rmse:0.17347 validation_1-rmse:0.15032 +[55] validation_0-rmse:0.17275 validation_1-rmse:0.14932 +[56] validation_0-rmse:0.17211 validation_1-rmse:0.14834 +[57] validation_0-rmse:0.17131 validation_1-rmse:0.14741 +[58] validation_0-rmse:0.17072 validation_1-rmse:0.14617 +[59] validation_0-rmse:0.16999 validation_1-rmse:0.14528 +[60] validation_0-rmse:0.16934 validation_1-rmse:0.14416 +[61] validation_0-rmse:0.16887 validation_1-rmse:0.14321 +[62] validation_0-rmse:0.16842 validation_1-rmse:0.14213 +[63] validation_0-rmse:0.16765 validation_1-rmse:0.14130 +[64] validation_0-rmse:0.16691 validation_1-rmse:0.14048 +[65] validation_0-rmse:0.16629 validation_1-rmse:0.13956 +[66] validation_0-rmse:0.16565 validation_1-rmse:0.13882 +[67] validation_0-rmse:0.16530 validation_1-rmse:0.13793 +[68] validation_0-rmse:0.16467 validation_1-rmse:0.13710 +[69] validation_0-rmse:0.16436 validation_1-rmse:0.13621 +[70] validation_0-rmse:0.16377 validation_1-rmse:0.13542 +[71] validation_0-rmse:0.16334 validation_1-rmse:0.13463 +[72] validation_0-rmse:0.16280 validation_1-rmse:0.13394 +[73] validation_0-rmse:0.16230 validation_1-rmse:0.13328 +[74] validation_0-rmse:0.16156 validation_1-rmse:0.13246 +[75] validation_0-rmse:0.16122 validation_1-rmse:0.13151 +[76] validation_0-rmse:0.16080 validation_1-rmse:0.13080 +[77] validation_0-rmse:0.16033 validation_1-rmse:0.13015 +[78] validation_0-rmse:0.15992 validation_1-rmse:0.12951 +[79] validation_0-rmse:0.15950 validation_1-rmse:0.12888 +[80] validation_0-rmse:0.15909 validation_1-rmse:0.12822 +[81] validation_0-rmse:0.15875 validation_1-rmse:0.12744 +[82] validation_0-rmse:0.15831 validation_1-rmse:0.12683 +[83] validation_0-rmse:0.15786 validation_1-rmse:0.12626 +[84] validation_0-rmse:0.15747 validation_1-rmse:0.12572 +[85] validation_0-rmse:0.15724 validation_1-rmse:0.12495 +[86] validation_0-rmse:0.15695 validation_1-rmse:0.12442 +[87] validation_0-rmse:0.15664 validation_1-rmse:0.12382 +[88] validation_0-rmse:0.15651 validation_1-rmse:0.12326 +[89] validation_0-rmse:0.15629 validation_1-rmse:0.12256 +[90] validation_0-rmse:0.15596 validation_1-rmse:0.12196 +[91] validation_0-rmse:0.15559 validation_1-rmse:0.12141 +[92] validation_0-rmse:0.15511 validation_1-rmse:0.12088 +[93] validation_0-rmse:0.15487 validation_1-rmse:0.12033 +[94] validation_0-rmse:0.15472 validation_1-rmse:0.11975 +[95] validation_0-rmse:0.15438 validation_1-rmse:0.11924 +[96] validation_0-rmse:0.15408 validation_1-rmse:0.11882 +[97] validation_0-rmse:0.15382 validation_1-rmse:0.11819 +[98] validation_0-rmse:0.15350 validation_1-rmse:0.11777 +[99] validation_0-rmse:0.15331 validation_1-rmse:0.11727 +2025-04-29 01:56:40,600 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.45 secs) -------------------- +2025-04-29 01:56:40,601 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:41,171 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-11 00:00:00 to 2025-02-10 00:00:00, 5/11 trains +2025-04-29 01:56:41,172 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1739145600_prediction.feather +2025-04-29 01:56:41,177 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:41,183 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:56:41,185 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.830756 +1 0.003044 49.830756 +2 0.000465 49.830756 +3 -0.000380 49.830756 +4 0.002829 49.830756 +2025-04-29 01:56:41,193 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:41,200 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:56:41,201 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.714422 +1 0.003044 49.714422 +2 0.000465 49.714422 +3 -0.000380 49.714422 +4 0.002829 49.714422 +2025-04-29 01:56:41,206 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1739145600/cb_sol_1739145600 +2025-04-29 01:56:41,207 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:41,228 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:41,229 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-11 to 2025-02-09 -------------------- +2025-04-29 01:56:46,277 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:46,278 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.29889 validation_1-rmse:0.30153 +[1] validation_0-rmse:0.29317 validation_1-rmse:0.29483 +[2] validation_0-rmse:0.28819 validation_1-rmse:0.28860 +[3] validation_0-rmse:0.28336 validation_1-rmse:0.28273 +[4] validation_0-rmse:0.27885 validation_1-rmse:0.27694 +[5] validation_0-rmse:0.27448 validation_1-rmse:0.27155 +[6] validation_0-rmse:0.27020 validation_1-rmse:0.26634 +[7] validation_0-rmse:0.26629 validation_1-rmse:0.26134 +[8] validation_0-rmse:0.26241 validation_1-rmse:0.25653 +[9] validation_0-rmse:0.25876 validation_1-rmse:0.25192 +[10] validation_0-rmse:0.25559 validation_1-rmse:0.24747 +[11] validation_0-rmse:0.25223 validation_1-rmse:0.24337 +[12] validation_0-rmse:0.24904 validation_1-rmse:0.23934 +[13] validation_0-rmse:0.24639 validation_1-rmse:0.23548 +[14] validation_0-rmse:0.24353 validation_1-rmse:0.23187 +[15] validation_0-rmse:0.24076 validation_1-rmse:0.22837 +[16] validation_0-rmse:0.23849 validation_1-rmse:0.22484 +[17] validation_0-rmse:0.23581 validation_1-rmse:0.22147 +[18] validation_0-rmse:0.23342 validation_1-rmse:0.21814 +[19] validation_0-rmse:0.23133 validation_1-rmse:0.21509 +[20] validation_0-rmse:0.22937 validation_1-rmse:0.21187 +[21] validation_0-rmse:0.22713 validation_1-rmse:0.20902 +[22] validation_0-rmse:0.22509 validation_1-rmse:0.20631 +[23] validation_0-rmse:0.22312 validation_1-rmse:0.20373 +[24] validation_0-rmse:0.22123 validation_1-rmse:0.20076 +[25] validation_0-rmse:0.21951 validation_1-rmse:0.19837 +[26] validation_0-rmse:0.21751 validation_1-rmse:0.19562 +[27] validation_0-rmse:0.21589 validation_1-rmse:0.19309 +[28] validation_0-rmse:0.21422 validation_1-rmse:0.19091 +[29] validation_0-rmse:0.21272 validation_1-rmse:0.18879 +[30] validation_0-rmse:0.21119 validation_1-rmse:0.18660 +[31] validation_0-rmse:0.20982 validation_1-rmse:0.18468 +[32] validation_0-rmse:0.20829 validation_1-rmse:0.18239 +[33] validation_0-rmse:0.20681 validation_1-rmse:0.18048 +[34] validation_0-rmse:0.20548 validation_1-rmse:0.17869 +[35] validation_0-rmse:0.20431 validation_1-rmse:0.17665 +[36] validation_0-rmse:0.20297 validation_1-rmse:0.17483 +[37] validation_0-rmse:0.20174 validation_1-rmse:0.17311 +[38] validation_0-rmse:0.20060 validation_1-rmse:0.17153 +[39] validation_0-rmse:0.19951 validation_1-rmse:0.16958 +[40] validation_0-rmse:0.19848 validation_1-rmse:0.16805 +[41] validation_0-rmse:0.19745 validation_1-rmse:0.16652 +[42] validation_0-rmse:0.19647 validation_1-rmse:0.16509 +[43] validation_0-rmse:0.19570 validation_1-rmse:0.16325 +[44] validation_0-rmse:0.19473 validation_1-rmse:0.16187 +[45] validation_0-rmse:0.19397 validation_1-rmse:0.16012 +[46] validation_0-rmse:0.19314 validation_1-rmse:0.15887 +[47] validation_0-rmse:0.19196 validation_1-rmse:0.15723 +[48] validation_0-rmse:0.19096 validation_1-rmse:0.15595 +[49] validation_0-rmse:0.19009 validation_1-rmse:0.15468 +[50] validation_0-rmse:0.18931 validation_1-rmse:0.15355 +[51] validation_0-rmse:0.18864 validation_1-rmse:0.15207 +[52] validation_0-rmse:0.18786 validation_1-rmse:0.15101 +[53] validation_0-rmse:0.18690 validation_1-rmse:0.14960 +[54] validation_0-rmse:0.18614 validation_1-rmse:0.14859 +[55] validation_0-rmse:0.18550 validation_1-rmse:0.14756 +[56] validation_0-rmse:0.18475 validation_1-rmse:0.14647 +[57] validation_0-rmse:0.18405 validation_1-rmse:0.14545 +[58] validation_0-rmse:0.18346 validation_1-rmse:0.14415 +[59] validation_0-rmse:0.18277 validation_1-rmse:0.14321 +[60] validation_0-rmse:0.18219 validation_1-rmse:0.14221 +[61] validation_0-rmse:0.18158 validation_1-rmse:0.14129 +[62] validation_0-rmse:0.18100 validation_1-rmse:0.14043 +[63] validation_0-rmse:0.18059 validation_1-rmse:0.13920 +[64] validation_0-rmse:0.17997 validation_1-rmse:0.13842 +[65] validation_0-rmse:0.17941 validation_1-rmse:0.13754 +[66] validation_0-rmse:0.17881 validation_1-rmse:0.13652 +[67] validation_0-rmse:0.17823 validation_1-rmse:0.13576 +[68] validation_0-rmse:0.17784 validation_1-rmse:0.13468 +[69] validation_0-rmse:0.17735 validation_1-rmse:0.13396 +[70] validation_0-rmse:0.17687 validation_1-rmse:0.13311 +[71] validation_0-rmse:0.17628 validation_1-rmse:0.13225 +[72] validation_0-rmse:0.17599 validation_1-rmse:0.13154 +[73] validation_0-rmse:0.17542 validation_1-rmse:0.13080 +[74] validation_0-rmse:0.17497 validation_1-rmse:0.13013 +[75] validation_0-rmse:0.17456 validation_1-rmse:0.12954 +[76] validation_0-rmse:0.17416 validation_1-rmse:0.12864 +[77] validation_0-rmse:0.17369 validation_1-rmse:0.12802 +[78] validation_0-rmse:0.17345 validation_1-rmse:0.12735 +[79] validation_0-rmse:0.17302 validation_1-rmse:0.12672 +[80] validation_0-rmse:0.17254 validation_1-rmse:0.12609 +[81] validation_0-rmse:0.17248 validation_1-rmse:0.12527 +[82] validation_0-rmse:0.17210 validation_1-rmse:0.12470 +[83] validation_0-rmse:0.17196 validation_1-rmse:0.12398 +[84] validation_0-rmse:0.17189 validation_1-rmse:0.12334 +[85] validation_0-rmse:0.17155 validation_1-rmse:0.12280 +[86] validation_0-rmse:0.17124 validation_1-rmse:0.12230 +[87] validation_0-rmse:0.17103 validation_1-rmse:0.12178 +[88] validation_0-rmse:0.17086 validation_1-rmse:0.12118 +[89] validation_0-rmse:0.17064 validation_1-rmse:0.12049 +[90] validation_0-rmse:0.17029 validation_1-rmse:0.11993 +[91] validation_0-rmse:0.16981 validation_1-rmse:0.11942 +[92] validation_0-rmse:0.16950 validation_1-rmse:0.11894 +[93] validation_0-rmse:0.16937 validation_1-rmse:0.11833 +[94] validation_0-rmse:0.16928 validation_1-rmse:0.11786 +[95] validation_0-rmse:0.16899 validation_1-rmse:0.11735 +[96] validation_0-rmse:0.16869 validation_1-rmse:0.11693 +[97] validation_0-rmse:0.16843 validation_1-rmse:0.11650 +[98] validation_0-rmse:0.16829 validation_1-rmse:0.11591 +[99] validation_0-rmse:0.16802 validation_1-rmse:0.11547 +2025-04-29 01:56:47,778 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.57 secs) -------------------- +2025-04-29 01:56:47,779 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:48,320 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-21 00:00:00 to 2025-02-20 00:00:00, 6/11 trains +2025-04-29 01:56:48,321 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1740009600_prediction.feather +2025-04-29 01:56:48,327 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:48,333 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:56:48,334 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.714422 +1 0.003044 49.714422 +2 0.000465 49.714422 +3 -0.000380 49.714422 +4 0.002829 49.714422 +2025-04-29 01:56:48,346 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:48,353 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:56:48,354 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.626186 +1 0.003044 49.626186 +2 0.000465 49.626186 +3 -0.000380 49.626186 +4 0.002829 49.626186 +2025-04-29 01:56:48,361 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1740009600/cb_sol_1740009600 +2025-04-29 01:56:48,361 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:48,383 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:48,383 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-21 to 2025-02-19 -------------------- +2025-04-29 01:56:53,532 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:53,533 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.29357 validation_1-rmse:0.28852 +[1] validation_0-rmse:0.28850 validation_1-rmse:0.28219 +[2] validation_0-rmse:0.28292 validation_1-rmse:0.27618 +[3] validation_0-rmse:0.27862 validation_1-rmse:0.27046 +[4] validation_0-rmse:0.27383 validation_1-rmse:0.26510 +[5] validation_0-rmse:0.27018 validation_1-rmse:0.25989 +[6] validation_0-rmse:0.26615 validation_1-rmse:0.25477 +[7] validation_0-rmse:0.26234 validation_1-rmse:0.25007 +[8] validation_0-rmse:0.25794 validation_1-rmse:0.24560 +[9] validation_0-rmse:0.25417 validation_1-rmse:0.24109 +[10] validation_0-rmse:0.25083 validation_1-rmse:0.23700 +[11] validation_0-rmse:0.24683 validation_1-rmse:0.23303 +[12] validation_0-rmse:0.24384 validation_1-rmse:0.22908 +[13] validation_0-rmse:0.24093 validation_1-rmse:0.22542 +[14] validation_0-rmse:0.23743 validation_1-rmse:0.22186 +[15] validation_0-rmse:0.23484 validation_1-rmse:0.21841 +[16] validation_0-rmse:0.23215 validation_1-rmse:0.21525 +[17] validation_0-rmse:0.22951 validation_1-rmse:0.21206 +[18] validation_0-rmse:0.22658 validation_1-rmse:0.20906 +[19] validation_0-rmse:0.22440 validation_1-rmse:0.20615 +[20] validation_0-rmse:0.22193 validation_1-rmse:0.20314 +[21] validation_0-rmse:0.22009 validation_1-rmse:0.20016 +[22] validation_0-rmse:0.21755 validation_1-rmse:0.19751 +[23] validation_0-rmse:0.21578 validation_1-rmse:0.19498 +[24] validation_0-rmse:0.21440 validation_1-rmse:0.19241 +[25] validation_0-rmse:0.21229 validation_1-rmse:0.19006 +[26] validation_0-rmse:0.21038 validation_1-rmse:0.18780 +[27] validation_0-rmse:0.20897 validation_1-rmse:0.18529 +[28] validation_0-rmse:0.20703 validation_1-rmse:0.18313 +[29] validation_0-rmse:0.20556 validation_1-rmse:0.18091 +[30] validation_0-rmse:0.20384 validation_1-rmse:0.17884 +[31] validation_0-rmse:0.20281 validation_1-rmse:0.17690 +[32] validation_0-rmse:0.20169 validation_1-rmse:0.17483 +[33] validation_0-rmse:0.20012 validation_1-rmse:0.17300 +[34] validation_0-rmse:0.19876 validation_1-rmse:0.17106 +[35] validation_0-rmse:0.19755 validation_1-rmse:0.16934 +[36] validation_0-rmse:0.19649 validation_1-rmse:0.16752 +[37] validation_0-rmse:0.19501 validation_1-rmse:0.16586 +[38] validation_0-rmse:0.19423 validation_1-rmse:0.16418 +[39] validation_0-rmse:0.19297 validation_1-rmse:0.16264 +[40] validation_0-rmse:0.19162 validation_1-rmse:0.16092 +[41] validation_0-rmse:0.19049 validation_1-rmse:0.15952 +[42] validation_0-rmse:0.18925 validation_1-rmse:0.15810 +[43] validation_0-rmse:0.18845 validation_1-rmse:0.15638 +[44] validation_0-rmse:0.18730 validation_1-rmse:0.15506 +[45] validation_0-rmse:0.18661 validation_1-rmse:0.15357 +[46] validation_0-rmse:0.18563 validation_1-rmse:0.15226 +[47] validation_0-rmse:0.18473 validation_1-rmse:0.15101 +[48] validation_0-rmse:0.18399 validation_1-rmse:0.14957 +[49] validation_0-rmse:0.18304 validation_1-rmse:0.14841 +[50] validation_0-rmse:0.18219 validation_1-rmse:0.14717 +[51] validation_0-rmse:0.18131 validation_1-rmse:0.14599 +[52] validation_0-rmse:0.18043 validation_1-rmse:0.14492 +[53] validation_0-rmse:0.17966 validation_1-rmse:0.14388 +[54] validation_0-rmse:0.17901 validation_1-rmse:0.14274 +[55] validation_0-rmse:0.17850 validation_1-rmse:0.14134 +[56] validation_0-rmse:0.17764 validation_1-rmse:0.14035 +[57] validation_0-rmse:0.17682 validation_1-rmse:0.13937 +[58] validation_0-rmse:0.17604 validation_1-rmse:0.13844 +[59] validation_0-rmse:0.17526 validation_1-rmse:0.13754 +[60] validation_0-rmse:0.17488 validation_1-rmse:0.13621 +[61] validation_0-rmse:0.17432 validation_1-rmse:0.13530 +[62] validation_0-rmse:0.17345 validation_1-rmse:0.13439 +[63] validation_0-rmse:0.17284 validation_1-rmse:0.13358 +[64] validation_0-rmse:0.17213 validation_1-rmse:0.13278 +[65] validation_0-rmse:0.17164 validation_1-rmse:0.13175 +[66] validation_0-rmse:0.17098 validation_1-rmse:0.13088 +[67] validation_0-rmse:0.17049 validation_1-rmse:0.13002 +[68] validation_0-rmse:0.17000 validation_1-rmse:0.12918 +[69] validation_0-rmse:0.16969 validation_1-rmse:0.12815 +[70] validation_0-rmse:0.16917 validation_1-rmse:0.12746 +[71] validation_0-rmse:0.16857 validation_1-rmse:0.12678 +[72] validation_0-rmse:0.16830 validation_1-rmse:0.12595 +[73] validation_0-rmse:0.16793 validation_1-rmse:0.12522 +[74] validation_0-rmse:0.16752 validation_1-rmse:0.12457 +[75] validation_0-rmse:0.16704 validation_1-rmse:0.12395 +[76] validation_0-rmse:0.16668 validation_1-rmse:0.12316 +[77] validation_0-rmse:0.16621 validation_1-rmse:0.12251 +[78] validation_0-rmse:0.16591 validation_1-rmse:0.12185 +[79] validation_0-rmse:0.16550 validation_1-rmse:0.12115 +[80] validation_0-rmse:0.16506 validation_1-rmse:0.12055 +[81] validation_0-rmse:0.16467 validation_1-rmse:0.12001 +[82] validation_0-rmse:0.16422 validation_1-rmse:0.11944 +[83] validation_0-rmse:0.16379 validation_1-rmse:0.11892 +[84] validation_0-rmse:0.16344 validation_1-rmse:0.11825 +[85] validation_0-rmse:0.16317 validation_1-rmse:0.11766 +[86] validation_0-rmse:0.16289 validation_1-rmse:0.11712 +[87] validation_0-rmse:0.16271 validation_1-rmse:0.11639 +[88] validation_0-rmse:0.16236 validation_1-rmse:0.11591 +[89] validation_0-rmse:0.16210 validation_1-rmse:0.11515 +[90] validation_0-rmse:0.16170 validation_1-rmse:0.11457 +[91] validation_0-rmse:0.16149 validation_1-rmse:0.11411 +[92] validation_0-rmse:0.16132 validation_1-rmse:0.11360 +[93] validation_0-rmse:0.16108 validation_1-rmse:0.11292 +[94] validation_0-rmse:0.16077 validation_1-rmse:0.11247 +[95] validation_0-rmse:0.16040 validation_1-rmse:0.11205 +[96] validation_0-rmse:0.16017 validation_1-rmse:0.11157 +[97] validation_0-rmse:0.15988 validation_1-rmse:0.11117 +[98] validation_0-rmse:0.15964 validation_1-rmse:0.11074 +[99] validation_0-rmse:0.15958 validation_1-rmse:0.11029 +2025-04-29 01:56:54,862 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.50 secs) -------------------- +2025-04-29 01:56:54,863 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:55,419 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-31 00:00:00 to 2025-03-02 00:00:00, 7/11 trains +2025-04-29 01:56:55,420 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1740873600_prediction.feather +2025-04-29 01:56:55,426 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:55,433 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:56:55,435 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.626186 +1 0.003044 49.626186 +2 0.000465 49.626186 +3 -0.000380 49.626186 +4 0.002829 49.626186 +2025-04-29 01:56:55,445 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:55,452 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:56:55,453 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.568812 +1 0.003044 49.568812 +2 0.000465 49.568812 +3 -0.000380 49.568812 +4 0.002829 49.568812 +2025-04-29 01:56:55,459 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1740873600/cb_sol_1740873600 +2025-04-29 01:56:55,459 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:55,481 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:55,482 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-31 to 2025-03-01 -------------------- +2025-04-29 01:57:00,566 - datasieve.pipeline - INFO - DI tossed 2417 predictions for being too far from training data. +2025-04-29 01:57:00,569 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:00,570 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.33058 validation_1-rmse:0.29214 +[1] validation_0-rmse:0.32414 validation_1-rmse:0.28558 +[2] validation_0-rmse:0.31832 validation_1-rmse:0.27962 +[3] validation_0-rmse:0.31280 validation_1-rmse:0.27380 +[4] validation_0-rmse:0.30679 validation_1-rmse:0.26829 +[5] validation_0-rmse:0.30182 validation_1-rmse:0.26306 +[6] validation_0-rmse:0.29686 validation_1-rmse:0.25797 +[7] validation_0-rmse:0.29291 validation_1-rmse:0.25323 +[8] validation_0-rmse:0.28868 validation_1-rmse:0.24871 +[9] validation_0-rmse:0.28559 validation_1-rmse:0.24437 +[10] validation_0-rmse:0.28262 validation_1-rmse:0.24018 +[11] validation_0-rmse:0.27890 validation_1-rmse:0.23606 +[12] validation_0-rmse:0.27663 validation_1-rmse:0.23225 +[13] validation_0-rmse:0.27306 validation_1-rmse:0.22870 +[14] validation_0-rmse:0.26948 validation_1-rmse:0.22493 +[15] validation_0-rmse:0.26663 validation_1-rmse:0.22157 +[16] validation_0-rmse:0.26427 validation_1-rmse:0.21817 +[17] validation_0-rmse:0.26195 validation_1-rmse:0.21492 +[18] validation_0-rmse:0.25856 validation_1-rmse:0.21177 +[19] validation_0-rmse:0.25606 validation_1-rmse:0.20861 +[20] validation_0-rmse:0.25343 validation_1-rmse:0.20580 +[21] validation_0-rmse:0.25243 validation_1-rmse:0.20301 +[22] validation_0-rmse:0.25066 validation_1-rmse:0.20027 +[23] validation_0-rmse:0.24864 validation_1-rmse:0.19761 +[24] validation_0-rmse:0.24630 validation_1-rmse:0.19522 +[25] validation_0-rmse:0.24491 validation_1-rmse:0.19283 +[26] validation_0-rmse:0.24339 validation_1-rmse:0.19036 +[27] validation_0-rmse:0.24108 validation_1-rmse:0.18818 +[28] validation_0-rmse:0.23976 validation_1-rmse:0.18592 +[29] validation_0-rmse:0.23882 validation_1-rmse:0.18348 +[30] validation_0-rmse:0.23676 validation_1-rmse:0.18142 +[31] validation_0-rmse:0.23520 validation_1-rmse:0.17945 +[32] validation_0-rmse:0.23395 validation_1-rmse:0.17754 +[33] validation_0-rmse:0.23229 validation_1-rmse:0.17545 +[34] validation_0-rmse:0.23073 validation_1-rmse:0.17360 +[35] validation_0-rmse:0.22951 validation_1-rmse:0.17182 +[36] validation_0-rmse:0.22806 validation_1-rmse:0.16995 +[37] validation_0-rmse:0.22713 validation_1-rmse:0.16834 +[38] validation_0-rmse:0.22541 validation_1-rmse:0.16668 +[39] validation_0-rmse:0.22393 validation_1-rmse:0.16509 +[40] validation_0-rmse:0.22282 validation_1-rmse:0.16343 +[41] validation_0-rmse:0.22168 validation_1-rmse:0.16185 +[42] validation_0-rmse:0.22085 validation_1-rmse:0.16046 +[43] validation_0-rmse:0.21991 validation_1-rmse:0.15907 +[44] validation_0-rmse:0.21833 validation_1-rmse:0.15756 +[45] validation_0-rmse:0.21710 validation_1-rmse:0.15618 +[46] validation_0-rmse:0.21619 validation_1-rmse:0.15490 +[47] validation_0-rmse:0.21518 validation_1-rmse:0.15345 +[48] validation_0-rmse:0.21402 validation_1-rmse:0.15221 +[49] validation_0-rmse:0.21305 validation_1-rmse:0.15086 +[50] validation_0-rmse:0.21229 validation_1-rmse:0.14968 +[51] validation_0-rmse:0.21119 validation_1-rmse:0.14854 +[52] validation_0-rmse:0.21019 validation_1-rmse:0.14745 +[53] validation_0-rmse:0.20924 validation_1-rmse:0.14637 +[54] validation_0-rmse:0.20982 validation_1-rmse:0.14517 +[55] validation_0-rmse:0.20888 validation_1-rmse:0.14405 +[56] validation_0-rmse:0.20806 validation_1-rmse:0.14305 +[57] validation_0-rmse:0.20822 validation_1-rmse:0.14169 +[58] validation_0-rmse:0.20741 validation_1-rmse:0.14071 +[59] validation_0-rmse:0.20663 validation_1-rmse:0.13976 +[60] validation_0-rmse:0.20602 validation_1-rmse:0.13882 +[61] validation_0-rmse:0.20523 validation_1-rmse:0.13776 +[62] validation_0-rmse:0.20558 validation_1-rmse:0.13689 +[63] validation_0-rmse:0.20501 validation_1-rmse:0.13605 +[64] validation_0-rmse:0.20348 validation_1-rmse:0.13462 +[65] validation_0-rmse:0.20273 validation_1-rmse:0.13382 +[66] validation_0-rmse:0.20203 validation_1-rmse:0.13306 +[67] validation_0-rmse:0.20166 validation_1-rmse:0.13228 +[68] validation_0-rmse:0.20002 validation_1-rmse:0.13102 +[69] validation_0-rmse:0.19928 validation_1-rmse:0.13021 +[70] validation_0-rmse:0.19870 validation_1-rmse:0.12946 +[71] validation_0-rmse:0.19830 validation_1-rmse:0.12876 +[72] validation_0-rmse:0.19814 validation_1-rmse:0.12801 +[73] validation_0-rmse:0.19798 validation_1-rmse:0.12711 +[74] validation_0-rmse:0.19746 validation_1-rmse:0.12649 +[75] validation_0-rmse:0.19701 validation_1-rmse:0.12588 +[76] validation_0-rmse:0.19555 validation_1-rmse:0.12467 +[77] validation_0-rmse:0.19514 validation_1-rmse:0.12407 +[78] validation_0-rmse:0.19468 validation_1-rmse:0.12347 +[79] validation_0-rmse:0.19439 validation_1-rmse:0.12277 +[80] validation_0-rmse:0.19473 validation_1-rmse:0.12220 +[81] validation_0-rmse:0.19448 validation_1-rmse:0.12154 +[82] validation_0-rmse:0.19418 validation_1-rmse:0.12086 +[83] validation_0-rmse:0.19370 validation_1-rmse:0.12030 +[84] validation_0-rmse:0.19346 validation_1-rmse:0.11976 +[85] validation_0-rmse:0.19322 validation_1-rmse:0.11879 +[86] validation_0-rmse:0.19282 validation_1-rmse:0.11819 +[87] validation_0-rmse:0.19226 validation_1-rmse:0.11770 +[88] validation_0-rmse:0.19187 validation_1-rmse:0.11719 +[89] validation_0-rmse:0.19145 validation_1-rmse:0.11671 +[90] validation_0-rmse:0.19134 validation_1-rmse:0.11619 +[91] validation_0-rmse:0.19030 validation_1-rmse:0.11531 +[92] validation_0-rmse:0.18998 validation_1-rmse:0.11487 +[93] validation_0-rmse:0.18945 validation_1-rmse:0.11445 +[94] validation_0-rmse:0.18919 validation_1-rmse:0.11395 +[95] validation_0-rmse:0.18862 validation_1-rmse:0.11324 +[96] validation_0-rmse:0.18824 validation_1-rmse:0.11283 +[97] validation_0-rmse:0.18778 validation_1-rmse:0.11225 +[98] validation_0-rmse:0.18755 validation_1-rmse:0.11186 +[99] validation_0-rmse:0.18742 validation_1-rmse:0.11149 +2025-04-29 01:57:02,441 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.98 secs) -------------------- +2025-04-29 01:57:02,442 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:02,968 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-02-10 00:00:00 to 2025-03-12 00:00:00, 8/11 trains +2025-04-29 01:57:02,968 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1741737600_prediction.feather +2025-04-29 01:57:02,980 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:02,987 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:57:02,989 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.568812 +1 0.003044 49.568812 +2 0.000465 49.568812 +3 -0.000380 49.568812 +4 0.002829 49.568812 +2025-04-29 01:57:03,001 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:03,007 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:57:03,009 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.623338 +1 0.003044 49.623338 +2 0.000465 49.623338 +3 -0.000380 49.623338 +4 0.002829 49.623338 +2025-04-29 01:57:03,014 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1741737600/cb_sol_1741737600 +2025-04-29 01:57:03,015 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:03,042 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:03,042 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-10 to 2025-03-11 -------------------- +2025-04-29 01:57:08,138 - datasieve.pipeline - INFO - DI tossed 3 predictions for being too far from training data. +2025-04-29 01:57:08,141 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:08,141 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.25025 validation_1-rmse:0.24842 +[1] validation_0-rmse:0.24557 validation_1-rmse:0.24302 +[2] validation_0-rmse:0.24132 validation_1-rmse:0.23806 +[3] validation_0-rmse:0.23733 validation_1-rmse:0.23332 +[4] validation_0-rmse:0.23376 validation_1-rmse:0.22859 +[5] validation_0-rmse:0.23049 validation_1-rmse:0.22444 +[6] validation_0-rmse:0.22702 validation_1-rmse:0.22025 +[7] validation_0-rmse:0.22380 validation_1-rmse:0.21631 +[8] validation_0-rmse:0.22066 validation_1-rmse:0.21250 +[9] validation_0-rmse:0.21772 validation_1-rmse:0.20892 +[10] validation_0-rmse:0.21473 validation_1-rmse:0.20536 +[11] validation_0-rmse:0.21219 validation_1-rmse:0.20211 +[12] validation_0-rmse:0.20968 validation_1-rmse:0.19897 +[13] validation_0-rmse:0.20730 validation_1-rmse:0.19597 +[14] validation_0-rmse:0.20552 validation_1-rmse:0.19281 +[15] validation_0-rmse:0.20361 validation_1-rmse:0.18992 +[16] validation_0-rmse:0.20165 validation_1-rmse:0.18721 +[17] validation_0-rmse:0.19948 validation_1-rmse:0.18463 +[18] validation_0-rmse:0.19807 validation_1-rmse:0.18193 +[19] validation_0-rmse:0.19703 validation_1-rmse:0.17939 +[20] validation_0-rmse:0.19569 validation_1-rmse:0.17683 +[21] validation_0-rmse:0.19388 validation_1-rmse:0.17462 +[22] validation_0-rmse:0.19219 validation_1-rmse:0.17240 +[23] validation_0-rmse:0.19062 validation_1-rmse:0.17026 +[24] validation_0-rmse:0.18933 validation_1-rmse:0.16813 +[25] validation_0-rmse:0.18829 validation_1-rmse:0.16598 +[26] validation_0-rmse:0.18704 validation_1-rmse:0.16411 +[27] validation_0-rmse:0.18563 validation_1-rmse:0.16221 +[28] validation_0-rmse:0.18446 validation_1-rmse:0.16034 +[29] validation_0-rmse:0.18316 validation_1-rmse:0.15841 +[30] validation_0-rmse:0.18192 validation_1-rmse:0.15674 +[31] validation_0-rmse:0.18091 validation_1-rmse:0.15479 +[32] validation_0-rmse:0.18003 validation_1-rmse:0.15312 +[33] validation_0-rmse:0.17886 validation_1-rmse:0.15150 +[34] validation_0-rmse:0.17786 validation_1-rmse:0.14997 +[35] validation_0-rmse:0.17692 validation_1-rmse:0.14855 +[36] validation_0-rmse:0.17613 validation_1-rmse:0.14709 +[37] validation_0-rmse:0.17547 validation_1-rmse:0.14549 +[38] validation_0-rmse:0.17467 validation_1-rmse:0.14404 +[39] validation_0-rmse:0.17393 validation_1-rmse:0.14267 +[40] validation_0-rmse:0.17348 validation_1-rmse:0.14118 +[41] validation_0-rmse:0.17258 validation_1-rmse:0.13993 +[42] validation_0-rmse:0.17168 validation_1-rmse:0.13871 +[43] validation_0-rmse:0.17077 validation_1-rmse:0.13757 +[44] validation_0-rmse:0.17015 validation_1-rmse:0.13621 +[45] validation_0-rmse:0.16924 validation_1-rmse:0.13509 +[46] validation_0-rmse:0.16833 validation_1-rmse:0.13401 +[47] validation_0-rmse:0.16756 validation_1-rmse:0.13297 +[48] validation_0-rmse:0.16717 validation_1-rmse:0.13198 +[49] validation_0-rmse:0.16664 validation_1-rmse:0.13081 +[50] validation_0-rmse:0.16615 validation_1-rmse:0.12979 +[51] validation_0-rmse:0.16541 validation_1-rmse:0.12879 +[52] validation_0-rmse:0.16478 validation_1-rmse:0.12767 +[53] validation_0-rmse:0.16408 validation_1-rmse:0.12675 +[54] validation_0-rmse:0.16363 validation_1-rmse:0.12571 +[55] validation_0-rmse:0.16320 validation_1-rmse:0.12485 +[56] validation_0-rmse:0.16253 validation_1-rmse:0.12398 +[57] validation_0-rmse:0.16192 validation_1-rmse:0.12307 +[58] validation_0-rmse:0.16149 validation_1-rmse:0.12229 +[59] validation_0-rmse:0.16137 validation_1-rmse:0.12128 +[60] validation_0-rmse:0.16117 validation_1-rmse:0.12045 +[61] validation_0-rmse:0.16064 validation_1-rmse:0.11966 +[62] validation_0-rmse:0.16050 validation_1-rmse:0.11890 +[63] validation_0-rmse:0.16003 validation_1-rmse:0.11809 +[64] validation_0-rmse:0.15969 validation_1-rmse:0.11739 +[65] validation_0-rmse:0.15922 validation_1-rmse:0.11661 +[66] validation_0-rmse:0.15868 validation_1-rmse:0.11577 +[67] validation_0-rmse:0.15830 validation_1-rmse:0.11509 +[68] validation_0-rmse:0.15789 validation_1-rmse:0.11446 +[69] validation_0-rmse:0.15733 validation_1-rmse:0.11372 +[70] validation_0-rmse:0.15694 validation_1-rmse:0.11307 +[71] validation_0-rmse:0.15692 validation_1-rmse:0.11224 +[72] validation_0-rmse:0.15659 validation_1-rmse:0.11166 +[73] validation_0-rmse:0.15634 validation_1-rmse:0.11111 +[74] validation_0-rmse:0.15595 validation_1-rmse:0.11056 +[75] validation_0-rmse:0.15579 validation_1-rmse:0.10985 +[76] validation_0-rmse:0.15543 validation_1-rmse:0.10903 +[77] validation_0-rmse:0.15500 validation_1-rmse:0.10848 +[78] validation_0-rmse:0.15499 validation_1-rmse:0.10778 +[79] validation_0-rmse:0.15471 validation_1-rmse:0.10721 +[80] validation_0-rmse:0.15442 validation_1-rmse:0.10666 +[81] validation_0-rmse:0.15416 validation_1-rmse:0.10608 +[82] validation_0-rmse:0.15388 validation_1-rmse:0.10560 +[83] validation_0-rmse:0.15368 validation_1-rmse:0.10498 +[84] validation_0-rmse:0.15346 validation_1-rmse:0.10449 +[85] validation_0-rmse:0.15329 validation_1-rmse:0.10392 +[86] validation_0-rmse:0.15302 validation_1-rmse:0.10347 +[87] validation_0-rmse:0.15270 validation_1-rmse:0.10303 +[88] validation_0-rmse:0.15259 validation_1-rmse:0.10258 +[89] validation_0-rmse:0.15269 validation_1-rmse:0.10204 +[90] validation_0-rmse:0.15239 validation_1-rmse:0.10159 +[91] validation_0-rmse:0.15204 validation_1-rmse:0.10116 +[92] validation_0-rmse:0.15175 validation_1-rmse:0.10070 +[93] validation_0-rmse:0.15167 validation_1-rmse:0.10017 +[94] validation_0-rmse:0.15154 validation_1-rmse:0.09982 +[95] validation_0-rmse:0.15122 validation_1-rmse:0.09932 +[96] validation_0-rmse:0.15119 validation_1-rmse:0.09880 +[97] validation_0-rmse:0.15112 validation_1-rmse:0.09842 +[98] validation_0-rmse:0.15095 validation_1-rmse:0.09807 +[99] validation_0-rmse:0.15075 validation_1-rmse:0.09770 +2025-04-29 01:57:09,614 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.60 secs) -------------------- +2025-04-29 01:57:09,615 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:10,150 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-02-20 00:00:00 to 2025-03-22 00:00:00, 9/11 trains +2025-04-29 01:57:10,151 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1742601600_prediction.feather +2025-04-29 01:57:10,159 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:10,167 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:57:10,168 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.623338 +1 0.003044 49.623338 +2 0.000465 49.623338 +3 -0.000380 49.623338 +4 0.002829 49.623338 +2025-04-29 01:57:10,181 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:10,188 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:57:10,190 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.644115 +1 0.003044 49.644115 +2 0.000465 49.644115 +3 -0.000380 49.644115 +4 0.002829 49.644115 +2025-04-29 01:57:10,195 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1742601600/cb_sol_1742601600 +2025-04-29 01:57:10,196 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:10,218 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:10,218 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-20 to 2025-03-21 -------------------- +2025-04-29 01:57:15,185 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:15,186 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.24126 validation_1-rmse:0.24985 +[1] validation_0-rmse:0.23710 validation_1-rmse:0.24457 +[2] validation_0-rmse:0.23323 validation_1-rmse:0.23968 +[3] validation_0-rmse:0.22960 validation_1-rmse:0.23491 +[4] validation_0-rmse:0.22600 validation_1-rmse:0.23038 +[5] validation_0-rmse:0.22255 validation_1-rmse:0.22616 +[6] validation_0-rmse:0.21946 validation_1-rmse:0.22213 +[7] validation_0-rmse:0.21640 validation_1-rmse:0.21827 +[8] validation_0-rmse:0.21381 validation_1-rmse:0.21453 +[9] validation_0-rmse:0.21110 validation_1-rmse:0.21092 +[10] validation_0-rmse:0.20854 validation_1-rmse:0.20742 +[11] validation_0-rmse:0.20586 validation_1-rmse:0.20418 +[12] validation_0-rmse:0.20373 validation_1-rmse:0.20097 +[13] validation_0-rmse:0.20156 validation_1-rmse:0.19779 +[14] validation_0-rmse:0.19934 validation_1-rmse:0.19493 +[15] validation_0-rmse:0.19739 validation_1-rmse:0.19211 +[16] validation_0-rmse:0.19537 validation_1-rmse:0.18929 +[17] validation_0-rmse:0.19333 validation_1-rmse:0.18671 +[18] validation_0-rmse:0.19163 validation_1-rmse:0.18396 +[19] validation_0-rmse:0.18975 validation_1-rmse:0.18157 +[20] validation_0-rmse:0.18799 validation_1-rmse:0.17903 +[21] validation_0-rmse:0.18612 validation_1-rmse:0.17673 +[22] validation_0-rmse:0.18451 validation_1-rmse:0.17454 +[23] validation_0-rmse:0.18299 validation_1-rmse:0.17225 +[24] validation_0-rmse:0.18150 validation_1-rmse:0.17025 +[25] validation_0-rmse:0.18016 validation_1-rmse:0.16803 +[26] validation_0-rmse:0.17866 validation_1-rmse:0.16614 +[27] validation_0-rmse:0.17732 validation_1-rmse:0.16429 +[28] validation_0-rmse:0.17619 validation_1-rmse:0.16247 +[29] validation_0-rmse:0.17494 validation_1-rmse:0.16080 +[30] validation_0-rmse:0.17391 validation_1-rmse:0.15889 +[31] validation_0-rmse:0.17282 validation_1-rmse:0.15724 +[32] validation_0-rmse:0.17156 validation_1-rmse:0.15548 +[33] validation_0-rmse:0.17054 validation_1-rmse:0.15393 +[34] validation_0-rmse:0.16943 validation_1-rmse:0.15244 +[35] validation_0-rmse:0.16841 validation_1-rmse:0.15088 +[36] validation_0-rmse:0.16736 validation_1-rmse:0.14950 +[37] validation_0-rmse:0.16647 validation_1-rmse:0.14797 +[38] validation_0-rmse:0.16544 validation_1-rmse:0.14641 +[39] validation_0-rmse:0.16454 validation_1-rmse:0.14508 +[40] validation_0-rmse:0.16357 validation_1-rmse:0.14380 +[41] validation_0-rmse:0.16266 validation_1-rmse:0.14261 +[42] validation_0-rmse:0.16198 validation_1-rmse:0.14134 +[43] validation_0-rmse:0.16105 validation_1-rmse:0.14019 +[44] validation_0-rmse:0.16046 validation_1-rmse:0.13896 +[45] validation_0-rmse:0.15963 validation_1-rmse:0.13773 +[46] validation_0-rmse:0.15899 validation_1-rmse:0.13662 +[47] validation_0-rmse:0.15822 validation_1-rmse:0.13555 +[48] validation_0-rmse:0.15757 validation_1-rmse:0.13452 +[49] validation_0-rmse:0.15688 validation_1-rmse:0.13322 +[50] validation_0-rmse:0.15627 validation_1-rmse:0.13206 +[51] validation_0-rmse:0.15558 validation_1-rmse:0.13110 +[52] validation_0-rmse:0.15493 validation_1-rmse:0.13017 +[53] validation_0-rmse:0.15429 validation_1-rmse:0.12924 +[54] validation_0-rmse:0.15365 validation_1-rmse:0.12838 +[55] validation_0-rmse:0.15303 validation_1-rmse:0.12741 +[56] validation_0-rmse:0.15258 validation_1-rmse:0.12653 +[57] validation_0-rmse:0.15202 validation_1-rmse:0.12569 +[58] validation_0-rmse:0.15142 validation_1-rmse:0.12478 +[59] validation_0-rmse:0.15106 validation_1-rmse:0.12392 +[60] validation_0-rmse:0.15049 validation_1-rmse:0.12297 +[61] validation_0-rmse:0.14990 validation_1-rmse:0.12223 +[62] validation_0-rmse:0.14932 validation_1-rmse:0.12144 +[63] validation_0-rmse:0.14876 validation_1-rmse:0.12071 +[64] validation_0-rmse:0.14826 validation_1-rmse:0.12000 +[65] validation_0-rmse:0.14788 validation_1-rmse:0.11931 +[66] validation_0-rmse:0.14753 validation_1-rmse:0.11842 +[67] validation_0-rmse:0.14714 validation_1-rmse:0.11776 +[68] validation_0-rmse:0.14665 validation_1-rmse:0.11706 +[69] validation_0-rmse:0.14655 validation_1-rmse:0.11614 +[70] validation_0-rmse:0.14616 validation_1-rmse:0.11556 +[71] validation_0-rmse:0.14579 validation_1-rmse:0.11478 +[72] validation_0-rmse:0.14533 validation_1-rmse:0.11418 +[73] validation_0-rmse:0.14491 validation_1-rmse:0.11358 +[74] validation_0-rmse:0.14448 validation_1-rmse:0.11300 +[75] validation_0-rmse:0.14446 validation_1-rmse:0.11235 +[76] validation_0-rmse:0.14414 validation_1-rmse:0.11173 +[77] validation_0-rmse:0.14371 validation_1-rmse:0.11116 +[78] validation_0-rmse:0.14344 validation_1-rmse:0.11066 +[79] validation_0-rmse:0.14321 validation_1-rmse:0.10996 +[80] validation_0-rmse:0.14280 validation_1-rmse:0.10942 +[81] validation_0-rmse:0.14250 validation_1-rmse:0.10885 +[82] validation_0-rmse:0.14222 validation_1-rmse:0.10837 +[83] validation_0-rmse:0.14184 validation_1-rmse:0.10787 +[84] validation_0-rmse:0.14140 validation_1-rmse:0.10731 +[85] validation_0-rmse:0.14114 validation_1-rmse:0.10683 +[86] validation_0-rmse:0.14100 validation_1-rmse:0.10625 +[87] validation_0-rmse:0.14077 validation_1-rmse:0.10574 +[88] validation_0-rmse:0.14048 validation_1-rmse:0.10534 +[89] validation_0-rmse:0.14010 validation_1-rmse:0.10485 +[90] validation_0-rmse:0.13990 validation_1-rmse:0.10443 +[91] validation_0-rmse:0.13956 validation_1-rmse:0.10400 +[92] validation_0-rmse:0.13949 validation_1-rmse:0.10341 +[93] validation_0-rmse:0.13930 validation_1-rmse:0.10298 +[94] validation_0-rmse:0.13905 validation_1-rmse:0.10254 +[95] validation_0-rmse:0.13884 validation_1-rmse:0.10211 +[96] validation_0-rmse:0.13867 validation_1-rmse:0.10167 +[97] validation_0-rmse:0.13859 validation_1-rmse:0.10114 +[98] validation_0-rmse:0.13839 validation_1-rmse:0.10078 +[99] validation_0-rmse:0.13818 validation_1-rmse:0.10038 +2025-04-29 01:57:16,538 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.34 secs) -------------------- +2025-04-29 01:57:16,539 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:17,068 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-03-02 00:00:00 to 2025-04-01 00:00:00, 10/11 trains +2025-04-29 01:57:17,069 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1743465600_prediction.feather +2025-04-29 01:57:17,084 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:17,092 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:57:17,094 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.644115 +1 0.003044 49.644115 +2 0.000465 49.644115 +3 -0.000380 49.644115 +4 0.002829 49.644115 +2025-04-29 01:57:17,108 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:17,115 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:57:17,117 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.601082 +1 0.003044 49.601082 +2 0.000465 49.601082 +3 -0.000380 49.601082 +4 0.002829 49.601082 +2025-04-29 01:57:17,124 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1743465600/cb_sol_1743465600 +2025-04-29 01:57:17,125 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:17,151 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:17,151 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-02 to 2025-03-31 -------------------- +2025-04-29 01:57:22,430 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:22,430 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.23717 validation_1-rmse:0.24954 +[1] validation_0-rmse:0.23311 validation_1-rmse:0.24432 +[2] validation_0-rmse:0.22894 validation_1-rmse:0.23928 +[3] validation_0-rmse:0.22483 validation_1-rmse:0.23452 +[4] validation_0-rmse:0.22141 validation_1-rmse:0.23005 +[5] validation_0-rmse:0.21750 validation_1-rmse:0.22575 +[6] validation_0-rmse:0.21419 validation_1-rmse:0.22161 +[7] validation_0-rmse:0.21074 validation_1-rmse:0.21764 +[8] validation_0-rmse:0.20776 validation_1-rmse:0.21374 +[9] validation_0-rmse:0.20479 validation_1-rmse:0.21020 +[10] validation_0-rmse:0.20193 validation_1-rmse:0.20664 +[11] validation_0-rmse:0.19915 validation_1-rmse:0.20326 +[12] validation_0-rmse:0.19683 validation_1-rmse:0.20013 +[13] validation_0-rmse:0.19459 validation_1-rmse:0.19705 +[14] validation_0-rmse:0.19243 validation_1-rmse:0.19415 +[15] validation_0-rmse:0.19013 validation_1-rmse:0.19115 +[16] validation_0-rmse:0.18828 validation_1-rmse:0.18836 +[17] validation_0-rmse:0.18621 validation_1-rmse:0.18557 +[18] validation_0-rmse:0.18402 validation_1-rmse:0.18302 +[19] validation_0-rmse:0.18198 validation_1-rmse:0.18050 +[20] validation_0-rmse:0.18015 validation_1-rmse:0.17803 +[21] validation_0-rmse:0.17857 validation_1-rmse:0.17575 +[22] validation_0-rmse:0.17681 validation_1-rmse:0.17350 +[23] validation_0-rmse:0.17537 validation_1-rmse:0.17132 +[24] validation_0-rmse:0.17377 validation_1-rmse:0.16919 +[25] validation_0-rmse:0.17225 validation_1-rmse:0.16720 +[26] validation_0-rmse:0.17072 validation_1-rmse:0.16529 +[27] validation_0-rmse:0.16931 validation_1-rmse:0.16310 +[28] validation_0-rmse:0.16784 validation_1-rmse:0.16126 +[29] validation_0-rmse:0.16650 validation_1-rmse:0.15940 +[30] validation_0-rmse:0.16512 validation_1-rmse:0.15771 +[31] validation_0-rmse:0.16392 validation_1-rmse:0.15605 +[32] validation_0-rmse:0.16287 validation_1-rmse:0.15428 +[33] validation_0-rmse:0.16159 validation_1-rmse:0.15277 +[34] validation_0-rmse:0.16033 validation_1-rmse:0.15125 +[35] validation_0-rmse:0.15910 validation_1-rmse:0.14974 +[36] validation_0-rmse:0.15821 validation_1-rmse:0.14832 +[37] validation_0-rmse:0.15733 validation_1-rmse:0.14664 +[38] validation_0-rmse:0.15624 validation_1-rmse:0.14525 +[39] validation_0-rmse:0.15518 validation_1-rmse:0.14395 +[40] validation_0-rmse:0.15451 validation_1-rmse:0.14267 +[41] validation_0-rmse:0.15396 validation_1-rmse:0.14127 +[42] validation_0-rmse:0.15309 validation_1-rmse:0.14006 +[43] validation_0-rmse:0.15219 validation_1-rmse:0.13890 +[44] validation_0-rmse:0.15156 validation_1-rmse:0.13749 +[45] validation_0-rmse:0.15061 validation_1-rmse:0.13637 +[46] validation_0-rmse:0.14982 validation_1-rmse:0.13528 +[47] validation_0-rmse:0.14918 validation_1-rmse:0.13414 +[48] validation_0-rmse:0.14840 validation_1-rmse:0.13312 +[49] validation_0-rmse:0.14802 validation_1-rmse:0.13212 +[50] validation_0-rmse:0.14738 validation_1-rmse:0.13089 +[51] validation_0-rmse:0.14671 validation_1-rmse:0.12994 +[52] validation_0-rmse:0.14604 validation_1-rmse:0.12894 +[53] validation_0-rmse:0.14534 validation_1-rmse:0.12802 +[54] validation_0-rmse:0.14464 validation_1-rmse:0.12718 +[55] validation_0-rmse:0.14423 validation_1-rmse:0.12625 +[56] validation_0-rmse:0.14371 validation_1-rmse:0.12531 +[57] validation_0-rmse:0.14321 validation_1-rmse:0.12446 +[58] validation_0-rmse:0.14279 validation_1-rmse:0.12346 +[59] validation_0-rmse:0.14234 validation_1-rmse:0.12257 +[60] validation_0-rmse:0.14194 validation_1-rmse:0.12181 +[61] validation_0-rmse:0.14176 validation_1-rmse:0.12077 +[62] validation_0-rmse:0.14120 validation_1-rmse:0.12003 +[63] validation_0-rmse:0.14073 validation_1-rmse:0.11932 +[64] validation_0-rmse:0.14023 validation_1-rmse:0.11862 +[65] validation_0-rmse:0.14001 validation_1-rmse:0.11791 +[66] validation_0-rmse:0.13966 validation_1-rmse:0.11720 +[67] validation_0-rmse:0.13920 validation_1-rmse:0.11644 +[68] validation_0-rmse:0.13872 validation_1-rmse:0.11560 +[69] validation_0-rmse:0.13831 validation_1-rmse:0.11494 +[70] validation_0-rmse:0.13808 validation_1-rmse:0.11425 +[71] validation_0-rmse:0.13762 validation_1-rmse:0.11348 +[72] validation_0-rmse:0.13725 validation_1-rmse:0.11284 +[73] validation_0-rmse:0.13681 validation_1-rmse:0.11225 +[74] validation_0-rmse:0.13629 validation_1-rmse:0.11165 +[75] validation_0-rmse:0.13595 validation_1-rmse:0.11109 +[76] validation_0-rmse:0.13585 validation_1-rmse:0.11023 +[77] validation_0-rmse:0.13541 validation_1-rmse:0.10972 +[78] validation_0-rmse:0.13505 validation_1-rmse:0.10920 +[79] validation_0-rmse:0.13465 validation_1-rmse:0.10861 +[80] validation_0-rmse:0.13433 validation_1-rmse:0.10810 +[81] validation_0-rmse:0.13409 validation_1-rmse:0.10744 +[82] validation_0-rmse:0.13377 validation_1-rmse:0.10695 +[83] validation_0-rmse:0.13353 validation_1-rmse:0.10641 +[84] validation_0-rmse:0.13337 validation_1-rmse:0.10588 +[85] validation_0-rmse:0.13329 validation_1-rmse:0.10533 +[86] validation_0-rmse:0.13296 validation_1-rmse:0.10488 +[87] validation_0-rmse:0.13264 validation_1-rmse:0.10442 +[88] validation_0-rmse:0.13247 validation_1-rmse:0.10394 +[89] validation_0-rmse:0.13216 validation_1-rmse:0.10351 +[90] validation_0-rmse:0.13188 validation_1-rmse:0.10297 +[91] validation_0-rmse:0.13145 validation_1-rmse:0.10203 +[92] validation_0-rmse:0.13122 validation_1-rmse:0.10157 +[93] validation_0-rmse:0.13102 validation_1-rmse:0.10118 +[94] validation_0-rmse:0.13060 validation_1-rmse:0.10033 +[95] validation_0-rmse:0.13033 validation_1-rmse:0.09981 +[96] validation_0-rmse:0.13016 validation_1-rmse:0.09933 +[97] validation_0-rmse:0.12995 validation_1-rmse:0.09894 +[98] validation_0-rmse:0.12972 validation_1-rmse:0.09860 +[99] validation_0-rmse:0.12954 validation_1-rmse:0.09825 +2025-04-29 01:57:23,725 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.60 secs) -------------------- +2025-04-29 01:57:23,726 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:24,305 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-03-12 00:00:00 to 2025-04-11 00:00:00, 11/11 trains +2025-04-29 01:57:24,305 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1744329600_prediction.feather +2025-04-29 01:57:24,318 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:24,325 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:57:24,327 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.601082 +1 0.003044 49.601082 +2 0.000465 49.601082 +3 -0.000380 49.601082 +4 0.002829 49.601082 +2025-04-29 01:57:24,337 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:24,345 - FreqaiExampleStrategy - INFO - 目标列形状：(66770,) +2025-04-29 01:57:24,346 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.729824 +1 0.003044 49.729824 +2 0.000465 49.729824 +3 -0.000380 49.729824 +4 0.002829 49.729824 +2025-04-29 01:57:24,352 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1744329600/cb_sol_1744329600 +2025-04-29 01:57:24,353 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:24,376 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:24,376 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-12 to 2025-04-10 -------------------- +2025-04-29 01:57:29,392 - datasieve.pipeline - INFO - DI tossed 1948 predictions for being too far from training data. +2025-04-29 01:57:29,396 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:29,396 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.30616 validation_1-rmse:0.27906 +[1] validation_0-rmse:0.30021 validation_1-rmse:0.27322 +[2] validation_0-rmse:0.29443 validation_1-rmse:0.26757 +[3] validation_0-rmse:0.28911 validation_1-rmse:0.26205 +[4] validation_0-rmse:0.28365 validation_1-rmse:0.25699 +[5] validation_0-rmse:0.27823 validation_1-rmse:0.25219 +[6] validation_0-rmse:0.27295 validation_1-rmse:0.24748 +[7] validation_0-rmse:0.26797 validation_1-rmse:0.24295 +[8] validation_0-rmse:0.26320 validation_1-rmse:0.23854 +[9] validation_0-rmse:0.25898 validation_1-rmse:0.23437 +[10] validation_0-rmse:0.25517 validation_1-rmse:0.23021 +[11] validation_0-rmse:0.25113 validation_1-rmse:0.22639 +[12] validation_0-rmse:0.24762 validation_1-rmse:0.22270 +[13] validation_0-rmse:0.24393 validation_1-rmse:0.21915 +[14] validation_0-rmse:0.24169 validation_1-rmse:0.21579 +[15] validation_0-rmse:0.23898 validation_1-rmse:0.21236 +[16] validation_0-rmse:0.23539 validation_1-rmse:0.20924 +[17] validation_0-rmse:0.23364 validation_1-rmse:0.20621 +[18] validation_0-rmse:0.23062 validation_1-rmse:0.20322 +[19] validation_0-rmse:0.22764 validation_1-rmse:0.20024 +[20] validation_0-rmse:0.22488 validation_1-rmse:0.19731 +[21] validation_0-rmse:0.22211 validation_1-rmse:0.19445 +[22] validation_0-rmse:0.21952 validation_1-rmse:0.19188 +[23] validation_0-rmse:0.21699 validation_1-rmse:0.18935 +[24] validation_0-rmse:0.21549 validation_1-rmse:0.18686 +[25] validation_0-rmse:0.21310 validation_1-rmse:0.18454 +[26] validation_0-rmse:0.21118 validation_1-rmse:0.18198 +[27] validation_0-rmse:0.20904 validation_1-rmse:0.17979 +[28] validation_0-rmse:0.20726 validation_1-rmse:0.17755 +[29] validation_0-rmse:0.20511 validation_1-rmse:0.17547 +[30] validation_0-rmse:0.20336 validation_1-rmse:0.17335 +[31] validation_0-rmse:0.20172 validation_1-rmse:0.17144 +[32] validation_0-rmse:0.19983 validation_1-rmse:0.16961 +[33] validation_0-rmse:0.19794 validation_1-rmse:0.16759 +[34] validation_0-rmse:0.19658 validation_1-rmse:0.16581 +[35] validation_0-rmse:0.19492 validation_1-rmse:0.16409 +[36] validation_0-rmse:0.19347 validation_1-rmse:0.16229 +[37] validation_0-rmse:0.19225 validation_1-rmse:0.16064 +[38] validation_0-rmse:0.19083 validation_1-rmse:0.15877 +[39] validation_0-rmse:0.18921 validation_1-rmse:0.15720 +[40] validation_0-rmse:0.18766 validation_1-rmse:0.15572 +[41] validation_0-rmse:0.18652 validation_1-rmse:0.15414 +[42] validation_0-rmse:0.18519 validation_1-rmse:0.15277 +[43] validation_0-rmse:0.18396 validation_1-rmse:0.15125 +[44] validation_0-rmse:0.18264 validation_1-rmse:0.14968 +[45] validation_0-rmse:0.18134 validation_1-rmse:0.14841 +[46] validation_0-rmse:0.18026 validation_1-rmse:0.14717 +[47] validation_0-rmse:0.17900 validation_1-rmse:0.14594 +[48] validation_0-rmse:0.17815 validation_1-rmse:0.14460 +[49] validation_0-rmse:0.17713 validation_1-rmse:0.14344 +[50] validation_0-rmse:0.17609 validation_1-rmse:0.14232 +[51] validation_0-rmse:0.17502 validation_1-rmse:0.14112 +[52] validation_0-rmse:0.17414 validation_1-rmse:0.13991 +[53] validation_0-rmse:0.17317 validation_1-rmse:0.13889 +[54] validation_0-rmse:0.17267 validation_1-rmse:0.13770 +[55] validation_0-rmse:0.17175 validation_1-rmse:0.13665 +[56] validation_0-rmse:0.17087 validation_1-rmse:0.13573 +[57] validation_0-rmse:0.17001 validation_1-rmse:0.13483 +[58] validation_0-rmse:0.16920 validation_1-rmse:0.13384 +[59] validation_0-rmse:0.16869 validation_1-rmse:0.13280 +[60] validation_0-rmse:0.16790 validation_1-rmse:0.13189 +[61] validation_0-rmse:0.16689 validation_1-rmse:0.13093 +[62] validation_0-rmse:0.16600 validation_1-rmse:0.13007 +[63] validation_0-rmse:0.16548 validation_1-rmse:0.12921 +[64] validation_0-rmse:0.16482 validation_1-rmse:0.12837 +[65] validation_0-rmse:0.16397 validation_1-rmse:0.12747 +[66] validation_0-rmse:0.16316 validation_1-rmse:0.12669 +[67] validation_0-rmse:0.16267 validation_1-rmse:0.12587 +[68] validation_0-rmse:0.16204 validation_1-rmse:0.12501 +[69] validation_0-rmse:0.16159 validation_1-rmse:0.12422 +[70] validation_0-rmse:0.16090 validation_1-rmse:0.12354 +[71] validation_0-rmse:0.16026 validation_1-rmse:0.12282 +[72] validation_0-rmse:0.15986 validation_1-rmse:0.12206 +[73] validation_0-rmse:0.15919 validation_1-rmse:0.12129 +[74] validation_0-rmse:0.15875 validation_1-rmse:0.12061 +[75] validation_0-rmse:0.15829 validation_1-rmse:0.11966 +[76] validation_0-rmse:0.15790 validation_1-rmse:0.11864 +[77] validation_0-rmse:0.15732 validation_1-rmse:0.11802 +[78] validation_0-rmse:0.15696 validation_1-rmse:0.11739 +[79] validation_0-rmse:0.15615 validation_1-rmse:0.11660 +[80] validation_0-rmse:0.15556 validation_1-rmse:0.11593 +[81] validation_0-rmse:0.15516 validation_1-rmse:0.11531 +[82] validation_0-rmse:0.15466 validation_1-rmse:0.11437 +[83] validation_0-rmse:0.15422 validation_1-rmse:0.11383 +[84] validation_0-rmse:0.15382 validation_1-rmse:0.11332 +[85] validation_0-rmse:0.15350 validation_1-rmse:0.11244 +[86] validation_0-rmse:0.15310 validation_1-rmse:0.11180 +[87] validation_0-rmse:0.15277 validation_1-rmse:0.11119 +[88] validation_0-rmse:0.15228 validation_1-rmse:0.11060 +[89] validation_0-rmse:0.15192 validation_1-rmse:0.11011 +[90] validation_0-rmse:0.15144 validation_1-rmse:0.10956 +[91] validation_0-rmse:0.15092 validation_1-rmse:0.10913 +[92] validation_0-rmse:0.15058 validation_1-rmse:0.10847 +[93] validation_0-rmse:0.15017 validation_1-rmse:0.10803 +[94] validation_0-rmse:0.14984 validation_1-rmse:0.10702 +[95] validation_0-rmse:0.14967 validation_1-rmse:0.10629 +[96] validation_0-rmse:0.14914 validation_1-rmse:0.10587 +[97] validation_0-rmse:0.14882 validation_1-rmse:0.10545 +[98] validation_0-rmse:0.14853 validation_1-rmse:0.10454 +[99] validation_0-rmse:0.14837 validation_1-rmse:0.10398 +2025-04-29 01:57:30,474 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.12 secs) -------------------- +2025-04-29 01:57:30,475 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:31,077 - FreqaiExampleStrategy - INFO - 动态参数：buy_rsi=50.0, sell_rsi=70.0, stoploss=-0.15, trailing_stop_positive=0.05 +2025-04-29 01:57:31,096 - FreqaiExampleStrategy - INFO - up_or_down 值统计： +up_or_down +0 33825 +1 32946 +2025-04-29 01:57:31,097 - FreqaiExampleStrategy - INFO - do_predict 值统计： +do_predict +0.0 36730 +1.0 30041 +2025-04-29 01:57:31,105 - freqtrade.optimize.backtesting - INFO - Backtesting with data from 2025-01-01 00:00:00 up to 2025-04-20 00:00:00 (109 days). +2025-04-29 01:57:31,109 - FreqaiExampleStrategy - ERROR - MACD 或 MACD 信号列缺失，无法生成买入信号。尝试重新计算 MACD 列。 +2025-04-29 01:57:31,111 - FreqaiExampleStrategy - INFO - MACD 列已成功重新计算。 +2025-04-29 01:57:31,193 - FreqaiExampleStrategy - ERROR - MACD 或 MACD 信号列缺失，无法生成买入信号。尝试重新计算 MACD 列。 +2025-04-29 01:57:31,195 - FreqaiExampleStrategy - INFO - MACD 列已成功重新计算。 +2025-04-29 01:57:33,776 - freqtrade.misc - INFO - dumping json to "/freqtrade/user_data/backtest_results/backtest-result-2025-04-29_01-57-33.meta.json" +Result for strategy FreqaiExampleStrategy + BACKTESTING REPORT  +┏━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃  Pair ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃  Win Draw Loss Win% ┃ +┡━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ BTC/USDT │ 38 │ -0.39 │ -22.029 │ -2.2 │ 22:13:00 │ 5 32 1 13.2 │ +│ SOL/USDT │ 44 │ -1.94 │ -128.236 │ -12.82 │ 16:35:00 │ 12 26 6 27.3 │ +│ TOTAL │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└──────────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┘ + LEFT OPEN TRADES REPORT  +┏━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃  Pair ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃  Win Draw Loss Win% ┃ +┡━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ TOTAL │ 0 │ 0.0 │ 0.000 │ 0.0 │ 0:00 │ 0 0 0 0 │ +└───────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┘ + ENTER TAG STATS  +┏━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Enter Tag ┃ Entries ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃  Win Draw Loss Win% ┃ +┡━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ long │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +│ TOTAL │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└───────────┴─────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┘ + EXIT REASON STATS  +┏━━━━━━━━━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃  Exit Reason ┃ Exits ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃  Avg Duration ┃  Win Draw Loss Win% ┃ +┡━━━━━━━━━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ roi │ 75 │ 0.07 │ 7.926 │ 0.79 │ 14:48:00 │ 17 58 0 100 │ +│ trailing_stop_loss │ 7 │ -15.04 │ -158.191 │ -15.82 │ 2 days, 18:13:00 │ 0 0 7 0 │ +│ TOTAL │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└────────────────────┴───────┴──────────────┴─────────────────┴──────────────┴──────────────────┴────────────────────────┘ + MIXED TAG STATS  +┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃  Enter Tag ┃ Exit Reason ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃  Avg Duration ┃  Win Draw Loss Win% ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ ('long', 'roi') │ │ 75 │ 0.07 │ 7.926 │ 0.79 │ 14:48:00 │ 17 58 0 100 │ +│ ('long', 'trailing_stop_loss') │ │ 7 │ -15.04 │ -158.191 │ -15.82 │ 2 days, 18:13:00 │ 0 0 7 0 │ +│ TOTAL │ │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└────────────────────────────────┴─────────────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────────┴────────────────────────┘ + SUMMARY METRICS  +┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┓ +┃ Metric  ┃ Value  ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━┩ +│ Backtesting from │ 2025-01-01 00:00:00 │ +│ Backtesting to │ 2025-04-20 00:00:00 │ +│ Trading Mode │ Spot │ +│ Max open trades │ 2 │ +│ │ │ +│ Total/Daily Avg Trades │ 82 / 0.75 │ +│ Starting balance │ 1000 USDT │ +│ Final balance │ 849.735 USDT │ +│ Absolute profit │ -150.265 USDT │ +│ Total profit % │ -15.03% │ +│ CAGR % │ -42.03% │ +│ Sortino │ -252.56 │ +│ Sharpe │ -4.15 │ +│ Calmar │ -17.48 │ +│ SQN │ -2.60 │ +│ Profit factor │ 0.05 │ +│ Expectancy (Ratio) │ -1.83 (-0.79) │ +│ Avg. daily profit % │ -0.14% │ +│ Avg. stake amount │ 150 USDT │ +│ Total trade volume │ 24523.15 USDT │ +│ │ │ +│ Best Pair │ BTC/USDT -2.20% │ +│ Worst Pair │ SOL/USDT -12.82% │ +│ Best trade │ SOL/USDT 0.90% │ +│ Worst trade │ SOL/USDT -15.19% │ +│ Best day │ 1.76 USDT │ +│ Worst day │ -22.827 USDT │ +│ Days win/draw/lose │ 14 / 80 / 7 │ +│ Avg. Duration Winners │ 0:55:00 │ +│ Avg. Duration Loser │ 2 days, 18:13:00 │ +│ Max Consecutive Wins / Loss │ 2 / 16 │ +│ Rejected Entry signals │ 0 │ +│ Entry/Exit Timeouts │ 0 / 0 │ +│ │ │ +│ Min balance │ 849.735 USDT │ +│ Max balance │ 1000.508 USDT │ +│ Max % of account underwater │ 15.07% │ +│ Absolute Drawdown (Account) │ 15.07% │ +│ Absolute Drawdown │ 150.773 USDT │ +│ Drawdown high │ 0.508 USDT │ +│ Drawdown low │ -150.265 USDT │ +│ Drawdown Start │ 2025-01-06 19:48:00 │ +│ Drawdown End │ 2025-04-06 23:15:00 │ +│ Market change │ -26.79% │ +└─────────────────────────────┴─────────────────────┘ + +Backtested 2025-01-01 00:00:00 -> 2025-04-20 00:00:00 | Max open trades : 2 + STRATEGY SUMMARY  +┏━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┓ +┃  Strategy ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃  Win Draw Loss Win% ┃  Drawdown ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━┩ +│ FreqaiExampleStrategy │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ 150.773 USDT 15.07% │ +└───────────────────────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┴──────────────────────┘ diff --git a/docs/advanced-backtesting.md b/md/advanced-backtesting.md similarity index 100% rename from docs/advanced-backtesting.md rename to md/advanced-backtesting.md diff --git a/docs/advanced-hyperopt.md b/md/advanced-hyperopt.md similarity index 100% rename from docs/advanced-hyperopt.md rename to md/advanced-hyperopt.md diff --git a/docs/backtesting.md b/md/backtesting.md similarity index 100% rename from docs/backtesting.md rename to md/backtesting.md diff --git a/md/configuration.md b/md/configuration.md new file mode 100644 index 00000000..89261c3d --- /dev/null +++ b/md/configuration.md @@ -0,0 +1,800 @@ +# Configure the bot + +Freqtrade has many configurable features and possibilities. +By default, these settings are configured via the configuration file (see below). + +## The Freqtrade configuration file + +The bot uses a set of configuration parameters during its operation that all together conform to the bot configuration. It normally reads its configuration from a file (Freqtrade configuration file). + +Per default, the bot loads the configuration from the `config.json` file, located in the current working directory. + +You can specify a different configuration file used by the bot with the `-c/--config` command-line option. + +If you used the [Quick start](docker_quickstart.md#docker-quick-start) method for installing +the bot, the installation script should have already created the default configuration file (`config.json`) for you. + +If the default configuration file is not created we recommend to use `freqtrade new-config --config user_data/config.json` to generate a basic configuration file. + +The Freqtrade configuration file is to be written in JSON format. + +Additionally to the standard JSON syntax, you may use one-line `// ...` and multi-line `/* ... */` comments in your configuration files and trailing commas in the lists of parameters. + +Do not worry if you are not familiar with JSON format -- simply open the configuration file with an editor of your choice, make some changes to the parameters you need, save your changes and, finally, restart the bot or, if it was previously stopped, run it again with the changes you made to the configuration. The bot validates the syntax of the configuration file at startup and will warn you if you made any errors editing it, pointing out problematic lines. + +### Environment variables + +Set options in the Freqtrade configuration via environment variables. +This takes priority over the corresponding value in configuration or strategy. + +Environment variables must be prefixed with `FREQTRADE__` to be loaded to the freqtrade configuration. + +`__` serves as level separator, so the format used should correspond to `FREQTRADE__{section}__{key}`. +As such - an environment variable defined as `export FREQTRADE__STAKE_AMOUNT=200` would result in `{stake_amount: 200}`. + +A more complex example might be `export FREQTRADE__EXCHANGE__KEY=` to keep your exchange key secret. This will move the value to the `exchange.key` section of the configuration. +Using this scheme, all configuration settings will also be available as environment variables. + +Please note that Environment variables will overwrite corresponding settings in your configuration, but command line Arguments will always win. + +Common example: + +``` bash +FREQTRADE__TELEGRAM__CHAT_ID= +FREQTRADE__TELEGRAM__TOKEN= +FREQTRADE__EXCHANGE__KEY= +FREQTRADE__EXCHANGE__SECRET= +``` + +Json lists are parsed as json - so you can use the following to set a list of pairs: + +``` bash +export FREQTRADE__EXCHANGE__PAIR_WHITELIST='["BTC/USDT", "ETH/USDT"]' +``` + +!!! Note + Environment variables detected are logged at startup - so if you can't find why a value is not what you think it should be based on the configuration, make sure it's not loaded from an environment variable. + +!!! Tip "Validate combined result" + You can use the [show-config subcommand](utils.md#show-config) to see the final, combined configuration. + +??? Warning "Loading sequence" + Environment variables are loaded after the initial configuration. As such, you cannot provide the path to the configuration through environment variables. Please use `--config path/to/config.json` for that. + This also applies to `user_dir` to some degree. while the user directory can be set through environment variables - the configuration will **not** be loaded from that location. + +### Multiple configuration files + +Multiple configuration files can be specified and used by the bot or the bot can read its configuration parameters from the process standard input stream. + +You can specify additional configuration files in `add_config_files`. Files specified in this parameter will be loaded and merged with the initial config file. The files are resolved relative to the initial configuration file. +This is similar to using multiple `--config` parameters, but simpler in usage as you don't have to specify all files for all commands. + +!!! Tip "Validate combined result" + You can use the [show-config subcommand](utils.md#show-config) to see the final, combined configuration. + +!!! Tip "Use multiple configuration files to keep secrets secret" + You can use a 2nd configuration file containing your secrets. That way you can share your "primary" configuration file, while still keeping your API keys for yourself. + The 2nd file should only specify what you intend to override. + If a key is in more than one of the configurations, then the "last specified configuration" wins (in the above example, `config-private.json`). + + For one-off commands, you can also use the below syntax by specifying multiple "--config" parameters. + + ``` bash + freqtrade trade --config user_data/config1.json --config user_data/config-private.json <...> + ``` + + The below is equivalent to the example above - but having 2 configuration files in the configuration, for easier reuse. + + ``` json title="user_data/config.json" + "add_config_files": [ + "config1.json", + "config-private.json" + ] + ``` + + ``` bash + freqtrade trade --config user_data/config.json <...> + ``` + +??? Note "config collision handling" + If the same configuration setting takes place in both `config.json` and `config-import.json`, then the parent configuration wins. + In the below case, `max_open_trades` would be 3 after the merging - as the reusable "import" configuration has this key overwritten. + + ``` json title="user_data/config.json" + { + "max_open_trades": 3, + "stake_currency": "USDT", + "add_config_files": [ + "config-import.json" + ] + } + ``` + + ``` json title="user_data/config-import.json" + { + "max_open_trades": 10, + "stake_amount": "unlimited", + } + ``` + + Resulting combined configuration: + + ``` json title="Result" + { + "max_open_trades": 3, + "stake_currency": "USDT", + "stake_amount": "unlimited" + } + ``` + + If multiple files are in the `add_config_files` section, then they will be assumed to be at identical levels, having the last occurrence override the earlier config (unless a parent already defined such a key). + +## Editor autocomplete and validation + +If you are using an editor that supports JSON schema, you can use the schema provided by Freqtrade to get autocompletion and validation of your configuration file by adding the following line to the top of your configuration file: + +``` json +{ + "$schema": "https://schema.freqtrade.io/schema.json", +} +``` + +??? Note "Develop version" + The develop schema is available as `https://schema.freqtrade.io/schema_dev.json` - though we recommend to stick to the stable version for the best experience. + +## Configuration parameters + +The table below will list all configuration parameters available. + +Freqtrade can also load many options via command line (CLI) arguments (check out the commands `--help` output for details). + +### Configuration option prevalence + +The prevalence for all Options is as follows: + +* CLI arguments override any other option +* [Environment Variables](#environment-variables) +* Configuration files are used in sequence (the last file wins) and override Strategy configurations. +* Strategy configurations are only used if they are not set via configuration or command-line arguments. These options are marked with [Strategy Override](#parameters-in-the-strategy) in the below table. + +### Parameters table + +Mandatory parameters are marked as **Required**, which means that they are required to be set in one of the possible ways. + +| Parameter | Description | +|------------|-------------| +| `max_open_trades` | **Required.** Number of open trades your bot is allowed to have. Only one open trade per pair is possible, so the length of your pairlist is another limitation that can apply. If -1 then it is ignored (i.e. potentially unlimited open trades, limited by the pairlist). [More information below](#configuring-amount-per-trade). [Strategy Override](#parameters-in-the-strategy).
**Datatype:** Positive integer or -1. +| `stake_currency` | **Required.** Crypto-currency used for trading.
**Datatype:** String +| `stake_amount` | **Required.** Amount of crypto-currency your bot will use for each trade. Set it to `"unlimited"` to allow the bot to use all available balance. [More information below](#configuring-amount-per-trade).
**Datatype:** Positive float or `"unlimited"`. +| `tradable_balance_ratio` | Ratio of the total account balance the bot is allowed to trade. [More information below](#configuring-amount-per-trade).
*Defaults to `0.99` 99%).*
**Datatype:** Positive float between `0.1` and `1.0`. +| `available_capital` | Available starting capital for the bot. Useful when running multiple bots on the same exchange account. [More information below](#configuring-amount-per-trade).
**Datatype:** Positive float. +| `amend_last_stake_amount` | Use reduced last stake amount if necessary. [More information below](#configuring-amount-per-trade).
*Defaults to `false`.*
**Datatype:** Boolean +| `last_stake_amount_min_ratio` | Defines minimum stake amount that has to be left and executed. Applies only to the last stake amount when it's amended to a reduced value (i.e. if `amend_last_stake_amount` is set to `true`). [More information below](#configuring-amount-per-trade).
*Defaults to `0.5`.*
**Datatype:** Float (as ratio) +| `amount_reserve_percent` | Reserve some amount in min pair stake amount. The bot will reserve `amount_reserve_percent` + stoploss value when calculating min pair stake amount in order to avoid possible trade refusals.
*Defaults to `0.05` (5%).*
**Datatype:** Positive Float as ratio. +| `timeframe` | The timeframe to use (e.g `1m`, `5m`, `15m`, `30m`, `1h` ...). Usually missing in configuration, and specified in the strategy. [Strategy Override](#parameters-in-the-strategy).
**Datatype:** String +| `fiat_display_currency` | Fiat currency used to show your profits. [More information below](#what-values-can-be-used-for-fiat_display_currency).
**Datatype:** String +| `dry_run` | **Required.** Define if the bot must be in Dry Run or production mode.
*Defaults to `true`.*
**Datatype:** Boolean +| `dry_run_wallet` | Define the starting amount in stake currency for the simulated wallet used by the bot running in Dry Run mode. [More information below](#dry-run-wallet)
*Defaults to `1000`.*
**Datatype:** Float or Dict +| `cancel_open_orders_on_exit` | Cancel open orders when the `/stop` RPC command is issued, `Ctrl+C` is pressed or the bot dies unexpectedly. When set to `true`, this allows you to use `/stop` to cancel unfilled and partially filled orders in the event of a market crash. It does not impact open positions.
*Defaults to `false`.*
**Datatype:** Boolean +| `process_only_new_candles` | Enable processing of indicators only when new candles arrive. If false each loop populates the indicators, this will mean the same candle is processed many times creating system load but can be useful of your strategy depends on tick data not only candle. [Strategy Override](#parameters-in-the-strategy).
*Defaults to `true`.*
**Datatype:** Boolean +| `minimal_roi` | **Required.** Set the threshold as ratio the bot will use to exit a trade. [More information below](#understand-minimal_roi). [Strategy Override](#parameters-in-the-strategy).
**Datatype:** Dict +| `stoploss` | **Required.** Value as ratio of the stoploss used by the bot. More details in the [stoploss documentation](stoploss.md). [Strategy Override](#parameters-in-the-strategy).
**Datatype:** Float (as ratio) +| `trailing_stop` | Enables trailing stoploss (based on `stoploss` in either configuration or strategy file). More details in the [stoploss documentation](stoploss.md#trailing-stop-loss). [Strategy Override](#parameters-in-the-strategy).
**Datatype:** Boolean +| `trailing_stop_positive` | Changes stoploss once profit has been reached. More details in the [stoploss documentation](stoploss.md#trailing-stop-loss-custom-positive-loss). [Strategy Override](#parameters-in-the-strategy).
**Datatype:** Float +| `trailing_stop_positive_offset` | Offset on when to apply `trailing_stop_positive`. Percentage value which should be positive. More details in the [stoploss documentation](stoploss.md#trailing-stop-loss-only-once-the-trade-has-reached-a-certain-offset). [Strategy Override](#parameters-in-the-strategy).
*Defaults to `0.0` (no offset).*
**Datatype:** Float +| `trailing_only_offset_is_reached` | Only apply trailing stoploss when the offset is reached. [stoploss documentation](stoploss.md). [Strategy Override](#parameters-in-the-strategy).
*Defaults to `false`.*
**Datatype:** Boolean +| `fee` | Fee used during backtesting / dry-runs. Should normally not be configured, which has freqtrade fall back to the exchange default fee. Set as ratio (e.g. 0.001 = 0.1%). Fee is applied twice for each trade, once when buying, once when selling.
**Datatype:** Float (as ratio) +| `futures_funding_rate` | User-specified funding rate to be used when historical funding rates are not available from the exchange. This does not overwrite real historical rates. It is recommended that this be set to 0 unless you are testing a specific coin and you understand how the funding rate will affect freqtrade's profit calculations. [More information here](leverage.md#unavailable-funding-rates)
*Defaults to `None`.*
**Datatype:** Float +| `trading_mode` | Specifies if you want to trade regularly, trade with leverage, or trade contracts whose prices are derived from matching cryptocurrency prices. [leverage documentation](leverage.md).
*Defaults to `"spot"`.*
**Datatype:** String +| `margin_mode` | When trading with leverage, this determines if the collateral owned by the trader will be shared or isolated to each trading pair [leverage documentation](leverage.md).
**Datatype:** String +| `liquidation_buffer` | A ratio specifying how large of a safety net to place between the liquidation price and the stoploss to prevent a position from reaching the liquidation price [leverage documentation](leverage.md).
*Defaults to `0.05`.*
**Datatype:** Float +| | **Unfilled timeout** +| `unfilledtimeout.entry` | **Required.** How long (in minutes or seconds) the bot will wait for an unfilled entry order to complete, after which the order will be cancelled. [Strategy Override](#parameters-in-the-strategy).
**Datatype:** Integer +| `unfilledtimeout.exit` | **Required.** How long (in minutes or seconds) the bot will wait for an unfilled exit order to complete, after which the order will be cancelled and repeated at current (new) price, as long as there is a signal. [Strategy Override](#parameters-in-the-strategy).
**Datatype:** Integer +| `unfilledtimeout.unit` | Unit to use in unfilledtimeout setting. Note: If you set unfilledtimeout.unit to "seconds", "internals.process_throttle_secs" must be inferior or equal to timeout [Strategy Override](#parameters-in-the-strategy).
*Defaults to `"minutes"`.*
**Datatype:** String +| `unfilledtimeout.exit_timeout_count` | How many times can exit orders time out. Once this number of timeouts is reached, an emergency exit is triggered. 0 to disable and allow unlimited order cancels. [Strategy Override](#parameters-in-the-strategy).
*Defaults to `0`.*
**Datatype:** Integer +| | **Pricing** +| `entry_pricing.price_side` | Select the side of the spread the bot should look at to get the entry rate. [More information below](#entry-price).
*Defaults to `"same"`.*
**Datatype:** String (either `ask`, `bid`, `same` or `other`). +| `entry_pricing.price_last_balance` | **Required.** Interpolate the bidding price. More information [below](#entry-price-without-orderbook-enabled). +| `entry_pricing.use_order_book` | Enable entering using the rates in [Order Book Entry](#entry-price-with-orderbook-enabled).
*Defaults to `true`.*
**Datatype:** Boolean +| `entry_pricing.order_book_top` | Bot will use the top N rate in Order Book "price_side" to enter a trade. I.e. a value of 2 will allow the bot to pick the 2nd entry in [Order Book Entry](#entry-price-with-orderbook-enabled).
*Defaults to `1`.*
**Datatype:** Positive Integer +| `entry_pricing. check_depth_of_market.enabled` | Do not enter if the difference of buy orders and sell orders is met in Order Book. [Check market depth](#check-depth-of-market).
*Defaults to `false`.*
**Datatype:** Boolean +| `entry_pricing. check_depth_of_market.bids_to_ask_delta` | The difference ratio of buy orders and sell orders found in Order Book. A value below 1 means sell order size is greater, while value greater than 1 means buy order size is higher. [Check market depth](#check-depth-of-market)
*Defaults to `0`.*
**Datatype:** Float (as ratio) +| `exit_pricing.price_side` | Select the side of the spread the bot should look at to get the exit rate. [More information below](#exit-price-side).
*Defaults to `"same"`.*
**Datatype:** String (either `ask`, `bid`, `same` or `other`). +| `exit_pricing.price_last_balance` | Interpolate the exiting price. More information [below](#exit-price-without-orderbook-enabled). +| `exit_pricing.use_order_book` | Enable exiting of open trades using [Order Book Exit](#exit-price-with-orderbook-enabled).
*Defaults to `true`.*
**Datatype:** Boolean +| `exit_pricing.order_book_top` | Bot will use the top N rate in Order Book "price_side" to exit. I.e. a value of 2 will allow the bot to pick the 2nd ask rate in [Order Book Exit](#exit-price-with-orderbook-enabled)
*Defaults to `1`.*
**Datatype:** Positive Integer +| `custom_price_max_distance_ratio` | Configure maximum distance ratio between current and custom entry or exit price.
*Defaults to `0.02` 2%).*
**Datatype:** Positive float +| | **TODO** +| `use_exit_signal` | Use exit signals produced by the strategy in addition to the `minimal_roi`.
Setting this to false disables the usage of `"exit_long"` and `"exit_short"` columns. Has no influence on other exit methods (Stoploss, ROI, callbacks). [Strategy Override](#parameters-in-the-strategy).
*Defaults to `true`.*
**Datatype:** Boolean +| `exit_profit_only` | Wait until the bot reaches `exit_profit_offset` before taking an exit decision. [Strategy Override](#parameters-in-the-strategy).
*Defaults to `false`.*
**Datatype:** Boolean +| `exit_profit_offset` | Exit-signal is only active above this value. Only active in combination with `exit_profit_only=True`. [Strategy Override](#parameters-in-the-strategy).
*Defaults to `0.0`.*
**Datatype:** Float (as ratio) +| `ignore_roi_if_entry_signal` | Do not exit if the entry signal is still active. This setting takes preference over `minimal_roi` and `use_exit_signal`. [Strategy Override](#parameters-in-the-strategy).
*Defaults to `false`.*
**Datatype:** Boolean +| `ignore_buying_expired_candle_after` | Specifies the number of seconds until a buy signal is no longer used.
**Datatype:** Integer +| `order_types` | Configure order-types depending on the action (`"entry"`, `"exit"`, `"stoploss"`, `"stoploss_on_exchange"`). [More information below](#understand-order_types). [Strategy Override](#parameters-in-the-strategy).
**Datatype:** Dict +| `order_time_in_force` | Configure time in force for entry and exit orders. [More information below](#understand-order_time_in_force). [Strategy Override](#parameters-in-the-strategy).
**Datatype:** Dict +| `position_adjustment_enable` | Enables the strategy to use position adjustments (additional buys or sells). [More information here](strategy-callbacks.md#adjust-trade-position).
[Strategy Override](#parameters-in-the-strategy).
*Defaults to `false`.*
**Datatype:** Boolean +| `max_entry_position_adjustment` | Maximum additional order(s) for each open trade on top of the first entry Order. Set it to `-1` for unlimited additional orders. [More information here](strategy-callbacks.md#adjust-trade-position).
[Strategy Override](#parameters-in-the-strategy).
*Defaults to `-1`.*
**Datatype:** Positive Integer or -1 +| | **Exchange** +| `exchange.name` | **Required.** Name of the exchange class to use.
**Datatype:** String +| `exchange.key` | API key to use for the exchange. Only required when you are in production mode.
**Keep it in secret, do not disclose publicly.**
**Datatype:** String +| `exchange.secret` | API secret to use for the exchange. Only required when you are in production mode.
**Keep it in secret, do not disclose publicly.**
**Datatype:** String +| `exchange.password` | API password to use for the exchange. Only required when you are in production mode and for exchanges that use password for API requests.
**Keep it in secret, do not disclose publicly.**
**Datatype:** String +| `exchange.uid` | API uid to use for the exchange. Only required when you are in production mode and for exchanges that use uid for API requests.
**Keep it in secret, do not disclose publicly.**
**Datatype:** String +| `exchange.pair_whitelist` | List of pairs to use by the bot for trading and to check for potential trades during backtesting. Supports regex pairs as `.*/BTC`. Not used by VolumePairList. [More information](plugins.md#pairlists-and-pairlist-handlers).
**Datatype:** List +| `exchange.pair_blacklist` | List of pairs the bot must absolutely avoid for trading and backtesting. [More information](plugins.md#pairlists-and-pairlist-handlers).
**Datatype:** List +| `exchange.ccxt_config` | Additional CCXT parameters passed to both ccxt instances (sync and async). This is usually the correct place for additional ccxt configurations. Parameters may differ from exchange to exchange and are documented in the [ccxt documentation](https://docs.ccxt.com/#/README?id=overriding-exchange-properties-upon-instantiation). Please avoid adding exchange secrets here (use the dedicated fields instead), as they may be contained in logs.
**Datatype:** Dict +| `exchange.ccxt_sync_config` | Additional CCXT parameters passed to the regular (sync) ccxt instance. Parameters may differ from exchange to exchange and are documented in the [ccxt documentation](https://docs.ccxt.com/#/README?id=overriding-exchange-properties-upon-instantiation)
**Datatype:** Dict +| `exchange.ccxt_async_config` | Additional CCXT parameters passed to the async ccxt instance. Parameters may differ from exchange to exchange and are documented in the [ccxt documentation](https://docs.ccxt.com/#/README?id=overriding-exchange-properties-upon-instantiation)
**Datatype:** Dict +| `exchange.enable_ws` | Enable the usage of Websockets for the exchange.
[More information](#consuming-exchange-websockets).
*Defaults to `true`.*
**Datatype:** Boolean +| `exchange.markets_refresh_interval` | The interval in minutes in which markets are reloaded.
*Defaults to `60` minutes.*
**Datatype:** Positive Integer +| `exchange.skip_open_order_update` | Skips open order updates on startup should the exchange cause problems. Only relevant in live conditions.
*Defaults to `false`*
**Datatype:** Boolean +| `exchange.unknown_fee_rate` | Fallback value to use when calculating trading fees. This can be useful for exchanges which have fees in non-tradable currencies. The value provided here will be multiplied with the "fee cost".
*Defaults to `None`
**Datatype:** float +| `exchange.log_responses` | Log relevant exchange responses. For debug mode only - use with care.
*Defaults to `false`*
**Datatype:** Boolean +| `exchange.only_from_ccxt` | Prevent data-download from data.binance.vision. Leaving this as false can greatly speed up downloads, but may be problematic if the site is not available.
*Defaults to `false`*
**Datatype:** Boolean +| `experimental.block_bad_exchanges` | Block exchanges known to not work with freqtrade. Leave on default unless you want to test if that exchange works now.
*Defaults to `true`.*
**Datatype:** Boolean +| | **Plugins** +| `edge.*` | Please refer to [edge configuration document](edge.md) for detailed explanation of all possible configuration options. +| `pairlists` | Define one or more pairlists to be used. [More information](plugins.md#pairlists-and-pairlist-handlers).
*Defaults to `StaticPairList`.*
**Datatype:** List of Dicts +| | **Telegram** +| `telegram.enabled` | Enable the usage of Telegram.
**Datatype:** Boolean +| `telegram.token` | Your Telegram bot token. Only required if `telegram.enabled` is `true`.
**Keep it in secret, do not disclose publicly.**
**Datatype:** String +| `telegram.chat_id` | Your personal Telegram account id. Only required if `telegram.enabled` is `true`.
**Keep it in secret, do not disclose publicly.**
**Datatype:** String +| `telegram.balance_dust_level` | Dust-level (in stake currency) - currencies with a balance below this will not be shown by `/balance`.
**Datatype:** float +| `telegram.reload` | Allow "reload" buttons on telegram messages.
*Defaults to `true`.
**Datatype:** boolean +| `telegram.notification_settings.*` | Detailed notification settings. Refer to the [telegram documentation](telegram-usage.md) for details.
**Datatype:** dictionary +| `telegram.allow_custom_messages` | Enable the sending of Telegram messages from strategies via the dataprovider.send_msg() function.
**Datatype:** Boolean +| | **Webhook** +| `webhook.enabled` | Enable usage of Webhook notifications
**Datatype:** Boolean +| `webhook.url` | URL for the webhook. Only required if `webhook.enabled` is `true`. See the [webhook documentation](webhook-config.md) for more details.
**Datatype:** String +| `webhook.entry` | Payload to send on entry. Only required if `webhook.enabled` is `true`. See the [webhook documentation](webhook-config.md) for more details.
**Datatype:** String +| `webhook.entry_cancel` | Payload to send on entry order cancel. Only required if `webhook.enabled` is `true`. See the [webhook documentation](webhook-config.md) for more details.
**Datatype:** String +| `webhook.entry_fill` | Payload to send on entry order filled. Only required if `webhook.enabled` is `true`. See the [webhook documentation](webhook-config.md) for more details.
**Datatype:** String +| `webhook.exit` | Payload to send on exit. Only required if `webhook.enabled` is `true`. See the [webhook documentation](webhook-config.md) for more details.
**Datatype:** String +| `webhook.exit_cancel` | Payload to send on exit order cancel. Only required if `webhook.enabled` is `true`. See the [webhook documentation](webhook-config.md) for more details.
**Datatype:** String +| `webhook.exit_fill` | Payload to send on exit order filled. Only required if `webhook.enabled` is `true`. See the [webhook documentation](webhook-config.md) for more details.
**Datatype:** String +| `webhook.status` | Payload to send on status calls. Only required if `webhook.enabled` is `true`. See the [webhook documentation](webhook-config.md) for more details.
**Datatype:** String +| `webhook.allow_custom_messages` | Enable the sending of Webhook messages from strategies via the dataprovider.send_msg() function.
**Datatype:** Boolean +| | **Rest API / FreqUI / Producer-Consumer** +| `api_server.enabled` | Enable usage of API Server. See the [API Server documentation](rest-api.md) for more details.
**Datatype:** Boolean +| `api_server.listen_ip_address` | Bind IP address. See the [API Server documentation](rest-api.md) for more details.
**Datatype:** IPv4 +| `api_server.listen_port` | Bind Port. See the [API Server documentation](rest-api.md) for more details.
**Datatype:** Integer between 1024 and 65535 +| `api_server.verbosity` | Logging verbosity. `info` will print all RPC Calls, while "error" will only display errors.
**Datatype:** Enum, either `info` or `error`. Defaults to `info`. +| `api_server.username` | Username for API server. See the [API Server documentation](rest-api.md) for more details.
**Keep it in secret, do not disclose publicly.**
**Datatype:** String +| `api_server.password` | Password for API server. See the [API Server documentation](rest-api.md) for more details.
**Keep it in secret, do not disclose publicly.**
**Datatype:** String +| `api_server.ws_token` | API token for the Message WebSocket. See the [API Server documentation](rest-api.md) for more details.
**Keep it in secret, do not disclose publicly.**
**Datatype:** String +| `bot_name` | Name of the bot. Passed via API to a client - can be shown to distinguish / name bots.
*Defaults to `freqtrade`*
**Datatype:** String +| `external_message_consumer` | Enable [Producer/Consumer mode](producer-consumer.md) for more details.
**Datatype:** Dict +| | **Other** +| `initial_state` | Defines the initial application state. If set to stopped, then the bot has to be explicitly started via `/start` RPC command.
*Defaults to `stopped`.*
**Datatype:** Enum, either `running`, `paused` or `stopped` +| `force_entry_enable` | Enables the RPC Commands to force a Trade entry. More information below.
**Datatype:** Boolean +| `disable_dataframe_checks` | Disable checking the OHLCV dataframe returned from the strategy methods for correctness. Only use when intentionally changing the dataframe and understand what you are doing. [Strategy Override](#parameters-in-the-strategy).
*Defaults to `False`*.
**Datatype:** Boolean +| `internals.process_throttle_secs` | Set the process throttle, or minimum loop duration for one bot iteration loop. Value in second.
*Defaults to `5` seconds.*
**Datatype:** Positive Integer +| `internals.heartbeat_interval` | Print heartbeat message every N seconds. Set to 0 to disable heartbeat messages.
*Defaults to `60` seconds.*
**Datatype:** Positive Integer or 0 +| `internals.sd_notify` | Enables use of the sd_notify protocol to tell systemd service manager about changes in the bot state and issue keep-alive pings. See [here](advanced-setup.md#configure-the-bot-running-as-a-systemd-service) for more details.
**Datatype:** Boolean +| `strategy` | **Required** Defines Strategy class to use. Recommended to be set via `--strategy NAME`.
**Datatype:** ClassName +| `strategy_path` | Adds an additional strategy lookup path (must be a directory).
**Datatype:** String +| `recursive_strategy_search` | Set to `true` to recursively search sub-directories inside `user_data/strategies` for a strategy.
**Datatype:** Boolean +| `user_data_dir` | Directory containing user data.
*Defaults to `./user_data/`*.
**Datatype:** String +| `db_url` | Declares database URL to use. NOTE: This defaults to `sqlite:///tradesv3.dryrun.sqlite` if `dry_run` is `true`, and to `sqlite:///tradesv3.sqlite` for production instances.
**Datatype:** String, SQLAlchemy connect string +| `logfile` | Specifies logfile name. Uses a rolling strategy for log file rotation for 10 files with the 1MB limit per file.
**Datatype:** String +| `add_config_files` | Additional config files. These files will be loaded and merged with the current config file. The files are resolved relative to the initial file.
*Defaults to `[]`*.
**Datatype:** List of strings +| `dataformat_ohlcv` | Data format to use to store historical candle (OHLCV) data.
*Defaults to `feather`*.
**Datatype:** String +| `dataformat_trades` | Data format to use to store historical trades data.
*Defaults to `feather`*.
**Datatype:** String +| `reduce_df_footprint` | Recast all numeric columns to float32/int32, with the objective of reducing ram/disk usage (and decreasing train/inference timing in FreqAI). (Currently only affects FreqAI use-cases)
**Datatype:** Boolean.
Default: `False`. +| `log_config` | Dictionary containing the log config for python logging. [more info](advanced-setup.md#advanced-logging)
**Datatype:** dict.
Default: `FtRichHandler` + +### Parameters in the strategy + +The following parameters can be set in the configuration file or strategy. +Values set in the configuration file always overwrite values set in the strategy. + +* `minimal_roi` +* `timeframe` +* `stoploss` +* `max_open_trades` +* `trailing_stop` +* `trailing_stop_positive` +* `trailing_stop_positive_offset` +* `trailing_only_offset_is_reached` +* `use_custom_stoploss` +* `process_only_new_candles` +* `order_types` +* `order_time_in_force` +* `unfilledtimeout` +* `disable_dataframe_checks` +* `use_exit_signal` +* `exit_profit_only` +* `exit_profit_offset` +* `ignore_roi_if_entry_signal` +* `ignore_buying_expired_candle_after` +* `position_adjustment_enable` +* `max_entry_position_adjustment` + +### Configuring amount per trade + +There are several methods to configure how much of the stake currency the bot will use to enter a trade. All methods respect the [available balance configuration](#tradable-balance) as explained below. + +#### Minimum trade stake + +The minimum stake amount will depend on exchange and pair and is usually listed in the exchange support pages. + +Assuming the minimum tradable amount for XRP/USD is 20 XRP (given by the exchange), and the price is 0.6\$, the minimum stake amount to buy this pair is `20 * 0.6 ~= 12`. +This exchange has also a limit on USD - where all orders must be > 10\$ - which however does not apply in this case. + +To guarantee safe execution, freqtrade will not allow buying with a stake-amount of 10.1\$, instead, it'll make sure that there's enough space to place a stoploss below the pair (+ an offset, defined by `amount_reserve_percent`, which defaults to 5%). + +With a reserve of 5%, the minimum stake amount would be ~12.6\$ (`12 * (1 + 0.05)`). If we take into account a stoploss of 10% on top of that - we'd end up with a value of ~14\$ (`12.6 / (1 - 0.1)`). + +To limit this calculation in case of large stoploss values, the calculated minimum stake-limit will never be more than 50% above the real limit. + +!!! Warning + Since the limits on exchanges are usually stable and are not updated often, some pairs can show pretty high minimum limits, simply because the price increased a lot since the last limit adjustment by the exchange. Freqtrade adjusts the stake-amount to this value, unless it's > 30% more than the calculated/desired stake-amount - in which case the trade is rejected. + +#### Dry-run wallet + +When running in dry-run mode, the bot will use a simulated wallet to execute trades. The starting balance of this wallet is defined by `dry_run_wallet` (defaults to 1000). +For more complex scenarios, you can also assign a dictionary to `dry_run_wallet` to define the starting balance for each currency. + +```json +"dry_run_wallet": { + "BTC": 0.01, + "ETH": 2, + "USDT": 1000 +} +``` + +Command line options (`--dry-run-wallet`) can be used to override the configuration value, but only for the float value, not for the dictionary. If you'd like to use the dictionary, please adjust the configuration file. + +!!! Note + Balances not in stake-currency will not be used for trading, but are shown as part of the wallet balance. + On Cross-margin exchanges, the wallet balance may be used to calculate the available collateral for trading. + +#### Tradable balance + +By default, the bot assumes that the `complete amount - 1%` is at it's disposal, and when using [dynamic stake amount](#dynamic-stake-amount), it will split the complete balance into `max_open_trades` buckets per trade. +Freqtrade will reserve 1% for eventual fees when entering a trade and will therefore not touch that by default. + +You can configure the "untouched" amount by using the `tradable_balance_ratio` setting. + +For example, if you have 10 ETH available in your wallet on the exchange and `tradable_balance_ratio=0.5` (which is 50%), then the bot will use a maximum amount of 5 ETH for trading and considers this as an available balance. The rest of the wallet is untouched by the trades. + +!!! Danger + This setting should **not** be used when running multiple bots on the same account. Please look at [Available Capital to the bot](#assign-available-capital) instead. + +!!! Warning + The `tradable_balance_ratio` setting applies to the current balance (free balance + tied up in trades). Therefore, assuming the starting balance of 1000, a configuration with `tradable_balance_ratio=0.99` will not guarantee that 10 currency units will always remain available on the exchange. For example, the free amount may reduce to 5 units if the total balance is reduced to 500 (either by a losing streak or by withdrawing balance). + +#### Assign available Capital + +To fully utilize compounding profits when using multiple bots on the same exchange account, you'll want to limit each bot to a certain starting balance. +This can be accomplished by setting `available_capital` to the desired starting balance. + +Assuming your account has 10000 USDT and you want to run 2 different strategies on this exchange. +You'd set `available_capital=5000` - granting each bot an initial capital of 5000 USDT. +The bot will then split this starting balance equally into `max_open_trades` buckets. +Profitable trades will result in increased stake-sizes for this bot - without affecting the stake-sizes of the other bot. + +Adjusting `available_capital` requires reloading the configuration to take effect. Adjusting the `available_capital` adds the difference between the previous `available_capital` and the new `available_capital`. Decreasing the available capital when trades are open doesn't exit the trades. The difference is returned to the wallet when the trades conclude. The outcome of this differs depending on the price movement between the adjustment and exiting the trades. + +!!! Warning "Incompatible with `tradable_balance_ratio`" + Setting this option will replace any configuration of `tradable_balance_ratio`. + +#### Amend last stake amount + +Assuming we have the tradable balance of 1000 USDT, `stake_amount=400`, and `max_open_trades=3`. +The bot would open 2 trades and will be unable to fill the last trading slot, since the requested 400 USDT are no longer available since 800 USDT are already tied in other trades. + +To overcome this, the option `amend_last_stake_amount` can be set to `True`, which will enable the bot to reduce stake_amount to the available balance to fill the last trade slot. + +In the example above this would mean: + +* Trade1: 400 USDT +* Trade2: 400 USDT +* Trade3: 200 USDT + +!!! Note + This option only applies with [Static stake amount](#static-stake-amount) - since [Dynamic stake amount](#dynamic-stake-amount) divides the balances evenly. + +!!! Note + The minimum last stake amount can be configured using `last_stake_amount_min_ratio` - which defaults to 0.5 (50%). This means that the minimum stake amount that's ever used is `stake_amount * 0.5`. This avoids very low stake amounts, that are close to the minimum tradable amount for the pair and can be refused by the exchange. + +#### Static stake amount + +The `stake_amount` configuration statically configures the amount of stake-currency your bot will use for each trade. + +The minimal configuration value is 0.0001, however, please check your exchange's trading minimums for the stake currency you're using to avoid problems. + +This setting works in combination with `max_open_trades`. The maximum capital engaged in trades is `stake_amount * max_open_trades`. +For example, the bot will at most use (0.05 BTC x 3) = 0.15 BTC, assuming a configuration of `max_open_trades=3` and `stake_amount=0.05`. + +!!! Note + This setting respects the [available balance configuration](#tradable-balance). + +#### Dynamic stake amount + +Alternatively, you can use a dynamic stake amount, which will use the available balance on the exchange, and divide that equally by the number of allowed trades (`max_open_trades`). + +To configure this, set `stake_amount="unlimited"`. We also recommend to set `tradable_balance_ratio=0.99` (99%) - to keep a minimum balance for eventual fees. + +In this case a trade amount is calculated as: + +```python +currency_balance / (max_open_trades - current_open_trades) +``` + +To allow the bot to trade all the available `stake_currency` in your account (minus `tradable_balance_ratio`) set + +```json +"stake_amount" : "unlimited", +"tradable_balance_ratio": 0.99, +``` + +!!! Tip "Compounding profits" + This configuration will allow increasing/decreasing stakes depending on the performance of the bot (lower stake if the bot is losing, higher stakes if the bot has a winning record since higher balances are available), and will result in profit compounding. + +!!! Note "When using Dry-Run Mode" + When using `"stake_amount" : "unlimited",` in combination with Dry-Run, Backtesting or Hyperopt, the balance will be simulated starting with a stake of `dry_run_wallet` which will evolve. + It is therefore important to set `dry_run_wallet` to a sensible value (like 0.05 or 0.01 for BTC and 1000 or 100 for USDT, for example), otherwise, it may simulate trades with 100 BTC (or more) or 0.05 USDT (or less) at once - which may not correspond to your real available balance or is less than the exchange minimal limit for the order amount for the stake currency. + +#### Dynamic stake amount with position adjustment + +When you want to use position adjustment with unlimited stakes, you must also implement `custom_stake_amount` to a return a value depending on your strategy. +Typical value would be in the range of 25% - 50% of the proposed stakes, but depends highly on your strategy and how much you wish to leave into the wallet as position adjustment buffer. + +For example if your position adjustment assumes it can do 2 additional buys with the same stake amounts then your buffer should be 66.6667% of the initially proposed unlimited stake amount. + +Or another example if your position adjustment assumes it can do 1 additional buy with 3x the original stake amount then `custom_stake_amount` should return 25% of proposed stake amount and leave 75% for possible later position adjustments. + +--8<-- "includes/pricing.md" + +## Further Configuration details + +### Understand minimal_roi + +The `minimal_roi` configuration parameter is a JSON object where the key is a duration +in minutes and the value is the minimum ROI as a ratio. +See the example below: + +```json +"minimal_roi": { + "40": 0.0, # Exit after 40 minutes if the profit is not negative + "30": 0.01, # Exit after 30 minutes if there is at least 1% profit + "20": 0.02, # Exit after 20 minutes if there is at least 2% profit + "0": 0.04 # Exit immediately if there is at least 4% profit +}, +``` + +Most of the strategy files already include the optimal `minimal_roi` value. +This parameter can be set in either Strategy or Configuration file. If you use it in the configuration file, it will override the +`minimal_roi` value from the strategy file. +If it is not set in either Strategy or Configuration, a default of 1000% `{"0": 10}` is used, and minimal ROI is disabled unless your trade generates 1000% profit. + +!!! Note "Special case to forceexit after a specific time" + A special case presents using `"": -1` as ROI. This forces the bot to exit a trade after N Minutes, no matter if it's positive or negative, so represents a time-limited force-exit. + +### Understand force_entry_enable + +The `force_entry_enable` configuration parameter enables the usage of force-enter (`/forcelong`, `/forceshort`) commands via Telegram and REST API. +For security reasons, it's disabled by default, and freqtrade will show a warning message on startup if enabled. +For example, you can send `/forceenter ETH/BTC` to the bot, which will result in freqtrade buying the pair and holds it until a regular exit-signal (ROI, stoploss, /forceexit) appears. + +This can be dangerous with some strategies, so use with care. + +See [the telegram documentation](telegram-usage.md) for details on usage. + +### Ignoring expired candles + +When working with larger timeframes (for example 1h or more) and using a low `max_open_trades` value, the last candle can be processed as soon as a trade slot becomes available. When processing the last candle, this can lead to a situation where it may not be desirable to use the buy signal on that candle. For example, when using a condition in your strategy where you use a cross-over, that point may have passed too long ago for you to start a trade on it. + +In these situations, you can enable the functionality to ignore candles that are beyond a specified period by setting `ignore_buying_expired_candle_after` to a positive number, indicating the number of seconds after which the buy signal becomes expired. + +For example, if your strategy is using a 1h timeframe, and you only want to buy within the first 5 minutes when a new candle comes in, you can add the following configuration to your strategy: + +``` json + { + //... + "ignore_buying_expired_candle_after": 300, + // ... + } +``` + +!!! Note + This setting resets with each new candle, so it will not prevent sticking-signals from executing on the 2nd or 3rd candle they're active. Best use a "trigger" selector for buy signals, which are only active for one candle. + +### Understand order_types + +The `order_types` configuration parameter maps actions (`entry`, `exit`, `stoploss`, `emergency_exit`, `force_exit`, `force_entry`) to order-types (`market`, `limit`, ...) as well as configures stoploss to be on the exchange and defines stoploss on exchange update interval in seconds. + +This allows to enter using limit orders, exit using limit-orders, and create stoplosses using market orders. +It also allows to set the +stoploss "on exchange" which means stoploss order would be placed immediately once the buy order is fulfilled. + +`order_types` set in the configuration file overwrites values set in the strategy as a whole, so you need to configure the whole `order_types` dictionary in one place. + +If this is configured, the following 4 values (`entry`, `exit`, `stoploss` and `stoploss_on_exchange`) need to be present, otherwise, the bot will fail to start. + +For information on (`emergency_exit`,`force_exit`, `force_entry`, `stoploss_on_exchange`,`stoploss_on_exchange_interval`,`stoploss_on_exchange_limit_ratio`) please see stop loss documentation [stop loss on exchange](stoploss.md) + +Syntax for Strategy: + +```python +order_types = { + "entry": "limit", + "exit": "limit", + "emergency_exit": "market", + "force_entry": "market", + "force_exit": "market", + "stoploss": "market", + "stoploss_on_exchange": False, + "stoploss_on_exchange_interval": 60, + "stoploss_on_exchange_limit_ratio": 0.99, +} +``` + +Configuration: + +```json +"order_types": { + "entry": "limit", + "exit": "limit", + "emergency_exit": "market", + "force_entry": "market", + "force_exit": "market", + "stoploss": "market", + "stoploss_on_exchange": false, + "stoploss_on_exchange_interval": 60 +} +``` + +!!! Note "Market order support" + Not all exchanges support "market" orders. + The following message will be shown if your exchange does not support market orders: + `"Exchange does not support market orders."` and the bot will refuse to start. + +!!! Warning "Using market orders" + Please carefully read the section [Market order pricing](#market-order-pricing) section when using market orders. + +!!! Note "Stoploss on exchange" + `order_types.stoploss_on_exchange_interval` is not mandatory. Do not change its value if you are + unsure of what you are doing. For more information about how stoploss works please + refer to [the stoploss documentation](stoploss.md). + + If `order_types.stoploss_on_exchange` is enabled and the stoploss is cancelled manually on the exchange, then the bot will create a new stoploss order. + +!!! Warning "Warning: order_types.stoploss_on_exchange failures" + If stoploss on exchange creation fails for some reason, then an "emergency exit" is initiated. By default, this will exit the trade using a market order. The order-type for the emergency-exit can be changed by setting the `emergency_exit` value in the `order_types` dictionary - however, this is not advised. + +### Understand order_time_in_force + +The `order_time_in_force` configuration parameter defines the policy by which the order +is executed on the exchange. Three commonly used time in force are: + +**GTC (Good Till Canceled):** + +This is most of the time the default time in force. It means the order will remain +on exchange till it is cancelled by the user. It can be fully or partially fulfilled. +If partially fulfilled, the remaining will stay on the exchange till cancelled. + +**FOK (Fill Or Kill):** + +It means if the order is not executed immediately AND fully then it is cancelled by the exchange. + +**IOC (Immediate Or Canceled):** + +It is the same as FOK (above) except it can be partially fulfilled. The remaining part +is automatically cancelled by the exchange. + +**PO (Post only):** + +Post only order. The order is either placed as a maker order, or it is canceled. +This means the order must be placed on orderbook for at least time in an unfilled state. + +#### time_in_force config + +The `order_time_in_force` parameter contains a dict with entry and exit time in force policy values. +This can be set in the configuration file or in the strategy. +Values set in the configuration file overwrites values set in the strategy. + +The possible values are: `GTC` (default), `FOK` or `IOC`. + +``` python +"order_time_in_force": { + "entry": "GTC", + "exit": "GTC" +}, +``` + +!!! Warning + This is ongoing work. For now, it is supported only for binance, gate and kucoin. + Please don't change the default value unless you know what you are doing and have researched the impact of using different values for your particular exchange. + +### Fiat conversion + +Freqtrade uses the Coingecko API to convert the coin value to it's corresponding fiat value for the Telegram reports. +The FIAT currency can be set in the configuration file as `fiat_display_currency`. + +Removing `fiat_display_currency` completely from the configuration will skip initializing coingecko, and will not show any FIAT currency conversion. This has no importance for the correct functioning of the bot. + +#### What values can be used for fiat_display_currency? + +The `fiat_display_currency` configuration parameter sets the base currency to use for the +conversion from coin to fiat in the bot Telegram reports. + +The valid values are: + +```json +"AUD", "BRL", "CAD", "CHF", "CLP", "CNY", "CZK", "DKK", "EUR", "GBP", "HKD", "HUF", "IDR", "ILS", "INR", "JPY", "KRW", "MXN", "MYR", "NOK", "NZD", "PHP", "PKR", "PLN", "RUB", "SEK", "SGD", "THB", "TRY", "TWD", "ZAR", "USD" +``` + +In addition to fiat currencies, a range of crypto currencies is supported. + +The valid values are: + +```json +"BTC", "ETH", "XRP", "LTC", "BCH", "BNB" +``` + +#### Coingecko Rate limit problems + +On some IP ranges, coingecko is heavily rate-limiting. +In such cases, you may want to add your coingecko API key to the configuration. + +``` json +{ + "fiat_display_currency": "USD", + "coingecko": { + "api_key": "your-api", + "is_demo": true + } +} +``` + +Freqtrade supports both Demo and Pro coingecko API keys. + +The Coingecko API key is NOT required for the bot to function correctly. +It is only used for the conversion of coin to fiat in the Telegram reports, which usually also work without API key. + +## Consuming exchange Websockets + +Freqtrade can consume websockets through ccxt.pro. + +Freqtrade aims ensure data is available at all times. +Should the websocket connection fail (or be disabled), the bot will fall back to REST API calls. + +Should you experience problems you suspect are caused by websockets, you can disable these via the setting `exchange.enable_ws`, which defaults to true. + +```jsonc +"exchange": { + // ... + "enable_ws": false, + // ... +} +``` + +Should you be required to use a proxy, please refer to the [proxy section](#using-proxy-with-freqtrade) for more information. + +!!! Info "Rollout" + We're implementing this out slowly, ensuring stability of your bots. + Currently, usage is limited to ohlcv data streams. + It's also limited to a few exchanges, with new exchanges being added on an ongoing basis. + +## Using Dry-run mode + +We recommend starting the bot in the Dry-run mode to see how your bot will +behave and what is the performance of your strategy. In the Dry-run mode, the +bot does not engage your money. It only runs a live simulation without +creating trades on the exchange. + +1. Edit your `config.json` configuration file. +2. Switch `dry-run` to `true` and specify `db_url` for a persistence database. + +```json +"dry_run": true, +"db_url": "sqlite:///tradesv3.dryrun.sqlite", +``` + +3. Remove your Exchange API key and secret (change them by empty values or fake credentials): + +```json +"exchange": { + "name": "binance", + "key": "key", + "secret": "secret", + ... +} +``` + +Once you will be happy with your bot performance running in the Dry-run mode, you can switch it to production mode. + +!!! Note + A simulated wallet is available during dry-run mode and will assume a starting capital of `dry_run_wallet` (defaults to 1000). + +### Considerations for dry-run + +* API-keys may or may not be provided. Only Read-Only operations (i.e. operations that do not alter account state) on the exchange are performed in dry-run mode. +* Wallets (`/balance`) are simulated based on `dry_run_wallet`. +* Orders are simulated, and will not be posted to the exchange. +* Market orders fill based on orderbook volume the moment the order is placed, with a maximum slippage of 5%. +* Limit orders fill once the price reaches the defined level - or time out based on `unfilledtimeout` settings. +* Limit orders will be converted to market orders if they cross the price by more than 1%, and will be filled immediately based regular market order rules (see point about Market orders above). +* In combination with `stoploss_on_exchange`, the stop_loss price is assumed to be filled. +* Open orders (not trades, which are stored in the database) are kept open after bot restarts, with the assumption that they were not filled while being offline. + +## Switch to production mode + +In production mode, the bot will engage your money. Be careful, since a wrong strategy can lose all your money. +Be aware of what you are doing when you run it in production mode. + +When switching to Production mode, please make sure to use a different / fresh database to avoid dry-run trades messing with your exchange money and eventually tainting your statistics. + +### Setup your exchange account + +You will need to create API Keys (usually you get `key` and `secret`, some exchanges require an additional `password`) from the Exchange website and you'll need to insert this into the appropriate fields in the configuration or when asked by the `freqtrade new-config` command. +API Keys are usually only required for live trading (trading for real money, bot running in "production mode", executing real orders on the exchange) and are not required for the bot running in dry-run (trade simulation) mode. When you set up the bot in dry-run mode, you may fill these fields with empty values. + +### To switch your bot in production mode + +**Edit your `config.json` file.** + +**Switch dry-run to false and don't forget to adapt your database URL if set:** + +```json +"dry_run": false, +``` + +**Insert your Exchange API key (change them by fake API keys):** + +```json +{ + "exchange": { + "name": "binance", + "key": "af8ddd35195e9dc500b9a6f799f6f5c93d89193b", + "secret": "08a9dc6db3d7b53e1acebd9275677f4b0a04f1a5", + //"password": "", // Optional, not needed by all exchanges) + // ... + } + //... +} +``` + +You should also make sure to read the [Exchanges](exchanges.md) section of the documentation to be aware of potential configuration details specific to your exchange. + +!!! Hint "Keep your secrets secret" + To keep your secrets secret, we recommend using a 2nd configuration for your API keys. + Simply use the above snippet in a new configuration file (e.g. `config-private.json`) and keep your settings in this file. + You can then start the bot with `freqtrade trade --config user_data/config.json --config user_data/config-private.json <...>` to have your keys loaded. + + **NEVER** share your private configuration file or your exchange keys with anyone! + +## Using a proxy with Freqtrade + +To use a proxy with freqtrade, export your proxy settings using the variables `"HTTP_PROXY"` and `"HTTPS_PROXY"` set to the appropriate values. +This will have the proxy settings applied to everything (telegram, coingecko, ...) **except** for exchange requests. + +``` bash +export HTTP_PROXY="http://addr:port" +export HTTPS_PROXY="http://addr:port" +freqtrade +``` + +### Proxy exchange requests + +To use a proxy for exchange connections - you will have to define the proxies as part of the ccxt configuration. + +``` json +{ + "exchange": { + "ccxt_config": { + "httpsProxy": "http://addr:port", + "wsProxy": "http://addr:port", + } + } +} +``` + +For more information on available proxy types, please consult the [ccxt proxy documentation](https://docs.ccxt.com/#/README?id=proxy). + +## Next step + +Now you have configured your config.json, the next step is to [start your bot](bot-usage.md). diff --git a/docs/developer.md b/md/developer.md similarity index 100% rename from docs/developer.md rename to md/developer.md diff --git a/docs/exchanges.md b/md/exchanges.md similarity index 100% rename from docs/exchanges.md rename to md/exchanges.md diff --git a/md/freqai-configuration.md b/md/freqai-configuration.md new file mode 100644 index 00000000..5ab7b260 --- /dev/null +++ b/md/freqai-configuration.md @@ -0,0 +1,423 @@ +# Configuration + +FreqAI is configured through the typical [Freqtrade config file](configuration.md) and the standard [Freqtrade strategy](strategy-customization.md). Examples of FreqAI config and strategy files can be found in `config_examples/config_freqai.example.json` and `freqtrade/templates/FreqaiExampleStrategy.py`, respectively. + +## Setting up the configuration file + + Although there are plenty of additional parameters to choose from, as highlighted in the [parameter table](freqai-parameter-table.md#parameter-table), a FreqAI config must at minimum include the following parameters (the parameter values are only examples): + +```json + "freqai": { + "enabled": true, + "purge_old_models": 2, + "train_period_days": 30, + "backtest_period_days": 7, + "identifier" : "unique-id", + "feature_parameters" : { + "include_timeframes": ["5m","15m","4h"], + "include_corr_pairlist": [ + "ETH/USD", + "LINK/USD", + "BNB/USD" + ], + "label_period_candles": 24, + "include_shifted_candles": 2, + "indicator_periods_candles": [10, 20] + }, + "data_split_parameters" : { + "test_size": 0.25 + } + } +``` + +A full example config is available in `config_examples/config_freqai.example.json`. + +!!! Note + The `identifier` is commonly overlooked by newcomers, however, this value plays an important role in your configuration. This value is a unique ID that you choose to describe one of your runs. Keeping it the same allows you to maintain crash resilience as well as faster backtesting. As soon as you want to try a new run (new features, new model, etc.), you should change this value (or delete the `user_data/models/unique-id` folder. More details available in the [parameter table](freqai-parameter-table.md#feature-parameters). + +## Building a FreqAI strategy + +The FreqAI strategy requires including the following lines of code in the standard [Freqtrade strategy](strategy-customization.md): + +```python + # user should define the maximum startup candle count (the largest number of candles + # passed to any single indicator) + startup_candle_count: int = 20 + + def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + + # the model will return all labels created by user in `set_freqai_targets()` + # (& appended targets), an indication of whether or not the prediction should be accepted, + # the target mean/std values for each of the labels created by user in + # `set_freqai_targets()` for each training period. + + dataframe = self.freqai.start(dataframe, metadata, self) + + return dataframe + + def feature_engineering_expand_all(self, dataframe: DataFrame, period, **kwargs) -> DataFrame: + """ + *Only functional with FreqAI enabled strategies* + This function will automatically expand the defined features on the config defined + `indicator_periods_candles`, `include_timeframes`, `include_shifted_candles`, and + `include_corr_pairs`. In other words, a single feature defined in this function + will automatically expand to a total of + `indicator_periods_candles` * `include_timeframes` * `include_shifted_candles` * + `include_corr_pairs` numbers of features added to the model. + + All features must be prepended with `%` to be recognized by FreqAI internals. + + :param df: strategy dataframe which will receive the features + :param period: period of the indicator - usage example: + dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period) + """ + + dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period) + dataframe["%-mfi-period"] = ta.MFI(dataframe, timeperiod=period) + dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period) + dataframe["%-sma-period"] = ta.SMA(dataframe, timeperiod=period) + dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period) + + return dataframe + + def feature_engineering_expand_basic(self, dataframe: DataFrame, **kwargs) -> DataFrame: + """ + *Only functional with FreqAI enabled strategies* + This function will automatically expand the defined features on the config defined + `include_timeframes`, `include_shifted_candles`, and `include_corr_pairs`. + In other words, a single feature defined in this function + will automatically expand to a total of + `include_timeframes` * `include_shifted_candles` * `include_corr_pairs` + numbers of features added to the model. + + Features defined here will *not* be automatically duplicated on user defined + `indicator_periods_candles` + + All features must be prepended with `%` to be recognized by FreqAI internals. + + :param df: strategy dataframe which will receive the features + dataframe["%-pct-change"] = dataframe["close"].pct_change() + dataframe["%-ema-200"] = ta.EMA(dataframe, timeperiod=200) + """ + dataframe["%-pct-change"] = dataframe["close"].pct_change() + dataframe["%-raw_volume"] = dataframe["volume"] + dataframe["%-raw_price"] = dataframe["close"] + return dataframe + + def feature_engineering_standard(self, dataframe: DataFrame, **kwargs) -> DataFrame: + """ + *Only functional with FreqAI enabled strategies* + This optional function will be called once with the dataframe of the base timeframe. + This is the final function to be called, which means that the dataframe entering this + function will contain all the features and columns created by all other + freqai_feature_engineering_* functions. + + This function is a good place to do custom exotic feature extractions (e.g. tsfresh). + This function is a good place for any feature that should not be auto-expanded upon + (e.g. day of the week). + + All features must be prepended with `%` to be recognized by FreqAI internals. + + :param df: strategy dataframe which will receive the features + usage example: dataframe["%-day_of_week"] = (dataframe["date"].dt.dayofweek + 1) / 7 + """ + dataframe["%-day_of_week"] = (dataframe["date"].dt.dayofweek + 1) / 7 + dataframe["%-hour_of_day"] = (dataframe["date"].dt.hour + 1) / 25 + return dataframe + + def set_freqai_targets(self, dataframe: DataFrame, **kwargs) -> DataFrame: + """ + *Only functional with FreqAI enabled strategies* + Required function to set the targets for the model. + All targets must be prepended with `&` to be recognized by the FreqAI internals. + + :param df: strategy dataframe which will receive the targets + usage example: dataframe["&-target"] = dataframe["close"].shift(-1) / dataframe["close"] + """ + dataframe["&-s_close"] = ( + dataframe["close"] + .shift(-self.freqai_info["feature_parameters"]["label_period_candles"]) + .rolling(self.freqai_info["feature_parameters"]["label_period_candles"]) + .mean() + / dataframe["close"] + - 1 + ) + return dataframe +``` + +Notice how the `feature_engineering_*()` is where [features](freqai-feature-engineering.md#feature-engineering) are added. Meanwhile `set_freqai_targets()` adds the labels/targets. A full example strategy is available in `templates/FreqaiExampleStrategy.py`. + +!!! Note + The `self.freqai.start()` function cannot be called outside the `populate_indicators()`. + +!!! Note + Features **must** be defined in `feature_engineering_*()`. Defining FreqAI features in `populate_indicators()` + will cause the algorithm to fail in live/dry mode. In order to add generalized features that are not associated with a specific pair or timeframe, you should use `feature_engineering_standard()` + (as exemplified in `freqtrade/templates/FreqaiExampleStrategy.py`). + +## Important dataframe key patterns + +Below are the values you can expect to include/use inside a typical strategy dataframe (`df[]`): + +| DataFrame Key | Description | +|------------|-------------| +| `df['&*']` | Any dataframe column prepended with `&` in `set_freqai_targets()` is treated as a training target (label) inside FreqAI (typically following the naming convention `&-s*`). For example, to predict the close price 40 candles into the future, you would set `df['&-s_close'] = df['close'].shift(-self.freqai_info["feature_parameters"]["label_period_candles"])` with `"label_period_candles": 40` in the config. FreqAI makes the predictions and gives them back under the same key (`df['&-s_close']`) to be used in `populate_entry/exit_trend()`.
**Datatype:** Depends on the output of the model. +| `df['&*_std/mean']` | Standard deviation and mean values of the defined labels during training (or live tracking with `fit_live_predictions_candles`). Commonly used to understand the rarity of a prediction (use the z-score as shown in `templates/FreqaiExampleStrategy.py` and explained [here](#creating-a-dynamic-target-threshold) to evaluate how often a particular prediction was observed during training or historically with `fit_live_predictions_candles`).
**Datatype:** Float. +| `df['do_predict']` | Indication of an outlier data point. The return value is integer between -2 and 2, which lets you know if the prediction is trustworthy or not. `do_predict==1` means that the prediction is trustworthy. If the Dissimilarity Index (DI, see details [here](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di)) of the input data point is above the threshold defined in the config, FreqAI will subtract 1 from `do_predict`, resulting in `do_predict==0`. If `use_SVM_to_remove_outliers` is active, the Support Vector Machine (SVM, see details [here](freqai-feature-engineering.md#identifying-outliers-using-a-support-vector-machine-svm)) may also detect outliers in training and prediction data. In this case, the SVM will also subtract 1 from `do_predict`. If the input data point was considered an outlier by the SVM but not by the DI, or vice versa, the result will be `do_predict==0`. If both the DI and the SVM considers the input data point to be an outlier, the result will be `do_predict==-1`. As with the SVM, if `use_DBSCAN_to_remove_outliers` is active, DBSCAN (see details [here](freqai-feature-engineering.md#identifying-outliers-with-dbscan)) may also detect outliers and subtract 1 from `do_predict`. Hence, if both the SVM and DBSCAN are active and identify a datapoint that was above the DI threshold as an outlier, the result will be `do_predict==-2`. A particular case is when `do_predict == 2`, which means that the model has expired due to exceeding `expired_hours`.
**Datatype:** Integer between -2 and 2. +| `df['DI_values']` | Dissimilarity Index (DI) values are proxies for the level of confidence FreqAI has in the prediction. A lower DI means the prediction is close to the training data, i.e., higher prediction confidence. See details about the DI [here](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di).
**Datatype:** Float. +| `df['%*']` | Any dataframe column prepended with `%` in `feature_engineering_*()` is treated as a training feature. For example, you can include the RSI in the training feature set (similar to in `templates/FreqaiExampleStrategy.py`) by setting `df['%-rsi']`. See more details on how this is done [here](freqai-feature-engineering.md).
**Note:** Since the number of features prepended with `%` can multiply very quickly (10s of thousands of features are easily engineered using the multiplictative functionality of, e.g., `include_shifted_candles` and `include_timeframes` as described in the [parameter table](freqai-parameter-table.md)), these features are removed from the dataframe that is returned from FreqAI to the strategy. To keep a particular type of feature for plotting purposes, you would prepend it with `%%` (see details below).
**Datatype:** Depends on the feature created by the user. +| `df['%%*']` | Any dataframe column prepended with `%%` in `feature_engineering_*()` is treated as a training feature, just the same as the above `%` prepend. However, in this case, the features are returned back to the strategy for FreqUI/plot-dataframe plotting and monitoring in Dry/Live/Backtesting
**Datatype:** Depends on the feature created by the user. Please note that features created in `feature_engineering_expand()` will have automatic FreqAI naming schemas depending on the expansions that you configured (i.e. `include_timeframes`, `include_corr_pairlist`, `indicators_periods_candles`, `include_shifted_candles`). So if you want to plot `%%-rsi` from `feature_engineering_expand_all()`, the final naming scheme for your plotting config would be: `%%-rsi-period_10_ETH/USDT:USDT_1h` for the `rsi` feature with `period=10`, `timeframe=1h`, and `pair=ETH/USDT:USDT` (the `:USDT` is added if you are using futures pairs). It is useful to simply add `print(dataframe.columns)` in your `populate_indicators()` after `self.freqai.start()` to see the full list of available features that are returned to the strategy for plotting purposes. + +## Setting the `startup_candle_count` + +The `startup_candle_count` in the FreqAI strategy needs to be set up in the same way as in the standard Freqtrade strategy (see details [here](strategy-customization.md#strategy-startup-period)). This value is used by Freqtrade to ensure that a sufficient amount of data is provided when calling the `dataprovider`, to avoid any NaNs at the beginning of the first training. You can easily set this value by identifying the longest period (in candle units) which is passed to the indicator creation functions (e.g., TA-Lib functions). In the presented example, `startup_candle_count` is 20 since this is the maximum value in `indicators_periods_candles`. + +!!! Note + There are instances where the TA-Lib functions actually require more data than just the passed `period` or else the feature dataset gets populated with NaNs. Anecdotally, multiplying the `startup_candle_count` by 2 always leads to a fully NaN free training dataset. Hence, it is typically safest to multiply the expected `startup_candle_count` by 2. Look out for this log message to confirm that the data is clean: + + ``` + 2022-08-31 15:14:04 - freqtrade.freqai.data_kitchen - INFO - dropped 0 training points due to NaNs in populated dataset 4319. + ``` + +## Creating a dynamic target threshold + +Deciding when to enter or exit a trade can be done in a dynamic way to reflect current market conditions. FreqAI allows you to return additional information from the training of a model (more info [here](freqai-feature-engineering.md#returning-additional-info-from-training)). For example, the `&*_std/mean` return values describe the statistical distribution of the target/label *during the most recent training*. Comparing a given prediction to these values allows you to know the rarity of the prediction. In `templates/FreqaiExampleStrategy.py`, the `target_roi` and `sell_roi` are defined to be 1.25 z-scores away from the mean which causes predictions that are closer to the mean to be filtered out. + +```python +dataframe["target_roi"] = dataframe["&-s_close_mean"] + dataframe["&-s_close_std"] * 1.25 +dataframe["sell_roi"] = dataframe["&-s_close_mean"] - dataframe["&-s_close_std"] * 1.25 +``` + +To consider the population of *historical predictions* for creating the dynamic target instead of information from the training as discussed above, you would set `fit_live_predictions_candles` in the config to the number of historical prediction candles you wish to use to generate target statistics. + +```json + "freqai": { + "fit_live_predictions_candles": 300, + } +``` + +If this value is set, FreqAI will initially use the predictions from the training data and subsequently begin introducing real prediction data as it is generated. FreqAI will save this historical data to be reloaded if you stop and restart a model with the same `identifier`. + +## Using different prediction models + +FreqAI has multiple example prediction model libraries that are ready to be used as is via the flag `--freqaimodel`. These libraries include `CatBoost`, `LightGBM`, and `XGBoost` regression, classification, and multi-target models, and can be found in `freqai/prediction_models/`. + +Regression and classification models differ in what targets they predict - a regression model will predict a target of continuous values, for example what price BTC will be at tomorrow, whilst a classifier will predict a target of discrete values, for example if the price of BTC will go up tomorrow or not. This means that you have to specify your targets differently depending on which model type you are using (see details [below](#setting-model-targets)). + +All of the aforementioned model libraries implement gradient boosted decision tree algorithms. They all work on the principle of ensemble learning, where predictions from multiple simple learners are combined to get a final prediction that is more stable and generalized. The simple learners in this case are decision trees. Gradient boosting refers to the method of learning, where each simple learner is built in sequence - the subsequent learner is used to improve on the error from the previous learner. If you want to learn more about the different model libraries you can find the information in their respective docs: + +* CatBoost: https://catboost.ai/en/docs/ +* LightGBM: https://lightgbm.readthedocs.io/en/v3.3.2/# +* XGBoost: https://xgboost.readthedocs.io/en/stable/# + +There are also numerous online articles describing and comparing the algorithms. Some relatively lightweight examples would be [CatBoost vs. LightGBM vs. XGBoost — Which is the best algorithm?](https://towardsdatascience.com/catboost-vs-lightgbm-vs-xgboost-c80f40662924#:~:text=In%20CatBoost%2C%20symmetric%20trees%2C%20or,the%20same%20depth%20can%20differ.) and [XGBoost, LightGBM or CatBoost — which boosting algorithm should I use?](https://medium.com/riskified-technology/xgboost-lightgbm-or-catboost-which-boosting-algorithm-should-i-use-e7fda7bb36bc). Keep in mind that the performance of each model is highly dependent on the application and so any reported metrics might not be true for your particular use of the model. + +Apart from the models already available in FreqAI, it is also possible to customize and create your own prediction models using the `IFreqaiModel` class. You are encouraged to inherit `fit()`, `train()`, and `predict()` to customize various aspects of the training procedures. You can place custom FreqAI models in `user_data/freqaimodels` - and freqtrade will pick them up from there based on the provided `--freqaimodel` name - which has to correspond to the class name of your custom model. +Make sure to use unique names to avoid overriding built-in models. + +### Setting model targets + +#### Regressors + +If you are using a regressor, you need to specify a target that has continuous values. FreqAI includes a variety of regressors, such as the `CatboostRegressor`via the flag `--freqaimodel CatboostRegressor`. An example of how you could set a regression target for predicting the price 100 candles into the future would be + +```python +df['&s-close_price'] = df['close'].shift(-100) +``` + +If you want to predict multiple targets, you need to define multiple labels using the same syntax as shown above. + +#### Classifiers + +If you are using a classifier, you need to specify a target that has discrete values. FreqAI includes a variety of classifiers, such as the `CatboostClassifier` via the flag `--freqaimodel CatboostClassifier`. If you elects to use a classifier, the classes need to be set using strings. For example, if you want to predict if the price 100 candles into the future goes up or down you would set + +```python +df['&s-up_or_down'] = np.where( df["close"].shift(-100) > df["close"], 'up', 'down') +``` + +If you want to predict multiple targets you must specify all labels in the same label column. You could, for example, add the label `same` to define where the price was unchanged by setting + +```python +df['&s-up_or_down'] = np.where( df["close"].shift(-100) > df["close"], 'up', 'down') +df['&s-up_or_down'] = np.where( df["close"].shift(-100) == df["close"], 'same', df['&s-up_or_down']) +``` + +## PyTorch Module + +### Quick start + +The easiest way to quickly run a pytorch model is with the following command (for regression task): + +```bash +freqtrade trade --config config_examples/config_freqai.example.json --strategy FreqaiExampleStrategy --freqaimodel PyTorchMLPRegressor --strategy-path freqtrade/templates +``` + +!!! Note "Installation/docker" + The PyTorch module requires large packages such as `torch`, which should be explicitly requested during `./setup.sh -i` by answering "y" to the question "Do you also want dependencies for freqai-rl or PyTorch (~700mb additional space required) [y/N]?". + Users who prefer docker should ensure they use the docker image appended with `_freqaitorch`. + We do provide an explicit docker-compose file for this in `docker/docker-compose-freqai.yml` - which can be used via `docker compose -f docker/docker-compose-freqai.yml run ...` - or can be copied to replace the original docker file. + This docker-compose file also contains a (disabled) section to enable GPU resources within docker containers. This obviously assumes the system has GPU resources available. + + PyTorch dropped support for macOS x64 (intel based Apple devices) in version 2.3. Subsequently, freqtrade also dropped support for PyTorch on this platform. + +### Structure + +#### Model + +You can construct your own Neural Network architecture in PyTorch by simply defining your `nn.Module` class inside your custom [`IFreqaiModel` file](#using-different-prediction-models) and then using that class in your `def train()` function. Here is an example of logistic regression model implementation using PyTorch (should be used with nn.BCELoss criterion) for classification tasks. + +```python + +class LogisticRegression(nn.Module): + def __init__(self, input_size: int): + super().__init__() + # Define your layers + self.linear = nn.Linear(input_size, 1) + self.activation = nn.Sigmoid() + + def forward(self, x: torch.Tensor) -> torch.Tensor: + # Define the forward pass + out = self.linear(x) + out = self.activation(out) + return out + +class MyCoolPyTorchClassifier(BasePyTorchClassifier): + """ + This is a custom IFreqaiModel showing how a user might setup their own + custom Neural Network architecture for their training. + """ + + @property + def data_convertor(self) -> PyTorchDataConvertor: + return DefaultPyTorchDataConvertor(target_tensor_type=torch.float) + + def __init__(self, **kwargs) -> None: + super().__init__(**kwargs) + config = self.freqai_info.get("model_training_parameters", {}) + self.learning_rate: float = config.get("learning_rate", 3e-4) + self.model_kwargs: dict[str, Any] = config.get("model_kwargs", {}) + self.trainer_kwargs: dict[str, Any] = config.get("trainer_kwargs", {}) + + def fit(self, data_dictionary: dict, dk: FreqaiDataKitchen, **kwargs) -> Any: + """ + User sets up the training and test data to fit their desired model here + :param data_dictionary: the dictionary holding all data for train, test, + labels, weights + :param dk: The datakitchen object for the current coin/model + """ + + class_names = self.get_class_names() + self.convert_label_column_to_int(data_dictionary, dk, class_names) + n_features = data_dictionary["train_features"].shape[-1] + model = LogisticRegression( + input_dim=n_features + ) + model.to(self.device) + optimizer = torch.optim.AdamW(model.parameters(), lr=self.learning_rate) + criterion = torch.nn.CrossEntropyLoss() + init_model = self.get_init_model(dk.pair) + trainer = PyTorchModelTrainer( + model=model, + optimizer=optimizer, + criterion=criterion, + model_meta_data={"class_names": class_names}, + device=self.device, + init_model=init_model, + data_convertor=self.data_convertor, + **self.trainer_kwargs, + ) + trainer.fit(data_dictionary, self.splits) + return trainer + +``` + +#### Trainer + +The `PyTorchModelTrainer` performs the idiomatic PyTorch train loop: +Define our model, loss function, and optimizer, and then move them to the appropriate device (GPU or CPU). Inside the loop, we iterate through the batches in the dataloader, move the data to the device, compute the prediction and loss, backpropagate, and update the model parameters using the optimizer. + +In addition, the trainer is responsible for the following: + - saving and loading the model + - converting the data from `pandas.DataFrame` to `torch.Tensor`. + +#### Integration with Freqai module + +Like all freqai models, PyTorch models inherit `IFreqaiModel`. `IFreqaiModel` declares three abstract methods: `train`, `fit`, and `predict`. we implement these methods in three levels of hierarchy. +From top to bottom: + +1. `BasePyTorchModel` - Implements the `train` method. all `BasePyTorch*` inherit it. responsible for general data preparation (e.g., data normalization) and calling the `fit` method. Sets `device` attribute used by children classes. Sets `model_type` attribute used by the parent class. +2. `BasePyTorch*` - Implements the `predict` method. Here, the `*` represents a group of algorithms, such as classifiers or regressors. responsible for data preprocessing, predicting, and postprocessing if needed. +3. `PyTorch*Classifier` / `PyTorch*Regressor` - implements the `fit` method. responsible for the main train flaw, where we initialize the trainer and model objects. + +![image](assets/freqai_pytorch-diagram.png) + +#### Full example + +Building a PyTorch regressor using MLP (multilayer perceptron) model, MSELoss criterion, and AdamW optimizer. + +```python +class PyTorchMLPRegressor(BasePyTorchRegressor): + def __init__(self, **kwargs) -> None: + super().__init__(**kwargs) + config = self.freqai_info.get("model_training_parameters", {}) + self.learning_rate: float = config.get("learning_rate", 3e-4) + self.model_kwargs: dict[str, Any] = config.get("model_kwargs", {}) + self.trainer_kwargs: dict[str, Any] = config.get("trainer_kwargs", {}) + + def fit(self, data_dictionary: dict, dk: FreqaiDataKitchen, **kwargs) -> Any: + n_features = data_dictionary["train_features"].shape[-1] + model = PyTorchMLPModel( + input_dim=n_features, + output_dim=1, + **self.model_kwargs + ) + model.to(self.device) + optimizer = torch.optim.AdamW(model.parameters(), lr=self.learning_rate) + criterion = torch.nn.MSELoss() + init_model = self.get_init_model(dk.pair) + trainer = PyTorchModelTrainer( + model=model, + optimizer=optimizer, + criterion=criterion, + device=self.device, + init_model=init_model, + target_tensor_type=torch.float, + **self.trainer_kwargs, + ) + trainer.fit(data_dictionary) + return trainer +``` + +Here we create a `PyTorchMLPRegressor` class that implements the `fit` method. The `fit` method specifies the training building blocks: model, optimizer, criterion, and trainer. We inherit both `BasePyTorchRegressor` and `BasePyTorchModel`, where the former implements the `predict` method that is suitable for our regression task, and the latter implements the train method. + +??? Note "Setting Class Names for Classifiers" + When using classifiers, the user must declare the class names (or targets) by overriding the `IFreqaiModel.class_names` attribute. This is achieved by setting `self.freqai.class_names` in the FreqAI strategy inside the `set_freqai_targets` method. + + For example, if you are using a binary classifier to predict price movements as up or down, you can set the class names as follows: + ```python + def set_freqai_targets(self, dataframe: DataFrame, metadata: dict, **kwargs) -> DataFrame: + self.freqai.class_names = ["down", "up"] + dataframe['&s-up_or_down'] = np.where(dataframe["close"].shift(-100) > + dataframe["close"], 'up', 'down') + + return dataframe + ``` + To see a full example, you can refer to the [classifier test strategy class](https://github.com/freqtrade/freqtrade/blob/develop/tests/strategy/strats/freqai_test_classifier.py). + + +#### Improving performance with `torch.compile()` + +Torch provides a `torch.compile()` method that can be used to improve performance for specific GPU hardware. More details can be found [here](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html). In brief, you simply wrap your `model` in `torch.compile()`: + + +```python + model = PyTorchMLPModel( + input_dim=n_features, + output_dim=1, + **self.model_kwargs + ) + model.to(self.device) + model = torch.compile(model) +``` + +Then proceed to use the model as normal. Keep in mind that doing this will remove eager execution, which means errors and tracebacks will not be informative. diff --git a/md/freqai-developers.md b/md/freqai-developers.md new file mode 100644 index 00000000..37f4543b --- /dev/null +++ b/md/freqai-developers.md @@ -0,0 +1,78 @@ +# Development + +## Project architecture + +The architecture and functions of FreqAI are generalized to encourages development of unique features, functions, models, etc. + +The class structure and a detailed algorithmic overview is depicted in the following diagram: + +![image](assets/freqai_algorithm-diagram.jpg) + +As shown, there are three distinct objects comprising FreqAI: + +* **IFreqaiModel** - A singular persistent object containing all the necessary logic to collect, store, and process data, engineer features, run training, and inference models. +* **FreqaiDataKitchen** - A non-persistent object which is created uniquely for each unique asset/model. Beyond metadata, it also contains a variety of data processing tools. +* **FreqaiDataDrawer** - A singular persistent object containing all the historical predictions, models, and save/load methods. + +There are a variety of built-in [prediction models](freqai-configuration.md#using-different-prediction-models) which inherit directly from `IFreqaiModel`. Each of these models have full access to all methods in `IFreqaiModel` and can therefore override any of those functions at will. However, advanced users will likely stick to overriding `fit()`, `train()`, `predict()`, and `data_cleaning_train/predict()`. + +## Data handling + +FreqAI aims to organize model files, prediction data, and meta data in a way that simplifies post-processing and enhances crash resilience by automatic data reloading. The data is saved in a file structure,`user_data_dir/models/`, which contains all the data associated with the trainings and backtests. The `FreqaiDataKitchen()` relies heavily on the file structure for proper training and inferencing and should therefore not be manually modified. + +### File structure + +The file structure is automatically generated based on the model `identifier` set in the [config](freqai-configuration.md#setting-up-the-configuration-file). The following structure shows where the data is stored for post processing: + +| Structure | Description | +|-----------|-------------| +| `config_*.json` | A copy of the model specific configuration file. | +| `historic_predictions.pkl` | A file containing all historic predictions generated during the lifetime of the `identifier` model during live deployment. `historic_predictions.pkl` is used to reload the model after a crash or a config change. A backup file is always held in case of corruption on the main file. FreqAI **automatically** detects corruption and replaces the corrupted file with the backup. | +| `pair_dictionary.json` | A file containing the training queue as well as the on disk location of the most recently trained model. | +| `sub-train-*_TIMESTAMP` | A folder containing all the files associated with a single model, such as:
+|| `*_metadata.json` - Metadata for the model, such as normalization max/min, expected training feature list, etc.
+|| `*_model.*` - The model file saved to disk for reloading from a crash. Can be `joblib` (typical boosting libs), `zip` (stable_baselines), `hd5` (keras type), etc.
+|| `*_pca_object.pkl` - The [Principal component analysis (PCA)](freqai-feature-engineering.md#data-dimensionality-reduction-with-principal-component-analysis) transform (if `principal_component_analysis: True` is set in the config) which will be used to transform unseen prediction features.
+|| `*_svm_model.pkl` - The [Support Vector Machine (SVM)](freqai-feature-engineering.md#identifying-outliers-using-a-support-vector-machine-svm) model (if `use_SVM_to_remove_outliers: True` is set in the config) which is used to detect outliers in unseen prediction features.
+|| `*_trained_df.pkl` - The dataframe containing all the training features used to train the `identifier` model. This is used for computing the [Dissimilarity Index (DI)](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di) and can also be used for post-processing.
+|| `*_trained_dates.df.pkl` - The dates associated with the `trained_df.pkl`, which is useful for post-processing. | + +The example file structure would look like this: + +``` +├── models +│   └── unique-id +│   ├── config_freqai.example.json +│   ├── historic_predictions.backup.pkl +│   ├── historic_predictions.pkl +│   ├── pair_dictionary.json +│   ├── sub-train-1INCH_1662821319 +│   │   ├── cb_1inch_1662821319_metadata.json +│   │   ├── cb_1inch_1662821319_model.joblib +│   │   ├── cb_1inch_1662821319_pca_object.pkl +│   │   ├── cb_1inch_1662821319_svm_model.joblib +│   │   ├── cb_1inch_1662821319_trained_dates_df.pkl +│   │   └── cb_1inch_1662821319_trained_df.pkl +│   ├── sub-train-1INCH_1662821371 +│   │   ├── cb_1inch_1662821371_metadata.json +│   │   ├── cb_1inch_1662821371_model.joblib +│   │   ├── cb_1inch_1662821371_pca_object.pkl +│   │   ├── cb_1inch_1662821371_svm_model.joblib +│   │   ├── cb_1inch_1662821371_trained_dates_df.pkl +│   │   └── cb_1inch_1662821371_trained_df.pkl +│   ├── sub-train-ADA_1662821344 +│   │   ├── cb_ada_1662821344_metadata.json +│   │   ├── cb_ada_1662821344_model.joblib +│   │   ├── cb_ada_1662821344_pca_object.pkl +│   │   ├── cb_ada_1662821344_svm_model.joblib +│   │   ├── cb_ada_1662821344_trained_dates_df.pkl +│   │   └── cb_ada_1662821344_trained_df.pkl +│   └── sub-train-ADA_1662821399 +│   ├── cb_ada_1662821399_metadata.json +│   ├── cb_ada_1662821399_model.joblib +│   ├── cb_ada_1662821399_pca_object.pkl +│   ├── cb_ada_1662821399_svm_model.joblib +│   ├── cb_ada_1662821399_trained_dates_df.pkl +│   └── cb_ada_1662821399_trained_df.pkl + +``` diff --git a/md/freqai-feature-engineering.md b/md/freqai-feature-engineering.md new file mode 100644 index 00000000..d2505129 --- /dev/null +++ b/md/freqai-feature-engineering.md @@ -0,0 +1,408 @@ +# Feature engineering + +## Defining the features + +Low level feature engineering is performed in the user strategy within a set of functions called `feature_engineering_*`. These function set the `base features` such as, `RSI`, `MFI`, `EMA`, `SMA`, time of day, volume, etc. The `base features` can be custom indicators or they can be imported from any technical-analysis library that you can find. FreqAI is equipped with a set of functions to simplify rapid large-scale feature engineering: + +| Function | Description | +|---------------|-------------| +| `feature_engineering_expand_all()` | This optional function will automatically expand the defined features on the config defined `indicator_periods_candles`, `include_timeframes`, `include_shifted_candles`, and `include_corr_pairs`. +| `feature_engineering_expand_basic()` | This optional function will automatically expand the defined features on the config defined `include_timeframes`, `include_shifted_candles`, and `include_corr_pairs`. Note: this function does *not* expand across `indicator_periods_candles`. +| `feature_engineering_standard()` | This optional function will be called once with the dataframe of the base timeframe. This is the final function to be called, which means that the dataframe entering this function will contain all the features and columns from the base asset created by the other `feature_engineering_expand` functions. This function is a good place to do custom exotic feature extractions (e.g. tsfresh). This function is also a good place for any feature that should not be auto-expanded upon (e.g., day of the week). +| `set_freqai_targets()` | Required function to set the targets for the model. All targets must be prepended with `&` to be recognized by the FreqAI internals. + +Meanwhile, high level feature engineering is handled within `"feature_parameters":{}` in the FreqAI config. Within this file, it is possible to decide large scale feature expansions on top of the `base_features` such as "including correlated pairs" or "including informative timeframes" or even "including recent candles." + +It is advisable to start from the template `feature_engineering_*` functions in the source provided example strategy (found in `templates/FreqaiExampleStrategy.py`) to ensure that the feature definitions are following the correct conventions. Here is an example of how to set the indicators and labels in the strategy: + +```python + def feature_engineering_expand_all(self, dataframe: DataFrame, period, metadata, **kwargs) -> DataFrame: + """ + *Only functional with FreqAI enabled strategies* + This function will automatically expand the defined features on the config defined + `indicator_periods_candles`, `include_timeframes`, `include_shifted_candles`, and + `include_corr_pairs`. In other words, a single feature defined in this function + will automatically expand to a total of + `indicator_periods_candles` * `include_timeframes` * `include_shifted_candles` * + `include_corr_pairs` numbers of features added to the model. + + All features must be prepended with `%` to be recognized by FreqAI internals. + + Access metadata such as the current pair/timeframe/period with: + + `metadata["pair"]` `metadata["tf"]` `metadata["period"]` + + :param df: strategy dataframe which will receive the features + :param period: period of the indicator - usage example: + :param metadata: metadata of current pair + dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period) + """ + + dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period) + dataframe["%-mfi-period"] = ta.MFI(dataframe, timeperiod=period) + dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period) + dataframe["%-sma-period"] = ta.SMA(dataframe, timeperiod=period) + dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period) + + bollinger = qtpylib.bollinger_bands( + qtpylib.typical_price(dataframe), window=period, stds=2.2 + ) + dataframe["bb_lowerband-period"] = bollinger["lower"] + dataframe["bb_middleband-period"] = bollinger["mid"] + dataframe["bb_upperband-period"] = bollinger["upper"] + + dataframe["%-bb_width-period"] = ( + dataframe["bb_upperband-period"] + - dataframe["bb_lowerband-period"] + ) / dataframe["bb_middleband-period"] + dataframe["%-close-bb_lower-period"] = ( + dataframe["close"] / dataframe["bb_lowerband-period"] + ) + + dataframe["%-roc-period"] = ta.ROC(dataframe, timeperiod=period) + + dataframe["%-relative_volume-period"] = ( + dataframe["volume"] / dataframe["volume"].rolling(period).mean() + ) + + return dataframe + + def feature_engineering_expand_basic(self, dataframe: DataFrame, metadata, **kwargs) -> DataFrame: + """ + *Only functional with FreqAI enabled strategies* + This function will automatically expand the defined features on the config defined + `include_timeframes`, `include_shifted_candles`, and `include_corr_pairs`. + In other words, a single feature defined in this function + will automatically expand to a total of + `include_timeframes` * `include_shifted_candles` * `include_corr_pairs` + numbers of features added to the model. + + Features defined here will *not* be automatically duplicated on user defined + `indicator_periods_candles` + + Access metadata such as the current pair/timeframe with: + + `metadata["pair"]` `metadata["tf"]` + + All features must be prepended with `%` to be recognized by FreqAI internals. + + :param df: strategy dataframe which will receive the features + :param metadata: metadata of current pair + dataframe["%-pct-change"] = dataframe["close"].pct_change() + dataframe["%-ema-200"] = ta.EMA(dataframe, timeperiod=200) + """ + dataframe["%-pct-change"] = dataframe["close"].pct_change() + dataframe["%-raw_volume"] = dataframe["volume"] + dataframe["%-raw_price"] = dataframe["close"] + return dataframe + + def feature_engineering_standard(self, dataframe: DataFrame, metadata, **kwargs) -> DataFrame: + """ + *Only functional with FreqAI enabled strategies* + This optional function will be called once with the dataframe of the base timeframe. + This is the final function to be called, which means that the dataframe entering this + function will contain all the features and columns created by all other + freqai_feature_engineering_* functions. + + This function is a good place to do custom exotic feature extractions (e.g. tsfresh). + This function is a good place for any feature that should not be auto-expanded upon + (e.g. day of the week). + + Access metadata such as the current pair with: + + `metadata["pair"]` + + All features must be prepended with `%` to be recognized by FreqAI internals. + + :param df: strategy dataframe which will receive the features + :param metadata: metadata of current pair + usage example: dataframe["%-day_of_week"] = (dataframe["date"].dt.dayofweek + 1) / 7 + """ + dataframe["%-day_of_week"] = (dataframe["date"].dt.dayofweek + 1) / 7 + dataframe["%-hour_of_day"] = (dataframe["date"].dt.hour + 1) / 25 + return dataframe + + def set_freqai_targets(self, dataframe: DataFrame, metadata, **kwargs) -> DataFrame: + """ + *Only functional with FreqAI enabled strategies* + Required function to set the targets for the model. + All targets must be prepended with `&` to be recognized by the FreqAI internals. + + Access metadata such as the current pair with: + + `metadata["pair"]` + + :param df: strategy dataframe which will receive the targets + :param metadata: metadata of current pair + usage example: dataframe["&-target"] = dataframe["close"].shift(-1) / dataframe["close"] + """ + dataframe["&-s_close"] = ( + dataframe["close"] + .shift(-self.freqai_info["feature_parameters"]["label_period_candles"]) + .rolling(self.freqai_info["feature_parameters"]["label_period_candles"]) + .mean() + / dataframe["close"] + - 1 + ) + + return dataframe +``` + +In the presented example, the user does not wish to pass the `bb_lowerband` as a feature to the model, +and has therefore not prepended it with `%`. The user does, however, wish to pass `bb_width` to the +model for training/prediction and has therefore prepended it with `%`. + +After having defined the `base features`, the next step is to expand upon them using the powerful `feature_parameters` in the configuration file: + +```json + "freqai": { + //... + "feature_parameters" : { + "include_timeframes": ["5m","15m","4h"], + "include_corr_pairlist": [ + "ETH/USD", + "LINK/USD", + "BNB/USD" + ], + "label_period_candles": 24, + "include_shifted_candles": 2, + "indicator_periods_candles": [10, 20] + }, + //... + } +``` + +The `include_timeframes` in the config above are the timeframes (`tf`) of each call to `feature_engineering_expand_*()` in the strategy. In the presented case, the user is asking for the `5m`, `15m`, and `4h` timeframes of the `rsi`, `mfi`, `roc`, and `bb_width` to be included in the feature set. + +You can ask for each of the defined features to be included also for informative pairs using the `include_corr_pairlist`. This means that the feature set will include all the features from `feature_engineering_expand_*()` on all the `include_timeframes` for each of the correlated pairs defined in the config (`ETH/USD`, `LINK/USD`, and `BNB/USD` in the presented example). + +`include_shifted_candles` indicates the number of previous candles to include in the feature set. For example, `include_shifted_candles: 2` tells FreqAI to include the past 2 candles for each of the features in the feature set. + +In total, the number of features the user of the presented example strategy has created is: length of `include_timeframes` * no. features in `feature_engineering_expand_*()` * length of `include_corr_pairlist` * no. `include_shifted_candles` * length of `indicator_periods_candles` + $= 3 * 3 * 3 * 2 * 2 = 108$. + + !!! note "Learn more about creative feature engineering" + Check out our [medium article](https://emergentmethods.medium.com/freqai-from-price-to-prediction-6fadac18b665) geared toward helping users learn how to creatively engineer features. + +### Gain finer control over `feature_engineering_*` functions with `metadata` + +All `feature_engineering_*` and `set_freqai_targets()` functions are passed a `metadata` dictionary which contains information about the `pair`, `tf` (timeframe), and `period` that FreqAI is automating for feature building. As such, a user can use `metadata` inside `feature_engineering_*` functions as criteria for blocking/reserving features for certain timeframes, periods, pairs etc. + +```python +def feature_engineering_expand_all(self, dataframe: DataFrame, period, metadata, **kwargs) -> DataFrame: + if metadata["tf"] == "1h": + dataframe["%-roc-period"] = ta.ROC(dataframe, timeperiod=period) +``` + +This will block `ta.ROC()` from being added to any timeframes other than `"1h"`. + +### Returning additional info from training + +Important metrics can be returned to the strategy at the end of each model training by assigning them to `dk.data['extra_returns_per_train']['my_new_value'] = XYZ` inside the custom prediction model class. + +FreqAI takes the `my_new_value` assigned in this dictionary and expands it to fit the dataframe that is returned to the strategy. You can then use the returned metrics in your strategy through `dataframe['my_new_value']`. An example of how return values can be used in FreqAI are the `&*_mean` and `&*_std` values that are used to [created a dynamic target threshold](freqai-configuration.md#creating-a-dynamic-target-threshold). + +Another example, where the user wants to use live metrics from the trade database, is shown below: + +```json + "freqai": { + "extra_returns_per_train": {"total_profit": 4} + } +``` + +You need to set the standard dictionary in the config so that FreqAI can return proper dataframe shapes. These values will likely be overridden by the prediction model, but in the case where the model has yet to set them, or needs a default initial value, the pre-set values are what will be returned. + +### Weighting features for temporal importance + +FreqAI allows you to set a `weight_factor` to weight recent data more strongly than past data via an exponential function: + +$$ W_i = \exp(\frac{-i}{\alpha*n}) $$ + +where $W_i$ is the weight of data point $i$ in a total set of $n$ data points. Below is a figure showing the effect of different weight factors on the data points in a feature set. + +![weight-factor](assets/freqai_weight-factor.jpg) + +## Building the data pipeline + +By default, FreqAI builds a dynamic pipeline based on user configuration settings. The default settings are robust and designed to work with a variety of methods. These two steps are a `MinMaxScaler(-1,1)` and a `VarianceThreshold` which removes any column that has 0 variance. Users can activate other steps with more configuration parameters. For example if users add `use_SVM_to_remove_outliers: true` to the `freqai` config, then FreqAI will automatically add the [`SVMOutlierExtractor`](#identifying-outliers-using-a-support-vector-machine-svm) to the pipeline. Likewise, users can add `principal_component_analysis: true` to the `freqai` config to activate PCA. The [DissimilarityIndex](#identifying-outliers-with-the-dissimilarity-index-di) is activated with `DI_threshold: 1`. Finally, noise can also be added to the data with `noise_standard_deviation: 0.1`. Finally, users can add [DBSCAN](#identifying-outliers-with-dbscan) outlier removal with `use_DBSCAN_to_remove_outliers: true`. + +!!! note "More information available" + Please review the [parameter table](freqai-parameter-table.md) for more information on these parameters. + + +### Customizing the pipeline + +Users are encouraged to customize the data pipeline to their needs by building their own data pipeline. This can be done by simply setting `dk.feature_pipeline` to their desired `Pipeline` object inside their `IFreqaiModel` `train()` function, or if they prefer not to touch the `train()` function, they can override `define_data_pipeline`/`define_label_pipeline` functions in their `IFreqaiModel`: + +!!! note "More information available" + FreqAI uses the [`DataSieve`](https://github.com/emergentmethods/datasieve) pipeline, which follows the SKlearn pipeline API, but adds, among other features, coherence between the X, y, and sample_weight vector point removals, feature removal, feature name following. + +```python +from datasieve.transforms import SKLearnWrapper, DissimilarityIndex +from datasieve.pipeline import Pipeline +from sklearn.preprocessing import QuantileTransformer, StandardScaler +from freqai.base_models import BaseRegressionModel + + +class MyFreqaiModel(BaseRegressionModel): + """ + Some cool custom model + """ + def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any: + """ + My custom fit function + """ + model = cool_model.fit() + return model + + def define_data_pipeline(self) -> Pipeline: + """ + User defines their custom feature pipeline here (if they wish) + """ + feature_pipeline = Pipeline([ + ('qt', SKLearnWrapper(QuantileTransformer(output_distribution='normal'))), + ('di', ds.DissimilarityIndex(di_threshold=1)) + ]) + + return feature_pipeline + + def define_label_pipeline(self) -> Pipeline: + """ + User defines their custom label pipeline here (if they wish) + """ + label_pipeline = Pipeline([ + ('qt', SKLearnWrapper(StandardScaler())), + ]) + + return label_pipeline +``` + +Here, you are defining the exact pipeline that will be used for your feature set during training and prediction. You can use *most* SKLearn transformation steps by wrapping them in the `SKLearnWrapper` class as shown above. In addition, you can use any of the transformations available in the [`DataSieve` library](https://github.com/emergentmethods/datasieve). + +You can easily add your own transformation by creating a class that inherits from the datasieve `BaseTransform` and implementing your `fit()`, `transform()` and `inverse_transform()` methods: + +```python +from datasieve.transforms.base_transform import BaseTransform +# import whatever else you need + +class MyCoolTransform(BaseTransform): + def __init__(self, **kwargs): + self.param1 = kwargs.get('param1', 1) + + def fit(self, X, y=None, sample_weight=None, feature_list=None, **kwargs): + # do something with X, y, sample_weight, or/and feature_list + return X, y, sample_weight, feature_list + + def transform(self, X, y=None, sample_weight=None, + feature_list=None, outlier_check=False, **kwargs): + # do something with X, y, sample_weight, or/and feature_list + return X, y, sample_weight, feature_list + + def inverse_transform(self, X, y=None, sample_weight=None, feature_list=None, **kwargs): + # do/dont do something with X, y, sample_weight, or/and feature_list + return X, y, sample_weight, feature_list +``` + +!!! note "Hint" + You can define this custom class in the same file as your `IFreqaiModel`. + +### Migrating a custom `IFreqaiModel` to the new Pipeline + +If you have created your own custom `IFreqaiModel` with a custom `train()`/`predict()` function, *and* you still rely on `data_cleaning_train/predict()`, then you will need to migrate to the new pipeline. If your model does *not* rely on `data_cleaning_train/predict()`, then you do not need to worry about this migration. + +More details about the migration can be found [here](strategy_migration.md#freqai---new-data-pipeline). + +## Outlier detection + +Equity and crypto markets suffer from a high level of non-patterned noise in the form of outlier data points. FreqAI implements a variety of methods to identify such outliers and hence mitigate risk. + +### Identifying outliers with the Dissimilarity Index (DI) + +The Dissimilarity Index (DI) aims to quantify the uncertainty associated with each prediction made by the model. + +You can tell FreqAI to remove outlier data points from the training/test data sets using the DI by including the following statement in the config: + +```json + "freqai": { + "feature_parameters" : { + "DI_threshold": 1 + } + } +``` + +Which will add `DissimilarityIndex` step to your `feature_pipeline` and set the threshold to 1. The DI allows predictions which are outliers (not existent in the model feature space) to be thrown out due to low levels of certainty. To do so, FreqAI measures the distance between each training data point (feature vector), $X_{a}$, and all other training data points: + +$$ d_{ab} = \sqrt{\sum_{j=1}^p(X_{a,j}-X_{b,j})^2} $$ + +where $d_{ab}$ is the distance between the normalized points $a$ and $b$, and $p$ is the number of features, i.e., the length of the vector $X$. The characteristic distance, $\overline{d}$, for a set of training data points is simply the mean of the average distances: + +$$ \overline{d} = \sum_{a=1}^n(\sum_{b=1}^n(d_{ab}/n)/n) $$ + +$\overline{d}$ quantifies the spread of the training data, which is compared to the distance between a new prediction feature vectors, $X_k$ and all the training data: + +$$ d_k = \arg \min d_{k,i} $$ + +This enables the estimation of the Dissimilarity Index as: + +$$ DI_k = d_k/\overline{d} $$ + +You can tweak the DI through the `DI_threshold` to increase or decrease the extrapolation of the trained model. A higher `DI_threshold` means that the DI is more lenient and allows predictions further away from the training data to be used whilst a lower `DI_threshold` has the opposite effect and hence discards more predictions. + +Below is a figure that describes the DI for a 3D data set. + +![DI](assets/freqai_DI.jpg) + +### Identifying outliers using a Support Vector Machine (SVM) + +You can tell FreqAI to remove outlier data points from the training/test data sets using a Support Vector Machine (SVM) by including the following statement in the config: + +```json + "freqai": { + "feature_parameters" : { + "use_SVM_to_remove_outliers": true + } + } +``` + +Which will add `SVMOutlierExtractor` step to your `feature_pipeline`. The SVM will be trained on the training data and any data point that the SVM deems to be beyond the feature space will be removed. + +You can elect to provide additional parameters for the SVM, such as `shuffle`, and `nu` via the `feature_parameters.svm_params` dictionary in the config. + +The parameter `shuffle` is by default set to `False` to ensure consistent results. If it is set to `True`, running the SVM multiple times on the same data set might result in different outcomes due to `max_iter` being to low for the algorithm to reach the demanded `tol`. Increasing `max_iter` solves this issue but causes the procedure to take longer time. + +The parameter `nu`, *very* broadly, is the amount of data points that should be considered outliers and should be between 0 and 1. + +### Identifying outliers with DBSCAN + +You can configure FreqAI to use DBSCAN to cluster and remove outliers from the training/test data set or incoming outliers from predictions, by activating `use_DBSCAN_to_remove_outliers` in the config: + +```json + "freqai": { + "feature_parameters" : { + "use_DBSCAN_to_remove_outliers": true + } + } +``` + +Which will add the `DataSieveDBSCAN` step to your `feature_pipeline`. This is an unsupervised machine learning algorithm that clusters data without needing to know how many clusters there should be. + +Given a number of data points $N$, and a distance $\varepsilon$, DBSCAN clusters the data set by setting all data points that have $N-1$ other data points within a distance of $\varepsilon$ as *core points*. A data point that is within a distance of $\varepsilon$ from a *core point* but that does not have $N-1$ other data points within a distance of $\varepsilon$ from itself is considered an *edge point*. A cluster is then the collection of *core points* and *edge points*. Data points that have no other data points at a distance $<\varepsilon$ are considered outliers. The figure below shows a cluster with $N = 3$. + +![dbscan](assets/freqai_dbscan.jpg) + +FreqAI uses `sklearn.cluster.DBSCAN` (details are available on scikit-learn's webpage [here](https://scikit-learn.org/stable/modules/generated/sklearn.cluster.DBSCAN.html) (external website)) with `min_samples` ($N$) taken as 1/4 of the no. of time points (candles) in the feature set. `eps` ($\varepsilon$) is computed automatically as the elbow point in the *k-distance graph* computed from the nearest neighbors in the pairwise distances of all data points in the feature set. + + +### Data dimensionality reduction with Principal Component Analysis + +You can reduce the dimensionality of your features by activating the principal_component_analysis in the config: + +```json + "freqai": { + "feature_parameters" : { + "principal_component_analysis": true + } + } +``` + +This will perform PCA on the features and reduce their dimensionality so that the explained variance of the data set is >= 0.999. Reducing data dimensionality makes training the model faster and hence allows for more up-to-date models. diff --git a/md/freqai-parameter-table.md b/md/freqai-parameter-table.md new file mode 100644 index 00000000..3bb28931 --- /dev/null +++ b/md/freqai-parameter-table.md @@ -0,0 +1,118 @@ +# Parameter table + +The table below will list all configuration parameters available for FreqAI. Some of the parameters are exemplified in `config_examples/config_freqai.example.json`. + +Mandatory parameters are marked as **Required** and have to be set in one of the suggested ways. + +### General configuration parameters + +| Parameter | Description | +|------------|-------------| +| | **General configuration parameters within the `config.freqai` tree** +| `freqai` | **Required.**
The parent dictionary containing all the parameters for controlling FreqAI.
**Datatype:** Dictionary. +| `train_period_days` | **Required.**
Number of days to use for the training data (width of the sliding window).
**Datatype:** Positive integer. +| `backtest_period_days` | **Required.**
Number of days to inference from the trained model before sliding the `train_period_days` window defined above, and retraining the model during backtesting (more info [here](freqai-running.md#backtesting)). This can be fractional days, but beware that the provided `timerange` will be divided by this number to yield the number of trainings necessary to complete the backtest.
**Datatype:** Float. +| `identifier` | **Required.**
A unique ID for the current model. If models are saved to disk, the `identifier` allows for reloading specific pre-trained models/data.
**Datatype:** String. +| `live_retrain_hours` | Frequency of retraining during dry/live runs.
**Datatype:** Float > 0.
Default: `0` (models retrain as often as possible). +| `expiration_hours` | Avoid making predictions if a model is more than `expiration_hours` old.
**Datatype:** Positive integer.
Default: `0` (models never expire). +| `purge_old_models` | Number of models to keep on disk (not relevant to backtesting). Default is 2, which means that dry/live runs will keep the latest 2 models on disk. Setting to 0 keeps all models. This parameter also accepts a boolean to maintain backwards compatibility.
**Datatype:** Integer.
Default: `2`. +| `save_backtest_models` | Save models to disk when running backtesting. Backtesting operates most efficiently by saving the prediction data and reusing them directly for subsequent runs (when you wish to tune entry/exit parameters). Saving backtesting models to disk also allows to use the same model files for starting a dry/live instance with the same model `identifier`.
**Datatype:** Boolean.
Default: `False` (no models are saved). +| `fit_live_predictions_candles` | Number of historical candles to use for computing target (label) statistics from prediction data, instead of from the training dataset (more information can be found [here](freqai-configuration.md#creating-a-dynamic-target-threshold)).
**Datatype:** Positive integer. +| `continual_learning` | Use the final state of the most recently trained model as starting point for the new model, allowing for incremental learning (more information can be found [here](freqai-running.md#continual-learning)). Beware that this is currently a naive approach to incremental learning, and it has a high probability of overfitting/getting stuck in local minima while the market moves away from your model. We have the connections here primarily for experimental purposes and so that it is ready for more mature approaches to continual learning in chaotic systems like the crypto market.
**Datatype:** Boolean.
Default: `False`. +| `write_metrics_to_disk` | Collect train timings, inference timings and cpu usage in json file.
**Datatype:** Boolean.
Default: `False` +| `data_kitchen_thread_count` |
Designate the number of threads you want to use for data processing (outlier methods, normalization, etc.). This has no impact on the number of threads used for training. If user does not set it (default), FreqAI will use max number of threads - 2 (leaving 1 physical core available for Freqtrade bot and FreqUI)
**Datatype:** Positive integer. +| `activate_tensorboard` |
Indicate whether or not to activate tensorboard for the tensorboard enabled modules (currently Reinforcment Learning, XGBoost, Catboost, and PyTorch). Tensorboard needs Torch installed, which means you will need the torch/RL docker image or you need to answer "yes" to the install question about whether or not you wish to install Torch.
**Datatype:** Boolean.
Default: `True`. +| `wait_for_training_iteration_on_reload` |
When using /reload or ctrl-c, wait for the current training iteration to finish before completing graceful shutdown. If set to `False`, FreqAI will break the current training iteration, allowing you to shutdown gracefully more quickly, but you will lose your current training iteration.
**Datatype:** Boolean.
Default: `True`. + +### Feature parameters + +| Parameter | Description | +|------------|-------------| +| | **Feature parameters within the `freqai.feature_parameters` sub dictionary** +| `feature_parameters` | A dictionary containing the parameters used to engineer the feature set. Details and examples are shown [here](freqai-feature-engineering.md).
**Datatype:** Dictionary. +| `include_timeframes` | A list of timeframes that all indicators in `feature_engineering_expand_*()` will be created for. The list is added as features to the base indicators dataset.
**Datatype:** List of timeframes (strings). +| `include_corr_pairlist` | A list of correlated coins that FreqAI will add as additional features to all `pair_whitelist` coins. All indicators set in `feature_engineering_expand_*()` during feature engineering (see details [here](freqai-feature-engineering.md)) will be created for each correlated coin. The correlated coins features are added to the base indicators dataset.
**Datatype:** List of assets (strings). +| `label_period_candles` | Number of candles into the future that the labels are created for. This can be used in `set_freqai_targets()` (see `templates/FreqaiExampleStrategy.py` for detailed usage). This parameter is not necessarily required, you can create custom labels and choose whether to make use of this parameter or not. Please see `templates/FreqaiExampleStrategy.py` to see the example usage.
**Datatype:** Positive integer. +| `include_shifted_candles` | Add features from previous candles to subsequent candles with the intent of adding historical information. If used, FreqAI will duplicate and shift all features from the `include_shifted_candles` previous candles so that the information is available for the subsequent candle.
**Datatype:** Positive integer. +| `weight_factor` | Weight training data points according to their recency (see details [here](freqai-feature-engineering.md#weighting-features-for-temporal-importance)).
**Datatype:** Positive float (typically < 1). +| `indicator_max_period_candles` | **No longer used (#7325)**. Replaced by `startup_candle_count` which is set in the [strategy](freqai-configuration.md#building-a-freqai-strategy). `startup_candle_count` is timeframe independent and defines the maximum *period* used in `feature_engineering_*()` for indicator creation. FreqAI uses this parameter together with the maximum timeframe in `include_time_frames` to calculate how many data points to download such that the first data point does not include a NaN.
**Datatype:** Positive integer. +| `indicator_periods_candles` | Time periods to calculate indicators for. The indicators are added to the base indicator dataset.
**Datatype:** List of positive integers. +| `principal_component_analysis` | Automatically reduce the dimensionality of the data set using Principal Component Analysis. See details about how it works [here](freqai-feature-engineering.md#data-dimensionality-reduction-with-principal-component-analysis)
**Datatype:** Boolean.
Default: `False`. +| `plot_feature_importances` | Create a feature importance plot for each model for the top/bottom `plot_feature_importances` number of features. Plot is stored in `user_data/models//sub-train-_.html`.
**Datatype:** Integer.
Default: `0`. +| `DI_threshold` | Activates the use of the Dissimilarity Index for outlier detection when set to > 0. See details about how it works [here](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di).
**Datatype:** Positive float (typically < 1). +| `use_SVM_to_remove_outliers` | Train a support vector machine to detect and remove outliers from the training dataset, as well as from incoming data points. See details about how it works [here](freqai-feature-engineering.md#identifying-outliers-using-a-support-vector-machine-svm).
**Datatype:** Boolean. +| `svm_params` | All parameters available in Sklearn's `SGDOneClassSVM()`. See details about some select parameters [here](freqai-feature-engineering.md#identifying-outliers-using-a-support-vector-machine-svm).
**Datatype:** Dictionary. +| `use_DBSCAN_to_remove_outliers` | Cluster data using the DBSCAN algorithm to identify and remove outliers from training and prediction data. See details about how it works [here](freqai-feature-engineering.md#identifying-outliers-with-dbscan).
**Datatype:** Boolean. +| `noise_standard_deviation` | If set, FreqAI adds noise to the training features with the aim of preventing overfitting. FreqAI generates random deviates from a gaussian distribution with a standard deviation of `noise_standard_deviation` and adds them to all data points. `noise_standard_deviation` should be kept relative to the normalized space, i.e., between -1 and 1. In other words, since data in FreqAI is always normalized to be between -1 and 1, `noise_standard_deviation: 0.05` would result in 32% of the data being randomly increased/decreased by more than 2.5% (i.e., the percent of data falling within the first standard deviation).
**Datatype:** Integer.
Default: `0`. +| `outlier_protection_percentage` | Enable to prevent outlier detection methods from discarding too much data. If more than `outlier_protection_percentage` % of points are detected as outliers by the SVM or DBSCAN, FreqAI will log a warning message and ignore outlier detection, i.e., the original dataset will be kept intact. If the outlier protection is triggered, no predictions will be made based on the training dataset.
**Datatype:** Float.
Default: `30`. +| `reverse_train_test_order` | Split the feature dataset (see below) and use the latest data split for training and test on historical split of the data. This allows the model to be trained up to the most recent data point, while avoiding overfitting. However, you should be careful to understand the unorthodox nature of this parameter before employing it.
**Datatype:** Boolean.
Default: `False` (no reversal). +| `shuffle_after_split` | Split the data into train and test sets, and then shuffle both sets individually.
**Datatype:** Boolean.
Default: `False`. +| `buffer_train_data_candles` | Cut `buffer_train_data_candles` off the beginning and end of the training data *after* the indicators were populated. The main example use is when predicting maxima and minima, the argrelextrema function cannot know the maxima/minima at the edges of the timerange. To improve model accuracy, it is best to compute argrelextrema on the full timerange and then use this function to cut off the edges (buffer) by the kernel. In another case, if the targets are set to a shifted price movement, this buffer is unnecessary because the shifted candles at the end of the timerange will be NaN and FreqAI will automatically cut those off of the training dataset.
**Datatype:** Integer.
Default: `0`. + +### Data split parameters + +| Parameter | Description | +|------------|-------------| +| | **Data split parameters within the `freqai.data_split_parameters` sub dictionary** +| `data_split_parameters` | Include any additional parameters available from scikit-learn `test_train_split()`, which are shown [here](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html) (external website).
**Datatype:** Dictionary. +| `test_size` | The fraction of data that should be used for testing instead of training.
**Datatype:** Positive float < 1. +| `shuffle` | Shuffle the training data points during training. Typically, to not remove the chronological order of data in time-series forecasting, this is set to `False`.
**Datatype:** Boolean.
Default: `False`. + +### Model training parameters + +| Parameter | Description | +|------------|-------------| +| | **Model training parameters within the `freqai.model_training_parameters` sub dictionary** +| `model_training_parameters` | A flexible dictionary that includes all parameters available by the selected model library. For example, if you use `LightGBMRegressor`, this dictionary can contain any parameter available by the `LightGBMRegressor` [here](https://lightgbm.readthedocs.io/en/latest/pythonapi/lightgbm.LGBMRegressor.html) (external website). If you select a different model, this dictionary can contain any parameter from that model. A list of the currently available models can be found [here](freqai-configuration.md#using-different-prediction-models).
**Datatype:** Dictionary. +| `n_estimators` | The number of boosted trees to fit in the training of the model.
**Datatype:** Integer. +| `learning_rate` | Boosting learning rate during training of the model.
**Datatype:** Float. +| `n_jobs`, `thread_count`, `task_type` | Set the number of threads for parallel processing and the `task_type` (`gpu` or `cpu`). Different model libraries use different parameter names.
**Datatype:** Float. + +### Reinforcement Learning parameters + +| Parameter | Description | +|------------|-------------| +| | **Reinforcement Learning Parameters within the `freqai.rl_config` sub dictionary** +| `rl_config` | A dictionary containing the control parameters for a Reinforcement Learning model.
**Datatype:** Dictionary. +| `train_cycles` | Training time steps will be set based on the `train_cycles * number of training data points.
**Datatype:** Integer. +| `max_trade_duration_candles`| Guides the agent training to keep trades below desired length. Example usage shown in `prediction_models/ReinforcementLearner.py` within the customizable `calculate_reward()` function.
**Datatype:** int. +| `model_type` | Model string from stable_baselines3 or SBcontrib. Available strings include: `'TRPO', 'ARS', 'RecurrentPPO', 'MaskablePPO', 'PPO', 'A2C', 'DQN'`. User should ensure that `model_training_parameters` match those available to the corresponding stable_baselines3 model by visiting their documentation. [PPO doc](https://stable-baselines3.readthedocs.io/en/master/modules/ppo.html) (external website)
**Datatype:** string. +| `policy_type` | One of the available policy types from stable_baselines3
**Datatype:** string. +| `max_training_drawdown_pct` | The maximum drawdown that the agent is allowed to experience during training.
**Datatype:** float.
Default: 0.8 +| `cpu_count` | Number of threads/cpus to dedicate to the Reinforcement Learning training process (depending on if `ReinforcementLearning_multiproc` is selected or not). Recommended to leave this untouched, by default, this value is set to the total number of physical cores minus 1.
**Datatype:** int. +| `model_reward_parameters` | Parameters used inside the customizable `calculate_reward()` function in `ReinforcementLearner.py`
**Datatype:** int. +| `add_state_info` | Tell FreqAI to include state information in the feature set for training and inferencing. The current state variables include trade duration, current profit, trade position. This is only available in dry/live runs, and is automatically switched to false for backtesting.
**Datatype:** bool.
Default: `False`. +| `net_arch` | Network architecture which is well described in [`stable_baselines3` doc](https://stable-baselines3.readthedocs.io/en/master/guide/custom_policy.html#examples). In summary: `[, dict(vf=[], pi=[])]`. By default this is set to `[128, 128]`, which defines 2 shared hidden layers with 128 units each. +| `randomize_starting_position` | Randomize the starting point of each episode to avoid overfitting.
**Datatype:** bool.
Default: `False`. +| `drop_ohlc_from_features` | Do not include the normalized ohlc data in the feature set passed to the agent during training (ohlc will still be used for driving the environment in all cases)
**Datatype:** Boolean.
**Default:** `False` +| `progress_bar` | Display a progress bar with the current progress, elapsed time and estimated remaining time.
**Datatype:** Boolean.
Default: `False`. + +### PyTorch parameters + +#### general + +| Parameter | Description | +|------------|-------------| +| | **Model training parameters within the `freqai.model_training_parameters` sub dictionary** +| `learning_rate` | Learning rate to be passed to the optimizer.
**Datatype:** float.
Default: `3e-4`. +| `model_kwargs` | Parameters to be passed to the model class.
**Datatype:** dict.
Default: `{}`. +| `trainer_kwargs` | Parameters to be passed to the trainer class.
**Datatype:** dict.
Default: `{}`. + +#### trainer_kwargs + +| Parameter | Description | +|--------------|-------------| +| | **Model training parameters within the `freqai.model_training_parameters.model_kwargs` sub dictionary** +| `n_epochs` | The `n_epochs` parameter is a crucial setting in the PyTorch training loop that determines the number of times the entire training dataset will be used to update the model's parameters. An epoch represents one full pass through the entire training dataset. Overrides `n_steps`. Either `n_epochs` or `n_steps` must be set.

**Datatype:** int. optional.
Default: `10`. +| `n_steps` | An alternative way of setting `n_epochs` - the number of training iterations to run. Iteration here refer to the number of times we call `optimizer.step()`. Ignored if `n_epochs` is set. A simplified version of the function:

n_epochs = n_steps / (n_obs / batch_size)

The motivation here is that `n_steps` is easier to optimize and keep stable across different n_obs - the number of data points.

**Datatype:** int. optional.
Default: `None`. +| `batch_size` | The size of the batches to use during training.

**Datatype:** int.
Default: `64`. + + +### Additional parameters + +| Parameter | Description | +|------------|-------------| +| | **Extraneous parameters** +| `freqai.keras` | If the selected model makes use of Keras (typical for TensorFlow-based prediction models), this flag needs to be activated so that the model save/loading follows Keras standards.
**Datatype:** Boolean.
Default: `False`. +| `freqai.conv_width` | The width of a neural network input tensor. This replaces the need for shifting candles (`include_shifted_candles`) by feeding in historical data points as the second dimension of the tensor. Technically, this parameter can also be used for regressors, but it only adds computational overhead and does not change the model training/prediction.
**Datatype:** Integer.
Default: `2`. +| `freqai.reduce_df_footprint` | Recast all numeric columns to float32/int32, with the objective of reducing ram/disk usage and decreasing train/inference timing. This parameter is set in the main level of the Freqtrade configuration file (not inside FreqAI).
**Datatype:** Boolean.
Default: `False`. diff --git a/md/freqai-reinforcement-learning.md b/md/freqai-reinforcement-learning.md new file mode 100644 index 00000000..3b75e6b7 --- /dev/null +++ b/md/freqai-reinforcement-learning.md @@ -0,0 +1,280 @@ +# Reinforcement Learning + +!!! Note "Installation size" + Reinforcement learning dependencies include large packages such as `torch`, which should be explicitly requested during `./setup.sh -i` by answering "y" to the question "Do you also want dependencies for freqai-rl (~700mb additional space required) [y/N]?". + Users who prefer docker should ensure they use the docker image appended with `_freqairl`. + +## Background and terminology + +### What is RL and why does FreqAI need it? + +Reinforcement learning involves two important components, the *agent* and the training *environment*. During agent training, the agent moves through historical data candle by candle, always making 1 of a set of actions: Long entry, long exit, short entry, short exit, neutral). During this training process, the environment tracks the performance of these actions and rewards the agent according to a custom user made `calculate_reward()` (here we offer a default reward for users to build on if they wish [details here](#creating-a-custom-reward-function)). The reward is used to train weights in a neural network. + +A second important component of the FreqAI RL implementation is the use of *state* information. State information is fed into the network at each step, including current profit, current position, and current trade duration. These are used to train the agent in the training environment, and to reinforce the agent in dry/live (this functionality is not available in backtesting). *FreqAI + Freqtrade is a perfect match for this reinforcing mechanism since this information is readily available in live deployments.* + +Reinforcement learning is a natural progression for FreqAI, since it adds a new layer of adaptivity and market reactivity that Classifiers and Regressors cannot match. However, Classifiers and Regressors have strengths that RL does not have such as robust predictions. Improperly trained RL agents may find "cheats" and "tricks" to maximize reward without actually winning any trades. For this reason, RL is more complex and demands a higher level of understanding than typical Classifiers and Regressors. + +### The RL interface + +With the current framework, we aim to expose the training environment via the common "prediction model" file, which is a user inherited `BaseReinforcementLearner` object (e.g. `freqai/prediction_models/ReinforcementLearner`). Inside this user class, the RL environment is available and customized via `MyRLEnv` as [shown below](#creating-a-custom-reward-function). + +We envision the majority of users focusing their effort on creative design of the `calculate_reward()` function [details here](#creating-a-custom-reward-function), while leaving the rest of the environment untouched. Other users may not touch the environment at all, and they will only play with the configuration settings and the powerful feature engineering that already exists in FreqAI. Meanwhile, we enable advanced users to create their own model classes entirely. + +The framework is built on stable_baselines3 (torch) and OpenAI gym for the base environment class. But generally speaking, the model class is well isolated. Thus, the addition of competing libraries can be easily integrated into the existing framework. For the environment, it is inheriting from `gym.Env` which means that it is necessary to write an entirely new environment in order to switch to a different library. + +### Important considerations + +As explained above, the agent is "trained" in an artificial trading "environment". In our case, that environment may seem quite similar to a real Freqtrade backtesting environment, but it is *NOT*. In fact, the RL training environment is much more simplified. It does not incorporate any of the complicated strategy logic, such as callbacks like `custom_exit`, `custom_stoploss`, leverage controls, etc. The RL environment is instead a very "raw" representation of the true market, where the agent has free will to learn the policy (read: stoploss, take profit, etc.) which is enforced by the `calculate_reward()`. Thus, it is important to consider that the agent training environment is not identical to the real world. + +## Running Reinforcement Learning + +Setting up and running a Reinforcement Learning model is the same as running a Regressor or Classifier. The same two flags, `--freqaimodel` and `--strategy`, must be defined on the command line: + +```bash +freqtrade trade --freqaimodel ReinforcementLearner --strategy MyRLStrategy --config config.json +``` + +where `ReinforcementLearner` will use the templated `ReinforcementLearner` from `freqai/prediction_models/ReinforcementLearner` (or a custom user defined one located in `user_data/freqaimodels`). The strategy, on the other hand, follows the same base [feature engineering](freqai-feature-engineering.md) with `feature_engineering_*` as a typical Regressor. The difference lies in the creation of the targets, Reinforcement Learning doesn't require them. However, FreqAI requires a default (neutral) value to be set in the action column: + +```python + def set_freqai_targets(self, dataframe, **kwargs) -> DataFrame: + """ + *Only functional with FreqAI enabled strategies* + Required function to set the targets for the model. + All targets must be prepended with `&` to be recognized by the FreqAI internals. + + More details about feature engineering available: + + https://www.freqtrade.io/en/latest/freqai-feature-engineering + + :param df: strategy dataframe which will receive the targets + usage example: dataframe["&-target"] = dataframe["close"].shift(-1) / dataframe["close"] + """ + # For RL, there are no direct targets to set. This is filler (neutral) + # until the agent sends an action. + dataframe["&-action"] = 0 + return dataframe +``` + +Most of the function remains the same as for typical Regressors, however, the function below shows how the strategy must pass the raw price data to the agent so that it has access to raw OHLCV in the training environment: + +```python + def feature_engineering_standard(self, dataframe: DataFrame, **kwargs) -> DataFrame: + # The following features are necessary for RL models + dataframe[f"%-raw_close"] = dataframe["close"] + dataframe[f"%-raw_open"] = dataframe["open"] + dataframe[f"%-raw_high"] = dataframe["high"] + dataframe[f"%-raw_low"] = dataframe["low"] + return dataframe +``` + +Finally, there is no explicit "label" to make - instead it is necessary to assign the `&-action` column which will contain the agent's actions when accessed in `populate_entry/exit_trends()`. In the present example, the neutral action to 0. This value should align with the environment used. FreqAI provides two environments, both use 0 as the neutral action. + +After users realize there are no labels to set, they will soon understand that the agent is making its "own" entry and exit decisions. This makes strategy construction rather simple. The entry and exit signals come from the agent in the form of an integer - which are used directly to decide entries and exits in the strategy: + +```python + def populate_entry_trend(self, df: DataFrame, metadata: dict) -> DataFrame: + + enter_long_conditions = [df["do_predict"] == 1, df["&-action"] == 1] + + if enter_long_conditions: + df.loc[ + reduce(lambda x, y: x & y, enter_long_conditions), ["enter_long", "enter_tag"] + ] = (1, "long") + + enter_short_conditions = [df["do_predict"] == 1, df["&-action"] == 3] + + if enter_short_conditions: + df.loc[ + reduce(lambda x, y: x & y, enter_short_conditions), ["enter_short", "enter_tag"] + ] = (1, "short") + + return df + + def populate_exit_trend(self, df: DataFrame, metadata: dict) -> DataFrame: + exit_long_conditions = [df["do_predict"] == 1, df["&-action"] == 2] + if exit_long_conditions: + df.loc[reduce(lambda x, y: x & y, exit_long_conditions), "exit_long"] = 1 + + exit_short_conditions = [df["do_predict"] == 1, df["&-action"] == 4] + if exit_short_conditions: + df.loc[reduce(lambda x, y: x & y, exit_short_conditions), "exit_short"] = 1 + + return df +``` + +It is important to consider that `&-action` depends on which environment they choose to use. The example above shows 5 actions, where 0 is neutral, 1 is enter long, 2 is exit long, 3 is enter short and 4 is exit short. + +## Configuring the Reinforcement Learner + +In order to configure the `Reinforcement Learner` the following dictionary must exist in the `freqai` config: + +```json + "rl_config": { + "train_cycles": 25, + "add_state_info": true, + "max_trade_duration_candles": 300, + "max_training_drawdown_pct": 0.02, + "cpu_count": 8, + "model_type": "PPO", + "policy_type": "MlpPolicy", + "model_reward_parameters": { + "rr": 1, + "profit_aim": 0.025 + } + } +``` + +Parameter details can be found [here](freqai-parameter-table.md), but in general the `train_cycles` decides how many times the agent should cycle through the candle data in its artificial environment to train weights in the model. `model_type` is a string which selects one of the available models in [stable_baselines](https://stable-baselines3.readthedocs.io/en/master/)(external link). + +!!! Note + If you would like to experiment with `continual_learning`, then you should set that value to `true` in the main `freqai` configuration dictionary. This will tell the Reinforcement Learning library to continue training new models from the final state of previous models, instead of retraining new models from scratch each time a retrain is initiated. + +!!! Note + Remember that the general `model_training_parameters` dictionary should contain all the model hyperparameter customizations for the particular `model_type`. For example, `PPO` parameters can be found [here](https://stable-baselines3.readthedocs.io/en/master/modules/ppo.html). + +## Creating a custom reward function + +!!! danger "Not for production" + Warning! + The reward function provided with the Freqtrade source code is a showcase of functionality designed to show/test as many possible environment control features as possible. It is also designed to run quickly on small computers. This is a benchmark, it is *not* for live production. Please beware that you will need to create your own custom_reward() function or use a template built by other users outside of the Freqtrade source code. + +As you begin to modify the strategy and the prediction model, you will quickly realize some important differences between the Reinforcement Learner and the Regressors/Classifiers. Firstly, the strategy does not set a target value (no labels!). Instead, you set the `calculate_reward()` function inside the `MyRLEnv` class (see below). A default `calculate_reward()` is provided inside `prediction_models/ReinforcementLearner.py` to demonstrate the necessary building blocks for creating rewards, but this is *not* designed for production. Users *must* create their own custom reinforcement learning model class or use a pre-built one from outside the Freqtrade source code and save it to `user_data/freqaimodels`. It is inside the `calculate_reward()` where creative theories about the market can be expressed. For example, you can reward your agent when it makes a winning trade, and penalize the agent when it makes a losing trade. Or perhaps, you wish to reward the agent for entering trades, and penalize the agent for sitting in trades too long. Below we show examples of how these rewards are all calculated: + +!!! note "Hint" + The best reward functions are ones that are continuously differentiable, and well scaled. In other words, adding a single large negative penalty to a rare event is not a good idea, and the neural net will not be able to learn that function. Instead, it is better to add a small negative penalty to a common event. This will help the agent learn faster. Not only this, but you can help improve the continuity of your rewards/penalties by having them scale with severity according to some linear/exponential functions. In other words, you'd slowly scale the penalty as the duration of the trade increases. This is better than a single large penalty occurring at a single point in time. + +```python +from freqtrade.freqai.prediction_models.ReinforcementLearner import ReinforcementLearner +from freqtrade.freqai.RL.Base5ActionRLEnv import Actions, Base5ActionRLEnv, Positions + + +class MyCoolRLModel(ReinforcementLearner): + """ + User created RL prediction model. + + Save this file to `freqtrade/user_data/freqaimodels` + + then use it with: + + freqtrade trade --freqaimodel MyCoolRLModel --config config.json --strategy SomeCoolStrat + + Here the users can override any of the functions + available in the `IFreqaiModel` inheritance tree. Most importantly for RL, this + is where the user overrides `MyRLEnv` (see below), to define custom + `calculate_reward()` function, or to override any other parts of the environment. + + This class also allows users to override any other part of the IFreqaiModel tree. + For example, the user can override `def fit()` or `def train()` or `def predict()` + to take fine-tuned control over these processes. + + Another common override may be `def data_cleaning_predict()` where the user can + take fine-tuned control over the data handling pipeline. + """ + class MyRLEnv(Base5ActionRLEnv): + """ + User made custom environment. This class inherits from BaseEnvironment and gym.Env. + Users can override any functions from those parent classes. Here is an example + of a user customized `calculate_reward()` function. + + Warning! + This is function is a showcase of functionality designed to show as many possible + environment control features as possible. It is also designed to run quickly + on small computers. This is a benchmark, it is *not* for live production. + """ + def calculate_reward(self, action: int) -> float: + # first, penalize if the action is not valid + if not self._is_valid(action): + return -2 + pnl = self.get_unrealized_profit() + + factor = 100 + + pair = self.pair.replace(':', '') + + # you can use feature values from dataframe + # Assumes the shifted RSI indicator has been generated in the strategy. + rsi_now = self.raw_features[f"%-rsi-period_10_shift-1_{pair}_" + f"{self.config['timeframe']}"].iloc[self._current_tick] + + # reward agent for entering trades + if (action in (Actions.Long_enter.value, Actions.Short_enter.value) + and self._position == Positions.Neutral): + if rsi_now < 40: + factor = 40 / rsi_now + else: + factor = 1 + return 25 * factor + + # discourage agent from not entering trades + if action == Actions.Neutral.value and self._position == Positions.Neutral: + return -1 + max_trade_duration = self.rl_config.get('max_trade_duration_candles', 300) + trade_duration = self._current_tick - self._last_trade_tick + if trade_duration <= max_trade_duration: + factor *= 1.5 + elif trade_duration > max_trade_duration: + factor *= 0.5 + # discourage sitting in position + if self._position in (Positions.Short, Positions.Long) and \ + action == Actions.Neutral.value: + return -1 * trade_duration / max_trade_duration + # close long + if action == Actions.Long_exit.value and self._position == Positions.Long: + if pnl > self.profit_aim * self.rr: + factor *= self.rl_config['model_reward_parameters'].get('win_reward_factor', 2) + return float(pnl * factor) + # close short + if action == Actions.Short_exit.value and self._position == Positions.Short: + if pnl > self.profit_aim * self.rr: + factor *= self.rl_config['model_reward_parameters'].get('win_reward_factor', 2) + return float(pnl * factor) + return 0. +``` + +## Using Tensorboard + +Reinforcement Learning models benefit from tracking training metrics. FreqAI has integrated Tensorboard to allow users to track training and evaluation performance across all coins and across all retrainings. Tensorboard is activated via the following command: + +```bash +tensorboard --logdir user_data/models/unique-id +``` + +where `unique-id` is the `identifier` set in the `freqai` configuration file. This command must be run in a separate shell to view the output in the browser at 127.0.0.1:6006 (6006 is the default port used by Tensorboard). + +![tensorboard](assets/tensorboard.jpg) + +## Custom logging + +FreqAI also provides a built in episodic summary logger called `self.tensorboard_log` for adding custom information to the Tensorboard log. By default, this function is already called once per step inside the environment to record the agent actions. All values accumulated for all steps in a single episode are reported at the conclusion of each episode, followed by a full reset of all metrics to 0 in preparation for the subsequent episode. + +`self.tensorboard_log` can also be used anywhere inside the environment, for example, it can be added to the `calculate_reward` function to collect more detailed information about how often various parts of the reward were called: + +```python + class MyRLEnv(Base5ActionRLEnv): + """ + User made custom environment. This class inherits from BaseEnvironment and gym.Env. + Users can override any functions from those parent classes. Here is an example + of a user customized `calculate_reward()` function. + """ + def calculate_reward(self, action: int) -> float: + if not self._is_valid(action): + self.tensorboard_log("invalid") + return -2 + +``` + +!!! Note + The `self.tensorboard_log()` function is designed for tracking incremented objects only i.e. events, actions inside the training environment. If the event of interest is a float, the float can be passed as the second argument e.g. `self.tensorboard_log("float_metric1", 0.23)`. In this case the metric values are not incremented. + +## Choosing a base environment + +FreqAI provides three base environments, `Base3ActionRLEnvironment`, `Base4ActionEnvironment` and `Base5ActionEnvironment`. As the names imply, the environments are customized for agents that can select from 3, 4 or 5 actions. The `Base3ActionEnvironment` is the simplest, the agent can select from hold, long, or short. This environment can also be used for long-only bots (it automatically follows the `can_short` flag from the strategy), where long is the enter condition and short is the exit condition. Meanwhile, in the `Base4ActionEnvironment`, the agent can enter long, enter short, hold neutral, or exit position. Finally, in the `Base5ActionEnvironment`, the agent has the same actions as Base4, but instead of a single exit action, it separates exit long and exit short. The main changes stemming from the environment selection include: + +* the actions available in the `calculate_reward` +* the actions consumed by the user strategy + +All of the FreqAI provided environments inherit from an action/position agnostic environment object called the `BaseEnvironment`, which contains all shared logic. The architecture is designed to be easily customized. The simplest customization is the `calculate_reward()` (see details [here](#creating-a-custom-reward-function)). However, the customizations can be further extended into any of the functions inside the environment. You can do this by simply overriding those functions inside your `MyRLEnv` in the prediction model file. Or for more advanced customizations, it is encouraged to create an entirely new environment inherited from `BaseEnvironment`. + +!!! Note + Only the `Base3ActionRLEnv` can do long-only training/trading (set the user strategy attribute `can_short = False`). diff --git a/md/freqai-running.md b/md/freqai-running.md new file mode 100644 index 00000000..d506ac3c --- /dev/null +++ b/md/freqai-running.md @@ -0,0 +1,187 @@ +# Running FreqAI + +There are two ways to train and deploy an adaptive machine learning model - live deployment and historical backtesting. In both cases, FreqAI runs/simulates periodic retraining of models as shown in the following figure: + +![freqai-window](assets/freqai_moving-window.jpg) + +## Live deployments + +FreqAI can be run dry/live using the following command: + +```bash +freqtrade trade --strategy FreqaiExampleStrategy --config config_freqai.example.json --freqaimodel LightGBMRegressor +``` + +When launched, FreqAI will start training a new model, with a new `identifier`, based on the config settings. Following training, the model will be used to make predictions on incoming candles until a new model is available. New models are typically generated as often as possible, with FreqAI managing an internal queue of the coin pairs to try to keep all models equally up to date. FreqAI will always use the most recently trained model to make predictions on incoming live data. If you do not want FreqAI to retrain new models as often as possible, you can set `live_retrain_hours` to tell FreqAI to wait at least that number of hours before training a new model. Additionally, you can set `expired_hours` to tell FreqAI to avoid making predictions on models that are older than that number of hours. + +Trained models are by default saved to disk to allow for reuse during backtesting or after a crash. You can opt to [purge old models](#purging-old-model-data) to save disk space by setting `"purge_old_models": true` in the config. + +To start a dry/live run from a saved backtest model (or from a previously crashed dry/live session), you only need to specify the `identifier` of the specific model: + +```json + "freqai": { + "identifier": "example", + "live_retrain_hours": 0.5 + } +``` + +In this case, although FreqAI will initiate with a pre-trained model, it will still check to see how much time has elapsed since the model was trained. If a full `live_retrain_hours` has elapsed since the end of the loaded model, FreqAI will start training a new model. + +### Automatic data download + +FreqAI automatically downloads the proper amount of data needed to ensure training of a model through the defined `train_period_days` and `startup_candle_count` (see the [parameter table](freqai-parameter-table.md) for detailed descriptions of these parameters). + +### Saving prediction data + +All predictions made during the lifetime of a specific `identifier` model are stored in `historic_predictions.pkl` to allow for reloading after a crash or changes made to the config. + +### Purging old model data + +FreqAI stores new model files after each successful training. These files become obsolete as new models are generated to adapt to new market conditions. If you are planning to leave FreqAI running for extended periods of time with high frequency retraining, you should enable `purge_old_models` in the config: + +```json + "freqai": { + "purge_old_models": 4, + } +``` + +This will automatically purge all models older than the four most recently trained ones to save disk space. Inputing "0" will never purge any models. + +## Backtesting + +The FreqAI backtesting module can be executed with the following command: + +```bash +freqtrade backtesting --strategy FreqaiExampleStrategy --strategy-path freqtrade/templates --config config_examples/config_freqai.example.json --freqaimodel LightGBMRegressor --timerange 20210501-20210701 +``` + +If this command has never been executed with the existing config file, FreqAI will train a new model +for each pair, for each backtesting window within the expanded `--timerange`. + +Backtesting mode requires [downloading the necessary data](#downloading-data-to-cover-the-full-backtest-period) before deployment (unlike in dry/live mode where FreqAI handles the data downloading automatically). You should be careful to consider that the time range of the downloaded data is more than the backtesting time range. This is because FreqAI needs data prior to the desired backtesting time range in order to train a model to be ready to make predictions on the first candle of the set backtesting time range. More details on how to calculate the data to download can be found [here](#deciding-the-size-of-the-sliding-training-window-and-backtesting-duration). + +!!! Note "Model reuse" + Once the training is completed, you can execute the backtesting again with the same config file and + FreqAI will find the trained models and load them instead of spending time training. This is useful + if you want to tweak (or even hyperopt) buy and sell criteria inside the strategy. If you + *want* to retrain a new model with the same config file, you should simply change the `identifier`. + This way, you can return to using any model you wish by simply specifying the `identifier`. + +!!! Note + Backtesting calls `set_freqai_targets()` one time for each backtest window (where the number of windows is the full backtest timerange divided by the `backtest_period_days` parameter). Doing this means that the targets simulate dry/live behavior without look ahead bias. However, the definition of the features in `feature_engineering_*()` is performed once on the entire training timerange. This means that you should be sure that features do not look-ahead into the future. + More details about look-ahead bias can be found in [Common Mistakes](strategy-customization.md#common-mistakes-when-developing-strategies). + +--- + +### Saving backtesting prediction data + +To allow for tweaking your strategy (**not** the features!), FreqAI will automatically save the predictions during backtesting so that they can be reused for future backtests and live runs using the same `identifier` model. This provides a performance enhancement geared towards enabling **high-level hyperopting** of entry/exit criteria. + +An additional directory called `backtesting_predictions`, which contains all the predictions stored in `feather` format, will be created in the `unique-id` folder. + +To change your **features**, you **must** set a new `identifier` in the config to signal to FreqAI to train new models. + +To save the models generated during a particular backtest so that you can start a live deployment from one of them instead of training a new model, you must set `save_backtest_models` to `True` in the config. + +!!! Note + To ensure that the model can be reused, freqAI will call your strategy with a dataframe of length 1. + If your strategy requires more data than this to generate the same features, you can't reuse backtest predictions for live deployment and need to update your `identifier` for each new backtest. + +### Backtest live collected predictions + +FreqAI allow you to reuse live historic predictions through the backtest parameter `--freqai-backtest-live-models`. This can be useful when you want to reuse predictions generated in dry/run for comparison or other study. + +The `--timerange` parameter must not be informed, as it will be automatically calculated through the data in the historic predictions file. + +### Downloading data to cover the full backtest period + +For live/dry deployments, FreqAI will download the necessary data automatically. However, to use backtesting functionality, you need to download the necessary data using `download-data` (details [here](data-download.md#data-downloading)). You need to pay careful attention to understanding how much *additional* data needs to be downloaded to ensure that there is a sufficient amount of training data *before* the start of the backtesting time range. The amount of additional data can be roughly estimated by moving the start date of the time range backwards by `train_period_days` and the `startup_candle_count` (see the [parameter table](freqai-parameter-table.md) for detailed descriptions of these parameters) from the beginning of the desired backtesting time range. + +As an example, to backtest the `--timerange 20210501-20210701` using the [example config](freqai-configuration.md#setting-up-the-configuration-file) which sets `train_period_days` to 30, together with `startup_candle_count: 40` on a maximum `include_timeframes` of 1h, the start date for the downloaded data needs to be `20210501` - 30 days - 40 * 1h / 24 hours = 20210330 (31.7 days earlier than the start of the desired training time range). + +### Deciding the size of the sliding training window and backtesting duration + +The backtesting time range is defined with the typical `--timerange` parameter in the configuration file. The duration of the sliding training window is set by `train_period_days`, whilst `backtest_period_days` is the sliding backtesting window, both in number of days (`backtest_period_days` can be +a float to indicate sub-daily retraining in live/dry mode). In the presented [example config](freqai-configuration.md#setting-up-the-configuration-file) (found in `config_examples/config_freqai.example.json`), the user is asking FreqAI to use a training period of 30 days and backtest on the subsequent 7 days. After the training of the model, FreqAI will backtest the subsequent 7 days. The "sliding window" then moves one week forward (emulating FreqAI retraining once per week in live mode) and the new model uses the previous 30 days (including the 7 days used for backtesting by the previous model) to train. This is repeated until the end of `--timerange`. This means that if you set `--timerange 20210501-20210701`, FreqAI will have trained 8 separate models at the end of `--timerange` (because the full range comprises 8 weeks). + +!!! Note + Although fractional `backtest_period_days` is allowed, you should be aware that the `--timerange` is divided by this value to determine the number of models that FreqAI will need to train in order to backtest the full range. For example, by setting a `--timerange` of 10 days, and a `backtest_period_days` of 0.1, FreqAI will need to train 100 models per pair to complete the full backtest. Because of this, a true backtest of FreqAI adaptive training would take a *very* long time. The best way to fully test a model is to run it dry and let it train constantly. In this case, backtesting would take the exact same amount of time as a dry run. + +## Defining model expirations + +During dry/live mode, FreqAI trains each coin pair sequentially (on separate threads/GPU from the main Freqtrade bot). This means that there is always an age discrepancy between models. If you are training on 50 pairs, and each pair requires 5 minutes to train, the oldest model will be over 4 hours old. This may be undesirable if the characteristic time scale (the trade duration target) for a strategy is less than 4 hours. You can decide to only make trade entries if the model is less than a certain number of hours old by setting the `expiration_hours` in the config file: + +```json + "freqai": { + "expiration_hours": 0.5, + } +``` + +In the presented example config, the user will only allow predictions on models that are less than 1/2 hours old. + +## Controlling the model learning process + +Model training parameters are unique to the selected machine learning library. FreqAI allows you to set any parameter for any library using the `model_training_parameters` dictionary in the config. The example config (found in `config_examples/config_freqai.example.json`) shows some of the example parameters associated with `Catboost` and `LightGBM`, but you can add any parameters available in those libraries or any other machine learning library you choose to implement. + +Data split parameters are defined in `data_split_parameters` which can be any parameters associated with scikit-learn's `train_test_split()` function. `train_test_split()` has a parameters called `shuffle` which allows to shuffle the data or keep it unshuffled. This is particularly useful to avoid biasing training with temporally auto-correlated data. More details about these parameters can be found the [scikit-learn website](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html) (external website). + +The FreqAI specific parameter `label_period_candles` defines the offset (number of candles into the future) used for the `labels`. In the presented [example config](freqai-configuration.md#setting-up-the-configuration-file), the user is asking for `labels` that are 24 candles in the future. + +## Continual learning + +You can choose to adopt a continual learning scheme by setting `"continual_learning": true` in the config. By enabling `continual_learning`, after training an initial model from scratch, subsequent trainings will start from the final model state of the preceding training. This gives the new model a "memory" of the previous state. By default, this is set to `False` which means that all new models are trained from scratch, without input from previous models. + +???+ danger "Continual learning enforces a constant parameter space" + Since `continual_learning` means that the model parameter space *cannot* change between trainings, `principal_component_analysis` is automatically disabled when `continual_learning` is enabled. Hint: PCA changes the parameter space and the number of features, learn more about PCA [here](freqai-feature-engineering.md#data-dimensionality-reduction-with-principal-component-analysis). + +???+ danger "Experimental functionality" + Beware that this is currently a naive approach to incremental learning, and it has a high probability of overfitting/getting stuck in local minima while the market moves away from your model. We have the mechanics available in FreqAI primarily for experimental purposes and so that it is ready for more mature approaches to continual learning in chaotic systems like the crypto market. + +## Hyperopt + +You can hyperopt using the same command as for [typical Freqtrade hyperopt](hyperopt.md): + +```bash +freqtrade hyperopt --hyperopt-loss SharpeHyperOptLoss --strategy FreqaiExampleStrategy --freqaimodel LightGBMRegressor --strategy-path freqtrade/templates --config config_examples/config_freqai.example.json --timerange 20220428-20220507 +``` + +`hyperopt` requires you to have the data pre-downloaded in the same fashion as if you were doing [backtesting](#backtesting). In addition, you must consider some restrictions when trying to hyperopt FreqAI strategies: + +- The `--analyze-per-epoch` hyperopt parameter is not compatible with FreqAI. +- It's not possible to hyperopt indicators in the `feature_engineering_*()` and `set_freqai_targets()` functions. This means that you cannot optimize model parameters using hyperopt. Apart from this exception, it is possible to optimize all other [spaces](hyperopt.md#running-hyperopt-with-smaller-search-space). +- The backtesting instructions also apply to hyperopt. + +The best method for combining hyperopt and FreqAI is to focus on hyperopting entry/exit thresholds/criteria. You need to focus on hyperopting parameters that are not used in your features. For example, you should not try to hyperopt rolling window lengths in the feature creation, or any part of the FreqAI config which changes predictions. In order to efficiently hyperopt the FreqAI strategy, FreqAI stores predictions as dataframes and reuses them. Hence the requirement to hyperopt entry/exit thresholds/criteria only. + +A good example of a hyperoptable parameter in FreqAI is a threshold for the [Dissimilarity Index (DI)](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di) `DI_values` beyond which we consider data points as outliers: + +```python +di_max = IntParameter(low=1, high=20, default=10, space='buy', optimize=True, load=True) +dataframe['outlier'] = np.where(dataframe['DI_values'] > self.di_max.value/10, 1, 0) +``` + +This specific hyperopt would help you understand the appropriate `DI_values` for your particular parameter space. + +## Using Tensorboard + +!!! note "Availability" + FreqAI includes tensorboard for a variety of models, including XGBoost, all PyTorch models, Reinforcement Learning, and Catboost. If you would like to see Tensorboard integrated into another model type, please open an issue on the [Freqtrade GitHub](https://github.com/freqtrade/freqtrade/issues) + +!!! danger "Requirements" + Tensorboard logging requires the FreqAI torch installation/docker image. + + +The easiest way to use tensorboard is to ensure `freqai.activate_tensorboard` is set to `True` (default setting) in your configuration file, run FreqAI, then open a separate shell and run: + +```bash +cd freqtrade +tensorboard --logdir user_data/models/unique-id +``` + +where `unique-id` is the `identifier` set in the `freqai` configuration file. This command must be run in a separate shell if you wish to view the output in your browser at 127.0.0.1:6060 (6060 is the default port used by Tensorboard). + +![tensorboard](assets/tensorboard.jpg) + + +!!! note "Deactivate for improved performance" + Tensorboard logging can slow down training and should be deactivated for production use. diff --git a/md/freqai.md b/md/freqai.md new file mode 100644 index 00000000..cda8efe1 --- /dev/null +++ b/md/freqai.md @@ -0,0 +1,141 @@ +![freqai-logo](assets/freqai_doc_logo.svg) + +# FreqAI + +## Introduction + +FreqAI is a software designed to automate a variety of tasks associated with training a predictive machine learning model to generate market forecasts given a set of input signals. In general, FreqAI aims to be a sandbox for easily deploying robust machine learning libraries on real-time data ([details](#freqai-position-in-open-source-machine-learning-landscape)). + +!!! Note + FreqAI is, and always will be, a not-for-profit, open-source project. FreqAI does *not* have a crypto token, FreqAI does *not* sell signals, and FreqAI does not have a domain besides the present [freqtrade documentation](https://www.freqtrade.io/en/latest/freqai/). + +Features include: + +* **Self-adaptive retraining** - Retrain models during [live deployments](freqai-running.md#live-deployments) to self-adapt to the market in a supervised manner +* **Rapid feature engineering** - Create large rich [feature sets](freqai-feature-engineering.md#feature-engineering) (10k+ features) based on simple user-created strategies +* **High performance** - Threading allows for adaptive model retraining on a separate thread (or on GPU if available) from model inferencing (prediction) and bot trade operations. Newest models and data are kept in RAM for rapid inferencing +* **Realistic backtesting** - Emulate self-adaptive training on historic data with a [backtesting module](freqai-running.md#backtesting) that automates retraining +* **Extensibility** - The generalized and robust architecture allows for incorporating any [machine learning library/method](freqai-configuration.md#using-different-prediction-models) available in Python. Eight examples are currently available, including classifiers, regressors, and a convolutional neural network +* **Smart outlier removal** - Remove outliers from training and prediction data sets using a variety of [outlier detection techniques](freqai-feature-engineering.md#outlier-detection) +* **Crash resilience** - Store trained models to disk to make reloading from a crash fast and easy, and [purge obsolete files](freqai-running.md#purging-old-model-data) for sustained dry/live runs +* **Automatic data normalization** - [Normalize the data](freqai-feature-engineering.md#building-the-data-pipeline) in a smart and statistically safe way +* **Automatic data download** - Compute timeranges for data downloads and update historic data (in live deployments) +* **Cleaning of incoming data** - Handle NaNs safely before training and model inferencing +* **Dimensionality reduction** - Reduce the size of the training data via [Principal Component Analysis](freqai-feature-engineering.md#data-dimensionality-reduction-with-principal-component-analysis) +* **Deploying bot fleets** - Set one bot to train models while a fleet of [consumers](producer-consumer.md) use signals. + +## Quick start + +The easiest way to quickly test FreqAI is to run it in dry mode with the following command: + +```bash +freqtrade trade --config config_examples/config_freqai.example.json --strategy FreqaiExampleStrategy --freqaimodel LightGBMRegressor --strategy-path freqtrade/templates +``` + +You will see the boot-up process of automatic data downloading, followed by simultaneous training and trading. + +!!! danger "Not for production" + The example strategy provided with the Freqtrade source code is designed for showcasing/testing a wide variety of FreqAI features. It is also designed to run on small computers so that it can be used as a benchmark between developers and users. It is *not* designed to be run in production. + +An example strategy, prediction model, and config to use as a starting points can be found in +`freqtrade/templates/FreqaiExampleStrategy.py`, `freqtrade/freqai/prediction_models/LightGBMRegressor.py`, and +`config_examples/config_freqai.example.json`, respectively. + +## General approach + +You provide FreqAI with a set of custom *base indicators* (the same way as in a [typical Freqtrade strategy](strategy-customization.md)) as well as target values (*labels*). For each pair in the whitelist, FreqAI trains a model to predict the target values based on the input of custom indicators. The models are then consistently retrained, with a predetermined frequency, to adapt to market conditions. FreqAI offers the ability to both backtest strategies (emulating reality with periodic retraining on historic data) and deploy dry/live runs. In dry/live conditions, FreqAI can be set to constant retraining in a background thread to keep models as up to date as possible. + +An overview of the algorithm, explaining the data processing pipeline and model usage, is shown below. + +![freqai-algo](assets/freqai_algo.jpg) + +### Important machine learning vocabulary + +**Features** - the parameters, based on historic data, on which a model is trained. All features for a single candle are stored as a vector. In FreqAI, you build a feature data set from anything you can construct in the strategy. + +**Labels** - the target values that the model is trained toward. Each feature vector is associated with a single label that is defined by you within the strategy. These labels intentionally look into the future and are what you are training the model to be able to predict. + +**Training** - the process of "teaching" the model to match the feature sets to the associated labels. Different types of models "learn" in different ways which means that one might be better than another for a specific application. More information about the different models that are already implemented in FreqAI can be found [here](freqai-configuration.md#using-different-prediction-models). + +**Train data** - a subset of the feature data set that is fed to the model during training to "teach" the model how to predict the targets. This data directly influences weight connections in the model. + +**Test data** - a subset of the feature data set that is used to evaluate the performance of the model after training. This data does not influence nodal weights within the model. + +**Inferencing** - the process of feeding a trained model new unseen data on which it will make a prediction. + +## Install prerequisites + +The normal Freqtrade install process will ask if you wish to install FreqAI dependencies. You should reply "yes" to this question if you wish to use FreqAI. If you did not reply yes, you can manually install these dependencies after the install with: + +``` bash +pip install -r requirements-freqai.txt +``` + +!!! Note + Catboost will not be installed on low-powered arm devices (raspberry), since it does not provide wheels for this platform. + +### Usage with docker + +If you are using docker, a dedicated tag with FreqAI dependencies is available as `:freqai`. As such - you can replace the image line in your docker compose file with `image: freqtradeorg/freqtrade:stable_freqai`. This image contains the regular FreqAI dependencies. Similar to native installs, Catboost will not be available on ARM based devices. If you would like to use PyTorch or Reinforcement learning, you should use the torch or RL tags, `image: freqtradeorg/freqtrade:stable_freqaitorch`, `image: freqtradeorg/freqtrade:stable_freqairl`. + +!!! note "docker-compose-freqai.yml" + We do provide an explicit docker-compose file for this in `docker/docker-compose-freqai.yml` - which can be used via `docker compose -f docker/docker-compose-freqai.yml run ...` - or can be copied to replace the original docker file. This docker-compose file also contains a (disabled) section to enable GPU resources within docker containers. This obviously assumes the system has GPU resources available. + +### FreqAI position in open-source machine learning landscape + +Forecasting chaotic time-series based systems, such as equity/cryptocurrency markets, requires a broad set of tools geared toward testing a wide range of hypotheses. Fortunately, a recent maturation of robust machine learning libraries (e.g. `scikit-learn`) has opened up a wide range of research possibilities. Scientists from a diverse range of fields can now easily prototype their studies on an abundance of established machine learning algorithms. Similarly, these user-friendly libraries enable "citizen scientists" to use their basic Python skills for data exploration. However, leveraging these machine learning libraries on historical and live chaotic data sources can be logistically difficult and expensive. Additionally, robust data collection, storage, and handling presents a disparate challenge. [`FreqAI`](#freqai) aims to provide a generalized and extensible open-sourced framework geared toward live deployments of adaptive modeling for market forecasting. The `FreqAI` framework is effectively a sandbox for the rich world of open-source machine learning libraries. Inside the `FreqAI` sandbox, users find they can combine a wide variety of third-party libraries to test creative hypotheses on a free live 24/7 chaotic data source - cryptocurrency exchange data. + +### Citing FreqAI + +FreqAI is [published in the Journal of Open Source Software](https://joss.theoj.org/papers/10.21105/joss.04864). If you find FreqAI useful in your research, please use the following citation: + +```bibtex +@article{Caulk2022, + doi = {10.21105/joss.04864}, + url = {https://doi.org/10.21105/joss.04864}, + year = {2022}, publisher = {The Open Journal}, + volume = {7}, number = {80}, pages = {4864}, + author = {Robert A. Caulk and Elin Törnquist and Matthias Voppichler and Andrew R. Lawless and Ryan McMullan and Wagner Costa Santos and Timothy C. Pogue and Johan van der Vlugt and Stefan P. Gehring and Pascal Schmidt}, + title = {FreqAI: generalizing adaptive modeling for chaotic time-series market forecasts}, + journal = {Journal of Open Source Software} } +``` + +## Common pitfalls + +FreqAI cannot be combined with dynamic `VolumePairlists` (or any pairlist filter that adds and removes pairs dynamically). +This is for performance reasons - FreqAI relies on making quick predictions/retrains. To do this effectively, +it needs to download all the training data at the beginning of a dry/live instance. FreqAI stores and appends +new candles automatically for future retrains. This means that if new pairs arrive later in the dry run due to a volume pairlist, it will not have the data ready. However, FreqAI does work with the `ShufflePairlist` or a `VolumePairlist` which keeps the total pairlist constant (but reorders the pairs according to volume). + +## Additional learning materials + +Here we compile some external materials that provide deeper looks into various components of FreqAI: + +- [Real-time head-to-head: Adaptive modeling of financial market data using XGBoost and CatBoost](https://emergentmethods.medium.com/real-time-head-to-head-adaptive-modeling-of-financial-market-data-using-xgboost-and-catboost-995a115a7495) +- [FreqAI - from price to prediction](https://emergentmethods.medium.com/freqai-from-price-to-prediction-6fadac18b665) + + +## Support + +You can find support for FreqAI in a variety of places, including the [Freqtrade discord](https://discord.gg/Jd8JYeWHc4), the dedicated [FreqAI discord](https://discord.gg/7AMWACmbjT), and in [github issues](https://github.com/freqtrade/freqtrade/issues). + +## Credits + +FreqAI is developed by a group of individuals who all contribute specific skillsets to the project. + +Conception and software development: +Robert Caulk @robcaulk + +Theoretical brainstorming and data analysis: +Elin Törnquist @th0rntwig + +Code review and software architecture brainstorming: +@xmatthias + +Software development: +Wagner Costa @wagnercosta +Emre Suzen @aemr3 +Timothy Pogue @wizrds + +Beta testing and bug reporting: +Stefan Gehring @bloodhunter4rc, @longyu, Andrew Lawless @paranoidandy, Pascal Schmidt @smidelis, Ryan McMullan @smarmau, Juha Nykänen @suikula, Johan van der Vlugt @jooopiert, Richárd Józsa @richardjosza diff --git a/docs/hyperopt.md b/md/hyperopt.md similarity index 100% rename from docs/hyperopt.md rename to md/hyperopt.md diff --git a/md/plan.md b/md/plan.md new file mode 100644 index 00000000..1e36beb5 --- /dev/null +++ b/md/plan.md @@ -0,0 +1,536 @@ +### Freqtrade AI 策略设计文档（补充完善版） + +设计目标 + +本策略旨在基于 Freqtrade 平台，设计一个利用 CCXT 绑定 OKX 交易所数据的 AI 交易策略，仅进行多头交易（不做空），使用回归模型进行预测，充分利用 AI 模型优化，确保运行可扩展、可追踪、可评估，代码可维护性强，并通过循序渐进的优化实现稳定持续的盈利预期。具体目标包括： + +1. 充分利用 AI 模型进行优化：基于回归模型，优化多头交易信号生成。 + +2. AI 模型运行可扩展、可追踪、可评估：支持模型切换、版本管理，记录详细性能指标。 + +3. 代码可维护性强：通过模块化设计和抽象接口提高代码可读性和扩展性。 + +4. 循序渐进优化：从简单模型开始，逐步引入复杂特征，最终实现稳定盈利。 + +5. 数据来源专一性（新增）：所有数据通过 CCXT 从 OKX 交易所获取，确保数据一致性和可靠性。 + +6. 仅做多头交易（新增）：策略仅生成买入和持有信号，不涉及卖空操作。 + +7. 回归模型（新增）：使用回归模型预测价格变化或收益率，生成交易信号。 + + +--- + +标签列的明确与初始化 + +标签列分类 + +所有标签列基于 CCXT 从 OKX 交易所获取的数据（如 K 线、成交量、订单簿、资金费率等），分为以下几类： + +目标变量（Target Variables） + +- &-s_close：未来一段时间内价格变化（收盘价差值），用于回归模型训练和预测。 + +- &-roi_0, &-roi_15, &-roi_30：不同时间窗口下的收益率目标值（如 0、15、30 分钟），用于动态设置止盈。 + +- 调整（新增）：移除 &-up_or_down（二分类目标），因回归模型仅需连续值目标。 + + +特征列（Feature Columns） + +- %-%-rsi-period, %-%-macd-period, %-%-bb_width-period：基于 OKX K 线数据的扩展技术指标（如 RSI、MACD、布林带宽度）。 + +- %-%-volume_ma：基于 OKX 成交量的移动平均值，判断市场活跃度。 + +- %-%-order_book_imbalance（新增）：基于 OKX 订单簿数据的买卖盘不平衡特征，反映市场供需。 + +- %-%-funding_rate（新增）：基于 OKX 资金费率数据，反映市场情绪，辅助多头信号生成。 + +- 补充：若 OKX API 支持，可引入链上数据（如链上转账量、活跃地址数），提升特征多样性。 + + +预测结果列（Prediction Columns） + +- do_predict：预测可信度，取值 1（可信）、0（不可信）、-1（异常数据）。 + +- DI_values：Dissimilarity Index（DI）值，识别预测异常点。 + +- &-action：回归模型预测的交易动作（买入或持有），不包含卖空动作。 + + +元数据列（Metadata Columns） + +- &-buy_rsi_pred：动态计算的 RSI 买入阈值，用于生成多头交易条件。 + +- &-stoploss_pred, &-roi_0_pred：动态计算的止损和止盈阈值，优化多头交易策略。 + + +优雅初始化标签列的方法 + +为确保鲁棒性，所有标签列在 set_freqai_targets 方法中初始化，基于 OKX 数据并遵循以下原则： + +统一命名规范 + +- 目标变量以 &- 开头，确保 FreqAI 识别。 + +- 特征列以 %-%- 开头，支持自动扩展。 + +- 预测结果列以 &- 或 %- 开头，确保正确处理。 + + +初始化逻辑清晰 + +- 检查 DataFrame 是否包含 OKX 数据必要列（如 close、volume、order_book、funding_rate），若缺失则抛出异常或填充默认值。 + +- 目标变量（如 &-s_close）基于 OKX K 线未来价格变化计算，符合回归模型要求。 + +- 特征列（如 %-%-rsi-period）通过 feature_engineering_expand_all 扩展，确保基于 OKX 数据生成。 + +- 补充（新增）：验证 OKX 数据时间戳一致性，避免因 API 延迟导致数据错位。 + + +数据清理与填充 + +- 处理 NaN 和 Inf 值，使用 fillna 或 replace 填充缺失值。 + +- 补充（新增）：为 OKX 订单簿或资金费率数据设计备用填充方案（如历史均值），应对数据不可用情况。 + + +日志记录与调试支持 + +- 输出 DataFrame 列名、形状和前几行 OKX 数据，便于调试。 + +- 若某列未生成，抛出异常或记录警告。 + +- 补充（新增）：记录 OKX 数据获取的 API 调用状态（如响应时间、错误码），追踪数据源可靠性。 + + +--- + +增强程序鲁棒性的措施 + +标签列的健壮性校验 + +- 校验关键列（如 &-s_close, &-action）基于 OKX 数据生成，若缺失抛出异常。 + +- 补充（新增）：校验 OKX 数据完整性（如 K 线连续性、订单簿深度），确保特征和目标变量可靠。 + + +特征工程的可扩展性 + +- 通过 feature_engineering_expand_all 和 feature_engineering_expand_basic 扩展 OKX 数据特征，支持多时间周期。 + +- 在配置文件中定义 include_timeframes 和 include_corr_pairlist，控制特征扩展。 + +- 补充（新增）：使用回归模型的特征重要性筛选（如 XGBoost 的 feature importance），减少 OKX 数据衍生特征的冗余，降低过拟合风险。 + + +模型训练与预测的分离 + +- 训练和预测逻辑分离，确保回归模型训练不干扰多头信号生成。 + +- 补充（新增）：缓存 OKX 数据预测结果，优化高频交易场景的计算效率。 + + +模型版本管理与回滚机制 + +- 使用 identifier 区分回归模型版本，确保保存和加载独立。 + +- 若模型表现不佳（如均方误差过大），回滚到上一版本。 + +- 补充（新增）：定义回滚触发条件（如验证集 MSE 超过阈值或夏普比率下降），支持多模型并行比较。 + + +计算效率与资源管理 + +- 优化 OKX 数据处理（如批量加载 K 线、订单簿），减少 CCXT API 调用和计算延迟。 + +- 监控 CPU/GPU 使用率，确保实盘信号生成及时。 + +- 补充（新增）：记录 OKX API 调用频率，遵守交易所速率限制（如每秒请求数）。 + + +--- + +防止未来数据泄露的审核机制 + +特征计算的时序约束 + +- 所有特征基于 OKX 历史数据（如 K 线、订单簿、资金费率），通过 CCXT 获取，避免未来数据。 + +- 在 feature_engineering_expand_all 方法中，校验数据时间戳。 + + +目标变量的时序约束 + +- 目标变量（如 &-s_close）通过 shift(-label_period_candles) 计算，确保基于未来 OKX 数据但不提前使用。 + +- 补充（新增）：审计 OKX 数据时间戳，确保目标变量生成合规。 + + +数据划分的严格控制 + +- 设置 test_size 和 shuffle，确保训练集和测试集基于 OKX 数据合理划分。 + +- 配置 backtest_period_days 和 train_period_days，避免未来数据误用。 + +- 补充（新增）：在实盘中监控 OKX API 数据延迟，防止间接泄露。 + + +回测过程的审计日志 + +- 记录 OKX 数据特征生成、目标变量计算和多头信号生成的时间戳和值。 + +- 补充（新增）：生成 OKX 数据审计报告，定期审查回测合规性。 + + +自动化检测机制 + +- 自动检测 OKX 数据特征和目标变量是否基于历史数据，若发现未来数据，抛出异常。 + +- 补充（新增）：实现 OKX 数据时间戳校验工具，扫描潜在泄露点。 + + +--- + +风险管理与资金管理 + +仓位与资金分配 + +- 动态调整仓位，基于 OKX 市场波动性和账户余额，限制单笔交易风险（如账户资金的 2%）。 + +- 调整（新增）：仅允许多头仓位，禁止杠杆空头交易，符合只做多要求。 + + +止损与止盈 + +- 使用动态止损和止盈（如 &-stoploss_pred, &-roi_0_pred），基于回归模型预测调整。 + +- 补充（新增）：设计分层止损（如硬性止损 + trailing stop），优化多头盈利，防止过早离场。 + + +极端市场事件处理 + +- 针对 OKX 市场异常（如价格闪崩、流动性不足），设计保护机制，如暂停交易或降低仓位。 + +- 补充（新增）：引入市场压力测试，模拟 OKX 市场极端场景，验证策略稳定性。 + + +--- + +外部数据源的可靠性和处理 + +数据源质量控制 + +- 所有数据通过 CCXT 从 OKX 获取，确保一致性。 + +- 对 OKX 订单簿或资金费率数据进行清洗，处理噪声、缺失值或延迟。 + +- 补充（新增）：设计备用数据获取方案（如切换 OKX API 端点），应对 API 不可用情况。 + + +数据源合规性 + +- 确保 OKX 数据使用符合交易所条款和法律法规（如数据隐私）。 + +- 补充（新增）：记录 CCXT API 调用和数据使用日志，便于合规性审计。 + + +--- + +用户交互与监控 + +实时监控 + +- 提供实时监控界面，展示回归模型表现、OKX 数据特征和多头信号。 + +- 设置自动报警机制，在模型异常或 OKX 市场剧变时通知用户。 + + +交互性设计 + +- 允许用户调整参数（如止损阈值、仓位比例），提高策略灵活性。 + +- 补充（新增）：生成每日/每周策略报告，总结 OKX 市场表现、盈利和优化建议。 + + +--- + +法律与合规性 + +- 确保策略符合 OKX 交易所规则和相关法律法规（如加密货币交易合规）。 + +- 记录所有交易和 OKX 数据操作，满足审计要求。 + +- 补充（新增）：定期与合规专家咨询，确保策略适应 OKX 市场监管变化。 + + +--- + +策略设计目标的实现路径 + +充分利用 AI 模型进行优化 + +- 模型选择：选择回归模型，如 XGBoost、LightGBM 或 PyTorch 回归模型，预测 OKX 价格变化或收益率。 + +- 特征工程：基于 OKX 数据，通过 feature_engineering_expand_all 和 feature_engineering_standard 生成丰富特征集。 + +- 模型训练：使用 train_test_split 分割 OKX 数据，通过 model_training_parameters 优化超参数。 + +- 补充（新增）：定期评估回归模型性能，探索深度学习回归模型（如 LSTM）以捕捉 OKX 市场时间序列特征。 + + +AI 模型运行可扩展、可追踪、可评估 + +- 可扩展性：通过 freqai.model_training_parameters 支持回归模型切换。 + +- 可追踪性：使用 identifier 区分模型版本，确保保存和加载独立。 + +- 可评估性：记录均方误差（MSE）、R²、夏普比率、最大回撤等指标，通过 TensorBoard 或日志可视化。 + +- 补充（新增）：在 OKX 市场不同条件下（牛市、熊市、震荡市）测试回归模型，确保适应性。 + + +代码可维护性强 + +- 模块化设计：将 OKX 数据处理、特征工程、回归模型训练、信号生成封装为独立函数或类。 + +- 抽象类与接口：继承 BaseRegressorModel，减少重复代码。 + +- 配置驱动：通过 config.json 配置模型、特征和训练参数。 + +- 补充（新增）：编写 OKX 数据处理和模型训练的文档和测试用例，确保代码易于维护。 + + +循序渐进的优化流程 + +- 初步验证：使用 OKX 数据和简单回归模型（如 XGBoost）验证多头信号逻辑。 + +- 逐步优化：引入复杂特征（如 OKX 订单簿、资金费率）和模型（如 PyTorch 回归）。 + +- 持续监控：通过 OKX 数据回测、模拟盘和实盘运行，调整特征和参数。 + +- 稳定获利：通过多维度测试，确保策略在 OKX 市场条件下 Profitable。 + +- 补充（新增）：设定优化阶段时间表（如初步验证 1 个月，复杂模型引入 3 个月），保持开发节奏。 + + +--- + +配置建议 + +以下是符合策略诉求的 Freqtrade 配置建议，基于 OKX 数据、只做多和回归模型： + +数据源配置 + +- exchange: + 交易所： + + json + + ```json + { + "exchange": { + "name": "okx", + "ccxt_config": { + "enableRateLimit": true, + "rateLimit": 1000 // 遵守 OKX API 速率限制 + } + } + } + ``` + +- pairlists: + pairlists：配对列表 + + - 配置 OKX 交易对（如 BTC/USDT、ETH/USDT），通过 include_corr_pairlist 扩展相关资产。 + + - 示例： + + json + + ```json + { + "pairlists": [ + { + "method": "StaticPairList", + "pairs": ["BTC/USDT", "ETH/USDT"] + } + ] + } + ``` + + +策略配置 + +- freqai: + freqai： + + json + + ```json + { + "freqai": { + "enabled": true, + "identifier": "okx_regression_v1", // 模型版本标识 + "model_training_parameters": { + "model_type": "XGBoost", // 初始回归模型，可切换为 LightGBM 或 PyTorch + "objective": "reg:squarederror", // 回归目标 + "n_estimators": 100, + "learning_rate": 0.05 + }, + "feature_parameters": { + "include_timeframes": ["5m", "15m", "1h"], // OKX K 线时间周期 + "include_corr_pairlist": ["BTC/USDT", "ETH/USDT"], + "feature_engineering": { + "rsi": {"periods": [14, 21]}, + "macd": {"fast": 12, "slow": 26}, + "bb_width": {"period": 20}, + "volume_ma": {"period": 20}, + "order_book_imbalance": {"depth": 10}, // OKX 订单簿特征 + "funding_rate": {} // OKX 资金费率 + } + }, + "data_split_parameters": { + "test_size": 0.2, + "shuffle": false // 防止时间序列数据打乱 + }, + "backtest_period_days": 30, + "train_period_days": 90 + } + } + ``` + + +交易逻辑配置 + +- entry/exit_rules: + 入口/出口规则： + + - 仅生成多头买入信号，基于回归模型预测（如 &-s_close > 阈值）。 + + - 退出信号基于动态止盈（如 &-roi_0_pred）或止损（如 &-stoploss_pred）。 + + - 示例： + + json + + ```json + { + "entry_rules": { + "conditions": [ + {"&-action": "buy"}, // 回归模型预测买入 + {"&-buy_rsi_pred": "> 30"} // RSI 阈值 + ] + }, + "exit_rules": { + "conditions": [ + {"&-roi_0_pred": "reached"}, // 达到止盈 + {"&-stoploss_pred": "triggered"} // 触发止损 + ] + } + } + ``` + + +风险管理配置 + +- stake_amount: + 投注金额： + + - 设置单笔交易风险，如账户余额的 2%。 + + - 示例： + + json + + ```json + { + "stake_amount": "dynamic", + "max_open_trades": 3, + "position_size": "2% of balance" + } + ``` + +- stoploss: + 止损： + + - 配置动态止损，结合 trailing stop。 + + - 示例： + + json + + ```json + { + "stoploss": { + "type": "dynamic", + "value": "&-stoploss_pred", + "trailing_stop": true, + "trailing_stop_positive": 0.01 + } + } + ``` + + +日志与监控配置 + +- logging: + 记录日志： + + json + + ```json + { + "logging": { + "level": "DEBUG", + "logfile": "freqtrade_okx.log", + "freqai_log": { + "feature_generation": true, + "model_performance": true, + "data_source_status": true // 记录 OKX API 状态 + } + } + } + ``` + + +--- + +总结与核心原则 + +本策略围绕以下核心目标展开，全面适配 OKX 数据、只做多和回归模型要求： + +1. 标签列的明确与初始化：基于 OKX 数据，通过 set_freqai_targets 和 feature_engineering_expand_all 初始化标签，涵盖目标变量、特征列、预测结果列和元数据列。 + +2. 程序鲁棒性增强：通过 OKX 数据校验、日志记录、异常处理和依赖管理，确保策略稳定运行。 + +3. 防止未来数据泄露：通过时序约束、OKX 数据划分、审计日志和自动化检测，确保回测和实盘不使用未来数据。 + +4. 风险与资金管理：通过动态止损、仓位管理和极端事件处理，平衡多头盈利与风险。 + +5. 数据源可靠性：确保 OKX 数据通过 CCXT 获取可靠，符合合规性要求。 + +6. 用户交互与监控：提供实时监控和报警机制，提升用户体验。 + +7. 策略可扩展性与可维护性：通过模块化设计、配置驱动和接口抽象，适应长期开发需求。 + +8. 循序渐进优化：从简单回归模型到复杂特征，逐步实现 OKX 市场稳定盈利。 + + +强调的重点 + +- 数据一致性：所有数据来自 OKX，通过 CCXT 确保可靠性和合规性。 + +- 只做多逻辑：严格限制交易信号为买入和持有，避免空头操作。 + +- 回归模型优化：优先回归模型的预测准确性和稳定性，定期评估新模型。 + +- 鲁棒性：在 OKX 数据处理、特征生成和信号生成中加入异常处理。 + +- 全面评估：通过 MSE、夏普比率、最大回撤等指标，验证 OKX 市场盈利能力。 + + +通过以上设计和配置，本策略能够在 OKX 市场环境中实现稳定多头盈利，同时保持高度的灵活性和鲁棒性。未来可根据 OKX 市场变化或新需求，进一步扩展特征或优化回归模型。 + +--- diff --git a/md/strategy-customization.md b/md/strategy-customization.md new file mode 100644 index 00000000..1220db49 --- /dev/null +++ b/md/strategy-customization.md @@ -0,0 +1,1149 @@ +# Strategy Customization + +This page explains how to customize your strategies, add new indicators and set up trading rules. + +If you haven't already, please familiarize yourself with: + +- the [Freqtrade strategy 101](strategy-101.md), which provides a quick start to strategy development +- the [Freqtrade bot basics](bot-basics.md), which provides overall info on how the bot operates + +## Develop your own strategy + +The bot includes a default strategy file. + +Also, several other strategies are available in the [strategy repository](https://github.com/freqtrade/freqtrade-strategies). + +You will however most likely have your own idea for a strategy. + +This document intends to help you convert your ideas into a working strategy. + +### Generating a strategy template + +To get started, you can use the command: + +```bash +freqtrade new-strategy --strategy AwesomeStrategy +``` + +This will create a new strategy called `AwesomeStrategy` from a template, which will be located using the filename `user_data/strategies/AwesomeStrategy.py`. + +!!! Note + There is a difference between the *name* of the strategy and the filename. In most commands, Freqtrade uses the *name* of the strategy, *not the filename*. + +!!! Note + The `new-strategy` command generates starting examples which will not be profitable out of the box. + +??? Hint "Different template levels" + `freqtrade new-strategy` has an additional parameter, `--template`, which controls the amount of pre-build information you get in the created strategy. Use `--template minimal` to get an empty strategy without any indicator examples, or `--template advanced` to get a template with more complicated features defined. + +### Anatomy of a strategy + +A strategy file contains all the information needed to build the strategy logic: + +- Candle data in OHLCV format +- Indicators +- Entry logic + - Signals +- Exit logic + - Signals + - Minimal ROI + - Callbacks ("custom functions") +- Stoploss + - Fixed/absolute + - Trailing + - Callbacks ("custom functions") +- Pricing [optional] +- Position adjustment [optional] + +The bot includes a sample strategy called `SampleStrategy` that you can use as a basis: `user_data/strategies/sample_strategy.py`. +You can test it with the parameter: `--strategy SampleStrategy`. Remember that you use the strategy class name, not the filename. + +Additionally, there is an attribute called `INTERFACE_VERSION`, which defines the version of the strategy interface the bot should use. +The current version is 3 - which is also the default when it's not set explicitly in the strategy. + +You may see older strategies set to interface version 2, and these will need to be updated to v3 terminology as future versions will require this to be set. + +Starting the bot in dry or live mode is accomplished using the `trade` command: + +```bash +freqtrade trade --strategy AwesomeStrategy +``` + +### Bot modes + +Freqtrade strategies can be processed by the Freqtrade bot in 5 main modes: + +- backtesting +- hyperopting +- dry ("forward testing") +- live +- FreqAI (not covered here) + +Check the [configuration documentation](configuration.md) about how to set the bot to dry or live mode. + +**Always use dry mode when testing as this gives you an idea of how your strategy will work in reality without risking capital.** + +## Diving in deeper +**For the following section we will use the [user_data/strategies/sample_strategy.py](https://github.com/freqtrade/freqtrade/blob/develop/freqtrade/templates/sample_strategy.py) +file as reference.** + +!!! Note "Strategies and Backtesting" + To avoid problems and unexpected differences between backtesting and dry/live modes, please be aware + that during backtesting the full time range is passed to the `populate_*()` methods at once. + It is therefore best to use vectorized operations (across the whole dataframe, not loops) and + avoid index referencing (`df.iloc[-1]`), but instead use `df.shift()` to get to the previous candle. + +!!! Warning "Warning: Using future data" + Since backtesting passes the full time range to the `populate_*()` methods, the strategy author + needs to take care to avoid having the strategy utilize data from the future. + Some common patterns for this are listed in the [Common Mistakes](#common-mistakes-when-developing-strategies) section of this document. + +??? Hint "Lookahead and recursive analysis" + Freqtrade includes two helpful commands to help assess common lookahead (using future data) and + recursive bias (variance in indicator values) issues. Before running a strategy in dry or live more, + you should always use these commands first. Please check the relevant documentation for + [lookahead](lookahead-analysis.md) and [recursive](recursive-analysis.md) analysis. + +### Dataframe + +Freqtrade uses [pandas](https://pandas.pydata.org/) to store/provide the candlestick (OHLCV) data. +Pandas is a great library developed for processing large amounts of data in tabular format. + +Each row in a dataframe corresponds to one candle on a chart, with the latest complete candle always being the last in the dataframe (sorted by date). + +If we were to look at the first few rows of the main dataframe using the pandas `head()` function, we would see: + +```output +> dataframe.head() + date open high low close volume +0 2021-11-09 23:25:00+00:00 67279.67 67321.84 67255.01 67300.97 44.62253 +1 2021-11-09 23:30:00+00:00 67300.97 67301.34 67183.03 67187.01 61.38076 +2 2021-11-09 23:35:00+00:00 67187.02 67187.02 67031.93 67123.81 113.42728 +3 2021-11-09 23:40:00+00:00 67123.80 67222.40 67080.33 67160.48 78.96008 +4 2021-11-09 23:45:00+00:00 67160.48 67160.48 66901.26 66943.37 111.39292 +``` + +A dataframe is a table where columns are not single values, but a series of data values. As such, simple python comparisons like the following will not work: + +``` python + if dataframe['rsi'] > 30: + dataframe['enter_long'] = 1 +``` + +The above section will fail with `The truth value of a Series is ambiguous [...]`. + +This must instead be written in a pandas-compatible way, so the operation is performed across the whole dataframe, i.e. `vectorisation`. + +``` python + dataframe.loc[ + (dataframe['rsi'] > 30) + , 'enter_long'] = 1 +``` + +With this section, you have a new column in your dataframe, which has `1` assigned whenever RSI is above 30. + +Freqtrade uses this new column as an entry signal, where it is assumed that a trade will subsequently open on the next open candle. + +Pandas provides fast ways to calculate metrics, i.e. "vectorisation". To benefit from this speed, it is advised to not use loops, but use vectorized methods instead. + +Vectorized operations perform calculations across the whole range of data and are therefore, compared to looping through each row, a lot faster when calculating indicators. + +??? Hint "Signals vs Trades" + - Signals are generated from indicators at candle close, and are intentions to enter a trade. + - Trades are orders that are executed (on the exchange in live mode) where a trade will then open as close to next candle open as possible. + +!!! Warning "Trade order assumptions" + In backtesting, signals are generated on candle close. Trades are then initiated immeditely on next candle open. + + In dry and live, this may be delayed due to all pair dataframes needing to be analysed first, then trade processing + for each of those pairs happens. This means that in dry/live you need to be mindful of having as low a computation + delay as possible, usually by running a low number of pairs and having a CPU with a good clock speed. + +#### Why can't I see "real time" candle data? + +Freqtrade does not store incomplete/unfinished candles in the dataframe. + +The use of incomplete data for making strategy decisions is called "repainting" and you might see other platforms allow this. + +Freqtrade does not. Only complete/finished candle data is available in the dataframe. + +### Customize Indicators + +Entry and exit signals need indicators. You can add more indicators by extending the list contained in the method `populate_indicators()` from your strategy file. + +You should only add the indicators used in either `populate_entry_trend()`, `populate_exit_trend()`, or to populate another indicator, otherwise performance may suffer. + +It's important to always return the dataframe from these three functions without removing/modifying the columns `"open", "high", "low", "close", "volume"`, otherwise these fields would contain something unexpected. + +Sample: + +```python +def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + """ + Adds several different TA indicators to the given DataFrame + + Performance Note: For the best performance be frugal on the number of indicators + you are using. Let uncomment only the indicator you are using in your strategies + or your hyperopt configuration, otherwise you will waste your memory and CPU usage. + :param dataframe: Dataframe with data from the exchange + :param metadata: Additional information, like the currently traded pair + :return: a Dataframe with all mandatory indicators for the strategies + """ + dataframe['sar'] = ta.SAR(dataframe) + dataframe['adx'] = ta.ADX(dataframe) + stoch = ta.STOCHF(dataframe) + dataframe['fastd'] = stoch['fastd'] + dataframe['fastk'] = stoch['fastk'] + dataframe['bb_lower'] = ta.BBANDS(dataframe, nbdevup=2, nbdevdn=2)['lowerband'] + dataframe['sma'] = ta.SMA(dataframe, timeperiod=40) + dataframe['tema'] = ta.TEMA(dataframe, timeperiod=9) + dataframe['mfi'] = ta.MFI(dataframe) + dataframe['rsi'] = ta.RSI(dataframe) + dataframe['ema5'] = ta.EMA(dataframe, timeperiod=5) + dataframe['ema10'] = ta.EMA(dataframe, timeperiod=10) + dataframe['ema50'] = ta.EMA(dataframe, timeperiod=50) + dataframe['ema100'] = ta.EMA(dataframe, timeperiod=100) + dataframe['ao'] = awesome_oscillator(dataframe) + macd = ta.MACD(dataframe) + dataframe['macd'] = macd['macd'] + dataframe['macdsignal'] = macd['macdsignal'] + dataframe['macdhist'] = macd['macdhist'] + hilbert = ta.HT_SINE(dataframe) + dataframe['htsine'] = hilbert['sine'] + dataframe['htleadsine'] = hilbert['leadsine'] + dataframe['plus_dm'] = ta.PLUS_DM(dataframe) + dataframe['plus_di'] = ta.PLUS_DI(dataframe) + dataframe['minus_dm'] = ta.MINUS_DM(dataframe) + dataframe['minus_di'] = ta.MINUS_DI(dataframe) + + # remember to always return the dataframe + return dataframe +``` + +!!! Note "Want more indicator examples?" + Look into the [user_data/strategies/sample_strategy.py](https://github.com/freqtrade/freqtrade/blob/develop/freqtrade/templates/sample_strategy.py). + Then uncomment indicators you need. + +#### Indicator libraries + +Out of the box, freqtrade installs the following technical libraries: + +- [ta-lib](https://ta-lib.github.io/ta-lib-python/) +- [pandas-ta](https://twopirllc.github.io/pandas-ta/) +- [technical](https://technical.freqtrade.io) + +Additional technical libraries can be installed as necessary, or custom indicators may be written / invented by the strategy author. + +### Strategy startup period + +Some indicators have an unstable startup period in which there isn't enough candle data to calculate any values (NaN), or the calculation is incorrect. This can lead to inconsistencies, since Freqtrade does not know how long this unstable period is and uses whatever indicator values are in the dataframe. + +To account for this, the strategy can be assigned the `startup_candle_count` attribute. + +This should be set to the maximum number of candles that the strategy requires to calculate stable indicators. In the case where a user includes higher timeframes with informative pairs, the `startup_candle_count` does not necessarily change. The value is the maximum period (in candles) that any of the informatives timeframes need to compute stable indicators. + +You can use [recursive-analysis](recursive-analysis.md) to check and find the correct `startup_candle_count` to be used. When recursive analysis shows a variance of 0%, then you can be sure that you have enough startup candle data. + +In this example strategy, this should be set to 400 (`startup_candle_count = 400`), since the minimum needed history for ema100 calculation to make sure the value is correct is 400 candles. + +``` python + dataframe['ema100'] = ta.EMA(dataframe, timeperiod=100) +``` + +By letting the bot know how much history is needed, backtest trades can start at the specified timerange during backtesting and hyperopt. + +!!! Warning "Using x calls to get OHLCV" + If you receive a warning like `WARNING - Using 3 calls to get OHLCV. This can result in slower operations for the bot. Please check if you really need 1500 candles for your strategy` - you should consider if you really need this much historic data for your signals. + Having this will cause Freqtrade to make multiple calls for the same pair, which will obviously be slower than one network request. + As a consequence, Freqtrade will take longer to refresh candles - and should therefore be avoided if possible. + This is capped to 5 total calls to avoid overloading the exchange, or make freqtrade too slow. + +!!! Warning + `startup_candle_count` should be below `ohlcv_candle_limit * 5` (which is 500 * 5 for most exchanges) - since only this amount of candles will be available during Dry-Run/Live Trade operations. + +#### Example + +Let's try to backtest 1 month (January 2019) of 5m candles using an example strategy with EMA100, as above. + +``` bash +freqtrade backtesting --timerange 20190101-20190201 --timeframe 5m +``` + +Assuming `startup_candle_count` is set to 400, backtesting knows it needs 400 candles to generate valid entry signals. It will load data from `20190101 - (400 * 5m)` - which is ~2018-12-30 11:40:00. + +If this data is available, indicators will be calculated with this extended timerange. The unstable startup period (up to 2019-01-01 00:00:00) will then be removed before backtesting is carried out. + +!!! Note "Unavailable startup candle data" + If data for the startup period is not available, then the timerange will be adjusted to account for this startup period. In our example, backtesting would then start from 2019-01-02 09:20:00. + +### Entry signal rules + +Edit the method `populate_entry_trend()` in your strategy file to update your entry strategy. + +It's important to always return the dataframe without removing/modifying the columns `"open", "high", "low", "close", "volume"`, otherwise these fields would contain something unexpected. The strategy may then produce invalid values, or cease to work entirely. + +This method will also define a new column, `"enter_long"` (`"enter_short"` for shorts), which needs to contain `1` for entries, and `0` for "no action". `enter_long` is a mandatory column that must be set even if the strategy is shorting only. + +You can name your entry signals by using the `"enter_tag"` column, which can help debug and assess your strategy later. + +Sample from `user_data/strategies/sample_strategy.py`: + +```python +def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + """ + Based on TA indicators, populates the buy signal for the given dataframe + :param dataframe: DataFrame populated with indicators + :param metadata: Additional information, like the currently traded pair + :return: DataFrame with buy column + """ + dataframe.loc[ + ( + (qtpylib.crossed_above(dataframe['rsi'], 30)) & # Signal: RSI crosses above 30 + (dataframe['tema'] <= dataframe['bb_middleband']) & # Guard + (dataframe['tema'] > dataframe['tema'].shift(1)) & # Guard + (dataframe['volume'] > 0) # Make sure Volume is not 0 + ), + ['enter_long', 'enter_tag']] = (1, 'rsi_cross') + + return dataframe +``` + +??? Note "Enter short trades" + Short entries can be created by setting `enter_short` (corresponds to `enter_long` for long trades). + The `enter_tag` column remains identical. + Shorting needs to be supported by your exchange and market configuration! + Also, make sure you set [`can_short`](#can-short) appropriately on your strategy if you intend to short. + + ```python + # allow both long and short trades + can_short = True + + def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + dataframe.loc[ + ( + (qtpylib.crossed_above(dataframe['rsi'], 30)) & # Signal: RSI crosses above 30 + (dataframe['tema'] <= dataframe['bb_middleband']) & # Guard + (dataframe['tema'] > dataframe['tema'].shift(1)) & # Guard + (dataframe['volume'] > 0) # Make sure Volume is not 0 + ), + ['enter_long', 'enter_tag']] = (1, 'rsi_cross') + + dataframe.loc[ + ( + (qtpylib.crossed_below(dataframe['rsi'], 70)) & # Signal: RSI crosses below 70 + (dataframe['tema'] > dataframe['bb_middleband']) & # Guard + (dataframe['tema'] < dataframe['tema'].shift(1)) & # Guard + (dataframe['volume'] > 0) # Make sure Volume is not 0 + ), + ['enter_short', 'enter_tag']] = (1, 'rsi_cross') + + return dataframe + ``` + +!!! Note + Buying requires sellers to buy from. Therefore volume needs to be > 0 (`dataframe['volume'] > 0`) to make sure that the bot does not buy/sell in no-activity periods. + +### Exit signal rules + +Edit the method `populate_exit_trend()` into your strategy file to update your exit strategy. + +The exit-signal can be suppressed by setting `use_exit_signal` to false in the configuration or strategy. + +`use_exit_signal` will not influence [signal collision rules](#colliding-signals) - which will still apply and can prevent entries. + +It's important to always return the dataframe without removing/modifying the columns `"open", "high", "low", "close", "volume"`, otherwise these fields would contain something unexpected. The strategy may then produce invalid values, or cease to work entirely. + +This method will also define a new column, `"exit_long"` (`"exit_short"` for shorts), which needs to contain `1` for exits, and `0` for "no action". + +You can name your exit signals by using the `"exit_tag"` column, which can help debug and assess your strategy later. + +Sample from `user_data/strategies/sample_strategy.py`: + +```python +def populate_exit_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + """ + Based on TA indicators, populates the exit signal for the given dataframe + :param dataframe: DataFrame populated with indicators + :param metadata: Additional information, like the currently traded pair + :return: DataFrame with buy column + """ + dataframe.loc[ + ( + (qtpylib.crossed_above(dataframe['rsi'], 70)) & # Signal: RSI crosses above 70 + (dataframe['tema'] > dataframe['bb_middleband']) & # Guard + (dataframe['tema'] < dataframe['tema'].shift(1)) & # Guard + (dataframe['volume'] > 0) # Make sure Volume is not 0 + ), + ['exit_long', 'exit_tag']] = (1, 'rsi_too_high') + return dataframe +``` + +??? Note "Exit short trades" + Short exits can be created by setting `exit_short` (corresponds to `exit_long`). + The `exit_tag` column remains identical. + Shorting needs to be supported by your exchange and market configuration! + Also, make sure you set [`can_short`](#can-short) appropriately on your strategy if you intend to short. + + ```python + # allow both long and short trades + can_short = True + + def populate_exit_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + dataframe.loc[ + ( + (qtpylib.crossed_above(dataframe['rsi'], 70)) & # Signal: RSI crosses above 70 + (dataframe['tema'] > dataframe['bb_middleband']) & # Guard + (dataframe['tema'] < dataframe['tema'].shift(1)) & # Guard + (dataframe['volume'] > 0) # Make sure Volume is not 0 + ), + ['exit_long', 'exit_tag']] = (1, 'rsi_too_high') + dataframe.loc[ + ( + (qtpylib.crossed_below(dataframe['rsi'], 30)) & # Signal: RSI crosses below 30 + (dataframe['tema'] < dataframe['bb_middleband']) & # Guard + (dataframe['tema'] > dataframe['tema'].shift(1)) & # Guard + (dataframe['volume'] > 0) # Make sure Volume is not 0 + ), + ['exit_short', 'exit_tag']] = (1, 'rsi_too_low') + return dataframe + ``` + +### Minimal ROI + +The `minimal_roi` strategy variable defines the minimal Return On Investment (ROI) a trade should reach before exiting, independent from the exit signal. + +It is of the following format, i.e. a python `dict`, with the dict key (left side of the colon) being the minutes passed since the trade opened, and the value (right side of the colon) being the percentage. + +```python +minimal_roi = { + "40": 0.0, + "30": 0.01, + "20": 0.02, + "0": 0.04 +} +``` + +The above configuration would therefore mean: + +- Exit whenever 4% profit was reached +- Exit when 2% profit was reached (in effect after 20 minutes) +- Exit when 1% profit was reached (in effect after 30 minutes) +- Exit when trade is non-loosing (in effect after 40 minutes) + +The calculation does include fees. + +#### Disabling minimal ROI + +To disable ROI completely, set it to an empty dictionary: + +```python +minimal_roi = {} +``` + +#### Using calculations in minimal ROI + +To use times based on candle duration (timeframe), the following snippet can be handy. + +This will allow you to change the timeframe for the strategy, but the minimal ROI times will still be set as candles, e.g. after 3 candles. + +``` python +from freqtrade.exchange import timeframe_to_minutes + +class AwesomeStrategy(IStrategy): + + timeframe = "1d" + timeframe_mins = timeframe_to_minutes(timeframe) + minimal_roi = { + "0": 0.05, # 5% for the first 3 candles + str(timeframe_mins * 3): 0.02, # 2% after 3 candles + str(timeframe_mins * 6): 0.01, # 1% After 6 candles + } +``` + +??? info "Orders that don't fill immediately" + `minimal_roi` will take the `trade.open_date` as reference, which is the time the trade was initialized, i.e. when the first order for this trade was placed. + This will also hold true for limit orders that don't fill immediately (usually in combination with "off-spot" prices through `custom_entry_price()`), as well as for cases where the initial order price is replaced through `adjust_entry_price()`. + The time used will still be from the initial `trade.open_date` (when the initial order was first placed), not from the newly placed or adjusted order date. + +### Stoploss + +Setting a stoploss is highly recommended to protect your capital from strong moves against you. + +Sample of setting a 10% stoploss: + +``` python +stoploss = -0.10 +``` + +For the full documentation on stoploss features, look at the dedicated [stoploss page](stoploss.md). + +### Timeframe + +This is the periodicity of candles the bot should use in the strategy. + +Common values are `"1m"`, `"5m"`, `"15m"`, `"1h"`, however all values supported by your exchange should work. + +Please note that the same entry/exit signals may work well with one timeframe, but not with others. + +This setting is accessible within the strategy methods as the `self.timeframe` attribute. + +### Can short + +To use short signals in futures markets, you will have to set `can_short = True`. + +Strategies which enable this will fail to load on spot markets. + +If you have `1` values in the `enter_short` column to raise short signals, setting `can_short = False` (which is the default) will mean that these short signals are ignored, even if you have specified futures markets in your configuration. + +### Metadata dict + +The `metadata` dict (available for `populate_entry_trend`, `populate_exit_trend`, `populate_indicators`) contains additional information. +Currently this is `pair`, which can be accessed using `metadata['pair']`, and will return a pair in the format `XRP/BTC` (or `XRP/BTC:BTC` for futures markets). + +The metadata dict should not be modified and does not persist information across multiple functions in your strategy. + +Instead, please check the [Storing information](strategy-advanced.md#storing-information-persistent) section. + +--8<-- "includes/strategy-imports.md" + +## Strategy file loading + +By default, freqtrade will attempt to load strategies from all `.py` files within the `userdir` (default `user_data/strategies`). + +Assuming your strategy is called `AwesomeStrategy`, stored in the file `user_data/strategies/AwesomeStrategy.py`, then you can start freqtrade in dry (or live, depending on your configuration) mode with: + +```bash +freqtrade trade --strategy AwesomeStrategy +``` + +Note that we're using the class name, not the file name. + +You can use `freqtrade list-strategies` to see a list of all strategies Freqtrade is able to load (all strategies in the correct folder). +It will also include a "status" field, highlighting potential problems. + +??? Hint "Customize strategy directory" + You can use a different directory by using `--strategy-path user_data/otherPath`. This parameter is available to all commands that require a strategy. + +## Informative Pairs + +### Get data for non-tradeable pairs + +Data for additional, informative pairs (reference pairs) can be beneficial for some strategies to see data on a wider timeframe. + +OHLCV data for these pairs will be downloaded as part of the regular whitelist refresh process and is available via `DataProvider` just as other pairs (see below). + +These pairs will **not** be traded unless they are also specified in the pair whitelist, or have been selected by Dynamic Whitelisting, e.g. `VolumePairlist`. + +The pairs need to be specified as tuples in the format `("pair", "timeframe")`, with pair as the first and timeframe as the second argument. + +Sample: + +``` python +def informative_pairs(self): + return [("ETH/USDT", "5m"), + ("BTC/TUSD", "15m"), + ] +``` + +A full sample can be found [in the DataProvider section](#complete-dataprovider-sample). + +!!! Warning + As these pairs will be refreshed as part of the regular whitelist refresh, it's best to keep this list short. + All timeframes and all pairs can be specified as long as they are available (and active) on the used exchange. + It is however better to use resampling to longer timeframes whenever possible + to avoid hammering the exchange with too many requests and risk being blocked. + +??? Note "Alternative candle types" + Informative_pairs can also provide a 3rd tuple element defining the candle type explicitly. + Availability of alternative candle-types will depend on the trading-mode and the exchange. + In general, spot pairs cannot be used in futures markets, and futures candles can't be used as informative pairs for spot bots. + Details about this may vary, if they do, this can be found in the exchange documentation. + + ``` python + def informative_pairs(self): + return [ + ("ETH/USDT", "5m", ""), # Uses default candletype, depends on trading_mode (recommended) + ("ETH/USDT", "5m", "spot"), # Forces usage of spot candles (only valid for bots running on spot markets). + ("BTC/TUSD", "15m", "futures"), # Uses futures candles (only bots with `trading_mode=futures`) + ("BTC/TUSD", "15m", "mark"), # Uses mark candles (only bots with `trading_mode=futures`) + ] + ``` +*** + +### Informative pairs decorator (`@informative()`) + +To easily define informative pairs, use the `@informative` decorator. All decorated `populate_indicators_*` methods run in isolation, +and do not have access to data from other informative pairs. However, all informative dataframes for each pair are merged and passed to main `populate_indicators()` method. + +!!! Note + Do not use the `@informative` decorator if you need to use data from one informative pair when generating another informative pair. Instead, define informative pairs manually as described [in the DataProvider section](#complete-dataprovider-sample). + +When hyperopting, use of the hyperoptable parameter `.value` attribute is not supported. Please use the `.range` attribute. See [optimizing an indicator parameter](hyperopt.md#optimizing-an-indicator-parameter) for more information. + +??? info "Full documentation" + ``` python + def informative( + timeframe: str, + asset: str = "", + fmt: str | Callable[[Any], str] | None = None, + *, + candle_type: CandleType | str | None = None, + ffill: bool = True, + ) -> Callable[[PopulateIndicators], PopulateIndicators]: + """ + A decorator for populate_indicators_Nn(self, dataframe, metadata), allowing these functions to + define informative indicators. + + Example usage: + + @informative('1h') + def populate_indicators_1h(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + dataframe['rsi'] = ta.RSI(dataframe, timeperiod=14) + return dataframe + + :param timeframe: Informative timeframe. Must always be equal or higher than strategy timeframe. + :param asset: Informative asset, for example BTC, BTC/USDT, ETH/BTC. Do not specify to use + current pair. Also supports limited pair format strings (see below) + :param fmt: Column format (str) or column formatter (callable(name, asset, timeframe)). When not + specified, defaults to: + * {base}_{quote}_{column}_{timeframe} if asset is specified. + * {column}_{timeframe} if asset is not specified. + Pair format supports these format variables: + * {base} - base currency in lower case, for example 'eth'. + * {BASE} - same as {base}, except in upper case. + * {quote} - quote currency in lower case, for example 'usdt'. + * {QUOTE} - same as {quote}, except in upper case. + Format string additionally supports this variables. + * {asset} - full name of the asset, for example 'BTC/USDT'. + * {column} - name of dataframe column. + * {timeframe} - timeframe of informative dataframe. + :param ffill: ffill dataframe after merging informative pair. + :param candle_type: '', mark, index, premiumIndex, or funding_rate + """ + ``` + +??? Example "Fast and easy way to define informative pairs" + + Most of the time we do not need power and flexibility offered by `merge_informative_pair()`, therefore we can use a decorator to quickly define informative pairs. + + ``` python + + from datetime import datetime + from freqtrade.persistence import Trade + from freqtrade.strategy import IStrategy, informative + + class AwesomeStrategy(IStrategy): + + # This method is not required. + # def informative_pairs(self): ... + + # Define informative upper timeframe for each pair. Decorators can be stacked on same + # method. Available in populate_indicators as 'rsi_30m' and 'rsi_1h'. + @informative('30m') + @informative('1h') + def populate_indicators_1h(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + dataframe['rsi'] = ta.RSI(dataframe, timeperiod=14) + return dataframe + + # Define BTC/STAKE informative pair. Available in populate_indicators and other methods as + # 'btc_rsi_1h'. Current stake currency should be specified as {stake} format variable + # instead of hard-coding actual stake currency. Available in populate_indicators and other + # methods as 'btc_usdt_rsi_1h' (when stake currency is USDT). + @informative('1h', 'BTC/{stake}') + def populate_indicators_btc_1h(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + dataframe['rsi'] = ta.RSI(dataframe, timeperiod=14) + return dataframe + + # Define BTC/ETH informative pair. You must specify quote currency if it is different from + # stake currency. Available in populate_indicators and other methods as 'eth_btc_rsi_1h'. + @informative('1h', 'ETH/BTC') + def populate_indicators_eth_btc_1h(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + dataframe['rsi'] = ta.RSI(dataframe, timeperiod=14) + return dataframe + + # Define BTC/STAKE informative pair. A custom formatter may be specified for formatting + # column names. A callable `fmt(**kwargs) -> str` may be specified, to implement custom + # formatting. Available in populate_indicators and other methods as 'rsi_upper_1h'. + @informative('1h', 'BTC/{stake}', '{column}_{timeframe}') + def populate_indicators_btc_1h_2(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + dataframe['rsi_upper'] = ta.RSI(dataframe, timeperiod=14) + return dataframe + + def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + # Strategy timeframe indicators for current pair. + dataframe['rsi'] = ta.RSI(dataframe, timeperiod=14) + # Informative pairs are available in this method. + dataframe['rsi_less'] = dataframe['rsi'] < dataframe['rsi_1h'] + return dataframe + + ``` + +!!! Note + Use string formatting when accessing informative dataframes of other pairs. This will allow easily changing stake currency in config without having to adjust strategy code. + + ``` python + def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + stake = self.config['stake_currency'] + dataframe.loc[ + ( + (dataframe[f'btc_{stake}_rsi_1h'] < 35) + & + (dataframe['volume'] > 0) + ), + ['enter_long', 'enter_tag']] = (1, 'buy_signal_rsi') + + return dataframe + ``` + + Alternatively column renaming may be used to remove stake currency from column names: `@informative('1h', 'BTC/{stake}', fmt='{base}_{column}_{timeframe}')`. + +!!! Warning "Duplicate method names" + Methods tagged with the `@informative()` decorator must always have unique names! Reusing the same name (for example when copy-pasting already defined informative methods) will overwrite previously defined methods and not produce any errors due to limitations of Python programming language. In such cases you will find that indicators created in methods higher up in the strategy file are not available in the dataframe. Carefully review method names and make sure they are unique! + +### *merge_informative_pair()* + +This method helps you merge an informative pair to the regular main dataframe safely and consistently, without lookahead bias. + +Options: + +- Rename the columns to create unique columns +- Merge the dataframe without lookahead bias +- Forward-fill (optional) + +For a full sample, please refer to the [complete data provider example](#complete-dataprovider-sample) below. + +All columns of the informative dataframe will be available on the returning dataframe in a renamed fashion: + +!!! Example "Column renaming" + Assuming `inf_tf = '1d'` the resulting columns will be: + + ``` python + 'date', 'open', 'high', 'low', 'close', 'rsi' # from the original dataframe + 'date_1d', 'open_1d', 'high_1d', 'low_1d', 'close_1d', 'rsi_1d' # from the informative dataframe + ``` + +??? Example "Column renaming - 1h" + Assuming `inf_tf = '1h'` the resulting columns will be: + + ``` python + 'date', 'open', 'high', 'low', 'close', 'rsi' # from the original dataframe + 'date_1h', 'open_1h', 'high_1h', 'low_1h', 'close_1h', 'rsi_1h' # from the informative dataframe + ``` + +??? Example "Custom implementation" + A custom implementation for this is possible, and can be done as follows: + + ``` python + + # Shift date by 1 candle + # This is necessary since the data is always the "open date" + # and a 15m candle starting at 12:15 should not know the close of the 1h candle from 12:00 to 13:00 + minutes = timeframe_to_minutes(inf_tf) + # Only do this if the timeframes are different: + informative['date_merge'] = informative["date"] + pd.to_timedelta(minutes, 'm') + + # Rename columns to be unique + informative.columns = [f"{col}_{inf_tf}" for col in informative.columns] + # Assuming inf_tf = '1d' - then the columns will now be: + # date_1d, open_1d, high_1d, low_1d, close_1d, rsi_1d + + # Combine the 2 dataframes + # all indicators on the informative sample MUST be calculated before this point + dataframe = pd.merge(dataframe, informative, left_on='date', right_on=f'date_merge_{inf_tf}', how='left') + # FFill to have the 1d value available in every row throughout the day. + # Without this, comparisons would only work once per day. + dataframe = dataframe.ffill() + + ``` + +!!! Warning "Informative timeframe < timeframe" + Using informative timeframes smaller than the main dataframe timeframe is not recommended with this method, as it will not use any of the additional information this would provide. + To use the more detailed information properly, more advanced methods should be applied (which are out of scope for this documentation). + +## Additional data (DataProvider) + +The strategy provides access to the `DataProvider`. This allows you to get additional data to use in your strategy. + +All methods return `None` in case of failure, i.e. failures do not raise an exception. + +Please always check the mode of operation to select the correct method to get data (see below for examples). + +!!! Warning "Hyperopt Limitations" + The DataProvider is available during hyperopt, however it can only be used in `populate_indicators()` **within a strategy**, not within a hyperopt class file. + It is also not available in `populate_entry_trend()` and `populate_exit_trend()` methods. + +### Possible options for DataProvider + +- [`available_pairs`](#available_pairs) - Property with tuples listing cached pairs with their timeframe (pair, timeframe). +- [`current_whitelist()`](#current_whitelist) - Returns a current list of whitelisted pairs. Useful for accessing dynamic whitelists (i.e. VolumePairlist) +- [`get_pair_dataframe(pair, timeframe)`](#get_pair_dataframepair-timeframe) - This is a universal method, which returns either historical data (for backtesting) or cached live data (for the Dry-Run and Live-Run modes). +- [`get_analyzed_dataframe(pair, timeframe)`](#get_analyzed_dataframepair-timeframe) - Returns the analyzed dataframe (after calling `populate_indicators()`, `populate_buy()`, `populate_sell()`) and the time of the latest analysis. +- `historic_ohlcv(pair, timeframe)` - Returns historical data stored on disk. +- `market(pair)` - Returns market data for the pair: fees, limits, precisions, activity flag, etc. See [ccxt documentation](https://github.com/ccxt/ccxt/wiki/Manual#markets) for more details on the Market data structure. +- `ohlcv(pair, timeframe)` - Currently cached candle (OHLCV) data for the pair, returns DataFrame or empty DataFrame. +- [`orderbook(pair, maximum)`](#orderbookpair-maximum) - Returns latest orderbook data for the pair, a dict with bids/asks with a total of `maximum` entries. +- [`ticker(pair)`](#tickerpair) - Returns current ticker data for the pair. See [ccxt documentation](https://github.com/ccxt/ccxt/wiki/Manual#price-tickers) for more details on the Ticker data structure. +- `runmode` - Property containing the current runmode. + +### Example Usages + +### *available_pairs* + +``` python +for pair, timeframe in self.dp.available_pairs: + print(f"available {pair}, {timeframe}") +``` + +### *current_whitelist()* + +Imagine you've developed a strategy that trades the `5m` timeframe using signals generated from a `1d` timeframe on the top 10 exchange pairs by volume. + +The strategy logic might look something like this: + +*Scan through the top 10 pairs by volume using the `VolumePairList` every 5 minutes and use a 14 day RSI to enter and exit.* + +Due to the limited available data, it's very difficult to resample `5m` candles into daily candles for use in a 14 day RSI. Most exchanges limit users to just 500-1000 candles which effectively gives us around 1.74 daily candles. We need 14 days at least! + +Since we can't resample the data we will have to use an informative pair, and since the whitelist will be dynamic we don't know which pair(s) to use! We have a problem! + +This is where calling `self.dp.current_whitelist()` comes in handy to retrieve only those pairs in the whitelist. + +```python + def informative_pairs(self): + + # get access to all pairs available in whitelist. + pairs = self.dp.current_whitelist() + # Assign timeframe to each pair so they can be downloaded and cached for strategy. + informative_pairs = [(pair, '1d') for pair in pairs] + return informative_pairs +``` + +??? Note "Plotting with current_whitelist" + Current whitelist is not supported for `plot-dataframe`, as this command is usually used by providing an explicit pairlist and would therefore make the return values of this method misleading. + It's also not supported for FreqUI visualization in [webserver mode](utils.md#webserver-mode), as the configuration for webserver mode doesn't require a pairlist to be set. + +### *get_pair_dataframe(pair, timeframe)* + +``` python +# fetch live / historical candle (OHLCV) data for the first informative pair +inf_pair, inf_timeframe = self.informative_pairs()[0] +informative = self.dp.get_pair_dataframe(pair=inf_pair, + timeframe=inf_timeframe) +``` + +!!! Warning "Warning about backtesting" + In backtesting, `dp.get_pair_dataframe()` behavior differs depending on where it's called. + Within `populate_*()` methods, `dp.get_pair_dataframe()` returns the full timerange. Please make sure to not "look into the future" to avoid surprises when running in dry/live mode. + Within [callbacks](strategy-callbacks.md), you'll get the full timerange up to the current (simulated) candle. + +### *get_analyzed_dataframe(pair, timeframe)* + +This method is used by freqtrade internally to determine the last signal. +It can also be used in specific callbacks to get the signal that caused the action (see [Advanced Strategy Documentation](strategy-advanced.md) for more details on available callbacks). + +``` python +# fetch current dataframe +dataframe, last_updated = self.dp.get_analyzed_dataframe(pair=metadata['pair'], + timeframe=self.timeframe) +``` + +!!! Note "No data available" + Returns an empty dataframe if the requested pair was not cached. + You can check for this with `if dataframe.empty:` and handle this case accordingly. + This should not happen when using whitelisted pairs. + +### *orderbook(pair, maximum)* + +``` python +if self.dp.runmode.value in ('live', 'dry_run'): + ob = self.dp.orderbook(metadata['pair'], 1) + dataframe['best_bid'] = ob['bids'][0][0] + dataframe['best_ask'] = ob['asks'][0][0] +``` + +The orderbook structure is aligned with the order structure from [ccxt](https://github.com/ccxt/ccxt/wiki/Manual#order-book-structure), so the result will be formatted as follows: + +``` js +{ + 'bids': [ + [ price, amount ], // [ float, float ] + [ price, amount ], + ... + ], + 'asks': [ + [ price, amount ], + [ price, amount ], + //... + ], + //... +} +``` + +Therefore, using `ob['bids'][0][0]` as demonstrated above will use the best bid price. `ob['bids'][0][1]` would look at the amount at this orderbook position. + +!!! Warning "Warning about backtesting" + The order book is not part of the historic data which means backtesting and hyperopt will not work correctly if this method is used, as the method will return up-to-date values. + +### *ticker(pair)* + +``` python +if self.dp.runmode.value in ('live', 'dry_run'): + ticker = self.dp.ticker(metadata['pair']) + dataframe['last_price'] = ticker['last'] + dataframe['volume24h'] = ticker['quoteVolume'] + dataframe['vwap'] = ticker['vwap'] +``` + +!!! Warning + Although the ticker data structure is a part of the ccxt Unified Interface, the values returned by this method can + vary for different exchanges. For instance, many exchanges do not return `vwap` values, and some exchanges + do not always fill in the `last` field (so it can be None), etc. So you need to carefully verify the ticker + data returned from the exchange and add appropriate error handling / defaults. + +!!! Warning "Warning about backtesting" + This method will always return up-to-date / real-time values. As such, usage during backtesting / hyperopt without runmode checks will lead to wrong results, e.g. your whole dataframe will contain the same single value in all rows. + +### Send Notification + +The dataprovider `.send_msg()` function allows you to send custom notifications from your strategy. +Identical notifications will only be sent once per candle, unless the 2nd argument (`always_send`) is set to True. + +``` python + self.dp.send_msg(f"{metadata['pair']} just got hot!") + + # Force send this notification, avoid caching (Please read warning below!) + self.dp.send_msg(f"{metadata['pair']} just got hot!", always_send=True) +``` + +Notifications will only be sent in trading modes (Live/Dry-run) - so this method can be called without conditions for backtesting. + +!!! Warning "Spamming" + You can spam yourself pretty good by setting `always_send=True` in this method. Use this with great care and only in conditions you know will not happen throughout a candle to avoid a message every 5 seconds. + +### Complete DataProvider sample + +```python +from freqtrade.strategy import IStrategy, merge_informative_pair +from pandas import DataFrame + +class SampleStrategy(IStrategy): + # strategy init stuff... + + timeframe = '5m' + + # more strategy init stuff.. + + def informative_pairs(self): + + # get access to all pairs available in whitelist. + pairs = self.dp.current_whitelist() + # Assign tf to each pair so they can be downloaded and cached for strategy. + informative_pairs = [(pair, '1d') for pair in pairs] + # Optionally Add additional "static" pairs + informative_pairs += [("ETH/USDT", "5m"), + ("BTC/TUSD", "15m"), + ] + return informative_pairs + + def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + if not self.dp: + # Don't do anything if DataProvider is not available. + return dataframe + + inf_tf = '1d' + # Get the informative pair + informative = self.dp.get_pair_dataframe(pair=metadata['pair'], timeframe=inf_tf) + # Get the 14 day rsi + informative['rsi'] = ta.RSI(informative, timeperiod=14) + + # Use the helper function merge_informative_pair to safely merge the pair + # Automatically renames the columns and merges a shorter timeframe dataframe and a longer timeframe informative pair + # use ffill to have the 1d value available in every row throughout the day. + # Without this, comparisons between columns of the original and the informative pair would only work once per day. + # Full documentation of this method, see below + dataframe = merge_informative_pair(dataframe, informative, self.timeframe, inf_tf, ffill=True) + + # Calculate rsi of the original dataframe (5m timeframe) + dataframe['rsi'] = ta.RSI(dataframe, timeperiod=14) + + # Do other stuff + # ... + + return dataframe + + def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + + dataframe.loc[ + ( + (qtpylib.crossed_above(dataframe['rsi'], 30)) & # Signal: RSI crosses above 30 + (dataframe['rsi_1d'] < 30) & # Ensure daily RSI is < 30 + (dataframe['volume'] > 0) # Ensure this candle had volume (important for backtesting) + ), + ['enter_long', 'enter_tag']] = (1, 'rsi_cross') + +``` + +*** + +## Additional data (Wallets) + +The strategy provides access to the `wallets` object. This contains the current balances of your wallets/accounts on the exchange. + +!!! Note "Backtesting / Hyperopt" + Wallets behaves differently depending on the function from which it is called. + Within `populate_*()` methods, it'll return the full wallet as configured. + Within [callbacks](strategy-callbacks.md), you'll get the wallet state corresponding to the actual simulated wallet at that point in the simulation process. + +Always check if `wallets` is available to avoid failures during backtesting. + +``` python +if self.wallets: + free_eth = self.wallets.get_free('ETH') + used_eth = self.wallets.get_used('ETH') + total_eth = self.wallets.get_total('ETH') +``` + +### Possible options for Wallets + +- `get_free(asset)` - currently available balance to trade +- `get_used(asset)` - currently tied up balance (open orders) +- `get_total(asset)` - total available balance - sum of the 2 above + +*** + +## Additional data (Trades) + +A history of trades can be retrieved in the strategy by querying the database. + +At the top of the file, import the required object: + +```python +from freqtrade.persistence import Trade +``` + +The following example queries trades from today for the current pair (`metadata['pair']`). Other filters can easily be added. + +``` python +trades = Trade.get_trades_proxy(pair=metadata['pair'], + open_date=datetime.now(timezone.utc) - timedelta(days=1), + is_open=False, + ]).order_by(Trade.close_date).all() +# Summarize profit for this pair. +curdayprofit = sum(trade.close_profit for trade in trades) +``` + +For a full list of available methods, please consult the [Trade object](trade-object.md) documentation. + +!!! Warning + Trade history is not available in `populate_*` methods during backtesting or hyperopt, and will result in empty results. + +## Prevent trades from happening for a specific pair + +Freqtrade locks pairs automatically for the current candle (until that candle is over) when a pair exits, preventing an immediate re-entry of that pair. + +This is to prevent "waterfalls" of many and frequent trades within a single candle. + +Locked pairs will show the message `Pair is currently locked.`. + +### Locking pairs from within the strategy + +Sometimes it may be desired to lock a pair after certain events happen (e.g. multiple losing trades in a row). + +Freqtrade has an easy method to do this from within the strategy, by calling `self.lock_pair(pair, until, [reason])`. +`until` must be a datetime object in the future, after which trading will be re-enabled for that pair, while `reason` is an optional string detailing why the pair was locked. + +Locks can also be lifted manually, by calling `self.unlock_pair(pair)` or `self.unlock_reason()`, providing the reason the pair was unlocked. +`self.unlock_reason()` will unlock all pairs currently locked with the provided reason. + +To verify if a pair is currently locked, use `self.is_pair_locked(pair)`. + +!!! Note + Locked pairs will always be rounded up to the next candle. So assuming a `5m` timeframe, a lock with `until` set to 10:18 will lock the pair until the candle from 10:15-10:20 will be finished. + +!!! Warning + Manually locking pairs is not available during backtesting. Only locks via Protections are allowed. + +#### Pair locking example + +``` python +from freqtrade.persistence import Trade +from datetime import timedelta, datetime, timezone +# Put the above lines a the top of the strategy file, next to all the other imports +# -------- + +# Within populate indicators (or populate_entry_trend): +if self.config['runmode'].value in ('live', 'dry_run'): + # fetch closed trades for the last 2 days + trades = Trade.get_trades_proxy( + pair=metadata['pair'], is_open=False, + open_date=datetime.now(timezone.utc) - timedelta(days=2)) + # Analyze the conditions you'd like to lock the pair .... will probably be different for every strategy + sumprofit = sum(trade.close_profit for trade in trades) + if sumprofit < 0: + # Lock pair for 12 hours + self.lock_pair(metadata['pair'], until=datetime.now(timezone.utc) + timedelta(hours=12)) +``` + +## Print the main dataframe + +To inspect the current main dataframe, you can issue a print-statement in either `populate_entry_trend()` or `populate_exit_trend()`. +You may also want to print the pair so it's clear what data is currently shown. + +``` python +def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame: + dataframe.loc[ + ( + #>> whatever condition<<< + ), + ['enter_long', 'enter_tag']] = (1, 'somestring') + + # Print the Analyzed pair + print(f"result for {metadata['pair']}") + + # Inspect the last 5 rows + print(dataframe.tail()) + + return dataframe +``` + +Printing more than a few rows is also possible by using `print(dataframe)` instead of `print(dataframe.tail())`. However this is not recommended, as can results in a lot of output (~500 lines per pair every 5 seconds). + +## Common mistakes when developing strategies + +### Looking into the future while backtesting + +Backtesting analyzes the whole dataframe timerange at once for performance reasons. Because of this, strategy authors need to make sure that strategies do not lookahead into the future, i.e. using data that would not be available in dry or live mode. + +This is a common pain-point, which can cause huge differences between backtesting and dry/live run methods. Strategies that look into the future will perform well during backtesting, often with incredible profits or winrates, but will fail or perform badly in real conditions. + +The following list contains some common patterns which should be avoided to prevent frustration: + +- don't use `shift(-1)` or other negative values. This uses data from the future in backtesting, which is not available in dry or live modes. +- don't use `.iloc[-1]` or any other absolute position in the dataframe within `populate_` functions, as this will be different between dry-run and backtesting. Absolute `iloc` indexing is safe to use in callbacks however - see [Strategy Callbacks](strategy-callbacks.md). +- don't use functions that use all dataframe or column values, e.g. `dataframe['mean_volume'] = dataframe['volume'].mean()`. As backtesting uses the full dataframe, at any point in the dataframe, the `'mean_volume'` series would include data from the future. Use rolling() calculations instead, e.g. `dataframe['volume'].rolling().mean()`. +- don't use `.resample('1h')`. This uses the left border of the period interval, so moves data from an hour boundary to the start of the hour. Use `.resample('1h', label='right')` instead. +- don't use `.merge()` to combine longer timeframes onto shorter ones. Instead, use the [informative pair](#informative-pairs) helpers. (A plain merge can implicitly cause a lookahead bias as date refers to open date, not close date). + +!!! Tip "Identifying problems" + You should always use the two helper commands [lookahead-analysis](lookahead-analysis.md) and [recursive-analysis](recursive-analysis.md), which can each help you figure out problems with your strategy in different ways. + Please treat them as what they are - helpers to identify most common problems. A negative result of each does not guarantee that there are none of the above errors included. + +### Colliding signals + +When conflicting signals collide (e.g. both `'enter_long'` and `'exit_long'` are set to `1`), freqtrade will do nothing and ignore the entry signal. This will avoid trades that enter, and exit immediately. Obviously, this can potentially lead to missed entries. + +The following rules apply, and entry signals will be ignored if more than one of the 3 signals is set: + +- `enter_long` -> `exit_long`, `enter_short` +- `enter_short` -> `exit_short`, `enter_long` + +## Further strategy ideas + +To get additional ideas for strategies, head over to the [strategy repository](https://github.com/freqtrade/freqtrade-strategies). Feel free to use them as examples, but results will depend on the current market situation, pairs used, etc. Therefore, these strategies should be considered only for learning purposes, not real world trading. Please backtest the strategy for your exchange/desired pairs first, then dry run to evaluate carefully, and use at your own risk. + +Feel free to use any of them as inspiration for your own strategies. We're happy to accept Pull Requests containing new strategies to the repository. + +## Next steps + +Now you have a perfect strategy you probably want to backtest it. +Your next step is to learn [how to use backtesting](backtesting.md). diff --git a/docs/strategy_analysis_example.md b/md/strategy_analysis_example.md similarity index 100% rename from docs/strategy_analysis_example.md rename to md/strategy_analysis_example.md diff --git a/nohup.out b/nohup.out new file mode 100644 index 00000000..4f7c6116 --- /dev/null +++ b/nohup.out @@ -0,0 +1,238 @@ +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +Archive: backtest-result-2025-05-06_01-08-03.zip + inflating: backtest-result-2025-05-06_01-08-03.json + inflating: backtest-result-2025-05-06_01-08-03_config.json + inflating: backtest-result-2025-05-06_01-08-03_OKXRegressionStrategy.py + inflating: backtest-result-2025-05-06_01-08-03_market_change.feather +/home/ubuntu/freqtrade +Archive: backtest-result-2025-05-06_01-28-09.zip + inflating: backtest-result-2025-05-06_01-28-09.json + inflating: backtest-result-2025-05-06_01-28-09_config.json + inflating: backtest-result-2025-05-06_01-28-09_OKXRegressionStrategy.py + inflating: backtest-result-2025-05-06_01-28-09_market_change.feather +/home/ubuntu/freqtrade +Archive: backtest-result-2025-05-06_01-53-53.zip + inflating: backtest-result-2025-05-06_01-53-53.json + inflating: backtest-result-2025-05-06_01-53-53_config.json + inflating: backtest-result-2025-05-06_01-53-53_OKXRegressionStrategy.py + inflating: backtest-result-2025-05-06_01-53-53_market_change.feather +/home/ubuntu/freqtrade +Archive: backtest-result-2025-05-06_02-15-16.zip + inflating: backtest-result-2025-05-06_02-15-16.json + inflating: backtest-result-2025-05-06_02-15-16_config.json + inflating: backtest-result-2025-05-06_02-15-16_OKXRegressionStrategy.py + inflating: backtest-result-2025-05-06_02-15-16_market_change.feather +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +Archive: backtest-result-2025-05-06_02-50-43.zip + inflating: backtest-result-2025-05-06_02-50-43.json + inflating: backtest-result-2025-05-06_02-50-43_config.json + inflating: backtest-result-2025-05-06_02-50-43_OKXRegressionStrategy.py + inflating: backtest-result-2025-05-06_02-50-43_market_change.feather +/home/ubuntu/freqtrade +Archive: backtest-result-2025-05-06_03-05-54.zip + inflating: backtest-result-2025-05-06_03-05-54.json + inflating: backtest-result-2025-05-06_03-05-54_config.json + inflating: backtest-result-2025-05-06_03-05-54_OKXRegressionStrategy.py + inflating: backtest-result-2025-05-06_03-05-54_market_change.feather +/home/ubuntu/freqtrade +./run.sh: line 33: result: Is a directory +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +mv: cannot stat './user_data/backtest_results/*': No such file or directory +unzip: cannot find or open *.zip, *.zip.zip or *.zip.ZIP. + +No zipfiles found. +rm: cannot remove '*.zip': No such file or directory +rm: cannot remove '*.feather': No such file or directory +/home/ubuntu/freqtrade +Archive: backtest-result-2025-05-06_03-47-33.zip + inflating: backtest-result-2025-05-06_03-47-33.json + inflating: backtest-result-2025-05-06_03-47-33_config.json + inflating: backtest-result-2025-05-06_03-47-33_OKXRegressionStrategy.py + inflating: backtest-result-2025-05-06_03-47-33_market_change.feather +/home/ubuntu/freqtrade +Archive: backtest-result-2025-05-06_04-07-15.zip + inflating: backtest-result-2025-05-06_04-07-15.json + inflating: backtest-result-2025-05-06_04-07-15_config.json + inflating: backtest-result-2025-05-06_04-07-15_OKXRegressionStrategy.py + inflating: backtest-result-2025-05-06_04-07-15_market_change.feather +/home/ubuntu/freqtrade diff --git a/run.sh_disabled b/run.sh_disabled new file mode 100755 index 00000000..d2188480 --- /dev/null +++ b/run.sh_disabled @@ -0,0 +1,30 @@ +#!/bin/bash + +rm -rf user_data/models/* +rm -rf ./freqtrade/user_data/data/backtest_results/* + +docker-compose run --rm freqtrade >output.log 2>&1 +sed -i 's/\x1B\[[0-9;]*m//g' output.log +python3 filter.py + +rm ./result/* -fr +mv ./user_data/backtest_results/* ./result/ + +cd ./result +# 查找当前目录下的所有 zip 文件 +zip_files=(*.zip) + +# 检查是否只有一个 zip 文件 +if [ ${#zip_files[@]} -eq 1 ]; then + # 解压缩该 zip 文件到当前目录 + unzip "${zip_files[0]}" + rm *.zip + rm *.feather +else + echo "当前目录下没有 zip 文件或者有多个 zip 文件，无法操作。" +fi + +cd - +sed -i 's/\x1B\[[0-9;]*m//g' output.log +python3 filter.py +cp output_filted.log result/ -f diff --git a/tools/analytic.py b/tools/analytic.py new file mode 100644 index 00000000..7c495e3d --- /dev/null +++ b/tools/analytic.py @@ -0,0 +1,74 @@ +import pandas as pd + +# 加载交易记录 +df = pd.read_csv('../result/backtest_trades.csv') + +# 转换日期格式 +df['open_date'] = pd.to_datetime(df['open_date']) +df['close_date'] = pd.to_datetime(df['close_date']) + +# 计算持仓天数 +df['holding_days'] = (df['close_date'] - df['open_date']).dt.total_seconds() / (60 * 60 * 24) + +# 按币种分组 +grouped_by_pair = df.groupby('pair').agg( + total_trades=('profit_abs', 'size'), + avg_profit_ratio=('profit_ratio', 'mean'), + total_profit_abs=('profit_abs', 'sum'), + win_rate=('profit_ratio', lambda x: (x > 0).mean()), + avg_duration=('trade_duration', 'mean') +) + +print(grouped_by_pair) + +#按退出原因分组 +grouped_by_exit = df.groupby('exit_reason').agg( + total_trades=('profit_abs', 'size'), + avg_profit_ratio=('profit_ratio', 'mean'), + total_profit_abs=('profit_abs', 'sum'), + win_rate=('profit_ratio', lambda x: (x > 0).mean()) +) + +print(grouped_by_exit) +#按月份分组统计 +df['open_date_naive'] = df['open_date'].dt.tz_localize(None) +df['month'] = df['open_date_naive'].dt.to_period('M') + + +grouped_by_month = df.groupby('month').agg( + total_trades=('profit_abs', 'size'), + avg_profit_ratio=('profit_ratio', 'mean'), + total_profit_abs=('profit_abs', 'sum'), + win_rate=('profit_ratio', lambda x: (x > 0).mean()) +) + +print(grouped_by_month) +# 按盈利区间分组统计 +bins = [-float('inf'), -0.05, -0.02, 0, 0.02, 0.05, float('inf')] +labels = ['<-5%', '-5%~-2%', '-2%~0%', '0%~2%', '2%~5%', '>5%'] + +df['profit_group'] = pd.cut(df['profit_ratio'], bins=bins, labels=labels) + +grouped_by_profit = df.groupby('profit_group', observed=True).agg( + count=('profit_abs', 'size'), + avg_profit=('profit_ratio', 'mean'), + total_profit=('profit_abs', 'sum') +) + +print(grouped_by_profit) +# 分组为短中长线 +df['duration_group'] = pd.cut(df['trade_duration'], + bins=[0, 60, 360, 1440, 100000], + labels=['<1小时', '1~6小时', '6小时~1天', '>1天']) + +grouped_by_duration = df.groupby('duration_group', observed=True).agg( + count=('profit_abs', 'size'), + avg_profit=('profit_ratio', 'mean'), + win_rate=('profit_ratio', lambda x: (x > 0).mean()), + total_profit=('profit_abs', 'sum') +) + +print(grouped_by_duration) + + + diff --git a/tools/analytic.sh b/tools/analytic.sh new file mode 100755 index 00000000..19d91a51 --- /dev/null +++ b/tools/analytic.sh @@ -0,0 +1,4 @@ +cd ../ +source .venv/bin/activate +cd - +python analytic.py diff --git a/tools/backtest.sh b/tools/backtest.sh new file mode 100755 index 00000000..f49eedad --- /dev/null +++ b/tools/backtest.sh @@ -0,0 +1,87 @@ +#!/bin/bash + +# 检查 .env 文件 +if [ ! -f ".env" ]; then + echo "⚠️ 本地缺少 .env 文件，请创建并配置。示例内容如下：" + echo "" + echo "STRATEGY_NAME=TheForceV7" + echo "CONFIG_FILE=basic.json" + echo "TEST_BRANCH=theforce-noai-test" + echo "DRYRUN_BRANCH=theforce-noai-dryrun" + echo "" + exit 1 +fi + +# 加载 .env 文件中的变量 +export $(grep -v '^#' .env | xargs) +# 设置默认值 +STRATEGY_NAME=${STRATEGY_NAME:-TheForceV7} +CONFIG_FILE=${CONFIG_FILE:-basic.json} + +echo "Using strategy: $STRATEGY_NAME" +echo "Using config: $CONFIG_FILE" +echo "Using testBranch: $TEST_BRANCH" +# Parse command line arguments +START_DATE=${1:-$(date -d "2 days ago" +"%Y%m%d")} +END_DATE=${2:-$(date -d "tomorrow" +"%Y%m%d")} + +cd ../ +source .venv/bin/activate +rm -rf user_data/models/* +rm -rf ./freqtrade/user_data/data/backtest_results/* +rm -fr ./user_data/dryrun_results/* +rm result/* + +hyperopt_config="${STRATEGY_NAME%.py}.json" +#docker-compose -f docker-compose_backtest.yml run --rm freqtrade >output.log 2>&1 + +echo "docker-compose run --rm freqtrade backtesting \ + --logfile /freqtrade/user_data/logs/freqtrade.log \ + --freqaimodel LightGBMRegressor \ + --config /freqtrade/config_examples/$CONFIG_FILE \ + --strategy-path /freqtrade/templates \ + --strategy $STRATEGY_NAME \ + --timerange $START_DATE-$END_DATE \ + --fee 0.0008 \ + --cache none >output.log" + +docker-compose run --rm freqtrade backtesting \ + --logfile /freqtrade/user_data/logs/freqtrade.log \ + --freqaimodel LightGBMRegressor \ + --config /freqtrade/config_examples/$CONFIG_FILE \ + --strategy-path /freqtrade/templates \ + --strategy $STRATEGY_NAME \ + --timerange $START_DATE-$END_DATE \ + --fee 0.0008 \ + --breakdown day \ + --cache none >output.log 2>&1 +sed -i 's/\x1B\[[0-9;]*m//g' output.log + +#python3 tools/filter.py + +rm ./result/*.json -fr +rm ./result/*.py -fr +mv ./user_data/backtest_results/* ./result/ + +cd ./result +# 查找当前目录下的所有 zip 文件 +zip_files=(*.zip) + +# 检查是否只有一个 zip 文件 +if [ ${#zip_files[@]} -eq 1 ]; then + # 解压缩该 zip 文件到当前目录 + unzip "${zip_files[0]}" + rm *.zip + rm *.feather +else + echo "当前目录下没有 zip 文件或者有多个 zip 文件，无法操作。" +fi + +cd - +sed -i 's/\x1B\[[0-9;]*m//g' output.log +#python3 ../filter.py +cp output.log result/ -f +cd tools/ +python tradestocsv.py +python analytic.py >../result/analytic.log +cd ../ diff --git a/tools/download.sh b/tools/download.sh new file mode 100755 index 00000000..566199c7 --- /dev/null +++ b/tools/download.sh @@ -0,0 +1,99 @@ +#!/bin/bash + +# Function to extract the value of a parameter +get_param_value() { + local param="$1" + shift + while [[ $# -gt 0 ]]; do + case "$1" in + $param=*) + echo "${1#*=}" + return + ;; + $param) + # Check if the next argument exists and does not start with a dash + if [[ -n "$2" && "$2" != -* ]]; then + echo "$2" + return + else + echo "Error: Missing value for parameter $param" >&2 + exit 1 + fi + ;; + esac + shift + done + echo "Error: Parameter $param not found" >&2 + exit 1 +} + +# Function to extract comma-separated values +get_csv_param_value() { + local param="$1" + shift + while [[ $# -gt 0 ]]; do + case "$1" in + $param=*) + echo "${1#*=}" + return + ;; + $param) + # Check if the next argument exists and does not start with a dash + if [[ -n "$2" && "$2" != -* ]]; then + echo "$2" + return + else + echo "Error: Missing value for parameter $param" >&2 + exit 1 + fi + ;; + esac + shift + done + echo "" + return +} + +if [[ "$@" == *"--timerange"* ]] && [[ "$@" == *"--days"* ]]; then + echo "Error: Both --timerange and --days cannot be provided." + exit 1 +fi + +# Get timerange or days from parameters +timerange="" +days="" +if [[ "$@" == *"--timerange"* ]]; then + timerange=$(get_param_value "--timerange" "$@") +elif [[ "$@" == *"--days"* ]]; then + days=$(get_param_value "--days" "$@") +fi + +# Get pairs and timeframe from parameters or use defaults +pairs=$(get_csv_param_value "--pairs" "$@") +timeframe=$(get_csv_param_value "--timeframe" "$@") + +# Use default values if parameters are not provided +if [[ -z "$pairs" ]]; then + pairs="BTC/USDT,OKB/USDT,TON/USDT,DOT/USDT,SOL/USDT,XRP/USDT" +fi + +if [[ -z "$timeframe" ]]; then + timeframe="5m,15m,30m,1h,4h,6h,12h,1d" +fi + +# Convert timeframe string to array +IFS=',' read -r -a timeframe_array <<<"$timeframe" +timeframe_array_str=$(printf " '%s'" "${timeframe_array[@]}") + +# Initialize the base command +cmd="docker-compose run --rm freqtrade download-data --config /freqtrade/config_examples/basic.json --pairs $pairs --timeframe$timeframe_array_str" + +# Add timerange or days if provided +if [[ -n "$timerange" ]]; then + cmd+=" --timerange='$timerange'" +elif [[ -n "$days" ]]; then + cmd+=" --days=$days" +fi + +# Execute the command +eval "$cmd" diff --git a/tools/dryrun.sh b/tools/dryrun.sh new file mode 100755 index 00000000..71e66381 --- /dev/null +++ b/tools/dryrun.sh @@ -0,0 +1,119 @@ +#!/bin/bash +# 加载 .env 文件中的变量 +if [ -f ".env" ]; then + export $(grep -v '^#' .env | xargs) +else + echo "⚠️ 本地缺少 .env 文件，请创建并配置。" + exit 1 +fi + +# 获取当前分支名称 +CURRENT_BRANCH=$(git rev-parse --abbrev-ref HEAD) + +# 检查当前分支是否匹配 TEST_BRANCH 或 DRYRUN_BRANCH +if [[ "$CURRENT_BRANCH" != "$TEST_BRANCH" && "$CURRENT_BRANCH" != "$DRYRUN_BRANCH" ]]; then + echo "⚠️ 错误：当前分支 '$CURRENT_BRANCH' 不符合环境变量配置的预期。" + echo "请确保当前分支与 .env 文件中的 TEST_BRANCH 或 DRYRUN_BRANCH 配置一致。" + echo "TEST_BRANCH=$TEST_BRANCH" + echo "DRYRUN_BRANCH=$DRYRUN_BRANCH" + exit 1 +else + echo "✅ 当前分支 '$CURRENT_BRANCH' 符合环境变量配置要求。" +fi + +# 检查当前分支名称是否包含 "dryrun" +CURRENT_BRANCH=$(git rev-parse --abbrev-ref HEAD) +if [[ "$CURRENT_BRANCH" != *"dryrun"* ]]; then + echo "⚠️ 警告：当前分支名称为 '$CURRENT_BRANCH'，不包含 'dryrun'。" + echo "⚠️ 确保您正在正确的分支上运行此脚本。" + read -p "是否继续？(y/n): " confirm + if [[ "$confirm" != "y" && "$confirm" != "Y" ]]; then + echo "已取消执行。" + exit 1 + fi +fi + +# 如果当前分支名称包含 "dryrun"，执行 git reset --hard +if [[ "$CURRENT_BRANCH" == *"dryrun"* ]]; then + echo "当前分支为 '$CURRENT_BRANCH'，正在执行 git reset --hard 以确保代码干净..." + git reset --hard + if [ $? -ne 0 ]; then + echo "⚠️ 执行 git reset --hard 失败，请检查 Git 状态。" + exit 1 + fi + echo "Git 工作区已清理。" +fi + +# 检查 .env 文件 +if [ ! -f ".env" ]; then + echo "⚠️ 本地缺少 .env 文件，请创建并配置。示例内容如下：" + echo "" + echo "STRATEGY_NAME=TheForceV7" + echo "CONFIG_FILE=basic.json" + echo "TEST_BRANCH=theforce-noai-test" + echo "DRYRUN_BRANCH=theforce-noai-dryrun" + echo "" + exit 1 +fi +# 加载 .env 文件中的变量 +export $(grep -v '^#' .env | xargs) +# 设置默认值 +STRATEGY_NAME=${STRATEGY_NAME:-TheForceV7} +CONFIG_FILE=${CONFIG_FILE:-basic.json} + +echo "Using strategy: $STRATEGY_NAME" +echo "Using config: $CONFIG_FILE" +echo "Using testBranch: $TEST_BRANCH" +# Parse command line arguments +START_DATE=${1:-$(date -d "2 days ago" +"%Y%m%d")} +END_DATE=${2:-$(date -d "tomorrow" +"%Y%m%d")} + +cd ../ +source .venv/bin/activate +rm -rf user_data/models/* +rm -rf ./freqtrade/user_data/data/backtest_results/* +rm -fr ./user_data/dryrun_results/* +rm result/* + +hyperopt_config="${STRATEGY_NAME%.py}.json" +docker rm $(docker ps -aq) -f + +# 获取当前 Git Commit 的前 8 位 +GIT_COMMIT_SHORT=$(git rev-parse HEAD | cut -c 1-8) +docker-compose run -d --rm --name freqtrade-dryrun-${GIT_COMMIT_SHORT} -p 8080:8080 freqtrade trade \ + --logfile /freqtrade/user_data/logs/freqtrade.log \ + --db-url sqlite:////freqtrade/user_data/tradesv3.sqlite \ + --freqaimodel LightGBMRegressor \ + --config /freqtrade/config_examples/$CONFIG_FILE \ + --strategy $STRATEGY_NAME \ + --fee 0.0008 \ + --strategy-path /freqtrade/templates + +#python3 tools/filter.py + +# rm ./result/*.json -fr +# rm ./result/*.py -fr +# mv ./user_data/backtest_results/* ./result/ +# +# cd ./result +# # 查找当前目录下的所有 zip 文件 +# zip_files=(*.zip) +# +# # 检查是否只有一个 zip 文件 +# if [ ${#zip_files[@]} -eq 1 ]; then +# # 解压缩该 zip 文件到当前目录 +# unzip "${zip_files[0]}" +# rm *.zip +# rm *.feather +# else +# echo "当前目录下没有 zip 文件或者有多个 zip 文件，无法操作。" +# fi +# +# cd - +# sed -i 's/\x1B\[[0-9;]*m//g' output.log +# #python3 ../filter.py +# cp output.log result/ -f +# cd tools/ +# python tradestocsv.py +# python analytic.py >../result/analytic.log +# cd ../ diff --git a/tools/filter.py b/tools/filter.py new file mode 100644 index 00000000..81292c26 --- /dev/null +++ b/tools/filter.py @@ -0,0 +1,11 @@ +import re + +pattern = re.compile(r'validation_0') + +with open('output.log', 'r') as input_file, open('output_filted.log', 'w') as output_file: + for line in input_file: + if "validation_0" not in line: + output_file.write(line) + else: + if "99" in line[:5]: + output_file.write(line) diff --git a/tools/gitpush.sh b/tools/gitpush.sh new file mode 100755 index 00000000..3be0eb27 --- /dev/null +++ b/tools/gitpush.sh @@ -0,0 +1,48 @@ +#!/bin/bash + +#!/bin/bash + +# 默认提交信息 +commit_msg="update" + +# 解析命令行参数 -m 指定提交信息 +while getopts m: option; do + case "${option}" in + m) commit_msg=${OPTARG} ;; + esac +done + +cd .. + +# 检查 result/ 是否已经在 .gitignore 中 +IGNORED=$(grep -c "^result/" .gitignore) + +# 创建标志文件路径 +LOCK_FILE=".gitignore.lock" + +# 如果 result/ 不在 .gitignore 中，则临时加入，并记录 +if [ "$IGNORED" -eq 0 ]; then + echo "result/" >>.gitignore + echo "已临时将 result/ 添加到 .gitignore" + touch $LOCK_FILE +else + echo "result/ 已经在 .gitignore 中，跳过处理" +fi + +rm output*.log +# 停止当前可能存在的交易进程（可选） +# pkill -f "freqtrade trade" || true + +# 执行 Git 操作 +git add . +git commit --no-verify -m "$commit_msg" +git push + +# 如果之前临时加入了 result/ 到 .gitignore，则现在恢复 +if [ -f "$LOCK_FILE" ]; then + sed -i '/^result\//d' .gitignore + rm -f $LOCK_FILE + echo "已恢复 .gitignore，result/ 重新纳入版本控制" +fi + +echo "Git push 完成" diff --git a/tools/hyperopt.sh b/tools/hyperopt.sh new file mode 100755 index 00000000..ca08c08b --- /dev/null +++ b/tools/hyperopt.sh @@ -0,0 +1,88 @@ +#!/bin/bash + +# 检查 .env 文件 +if [ ! -f ".env" ]; then + echo "⚠️ 本地缺少 .env 文件，请创建并配置。示例内容如下：" + echo "" + echo "STRATEGY_NAME=TheForceV7" + echo "CONFIG_FILE=basic.json" + echo "TEST_BRANCH=theforce-noai-test" + echo "DRYRUN_BRANCH=theforce-noai-dryrun" + echo "" + exit 1 +fi + +# 加载 .env 文件中的变量 +export $(grep -v '^#' .env | xargs) +# 设置默认值 +STRATEGY_NAME=${STRATEGY_NAME:-TheForceV7} +CONFIG_FILE=${CONFIG_FILE:-basic.json} + +echo "Using strategy: $STRATEGY_NAME" +echo "Using config: $CONFIG_FILE" +echo "Using testBranch: $TEST_BRANCH" +# Parse command line arguments +START_DATE=${1:-$(date -d "2 days ago" +"%Y%m%d")} +END_DATE=${2:-$(date -d "tomorrow" +"%Y%m%d")} + +cd ../ +source .venv/bin/activate +rm -rf user_data/models/* +rm -rf ./freqtrade/user_data/data/backtest_results/* +rm -fr ./user_data/dryrun_results/* + +#docker-compose -f docker-compose_backtest.yml run --rm freqtrade >output.log 2>&1 +echo "docker-compose run --rm freqtrade hyperopt \ + --logfile /freqtrade/user_data/logs/freqtrade.log \ + --freqaimodel LightGBMRegressor \ + --strategy $STRATEGY_NAME \ + --config /freqtrade/config_examples/$CONFIG_FILE \ + --strategy-path /freqtrade/templates \ + --timerange ${START_DATE}-${END_DATE} \ + -e 200 \ + --hyperopt-loss ShortTradeDurHyperOptLoss \ + --spaces roi stoploss trailing \ + --fee 0.0016" +docker-compose run --rm freqtrade hyperopt \ + --logfile /freqtrade/user_data/logs/freqtrade.log \ + --freqaimodel LightGBMRegressor \ + --strategy $STRATEGY_NAME \ + --config /freqtrade/config_examples/$CONFIG_FILE \ + --strategy-path /freqtrade/templates \ + --timerange ${START_DATE}-${END_DATE} \ + -e 200 \ + --hyperopt-loss ShortTradeDurHyperOptLoss \ + --spaces roi stoploss trailing \ + --fee 0.0016 + +#>output.log 2>&1 +#sed -i 's/\x1B\[[0-9;]*m//g' output.log + +#python3 tools/filter.py + +# rm ./result/*.json -fr +# rm ./result/*.py -fr +# mv ./user_data/backtest_results/* ./result/ +# +# cd ./result +# # 查找当前目录下的所有 zip 文件 +# zip_files=(*.zip) +# +# # 检查是否只有一个 zip 文件 +# if [ ${#zip_files[@]} -eq 1 ]; then +# # 解压缩该 zip 文件到当前目录 +# unzip "${zip_files[0]}" +# rm *.zip +# rm *.feather +# else +# echo "当前目录下没有 zip 文件或者有多个 zip 文件，无法操作。" +# fi +# +# cd - +# sed -i 's/\x1B\[[0-9;]*m//g' output.log +# #python3 ../filter.py +# cp output.log result/ -f +# cd tools/ +# python tradestocsv.py +# python analytic.py >../result/analytic.log +# cd ../ diff --git a/tools/tradestocsv.py b/tools/tradestocsv.py new file mode 100644 index 00000000..0cadef1f --- /dev/null +++ b/tools/tradestocsv.py @@ -0,0 +1,50 @@ +import json +import pandas as pd +import os +from pathlib import Path + +# 定义结果目录 +result_dir = Path('../result') + +# 确保结果目录存在 +if not result_dir.exists(): + raise FileNotFoundError(f"Directory {result_dir} does not exist") + +# 寻找文件名包含 'backtest-result-' 的 JSON 文件 +json_files = [f for f in result_dir.glob('*.json') if 'backtest-result-' in f.name] + +if not json_files: + raise FileNotFoundError("No JSON files with 'backtest-result-' in name found in ../result") + +# 找到文件大小最大的 JSON 文件 +largest_file = max(json_files, key=lambda x: x.stat().st_size) + +# 读取最大的 JSON 文件 +with open(largest_file) as f: + data = json.load(f) + +# 从环境变量中获取策略名称 +strategy_name = os.environ.get('STRATEGY_NAME', 'TheForceV7') # 如果未设置环境变量，则使用默认值 'TheForceV7' + +# 提取交易记录 +trades = data['strategy'][strategy_name]['trades'] +trades_df = pd.DataFrame(trades) + +# 选择关键字段 +trades_df = trades_df[[ + 'pair', 'open_date', 'close_date', 'open_rate', 'close_rate', 'amount', + 'profit_ratio', 'profit_abs', 'exit_reason', 'fee_open', 'fee_close', + 'trade_duration', 'min_rate', 'max_rate' +]] + +# 转换为本地时间（可选） +trades_df['open_date'] = pd.to_datetime(trades_df['open_date']) +trades_df['close_date'] = pd.to_datetime(trades_df['close_date']) + +# 定义输出 CSV 文件路径（在 ../result 目录下） +output_csv = result_dir / 'backtest_trades.csv' + +# 保存为 CSV +trades_df.to_csv(output_csv, index=False) + +print(f"Successfully converted {largest_file} to {output_csv}") diff --git a/tools/view_feather.py b/tools/view_feather.py new file mode 100644 index 00000000..f9e648ec --- /dev/null +++ b/tools/view_feather.py @@ -0,0 +1,65 @@ +import argparse +import pandas as pd + +def analyze_candlestick_data(file_path): + # 读取feather文件 + df = pd.read_feather(file_path) + + # 查看数据集行数和列数 + rows, columns = df.shape + + if rows < 500: + # 短表数据（行数少于500）查看全量数据信息 + print('数据全部内容信息：') + print(df.to_csv(sep='\t', na_rep='nan')) + else: + # 长表数据查看数据前几行信息 + print('数据前几行内容信息：') + print(df.head().to_csv(sep='\t', na_rep='nan')) + + # 查看数据的基本信息 + print('数据基本信息：') + df.info() + + # 查看数据集行数和列数 + rows, columns = df.shape + + if columns < 10 and rows < 500: + # 短表窄数据（列少于10且行数少于500）查看全量统计信息 + print('数据全部内容描述性统计信息：') + print(df.describe(include='all', percentiles=[.25, .5, .75]).to_csv(sep='\t', na_rep='nan')) + else: + # 长表数据查看数据前几行统计信息 + print('数据前几行描述性统计信息：') + print(df.head().describe(include='all', percentiles=[.25, .5, .75]).to_csv(sep='\t', na_rep='nan')) + + # 计算时间跨度 + min_date = df['date'].min() + max_date = df['date'].max() + time_span = max_date - min_date + + # 检查时间序列完整性 + df = df.sort_values('date') # 确保数据按时间排序 + df['time_diff'] = df['date'].diff().dt.total_seconds() # 计算相邻时间点的差值(秒) + expected_freq = df['time_diff'].mode()[0] # 使用最常见的间隔作为预期频率 + missing_intervals = df[df['time_diff'] > expected_freq] # 找出间隔大于预期的位置 + + print(f"\n数据时间跨度：{time_span}") + print(f"开始时间：{min_date}") + print(f"结束时间：{max_date}") + + if missing_intervals.empty: + print("数据完整性：完整，未发现缺失的蜡烛图数据") + else: + print(f"数据完整性：不完整，发现 {len(missing_intervals)} 处可能的缺失") + print("缺失位置示例：") + for _, row in missing_intervals.head(5).iterrows(): # 显示前5个缺失示例 + gap_duration = pd.Timedelta(seconds=row['time_diff']) + print(f" - 在 {row['date']} 之前缺失了 {gap_duration}") + +if __name__ == "__main__": + parser = argparse.ArgumentParser(description='分析Freqtrade蜡烛图Feather文件') + parser.add_argument('--path', required=True, help='Feather文件路径') + args = parser.parse_args() + + analyze_candlestick_data(args.path) diff --git a/utf8.py b/utf8.py new file mode 100644 index 00000000..64b52312 --- /dev/null +++ b/utf8.py @@ -0,0 +1,18 @@ +import chardet +import codecs + +def convert_encoding(input_file, output_file): + # 检测文件编码 + with open(input_file, 'rb') as f: + result = chardet.detect(f.read()) + encoding = result['encoding'] + + # 以检测到的编码读取文件内容，并以UTF-8编码写入新文件 + with codecs.open(input_file, 'r', encoding=encoding) as infile, \ + codecs.open(output_file, 'w', encoding='utf-8') as outfile: + outfile.write(infile.read()) + +if __name__ == "__main__": + input_file = 'freqtrade.log' # 替换为实际的输入文件名 + output_file = 'freqtrade_utf8.log' # 替换为你想要的输出文件名 + convert_encoding(input_file, output_file) diff --git a/your_output_file.log b/your_output_file.log new file mode 100644 index 00000000..13c51d31 --- /dev/null +++ b/your_output_file.log @@ -0,0 +1,3066 @@ +Creating freqtrade_freqtrade_run ... +Creating freqtrade_freqtrade_run ... done +2025-04-29 01:54:55,246 - freqtrade - INFO - freqtrade 2025.3 +2025-04-29 01:54:55,464 - numexpr.utils - INFO - NumExpr defaulting to 12 threads. +2025-04-29 01:54:56,878 - freqtrade.configuration.load_config - INFO - Using config: /freqtrade/config_examples/config_freqai.okx.json ... +2025-04-29 01:54:56,879 - freqtrade.configuration.load_config - INFO - Using config: /freqtrade/templates/FreqaiExampleStrategy.json ... +2025-04-29 01:54:56,881 - freqtrade.loggers - INFO - Enabling colorized output. +2025-04-29 01:54:56,881 - root - INFO - Logfile configured +2025-04-29 01:54:56,882 - freqtrade.loggers - INFO - Verbosity set to 0 +2025-04-29 01:54:56,882 - freqtrade.configuration.configuration - INFO - Using additional Strategy lookup path: /freqtrade/templates +2025-04-29 01:54:56,883 - freqtrade.configuration.configuration - INFO - Using max_open_trades: 4 ... +2025-04-29 01:54:56,883 - freqtrade.configuration.configuration - INFO - Parameter --timerange detected: 20250101-20250420 ... +2025-04-29 01:54:56,907 - freqtrade.configuration.configuration - INFO - Using user-data directory: /freqtrade/user_data ... +2025-04-29 01:54:56,908 - freqtrade.configuration.configuration - INFO - Using data directory: /freqtrade/user_data/data/okx ... +2025-04-29 01:54:56,908 - freqtrade.configuration.configuration - INFO - Parameter --cache=none detected ... +2025-04-29 01:54:56,908 - freqtrade.configuration.configuration - INFO - Filter trades by timerange: 20250101-20250420 +2025-04-29 01:54:56,909 - freqtrade.configuration.configuration - INFO - Using freqaimodel class name: XGBoostRegressor +2025-04-29 01:54:56,910 - freqtrade.exchange.check_exchange - INFO - Checking exchange... +2025-04-29 01:54:56,916 - freqtrade.exchange.check_exchange - INFO - Exchange "okx" is officially supported by the Freqtrade development team. +2025-04-29 01:54:56,916 - freqtrade.configuration.configuration - INFO - Using pairlist from configuration. +2025-04-29 01:54:56,917 - freqtrade.configuration.config_validation - INFO - Validating configuration ... +2025-04-29 01:54:56,919 - freqtrade.commands.optimize_commands - INFO - Starting freqtrade in Backtesting mode +2025-04-29 01:54:56,919 - freqtrade.exchange.exchange - INFO - Instance is running with dry_run enabled +2025-04-29 01:54:56,920 - freqtrade.exchange.exchange - INFO - Using CCXT 4.4.69 +2025-04-29 01:54:56,920 - freqtrade.exchange.exchange - INFO - Applying additional ccxt config: {'enableRateLimit': True, 'rateLimit': 500, 'options': {'defaultType': 'spot'}} +2025-04-29 01:54:56,925 - freqtrade.exchange.exchange - INFO - Applying additional ccxt config: {'enableRateLimit': True, 'rateLimit': 500, 'options': {'defaultType': 'spot'}, 'timeout': 20000} +2025-04-29 01:54:56,931 - freqtrade.exchange.exchange - INFO - Using Exchange "OKX" +2025-04-29 01:54:59,471 - freqtrade.resolvers.exchange_resolver - INFO - Using resolved exchange 'Okx'... +2025-04-29 01:54:59,491 - freqtrade.resolvers.iresolver - INFO - Using resolved strategy FreqaiExampleStrategy from '/freqtrade/templates/FreqaiExampleStrategy.py'... +2025-04-29 01:54:59,491 - freqtrade.strategy.hyper - INFO - Loading parameters from file /freqtrade/templates/FreqaiExampleStrategy.json +2025-04-29 01:54:59,492 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'timeframe' with value in config file: 3m. +2025-04-29 01:54:59,492 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'stoploss' with value in config file: -0.05. +2025-04-29 01:54:59,493 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'stake_currency' with value in config file: USDT. +2025-04-29 01:54:59,493 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'stake_amount' with value in config file: 150. +2025-04-29 01:54:59,493 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'startup_candle_count' with value in config file: 30. +2025-04-29 01:54:59,494 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'unfilledtimeout' with value in config file: {'entry': 5, 'exit': 15, 'exit_timeout_count': 0, 'unit': +'minutes'}. +2025-04-29 01:54:59,494 - freqtrade.resolvers.strategy_resolver - INFO - Override strategy 'max_open_trades' with value in config file: 4. +2025-04-29 01:54:59,494 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using minimal_roi: {'0': 0.132, '8': 0.047, '14': 0.007, '60': 0} +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using timeframe: 3m +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using stoploss: -0.05 +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_stop: True +2025-04-29 01:54:59,495 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_stop_positive: 0.01 +2025-04-29 01:54:59,496 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_stop_positive_offset: 0.02 +2025-04-29 01:54:59,496 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using trailing_only_offset_is_reached: False +2025-04-29 01:54:59,496 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using use_custom_stoploss: False +2025-04-29 01:54:59,497 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using process_only_new_candles: True +2025-04-29 01:54:59,497 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using order_types: {'entry': 'limit', 'exit': 'limit', 'stoploss': 'limit', 'stoploss_on_exchange': False, +'stoploss_on_exchange_interval': 60} +2025-04-29 01:54:59,497 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using order_time_in_force: {'entry': 'GTC', 'exit': 'GTC'} +2025-04-29 01:54:59,498 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using stake_currency: USDT +2025-04-29 01:54:59,498 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using stake_amount: 150 +2025-04-29 01:54:59,498 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using startup_candle_count: 30 +2025-04-29 01:54:59,499 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using unfilledtimeout: {'entry': 5, 'exit': 15, 'exit_timeout_count': 0, 'unit': 'minutes'} +2025-04-29 01:54:59,499 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using use_exit_signal: True +2025-04-29 01:54:59,499 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using exit_profit_only: False +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using ignore_roi_if_entry_signal: False +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using exit_profit_offset: 0.0 +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using disable_dataframe_checks: False +2025-04-29 01:54:59,500 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using ignore_buying_expired_candle_after: 0 +2025-04-29 01:54:59,501 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using position_adjustment_enable: False +2025-04-29 01:54:59,501 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using max_entry_position_adjustment: -1 +2025-04-29 01:54:59,501 - freqtrade.resolvers.strategy_resolver - INFO - Strategy using max_open_trades: 4 +2025-04-29 01:54:59,502 - freqtrade.configuration.config_validation - INFO - Validating configuration ... +2025-04-29 01:54:59,505 - freqtrade.resolvers.iresolver - INFO - Using resolved pairlist StaticPairList from '/freqtrade/freqtrade/plugins/pairlist/StaticPairList.py'... +2025-04-29 01:54:59,512 - freqtrade.optimize.backtesting - INFO - Using fee 0.1500% - worst case fee from exchange (lowest tier). +2025-04-29 01:54:59,512 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 3m to 14450 +2025-04-29 01:54:59,513 - freqtrade.data.history.history_utils - INFO - Using indicator startup period: 14450 ... +2025-04-29 01:54:59,672 - freqtrade.optimize.backtesting - INFO - Loading data from 2024-12-01 21:30:00 up to 2025-04-20 00:00:00 (139 days). +2025-04-29 01:54:59,672 - freqtrade.optimize.backtesting - INFO - Dataload complete. Calculating indicators +2025-04-29 01:54:59,673 - freqtrade.optimize.backtesting - INFO - Running backtesting for Strategy FreqaiExampleStrategy +2025-04-29 01:55:01,274 - matplotlib.font_manager - INFO - generated new fontManager +2025-04-29 01:55:01,489 - freqtrade.resolvers.iresolver - INFO - Using resolved freqaimodel XGBoostRegressor from '/freqtrade/freqtrade/freqai/prediction_models/XGBoostRegressor.py'... +2025-04-29 01:55:01,490 - freqtrade.freqai.data_drawer - INFO - Could not find existing datadrawer, starting from scratch +2025-04-29 01:55:01,491 - freqtrade.freqai.data_drawer - INFO - Could not find existing historic_predictions, starting from scratch +2025-04-29 01:55:01,491 - freqtrade.freqai.freqai_interface - INFO - Set fresh train queue from whitelist. Queue: ['BTC/USDT', 'SOL/USDT'] +2025-04-29 01:55:01,492 - freqtrade.strategy.hyper - INFO - Strategy Parameter: buy_rsi = 39.92672300850069 +2025-04-29 01:55:01,492 - freqtrade.strategy.hyper - INFO - Strategy Parameter: sell_rsi = 69.92672300850067 +2025-04-29 01:55:01,493 - freqtrade.strategy.hyper - INFO - No params for protection found, using default values. +2025-04-29 01:55:01,498 - FreqaiExampleStrategy - INFO - 处理交易对：BTC/USDT +2025-04-29 01:55:01,500 - freqtrade.freqai.freqai_interface - INFO - Training 11 timeranges +2025-04-29 01:55:01,501 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2024-12-02 00:00:00 to 2025-01-01 00:00:00, 1/11 trains +2025-04-29 01:55:01,502 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1735689600_prediction.feather +2025-04-29 01:55:01,602 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 5m to 8690 +2025-04-29 01:55:01,603 - freqtrade.data.dataprovider - INFO - Loading data for BTC/USDT 5m from 2024-12-01 19:50:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:01,705 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 1h to 770 +2025-04-29 01:55:01,706 - freqtrade.data.dataprovider - INFO - Loading data for BTC/USDT 1h from 2024-11-29 22:00:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:01,814 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 3m to 14450 +2025-04-29 01:55:01,815 - freqtrade.data.dataprovider - INFO - Loading data for ETH/USDT 3m from 2024-12-01 21:30:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:01,942 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 5m to 8690 +2025-04-29 01:55:01,943 - freqtrade.data.dataprovider - INFO - Loading data for ETH/USDT 5m from 2024-12-01 19:50:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:02,037 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 1h to 770 +2025-04-29 01:55:02,038 - freqtrade.data.dataprovider - INFO - Loading data for ETH/USDT 1h from 2024-11-29 22:00:00 to 2025-04-20 00:00:00 +2025-04-29 01:55:02,113 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:02,118 - FreqaiExampleStrategy - INFO - 目标列形状：(14450,) +2025-04-29 01:55:02,121 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.152831 +1 0.003285 50.152831 +2 0.001898 50.152831 +3 0.000484 50.152831 +4 0.001688 50.152831 +2025-04-29 01:55:02,123 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:02,129 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:55:02,130 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.202701 +1 0.003285 50.202701 +2 0.001898 50.202701 +3 0.000484 50.202701 +4 0.001688 50.202701 +2025-04-29 01:55:02,134 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1735689600/cb_btc_1735689600 +2025-04-29 01:55:02,135 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:02,151 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:02,152 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-02 to 2024-12-31 -------------------- +2025-04-29 01:55:07,277 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:07,278 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.24624 validation_1-rmse:0.26036 +[1] validation_0-rmse:0.24176 validation_1-rmse:0.25460 +[2] validation_0-rmse:0.23782 validation_1-rmse:0.24904 +[3] validation_0-rmse:0.23408 validation_1-rmse:0.24381 +[4] validation_0-rmse:0.23057 validation_1-rmse:0.23882 +[5] validation_0-rmse:0.22701 validation_1-rmse:0.23409 +[6] validation_0-rmse:0.22400 validation_1-rmse:0.22962 +[7] validation_0-rmse:0.22088 validation_1-rmse:0.22533 +[8] validation_0-rmse:0.21817 validation_1-rmse:0.22130 +[9] validation_0-rmse:0.21491 validation_1-rmse:0.21740 +[10] validation_0-rmse:0.21265 validation_1-rmse:0.21347 +[11] validation_0-rmse:0.20982 validation_1-rmse:0.20978 +[12] validation_0-rmse:0.20747 validation_1-rmse:0.20640 +[13] validation_0-rmse:0.20512 validation_1-rmse:0.20299 +[14] validation_0-rmse:0.20280 validation_1-rmse:0.19966 +[15] validation_0-rmse:0.20012 validation_1-rmse:0.19656 +[16] validation_0-rmse:0.19785 validation_1-rmse:0.19346 +[17] validation_0-rmse:0.19572 validation_1-rmse:0.19054 +[18] validation_0-rmse:0.19400 validation_1-rmse:0.18759 +[19] validation_0-rmse:0.19164 validation_1-rmse:0.18488 +[20] validation_0-rmse:0.18956 validation_1-rmse:0.18205 +[21] validation_0-rmse:0.18746 validation_1-rmse:0.17951 +[22] validation_0-rmse:0.18593 validation_1-rmse:0.17696 +[23] validation_0-rmse:0.18395 validation_1-rmse:0.17465 +[24] validation_0-rmse:0.18249 validation_1-rmse:0.17217 +[25] validation_0-rmse:0.18084 validation_1-rmse:0.16993 +[26] validation_0-rmse:0.17928 validation_1-rmse:0.16771 +[27] validation_0-rmse:0.17776 validation_1-rmse:0.16571 +[28] validation_0-rmse:0.17652 validation_1-rmse:0.16356 +[29] validation_0-rmse:0.17499 validation_1-rmse:0.16166 +[30] validation_0-rmse:0.17371 validation_1-rmse:0.15983 +[31] validation_0-rmse:0.17243 validation_1-rmse:0.15792 +[32] validation_0-rmse:0.17110 validation_1-rmse:0.15628 +[33] validation_0-rmse:0.16996 validation_1-rmse:0.15433 +[34] validation_0-rmse:0.16884 validation_1-rmse:0.15277 +[35] validation_0-rmse:0.16785 validation_1-rmse:0.15090 +[36] validation_0-rmse:0.16682 validation_1-rmse:0.14942 +[37] validation_0-rmse:0.16559 validation_1-rmse:0.14774 +[38] validation_0-rmse:0.16459 validation_1-rmse:0.14628 +[39] validation_0-rmse:0.16356 validation_1-rmse:0.14466 +[40] validation_0-rmse:0.16250 validation_1-rmse:0.14330 +[41] validation_0-rmse:0.16153 validation_1-rmse:0.14201 +[42] validation_0-rmse:0.16059 validation_1-rmse:0.14075 +[43] validation_0-rmse:0.15986 validation_1-rmse:0.13938 +[44] validation_0-rmse:0.15908 validation_1-rmse:0.13822 +[45] validation_0-rmse:0.15810 validation_1-rmse:0.13687 +[46] validation_0-rmse:0.15733 validation_1-rmse:0.13577 +[47] validation_0-rmse:0.15655 validation_1-rmse:0.13458 +[48] validation_0-rmse:0.15580 validation_1-rmse:0.13355 +[49] validation_0-rmse:0.15512 validation_1-rmse:0.13228 +[50] validation_0-rmse:0.15434 validation_1-rmse:0.13121 +[51] validation_0-rmse:0.15363 validation_1-rmse:0.13030 +[52] validation_0-rmse:0.15294 validation_1-rmse:0.12937 +[53] validation_0-rmse:0.15243 validation_1-rmse:0.12818 +[54] validation_0-rmse:0.15170 validation_1-rmse:0.12720 +[55] validation_0-rmse:0.15096 validation_1-rmse:0.12632 +[56] validation_0-rmse:0.15035 validation_1-rmse:0.12538 +[57] validation_0-rmse:0.14977 validation_1-rmse:0.12453 +[58] validation_0-rmse:0.14914 validation_1-rmse:0.12363 +[59] validation_0-rmse:0.14867 validation_1-rmse:0.12263 +[60] validation_0-rmse:0.14819 validation_1-rmse:0.12183 +[61] validation_0-rmse:0.14763 validation_1-rmse:0.12108 +[62] validation_0-rmse:0.14706 validation_1-rmse:0.12035 +[63] validation_0-rmse:0.14648 validation_1-rmse:0.11946 +[64] validation_0-rmse:0.14601 validation_1-rmse:0.11876 +[65] validation_0-rmse:0.14553 validation_1-rmse:0.11808 +[66] validation_0-rmse:0.14506 validation_1-rmse:0.11742 +[67] validation_0-rmse:0.14469 validation_1-rmse:0.11671 +[68] validation_0-rmse:0.14422 validation_1-rmse:0.11604 +[69] validation_0-rmse:0.14381 validation_1-rmse:0.11543 +[70] validation_0-rmse:0.14337 validation_1-rmse:0.11485 +[71] validation_0-rmse:0.14294 validation_1-rmse:0.11398 +[72] validation_0-rmse:0.14260 validation_1-rmse:0.11335 +[73] validation_0-rmse:0.14223 validation_1-rmse:0.11278 +[74] validation_0-rmse:0.14190 validation_1-rmse:0.11225 +[75] validation_0-rmse:0.14144 validation_1-rmse:0.11143 +[76] validation_0-rmse:0.14098 validation_1-rmse:0.11052 +[77] validation_0-rmse:0.14062 validation_1-rmse:0.10998 +[78] validation_0-rmse:0.14029 validation_1-rmse:0.10953 +[79] validation_0-rmse:0.13993 validation_1-rmse:0.10888 +[80] validation_0-rmse:0.13958 validation_1-rmse:0.10839 +[81] validation_0-rmse:0.13918 validation_1-rmse:0.10767 +[82] validation_0-rmse:0.13897 validation_1-rmse:0.10720 +[83] validation_0-rmse:0.13864 validation_1-rmse:0.10669 +[84] validation_0-rmse:0.13836 validation_1-rmse:0.10620 +[85] validation_0-rmse:0.13810 validation_1-rmse:0.10573 +[86] validation_0-rmse:0.13782 validation_1-rmse:0.10526 +[87] validation_0-rmse:0.13756 validation_1-rmse:0.10458 +[88] validation_0-rmse:0.13736 validation_1-rmse:0.10420 +[89] validation_0-rmse:0.13708 validation_1-rmse:0.10383 +[90] validation_0-rmse:0.13685 validation_1-rmse:0.10343 +[91] validation_0-rmse:0.13658 validation_1-rmse:0.10298 +[92] validation_0-rmse:0.13646 validation_1-rmse:0.10231 +[93] validation_0-rmse:0.13615 validation_1-rmse:0.10190 +[94] validation_0-rmse:0.13589 validation_1-rmse:0.10154 +[95] validation_0-rmse:0.13572 validation_1-rmse:0.10095 +[96] validation_0-rmse:0.13550 validation_1-rmse:0.10058 +[97] validation_0-rmse:0.13530 validation_1-rmse:0.10026 +[98] validation_0-rmse:0.13513 validation_1-rmse:0.09995 +[99] validation_0-rmse:0.13480 validation_1-rmse:0.09950 +2025-04-29 01:55:08,221 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (6.09 secs) -------------------- +2025-04-29 01:55:08,222 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:08,903 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2024-12-12 00:00:00 to 2025-01-11 00:00:00, 2/11 trains +2025-04-29 01:55:08,904 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1736553600_prediction.feather +2025-04-29 01:55:08,907 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:08,912 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:55:08,914 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.202701 +1 0.003285 50.202701 +2 0.001898 50.202701 +3 0.000484 50.202701 +4 0.001688 50.202701 +2025-04-29 01:55:08,917 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:08,924 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:55:08,925 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.367593 +1 0.003285 50.367593 +2 0.001898 50.367593 +3 0.000484 50.367593 +4 0.001688 50.367593 +2025-04-29 01:55:08,929 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1736553600/cb_btc_1736553600 +2025-04-29 01:55:08,930 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:08,946 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:08,947 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-12 to 2025-01-10 -------------------- +2025-04-29 01:55:13,908 - datasieve.pipeline - INFO - DI tossed 5 predictions for being too far from training data. +2025-04-29 01:55:13,911 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:13,912 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.26037 validation_1-rmse:0.25324 +[1] validation_0-rmse:0.25572 validation_1-rmse:0.24787 +[2] validation_0-rmse:0.25117 validation_1-rmse:0.24281 +[3] validation_0-rmse:0.24697 validation_1-rmse:0.23802 +[4] validation_0-rmse:0.24328 validation_1-rmse:0.23332 +[5] validation_0-rmse:0.23939 validation_1-rmse:0.22905 +[6] validation_0-rmse:0.23522 validation_1-rmse:0.22484 +[7] validation_0-rmse:0.23148 validation_1-rmse:0.22085 +[8] validation_0-rmse:0.22873 validation_1-rmse:0.21697 +[9] validation_0-rmse:0.22519 validation_1-rmse:0.21317 +[10] validation_0-rmse:0.22206 validation_1-rmse:0.20963 +[11] validation_0-rmse:0.21866 validation_1-rmse:0.20626 +[12] validation_0-rmse:0.21563 validation_1-rmse:0.20296 +[13] validation_0-rmse:0.21313 validation_1-rmse:0.19956 +[14] validation_0-rmse:0.21062 validation_1-rmse:0.19636 +[15] validation_0-rmse:0.20808 validation_1-rmse:0.19339 +[16] validation_0-rmse:0.20570 validation_1-rmse:0.19058 +[17] validation_0-rmse:0.20318 validation_1-rmse:0.18781 +[18] validation_0-rmse:0.20113 validation_1-rmse:0.18518 +[19] validation_0-rmse:0.19934 validation_1-rmse:0.18248 +[20] validation_0-rmse:0.19735 validation_1-rmse:0.18006 +[21] validation_0-rmse:0.19541 validation_1-rmse:0.17744 +[22] validation_0-rmse:0.19336 validation_1-rmse:0.17517 +[23] validation_0-rmse:0.19145 validation_1-rmse:0.17301 +[24] validation_0-rmse:0.18989 validation_1-rmse:0.17058 +[25] validation_0-rmse:0.18782 validation_1-rmse:0.16854 +[26] validation_0-rmse:0.18634 validation_1-rmse:0.16625 +[27] validation_0-rmse:0.18471 validation_1-rmse:0.16430 +[28] validation_0-rmse:0.18312 validation_1-rmse:0.16236 +[29] validation_0-rmse:0.18157 validation_1-rmse:0.16053 +[30] validation_0-rmse:0.17991 validation_1-rmse:0.15849 +[31] validation_0-rmse:0.17839 validation_1-rmse:0.15677 +[32] validation_0-rmse:0.17693 validation_1-rmse:0.15498 +[33] validation_0-rmse:0.17574 validation_1-rmse:0.15336 +[34] validation_0-rmse:0.17469 validation_1-rmse:0.15168 +[35] validation_0-rmse:0.17352 validation_1-rmse:0.15015 +[36] validation_0-rmse:0.17228 validation_1-rmse:0.14868 +[37] validation_0-rmse:0.17127 validation_1-rmse:0.14692 +[38] validation_0-rmse:0.17030 validation_1-rmse:0.14553 +[39] validation_0-rmse:0.16926 validation_1-rmse:0.14420 +[40] validation_0-rmse:0.16821 validation_1-rmse:0.14297 +[41] validation_0-rmse:0.16740 validation_1-rmse:0.14144 +[42] validation_0-rmse:0.16647 validation_1-rmse:0.14020 +[43] validation_0-rmse:0.16548 validation_1-rmse:0.13903 +[44] validation_0-rmse:0.16440 validation_1-rmse:0.13765 +[45] validation_0-rmse:0.16353 validation_1-rmse:0.13652 +[46] validation_0-rmse:0.16269 validation_1-rmse:0.13522 +[47] validation_0-rmse:0.16193 validation_1-rmse:0.13419 +[48] validation_0-rmse:0.16114 validation_1-rmse:0.13311 +[49] validation_0-rmse:0.16043 validation_1-rmse:0.13214 +[50] validation_0-rmse:0.15971 validation_1-rmse:0.13090 +[51] validation_0-rmse:0.15909 validation_1-rmse:0.12992 +[52] validation_0-rmse:0.15834 validation_1-rmse:0.12899 +[53] validation_0-rmse:0.15763 validation_1-rmse:0.12809 +[54] validation_0-rmse:0.15697 validation_1-rmse:0.12724 +[55] validation_0-rmse:0.15631 validation_1-rmse:0.12637 +[56] validation_0-rmse:0.15553 validation_1-rmse:0.12535 +[57] validation_0-rmse:0.15494 validation_1-rmse:0.12456 +[58] validation_0-rmse:0.15452 validation_1-rmse:0.12352 +[59] validation_0-rmse:0.15396 validation_1-rmse:0.12273 +[60] validation_0-rmse:0.15334 validation_1-rmse:0.12196 +[61] validation_0-rmse:0.15274 validation_1-rmse:0.12123 +[62] validation_0-rmse:0.15221 validation_1-rmse:0.12048 +[63] validation_0-rmse:0.15176 validation_1-rmse:0.11953 +[64] validation_0-rmse:0.15133 validation_1-rmse:0.11887 +[65] validation_0-rmse:0.15080 validation_1-rmse:0.11796 +[66] validation_0-rmse:0.15035 validation_1-rmse:0.11734 +[67] validation_0-rmse:0.14995 validation_1-rmse:0.11667 +[68] validation_0-rmse:0.14954 validation_1-rmse:0.11616 +[69] validation_0-rmse:0.14916 validation_1-rmse:0.11535 +[70] validation_0-rmse:0.14887 validation_1-rmse:0.11469 +[71] validation_0-rmse:0.14854 validation_1-rmse:0.11408 +[72] validation_0-rmse:0.14811 validation_1-rmse:0.11334 +[73] validation_0-rmse:0.14766 validation_1-rmse:0.11278 +[74] validation_0-rmse:0.14738 validation_1-rmse:0.11231 +[75] validation_0-rmse:0.14697 validation_1-rmse:0.11184 +[76] validation_0-rmse:0.14663 validation_1-rmse:0.11108 +[77] validation_0-rmse:0.14635 validation_1-rmse:0.11058 +[78] validation_0-rmse:0.14591 validation_1-rmse:0.10984 +[79] validation_0-rmse:0.14561 validation_1-rmse:0.10929 +[80] validation_0-rmse:0.14529 validation_1-rmse:0.10875 +[81] validation_0-rmse:0.14510 validation_1-rmse:0.10826 +[82] validation_0-rmse:0.14471 validation_1-rmse:0.10772 +[83] validation_0-rmse:0.14444 validation_1-rmse:0.10725 +[84] validation_0-rmse:0.14420 validation_1-rmse:0.10652 +[85] validation_0-rmse:0.14393 validation_1-rmse:0.10608 +[86] validation_0-rmse:0.14371 validation_1-rmse:0.10567 +[87] validation_0-rmse:0.14342 validation_1-rmse:0.10528 +[88] validation_0-rmse:0.14314 validation_1-rmse:0.10483 +[89] validation_0-rmse:0.14307 validation_1-rmse:0.10439 +[90] validation_0-rmse:0.14273 validation_1-rmse:0.10395 +[91] validation_0-rmse:0.14237 validation_1-rmse:0.10353 +[92] validation_0-rmse:0.14210 validation_1-rmse:0.10318 +[93] validation_0-rmse:0.14186 validation_1-rmse:0.10279 +[94] validation_0-rmse:0.14175 validation_1-rmse:0.10234 +[95] validation_0-rmse:0.14153 validation_1-rmse:0.10204 +[96] validation_0-rmse:0.14142 validation_1-rmse:0.10160 +[97] validation_0-rmse:0.14124 validation_1-rmse:0.10126 +[98] validation_0-rmse:0.14102 validation_1-rmse:0.10068 +[99] validation_0-rmse:0.14079 validation_1-rmse:0.10036 +2025-04-29 01:55:14,692 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.76 secs) -------------------- +2025-04-29 01:55:14,693 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:15,250 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2024-12-22 00:00:00 to 2025-01-21 00:00:00, 3/11 trains +2025-04-29 01:55:15,250 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1737417600_prediction.feather +2025-04-29 01:55:15,254 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:15,261 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:55:15,262 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.367593 +1 0.003285 50.367593 +2 0.001898 50.367593 +3 0.000484 50.367593 +4 0.001688 50.367593 +2025-04-29 01:55:15,268 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:15,275 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:55:15,276 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.305589 +1 0.003285 50.305589 +2 0.001898 50.305589 +3 0.000484 50.305589 +4 0.001688 50.305589 +2025-04-29 01:55:15,281 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1737417600/cb_btc_1737417600 +2025-04-29 01:55:15,281 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:15,297 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:15,298 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-22 to 2025-01-20 -------------------- +2025-04-29 01:55:20,324 - datasieve.pipeline - INFO - DI tossed 1622 predictions for being too far from training data. +2025-04-29 01:55:20,327 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:20,327 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.25769 validation_1-rmse:0.25549 +[1] validation_0-rmse:0.25314 validation_1-rmse:0.24986 +[2] validation_0-rmse:0.24864 validation_1-rmse:0.24456 +[3] validation_0-rmse:0.24486 validation_1-rmse:0.23955 +[4] validation_0-rmse:0.24144 validation_1-rmse:0.23480 +[5] validation_0-rmse:0.23803 validation_1-rmse:0.23024 +[6] validation_0-rmse:0.23468 validation_1-rmse:0.22599 +[7] validation_0-rmse:0.23134 validation_1-rmse:0.22162 +[8] validation_0-rmse:0.22843 validation_1-rmse:0.21773 +[9] validation_0-rmse:0.22560 validation_1-rmse:0.21396 +[10] validation_0-rmse:0.22402 validation_1-rmse:0.21023 +[11] validation_0-rmse:0.22155 validation_1-rmse:0.20680 +[12] validation_0-rmse:0.21899 validation_1-rmse:0.20342 +[13] validation_0-rmse:0.21654 validation_1-rmse:0.20029 +[14] validation_0-rmse:0.21431 validation_1-rmse:0.19719 +[15] validation_0-rmse:0.21282 validation_1-rmse:0.19411 +[16] validation_0-rmse:0.21076 validation_1-rmse:0.19117 +[17] validation_0-rmse:0.20882 validation_1-rmse:0.18835 +[18] validation_0-rmse:0.20695 validation_1-rmse:0.18547 +[19] validation_0-rmse:0.20538 validation_1-rmse:0.18292 +[20] validation_0-rmse:0.20345 validation_1-rmse:0.18038 +[21] validation_0-rmse:0.20148 validation_1-rmse:0.17799 +[22] validation_0-rmse:0.19991 validation_1-rmse:0.17569 +[23] validation_0-rmse:0.19832 validation_1-rmse:0.17350 +[24] validation_0-rmse:0.19658 validation_1-rmse:0.17096 +[25] validation_0-rmse:0.19474 validation_1-rmse:0.16879 +[26] validation_0-rmse:0.19292 validation_1-rmse:0.16665 +[27] validation_0-rmse:0.19134 validation_1-rmse:0.16470 +[28] validation_0-rmse:0.19034 validation_1-rmse:0.16253 +[29] validation_0-rmse:0.18882 validation_1-rmse:0.16068 +[30] validation_0-rmse:0.18736 validation_1-rmse:0.15892 +[31] validation_0-rmse:0.18605 validation_1-rmse:0.15690 +[32] validation_0-rmse:0.18481 validation_1-rmse:0.15521 +[33] validation_0-rmse:0.18346 validation_1-rmse:0.15356 +[34] validation_0-rmse:0.18222 validation_1-rmse:0.15188 +[35] validation_0-rmse:0.18095 validation_1-rmse:0.15028 +[36] validation_0-rmse:0.18015 validation_1-rmse:0.14857 +[37] validation_0-rmse:0.17915 validation_1-rmse:0.14713 +[38] validation_0-rmse:0.17817 validation_1-rmse:0.14573 +[39] validation_0-rmse:0.17723 validation_1-rmse:0.14437 +[40] validation_0-rmse:0.17619 validation_1-rmse:0.14308 +[41] validation_0-rmse:0.17509 validation_1-rmse:0.14176 +[42] validation_0-rmse:0.17407 validation_1-rmse:0.14047 +[43] validation_0-rmse:0.17340 validation_1-rmse:0.13921 +[44] validation_0-rmse:0.17245 validation_1-rmse:0.13806 +[45] validation_0-rmse:0.17212 validation_1-rmse:0.13685 +[46] validation_0-rmse:0.17133 validation_1-rmse:0.13577 +[47] validation_0-rmse:0.17064 validation_1-rmse:0.13451 +[48] validation_0-rmse:0.17004 validation_1-rmse:0.13331 +[49] validation_0-rmse:0.16941 validation_1-rmse:0.13222 +[50] validation_0-rmse:0.16858 validation_1-rmse:0.13123 +[51] validation_0-rmse:0.16786 validation_1-rmse:0.13007 +[52] validation_0-rmse:0.16718 validation_1-rmse:0.12912 +[53] validation_0-rmse:0.16651 validation_1-rmse:0.12806 +[54] validation_0-rmse:0.16592 validation_1-rmse:0.12709 +[55] validation_0-rmse:0.16542 validation_1-rmse:0.12604 +[56] validation_0-rmse:0.16479 validation_1-rmse:0.12523 +[57] validation_0-rmse:0.16426 validation_1-rmse:0.12439 +[58] validation_0-rmse:0.16363 validation_1-rmse:0.12352 +[59] validation_0-rmse:0.16325 validation_1-rmse:0.12263 +[60] validation_0-rmse:0.16289 validation_1-rmse:0.12173 +[61] validation_0-rmse:0.16226 validation_1-rmse:0.12099 +[62] validation_0-rmse:0.16176 validation_1-rmse:0.12010 +[63] validation_0-rmse:0.16144 validation_1-rmse:0.11936 +[64] validation_0-rmse:0.16088 validation_1-rmse:0.11862 +[65] validation_0-rmse:0.16030 validation_1-rmse:0.11786 +[66] validation_0-rmse:0.15991 validation_1-rmse:0.11714 +[67] validation_0-rmse:0.15947 validation_1-rmse:0.11640 +[68] validation_0-rmse:0.15912 validation_1-rmse:0.11574 +[69] validation_0-rmse:0.15874 validation_1-rmse:0.11507 +[70] validation_0-rmse:0.15837 validation_1-rmse:0.11430 +[71] validation_0-rmse:0.15798 validation_1-rmse:0.11365 +[72] validation_0-rmse:0.15763 validation_1-rmse:0.11305 +[73] validation_0-rmse:0.15713 validation_1-rmse:0.11250 +[74] validation_0-rmse:0.15648 validation_1-rmse:0.11177 +[75] validation_0-rmse:0.15619 validation_1-rmse:0.11122 +[76] validation_0-rmse:0.15593 validation_1-rmse:0.11066 +[77] validation_0-rmse:0.15562 validation_1-rmse:0.11007 +[78] validation_0-rmse:0.15519 validation_1-rmse:0.10953 +[79] validation_0-rmse:0.15500 validation_1-rmse:0.10883 +[80] validation_0-rmse:0.15461 validation_1-rmse:0.10835 +[81] validation_0-rmse:0.15417 validation_1-rmse:0.10780 +[82] validation_0-rmse:0.15393 validation_1-rmse:0.10742 +[83] validation_0-rmse:0.15395 validation_1-rmse:0.10634 +[84] validation_0-rmse:0.15359 validation_1-rmse:0.10588 +[85] validation_0-rmse:0.15315 validation_1-rmse:0.10539 +[86] validation_0-rmse:0.15315 validation_1-rmse:0.10440 +[87] validation_0-rmse:0.15278 validation_1-rmse:0.10400 +[88] validation_0-rmse:0.15239 validation_1-rmse:0.10353 +[89] validation_0-rmse:0.15200 validation_1-rmse:0.10310 +[90] validation_0-rmse:0.15182 validation_1-rmse:0.10245 +[91] validation_0-rmse:0.15175 validation_1-rmse:0.10182 +[92] validation_0-rmse:0.15139 validation_1-rmse:0.10138 +[93] validation_0-rmse:0.15105 validation_1-rmse:0.10095 +[94] validation_0-rmse:0.15091 validation_1-rmse:0.10056 +[95] validation_0-rmse:0.15088 validation_1-rmse:0.09964 +[96] validation_0-rmse:0.15065 validation_1-rmse:0.09927 +[97] validation_0-rmse:0.15036 validation_1-rmse:0.09888 +[98] validation_0-rmse:0.15021 validation_1-rmse:0.09852 +[99] validation_0-rmse:0.15004 validation_1-rmse:0.09815 +2025-04-29 01:55:21,007 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.73 secs) -------------------- +2025-04-29 01:55:21,008 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:21,504 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-01 00:00:00 to 2025-01-31 00:00:00, 4/11 trains +2025-04-29 01:55:21,505 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1738281600_prediction.feather +2025-04-29 01:55:21,510 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:21,516 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:55:21,517 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.305589 +1 0.003285 50.305589 +2 0.001898 50.305589 +3 0.000484 50.305589 +4 0.001688 50.305589 +2025-04-29 01:55:21,522 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:21,528 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:55:21,529 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.168798 +1 0.003285 50.168798 +2 0.001898 50.168798 +3 0.000484 50.168798 +4 0.001688 50.168798 +2025-04-29 01:55:21,533 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1738281600/cb_btc_1738281600 +2025-04-29 01:55:21,534 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:21,550 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:21,550 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-01 to 2025-01-30 -------------------- +2025-04-29 01:55:26,605 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:26,606 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.25046 validation_1-rmse:0.26128 +[1] validation_0-rmse:0.24588 validation_1-rmse:0.25570 +[2] validation_0-rmse:0.24156 validation_1-rmse:0.25047 +[3] validation_0-rmse:0.23757 validation_1-rmse:0.24551 +[4] validation_0-rmse:0.23411 validation_1-rmse:0.24075 +[5] validation_0-rmse:0.23029 validation_1-rmse:0.23637 +[6] validation_0-rmse:0.22707 validation_1-rmse:0.23199 +[7] validation_0-rmse:0.22405 validation_1-rmse:0.22801 +[8] validation_0-rmse:0.22083 validation_1-rmse:0.22420 +[9] validation_0-rmse:0.21768 validation_1-rmse:0.22038 +[10] validation_0-rmse:0.21473 validation_1-rmse:0.21674 +[11] validation_0-rmse:0.21187 validation_1-rmse:0.21322 +[12] validation_0-rmse:0.20911 validation_1-rmse:0.20996 +[13] validation_0-rmse:0.20669 validation_1-rmse:0.20679 +[14] validation_0-rmse:0.20441 validation_1-rmse:0.20366 +[15] validation_0-rmse:0.20250 validation_1-rmse:0.20054 +[16] validation_0-rmse:0.20017 validation_1-rmse:0.19757 +[17] validation_0-rmse:0.19804 validation_1-rmse:0.19490 +[18] validation_0-rmse:0.19618 validation_1-rmse:0.19221 +[19] validation_0-rmse:0.19404 validation_1-rmse:0.18954 +[20] validation_0-rmse:0.19209 validation_1-rmse:0.18666 +[21] validation_0-rmse:0.19014 validation_1-rmse:0.18430 +[22] validation_0-rmse:0.18845 validation_1-rmse:0.18197 +[23] validation_0-rmse:0.18653 validation_1-rmse:0.17972 +[24] validation_0-rmse:0.18468 validation_1-rmse:0.17722 +[25] validation_0-rmse:0.18325 validation_1-rmse:0.17491 +[26] validation_0-rmse:0.18152 validation_1-rmse:0.17284 +[27] validation_0-rmse:0.17999 validation_1-rmse:0.17092 +[28] validation_0-rmse:0.17846 validation_1-rmse:0.16892 +[29] validation_0-rmse:0.17696 validation_1-rmse:0.16709 +[30] validation_0-rmse:0.17558 validation_1-rmse:0.16510 +[31] validation_0-rmse:0.17418 validation_1-rmse:0.16335 +[32] validation_0-rmse:0.17293 validation_1-rmse:0.16161 +[33] validation_0-rmse:0.17159 validation_1-rmse:0.16003 +[34] validation_0-rmse:0.17030 validation_1-rmse:0.15831 +[35] validation_0-rmse:0.16907 validation_1-rmse:0.15681 +[36] validation_0-rmse:0.16796 validation_1-rmse:0.15513 +[37] validation_0-rmse:0.16690 validation_1-rmse:0.15349 +[38] validation_0-rmse:0.16580 validation_1-rmse:0.15204 +[39] validation_0-rmse:0.16492 validation_1-rmse:0.15050 +[40] validation_0-rmse:0.16383 validation_1-rmse:0.14918 +[41] validation_0-rmse:0.16281 validation_1-rmse:0.14788 +[42] validation_0-rmse:0.16176 validation_1-rmse:0.14660 +[43] validation_0-rmse:0.16082 validation_1-rmse:0.14516 +[44] validation_0-rmse:0.15990 validation_1-rmse:0.14395 +[45] validation_0-rmse:0.15891 validation_1-rmse:0.14281 +[46] validation_0-rmse:0.15797 validation_1-rmse:0.14168 +[47] validation_0-rmse:0.15712 validation_1-rmse:0.14040 +[48] validation_0-rmse:0.15632 validation_1-rmse:0.13933 +[49] validation_0-rmse:0.15542 validation_1-rmse:0.13821 +[50] validation_0-rmse:0.15458 validation_1-rmse:0.13705 +[51] validation_0-rmse:0.15404 validation_1-rmse:0.13583 +[52] validation_0-rmse:0.15334 validation_1-rmse:0.13483 +[53] validation_0-rmse:0.15256 validation_1-rmse:0.13387 +[54] validation_0-rmse:0.15190 validation_1-rmse:0.13290 +[55] validation_0-rmse:0.15122 validation_1-rmse:0.13174 +[56] validation_0-rmse:0.15065 validation_1-rmse:0.13080 +[57] validation_0-rmse:0.15006 validation_1-rmse:0.12993 +[58] validation_0-rmse:0.14955 validation_1-rmse:0.12897 +[59] validation_0-rmse:0.14893 validation_1-rmse:0.12814 +[60] validation_0-rmse:0.14843 validation_1-rmse:0.12735 +[61] validation_0-rmse:0.14789 validation_1-rmse:0.12642 +[62] validation_0-rmse:0.14718 validation_1-rmse:0.12561 +[63] validation_0-rmse:0.14659 validation_1-rmse:0.12486 +[64] validation_0-rmse:0.14600 validation_1-rmse:0.12397 +[65] validation_0-rmse:0.14547 validation_1-rmse:0.12324 +[66] validation_0-rmse:0.14499 validation_1-rmse:0.12255 +[67] validation_0-rmse:0.14451 validation_1-rmse:0.12188 +[68] validation_0-rmse:0.14393 validation_1-rmse:0.12114 +[69] validation_0-rmse:0.14346 validation_1-rmse:0.12048 +[70] validation_0-rmse:0.14293 validation_1-rmse:0.11974 +[71] validation_0-rmse:0.14256 validation_1-rmse:0.11893 +[72] validation_0-rmse:0.14212 validation_1-rmse:0.11830 +[73] validation_0-rmse:0.14177 validation_1-rmse:0.11748 +[74] validation_0-rmse:0.14134 validation_1-rmse:0.11686 +[75] validation_0-rmse:0.14101 validation_1-rmse:0.11609 +[76] validation_0-rmse:0.14060 validation_1-rmse:0.11536 +[77] validation_0-rmse:0.14020 validation_1-rmse:0.11484 +[78] validation_0-rmse:0.13983 validation_1-rmse:0.11412 +[79] validation_0-rmse:0.13951 validation_1-rmse:0.11357 +[80] validation_0-rmse:0.13928 validation_1-rmse:0.11273 +[81] validation_0-rmse:0.13889 validation_1-rmse:0.11221 +[82] validation_0-rmse:0.13855 validation_1-rmse:0.11166 +[83] validation_0-rmse:0.13824 validation_1-rmse:0.11114 +[84] validation_0-rmse:0.13808 validation_1-rmse:0.11050 +[85] validation_0-rmse:0.13767 validation_1-rmse:0.10998 +[86] validation_0-rmse:0.13731 validation_1-rmse:0.10947 +[87] validation_0-rmse:0.13716 validation_1-rmse:0.10876 +[88] validation_0-rmse:0.13678 validation_1-rmse:0.10832 +[89] validation_0-rmse:0.13659 validation_1-rmse:0.10782 +[90] validation_0-rmse:0.13629 validation_1-rmse:0.10736 +[91] validation_0-rmse:0.13600 validation_1-rmse:0.10662 +[92] validation_0-rmse:0.13577 validation_1-rmse:0.10613 +[93] validation_0-rmse:0.13541 validation_1-rmse:0.10565 +[94] validation_0-rmse:0.13534 validation_1-rmse:0.10501 +[95] validation_0-rmse:0.13511 validation_1-rmse:0.10453 +[96] validation_0-rmse:0.13483 validation_1-rmse:0.10401 +[97] validation_0-rmse:0.13455 validation_1-rmse:0.10362 +[98] validation_0-rmse:0.13425 validation_1-rmse:0.10323 +[99] validation_0-rmse:0.13402 validation_1-rmse:0.10289 +2025-04-29 01:55:27,556 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (6.02 secs) -------------------- +2025-04-29 01:55:27,557 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:28,076 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-11 00:00:00 to 2025-02-10 00:00:00, 5/11 trains +2025-04-29 01:55:28,077 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1739145600_prediction.feather +2025-04-29 01:55:28,081 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:28,088 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:55:28,089 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.168798 +1 0.003285 50.168798 +2 0.001898 50.168798 +3 0.000484 50.168798 +4 0.001688 50.168798 +2025-04-29 01:55:28,094 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:28,100 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:55:28,102 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.167897 +1 0.003285 50.167897 +2 0.001898 50.167897 +3 0.000484 50.167897 +4 0.001688 50.167897 +2025-04-29 01:55:28,106 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1739145600/cb_btc_1739145600 +2025-04-29 01:55:28,107 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:28,123 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:28,124 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-11 to 2025-02-09 -------------------- +2025-04-29 01:55:33,123 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:33,124 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.26428 validation_1-rmse:0.27464 +[1] validation_0-rmse:0.25911 validation_1-rmse:0.26865 +[2] validation_0-rmse:0.25427 validation_1-rmse:0.26296 +[3] validation_0-rmse:0.24970 validation_1-rmse:0.25748 +[4] validation_0-rmse:0.24525 validation_1-rmse:0.25222 +[5] validation_0-rmse:0.24140 validation_1-rmse:0.24725 +[6] validation_0-rmse:0.23748 validation_1-rmse:0.24264 +[7] validation_0-rmse:0.23368 validation_1-rmse:0.23792 +[8] validation_0-rmse:0.23022 validation_1-rmse:0.23363 +[9] validation_0-rmse:0.22695 validation_1-rmse:0.22945 +[10] validation_0-rmse:0.22381 validation_1-rmse:0.22543 +[11] validation_0-rmse:0.22105 validation_1-rmse:0.22154 +[12] validation_0-rmse:0.21818 validation_1-rmse:0.21797 +[13] validation_0-rmse:0.21526 validation_1-rmse:0.21430 +[14] validation_0-rmse:0.21284 validation_1-rmse:0.21101 +[15] validation_0-rmse:0.21034 validation_1-rmse:0.20769 +[16] validation_0-rmse:0.20802 validation_1-rmse:0.20438 +[17] validation_0-rmse:0.20590 validation_1-rmse:0.20136 +[18] validation_0-rmse:0.20386 validation_1-rmse:0.19837 +[19] validation_0-rmse:0.20219 validation_1-rmse:0.19549 +[20] validation_0-rmse:0.20037 validation_1-rmse:0.19283 +[21] validation_0-rmse:0.19826 validation_1-rmse:0.19005 +[22] validation_0-rmse:0.19657 validation_1-rmse:0.18750 +[23] validation_0-rmse:0.19525 validation_1-rmse:0.18498 +[24] validation_0-rmse:0.19373 validation_1-rmse:0.18267 +[25] validation_0-rmse:0.19197 validation_1-rmse:0.18037 +[26] validation_0-rmse:0.19063 validation_1-rmse:0.17799 +[27] validation_0-rmse:0.18897 validation_1-rmse:0.17587 +[28] validation_0-rmse:0.18765 validation_1-rmse:0.17382 +[29] validation_0-rmse:0.18608 validation_1-rmse:0.17185 +[30] validation_0-rmse:0.18456 validation_1-rmse:0.16992 +[31] validation_0-rmse:0.18340 validation_1-rmse:0.16793 +[32] validation_0-rmse:0.18206 validation_1-rmse:0.16616 +[33] validation_0-rmse:0.18077 validation_1-rmse:0.16437 +[34] validation_0-rmse:0.17960 validation_1-rmse:0.16270 +[35] validation_0-rmse:0.17857 validation_1-rmse:0.16105 +[36] validation_0-rmse:0.17748 validation_1-rmse:0.15925 +[37] validation_0-rmse:0.17649 validation_1-rmse:0.15762 +[38] validation_0-rmse:0.17540 validation_1-rmse:0.15611 +[39] validation_0-rmse:0.17427 validation_1-rmse:0.15469 +[40] validation_0-rmse:0.17312 validation_1-rmse:0.15301 +[41] validation_0-rmse:0.17217 validation_1-rmse:0.15169 +[42] validation_0-rmse:0.17119 validation_1-rmse:0.15037 +[43] validation_0-rmse:0.17030 validation_1-rmse:0.14910 +[44] validation_0-rmse:0.16939 validation_1-rmse:0.14786 +[45] validation_0-rmse:0.16851 validation_1-rmse:0.14660 +[46] validation_0-rmse:0.16793 validation_1-rmse:0.14518 +[47] validation_0-rmse:0.16760 validation_1-rmse:0.14365 +[48] validation_0-rmse:0.16674 validation_1-rmse:0.14258 +[49] validation_0-rmse:0.16588 validation_1-rmse:0.14152 +[50] validation_0-rmse:0.16505 validation_1-rmse:0.14051 +[51] validation_0-rmse:0.16437 validation_1-rmse:0.13919 +[52] validation_0-rmse:0.16361 validation_1-rmse:0.13818 +[53] validation_0-rmse:0.16290 validation_1-rmse:0.13715 +[54] validation_0-rmse:0.16217 validation_1-rmse:0.13621 +[55] validation_0-rmse:0.16207 validation_1-rmse:0.13493 +[56] validation_0-rmse:0.16153 validation_1-rmse:0.13395 +[57] validation_0-rmse:0.16077 validation_1-rmse:0.13302 +[58] validation_0-rmse:0.16021 validation_1-rmse:0.13218 +[59] validation_0-rmse:0.15972 validation_1-rmse:0.13117 +[60] validation_0-rmse:0.15954 validation_1-rmse:0.13003 +[61] validation_0-rmse:0.15896 validation_1-rmse:0.12926 +[62] validation_0-rmse:0.15849 validation_1-rmse:0.12848 +[63] validation_0-rmse:0.15801 validation_1-rmse:0.12770 +[64] validation_0-rmse:0.15737 validation_1-rmse:0.12678 +[65] validation_0-rmse:0.15736 validation_1-rmse:0.12578 +[66] validation_0-rmse:0.15684 validation_1-rmse:0.12506 +[67] validation_0-rmse:0.15638 validation_1-rmse:0.12437 +[68] validation_0-rmse:0.15618 validation_1-rmse:0.12336 +[69] validation_0-rmse:0.15581 validation_1-rmse:0.12269 +[70] validation_0-rmse:0.15537 validation_1-rmse:0.12205 +[71] validation_0-rmse:0.15534 validation_1-rmse:0.12117 +[72] validation_0-rmse:0.15485 validation_1-rmse:0.12049 +[73] validation_0-rmse:0.15465 validation_1-rmse:0.11968 +[74] validation_0-rmse:0.15430 validation_1-rmse:0.11906 +[75] validation_0-rmse:0.15386 validation_1-rmse:0.11840 +[76] validation_0-rmse:0.15353 validation_1-rmse:0.11781 +[77] validation_0-rmse:0.15354 validation_1-rmse:0.11697 +[78] validation_0-rmse:0.15325 validation_1-rmse:0.11630 +[79] validation_0-rmse:0.15282 validation_1-rmse:0.11572 +[80] validation_0-rmse:0.15239 validation_1-rmse:0.11514 +[81] validation_0-rmse:0.15226 validation_1-rmse:0.11431 +[82] validation_0-rmse:0.15189 validation_1-rmse:0.11381 +[83] validation_0-rmse:0.15171 validation_1-rmse:0.11316 +[84] validation_0-rmse:0.15136 validation_1-rmse:0.11270 +[85] validation_0-rmse:0.15112 validation_1-rmse:0.11212 +[86] validation_0-rmse:0.15112 validation_1-rmse:0.11140 +[87] validation_0-rmse:0.15074 validation_1-rmse:0.11094 +[88] validation_0-rmse:0.15048 validation_1-rmse:0.11035 +[89] validation_0-rmse:0.15026 validation_1-rmse:0.10983 +[90] validation_0-rmse:0.14989 validation_1-rmse:0.10938 +[91] validation_0-rmse:0.14955 validation_1-rmse:0.10893 +[92] validation_0-rmse:0.14955 validation_1-rmse:0.10815 +[93] validation_0-rmse:0.14933 validation_1-rmse:0.10765 +[94] validation_0-rmse:0.14908 validation_1-rmse:0.10711 +[95] validation_0-rmse:0.14889 validation_1-rmse:0.10668 +[96] validation_0-rmse:0.14853 validation_1-rmse:0.10627 +[97] validation_0-rmse:0.14853 validation_1-rmse:0.10553 +[98] validation_0-rmse:0.14835 validation_1-rmse:0.10513 +[99] validation_0-rmse:0.14818 validation_1-rmse:0.10475 +2025-04-29 01:55:33,929 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.82 secs) -------------------- +2025-04-29 01:55:33,930 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:34,433 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-21 00:00:00 to 2025-02-20 00:00:00, 6/11 trains +2025-04-29 01:55:34,434 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1740009600_prediction.feather +2025-04-29 01:55:34,440 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:34,447 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:55:34,448 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.167897 +1 0.003285 50.167897 +2 0.001898 50.167897 +3 0.000484 50.167897 +4 0.001688 50.167897 +2025-04-29 01:55:34,453 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:34,459 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:55:34,461 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.107698 +1 0.003285 50.107698 +2 0.001898 50.107698 +3 0.000484 50.107698 +4 0.001688 50.107698 +2025-04-29 01:55:34,465 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1740009600/cb_btc_1740009600 +2025-04-29 01:55:34,466 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:34,482 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:34,483 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-21 to 2025-02-19 -------------------- +2025-04-29 01:55:39,369 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:39,370 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.27166 validation_1-rmse:0.27726 +[1] validation_0-rmse:0.26708 validation_1-rmse:0.27112 +[2] validation_0-rmse:0.26297 validation_1-rmse:0.26523 +[3] validation_0-rmse:0.25865 validation_1-rmse:0.25959 +[4] validation_0-rmse:0.25494 validation_1-rmse:0.25419 +[5] validation_0-rmse:0.25100 validation_1-rmse:0.24913 +[6] validation_0-rmse:0.24763 validation_1-rmse:0.24437 +[7] validation_0-rmse:0.24441 validation_1-rmse:0.23970 +[8] validation_0-rmse:0.24110 validation_1-rmse:0.23527 +[9] validation_0-rmse:0.23801 validation_1-rmse:0.23102 +[10] validation_0-rmse:0.23492 validation_1-rmse:0.22691 +[11] validation_0-rmse:0.23229 validation_1-rmse:0.22297 +[12] validation_0-rmse:0.22956 validation_1-rmse:0.21923 +[13] validation_0-rmse:0.22707 validation_1-rmse:0.21564 +[14] validation_0-rmse:0.22482 validation_1-rmse:0.21221 +[15] validation_0-rmse:0.22237 validation_1-rmse:0.20891 +[16] validation_0-rmse:0.22030 validation_1-rmse:0.20557 +[17] validation_0-rmse:0.21784 validation_1-rmse:0.20243 +[18] validation_0-rmse:0.21591 validation_1-rmse:0.19949 +[19] validation_0-rmse:0.21399 validation_1-rmse:0.19664 +[20] validation_0-rmse:0.21182 validation_1-rmse:0.19378 +[21] validation_0-rmse:0.20992 validation_1-rmse:0.19110 +[22] validation_0-rmse:0.20821 validation_1-rmse:0.18850 +[23] validation_0-rmse:0.20621 validation_1-rmse:0.18597 +[24] validation_0-rmse:0.20490 validation_1-rmse:0.18353 +[25] validation_0-rmse:0.20318 validation_1-rmse:0.18126 +[26] validation_0-rmse:0.20168 validation_1-rmse:0.17896 +[27] validation_0-rmse:0.19992 validation_1-rmse:0.17679 +[28] validation_0-rmse:0.19865 validation_1-rmse:0.17458 +[29] validation_0-rmse:0.19722 validation_1-rmse:0.17257 +[30] validation_0-rmse:0.19571 validation_1-rmse:0.17039 +[31] validation_0-rmse:0.19429 validation_1-rmse:0.16855 +[32] validation_0-rmse:0.19285 validation_1-rmse:0.16664 +[33] validation_0-rmse:0.19141 validation_1-rmse:0.16488 +[34] validation_0-rmse:0.19022 validation_1-rmse:0.16312 +[35] validation_0-rmse:0.18904 validation_1-rmse:0.16145 +[36] validation_0-rmse:0.18832 validation_1-rmse:0.15973 +[37] validation_0-rmse:0.18723 validation_1-rmse:0.15815 +[38] validation_0-rmse:0.18610 validation_1-rmse:0.15653 +[39] validation_0-rmse:0.18504 validation_1-rmse:0.15503 +[40] validation_0-rmse:0.18402 validation_1-rmse:0.15358 +[41] validation_0-rmse:0.18333 validation_1-rmse:0.15193 +[42] validation_0-rmse:0.18213 validation_1-rmse:0.15058 +[43] validation_0-rmse:0.18176 validation_1-rmse:0.14922 +[44] validation_0-rmse:0.18093 validation_1-rmse:0.14792 +[45] validation_0-rmse:0.18017 validation_1-rmse:0.14667 +[46] validation_0-rmse:0.17928 validation_1-rmse:0.14537 +[47] validation_0-rmse:0.17858 validation_1-rmse:0.14420 +[48] validation_0-rmse:0.17770 validation_1-rmse:0.14306 +[49] validation_0-rmse:0.17695 validation_1-rmse:0.14199 +[50] validation_0-rmse:0.17613 validation_1-rmse:0.14094 +[51] validation_0-rmse:0.17545 validation_1-rmse:0.13979 +[52] validation_0-rmse:0.17490 validation_1-rmse:0.13874 +[53] validation_0-rmse:0.17452 validation_1-rmse:0.13755 +[54] validation_0-rmse:0.17383 validation_1-rmse:0.13663 +[55] validation_0-rmse:0.17327 validation_1-rmse:0.13568 +[56] validation_0-rmse:0.17255 validation_1-rmse:0.13477 +[57] validation_0-rmse:0.17192 validation_1-rmse:0.13382 +[58] validation_0-rmse:0.17138 validation_1-rmse:0.13277 +[59] validation_0-rmse:0.17074 validation_1-rmse:0.13188 +[60] validation_0-rmse:0.17026 validation_1-rmse:0.13089 +[61] validation_0-rmse:0.16969 validation_1-rmse:0.13010 +[62] validation_0-rmse:0.16932 validation_1-rmse:0.12904 +[63] validation_0-rmse:0.16888 validation_1-rmse:0.12818 +[64] validation_0-rmse:0.16849 validation_1-rmse:0.12745 +[65] validation_0-rmse:0.16802 validation_1-rmse:0.12639 +[66] validation_0-rmse:0.16747 validation_1-rmse:0.12567 +[67] validation_0-rmse:0.16710 validation_1-rmse:0.12496 +[68] validation_0-rmse:0.16672 validation_1-rmse:0.12426 +[69] validation_0-rmse:0.16635 validation_1-rmse:0.12331 +[70] validation_0-rmse:0.16597 validation_1-rmse:0.12267 +[71] validation_0-rmse:0.16554 validation_1-rmse:0.12196 +[72] validation_0-rmse:0.16522 validation_1-rmse:0.12121 +[73] validation_0-rmse:0.16481 validation_1-rmse:0.12054 +[74] validation_0-rmse:0.16442 validation_1-rmse:0.11996 +[75] validation_0-rmse:0.16409 validation_1-rmse:0.11939 +[76] validation_0-rmse:0.16375 validation_1-rmse:0.11878 +[77] validation_0-rmse:0.16275 validation_1-rmse:0.11753 +[78] validation_0-rmse:0.16248 validation_1-rmse:0.11692 +[79] validation_0-rmse:0.16215 validation_1-rmse:0.11619 +[80] validation_0-rmse:0.16187 validation_1-rmse:0.11564 +[81] validation_0-rmse:0.16150 validation_1-rmse:0.11493 +[82] validation_0-rmse:0.16123 validation_1-rmse:0.11438 +[83] validation_0-rmse:0.16109 validation_1-rmse:0.11358 +[84] validation_0-rmse:0.16065 validation_1-rmse:0.11304 +[85] validation_0-rmse:0.16038 validation_1-rmse:0.11256 +[86] validation_0-rmse:0.16022 validation_1-rmse:0.11205 +[87] validation_0-rmse:0.16007 validation_1-rmse:0.11158 +[88] validation_0-rmse:0.15945 validation_1-rmse:0.11054 +[89] validation_0-rmse:0.15912 validation_1-rmse:0.11008 +[90] validation_0-rmse:0.15894 validation_1-rmse:0.10937 +[91] validation_0-rmse:0.15868 validation_1-rmse:0.10886 +[92] validation_0-rmse:0.15845 validation_1-rmse:0.10844 +[93] validation_0-rmse:0.15817 validation_1-rmse:0.10803 +[94] validation_0-rmse:0.15789 validation_1-rmse:0.10758 +[95] validation_0-rmse:0.15772 validation_1-rmse:0.10721 +[96] validation_0-rmse:0.15763 validation_1-rmse:0.10676 +[97] validation_0-rmse:0.15751 validation_1-rmse:0.10609 +[98] validation_0-rmse:0.15731 validation_1-rmse:0.10574 +[99] validation_0-rmse:0.15738 validation_1-rmse:0.10531 +2025-04-29 01:55:40,266 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.80 secs) -------------------- +2025-04-29 01:55:40,267 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:40,801 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-01-31 00:00:00 to 2025-03-02 00:00:00, 7/11 trains +2025-04-29 01:55:40,802 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1740873600_prediction.feather +2025-04-29 01:55:40,807 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:40,814 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:55:40,816 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.107698 +1 0.003285 50.107698 +2 0.001898 50.107698 +3 0.000484 50.107698 +4 0.001688 50.107698 +2025-04-29 01:55:40,821 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:40,827 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:55:40,829 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079166 +1 0.003285 50.079166 +2 0.001898 50.079166 +3 0.000484 50.079166 +4 0.001688 50.079166 +2025-04-29 01:55:40,833 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1740873600/cb_btc_1740873600 +2025-04-29 01:55:40,834 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:40,849 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:40,850 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-31 to 2025-03-01 -------------------- +2025-04-29 01:55:45,643 - datasieve.pipeline - INFO - DI tossed 2275 predictions for being too far from training data. +2025-04-29 01:55:45,646 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:45,647 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.27618 validation_1-rmse:0.28955 +[1] validation_0-rmse:0.27005 validation_1-rmse:0.28323 +[2] validation_0-rmse:0.26414 validation_1-rmse:0.27722 +[3] validation_0-rmse:0.25897 validation_1-rmse:0.27161 +[4] validation_0-rmse:0.25425 validation_1-rmse:0.26622 +[5] validation_0-rmse:0.24886 validation_1-rmse:0.26100 +[6] validation_0-rmse:0.24522 validation_1-rmse:0.25606 +[7] validation_0-rmse:0.24137 validation_1-rmse:0.25132 +[8] validation_0-rmse:0.23765 validation_1-rmse:0.24687 +[9] validation_0-rmse:0.23323 validation_1-rmse:0.24254 +[10] validation_0-rmse:0.22900 validation_1-rmse:0.23827 +[11] validation_0-rmse:0.22588 validation_1-rmse:0.23450 +[12] validation_0-rmse:0.22228 validation_1-rmse:0.23055 +[13] validation_0-rmse:0.21872 validation_1-rmse:0.22698 +[14] validation_0-rmse:0.21492 validation_1-rmse:0.22348 +[15] validation_0-rmse:0.21329 validation_1-rmse:0.22011 +[16] validation_0-rmse:0.21024 validation_1-rmse:0.21686 +[17] validation_0-rmse:0.20823 validation_1-rmse:0.21380 +[18] validation_0-rmse:0.20544 validation_1-rmse:0.21075 +[19] validation_0-rmse:0.20415 validation_1-rmse:0.20787 +[20] validation_0-rmse:0.20143 validation_1-rmse:0.20515 +[21] validation_0-rmse:0.19917 validation_1-rmse:0.20247 +[22] validation_0-rmse:0.19745 validation_1-rmse:0.19994 +[23] validation_0-rmse:0.19508 validation_1-rmse:0.19746 +[24] validation_0-rmse:0.19300 validation_1-rmse:0.19490 +[25] validation_0-rmse:0.19085 validation_1-rmse:0.19254 +[26] validation_0-rmse:0.18898 validation_1-rmse:0.19031 +[27] validation_0-rmse:0.18720 validation_1-rmse:0.18794 +[28] validation_0-rmse:0.18503 validation_1-rmse:0.18584 +[29] validation_0-rmse:0.18314 validation_1-rmse:0.18382 +[30] validation_0-rmse:0.18132 validation_1-rmse:0.18164 +[31] validation_0-rmse:0.17984 validation_1-rmse:0.17967 +[32] validation_0-rmse:0.17818 validation_1-rmse:0.17779 +[33] validation_0-rmse:0.17637 validation_1-rmse:0.17572 +[34] validation_0-rmse:0.17473 validation_1-rmse:0.17399 +[35] validation_0-rmse:0.17338 validation_1-rmse:0.17229 +[36] validation_0-rmse:0.17253 validation_1-rmse:0.17055 +[37] validation_0-rmse:0.17149 validation_1-rmse:0.16883 +[38] validation_0-rmse:0.17030 validation_1-rmse:0.16730 +[39] validation_0-rmse:0.16950 validation_1-rmse:0.16556 +[40] validation_0-rmse:0.16815 validation_1-rmse:0.16412 +[41] validation_0-rmse:0.16704 validation_1-rmse:0.16268 +[42] validation_0-rmse:0.16617 validation_1-rmse:0.16128 +[43] validation_0-rmse:0.16542 validation_1-rmse:0.15970 +[44] validation_0-rmse:0.16438 validation_1-rmse:0.15840 +[45] validation_0-rmse:0.16356 validation_1-rmse:0.15692 +[46] validation_0-rmse:0.16239 validation_1-rmse:0.15574 +[47] validation_0-rmse:0.16153 validation_1-rmse:0.15456 +[48] validation_0-rmse:0.16076 validation_1-rmse:0.15314 +[49] validation_0-rmse:0.15998 validation_1-rmse:0.15201 +[50] validation_0-rmse:0.15946 validation_1-rmse:0.15084 +[51] validation_0-rmse:0.15891 validation_1-rmse:0.14954 +[52] validation_0-rmse:0.15834 validation_1-rmse:0.14847 +[53] validation_0-rmse:0.15764 validation_1-rmse:0.14722 +[54] validation_0-rmse:0.15707 validation_1-rmse:0.14623 +[55] validation_0-rmse:0.15653 validation_1-rmse:0.14527 +[56] validation_0-rmse:0.15583 validation_1-rmse:0.14434 +[57] validation_0-rmse:0.15549 validation_1-rmse:0.14329 +[58] validation_0-rmse:0.15507 validation_1-rmse:0.14241 +[59] validation_0-rmse:0.15468 validation_1-rmse:0.14053 +[60] validation_0-rmse:0.15398 validation_1-rmse:0.13968 +[61] validation_0-rmse:0.15390 validation_1-rmse:0.13864 +[62] validation_0-rmse:0.15360 validation_1-rmse:0.13783 +[63] validation_0-rmse:0.15368 validation_1-rmse:0.13704 +[64] validation_0-rmse:0.15338 validation_1-rmse:0.13624 +[65] validation_0-rmse:0.15273 validation_1-rmse:0.13551 +[66] validation_0-rmse:0.15238 validation_1-rmse:0.13451 +[67] validation_0-rmse:0.15212 validation_1-rmse:0.13290 +[68] validation_0-rmse:0.15191 validation_1-rmse:0.13217 +[69] validation_0-rmse:0.15138 validation_1-rmse:0.13143 +[70] validation_0-rmse:0.15090 validation_1-rmse:0.13071 +[71] validation_0-rmse:0.15082 validation_1-rmse:0.13001 +[72] validation_0-rmse:0.14988 validation_1-rmse:0.12847 +[73] validation_0-rmse:0.14953 validation_1-rmse:0.12783 +[74] validation_0-rmse:0.14924 validation_1-rmse:0.12709 +[75] validation_0-rmse:0.14926 validation_1-rmse:0.12578 +[76] validation_0-rmse:0.14903 validation_1-rmse:0.12499 +[77] validation_0-rmse:0.14851 validation_1-rmse:0.12435 +[78] validation_0-rmse:0.14808 validation_1-rmse:0.12368 +[79] validation_0-rmse:0.14768 validation_1-rmse:0.12305 +[80] validation_0-rmse:0.14741 validation_1-rmse:0.12217 +[81] validation_0-rmse:0.14712 validation_1-rmse:0.12165 +[82] validation_0-rmse:0.14696 validation_1-rmse:0.12110 +[83] validation_0-rmse:0.14686 validation_1-rmse:0.12045 +[84] validation_0-rmse:0.14648 validation_1-rmse:0.11984 +[85] validation_0-rmse:0.14623 validation_1-rmse:0.11923 +[86] validation_0-rmse:0.14606 validation_1-rmse:0.11869 +[87] validation_0-rmse:0.14583 validation_1-rmse:0.11754 +[88] validation_0-rmse:0.14572 validation_1-rmse:0.11710 +[89] validation_0-rmse:0.14537 validation_1-rmse:0.11660 +[90] validation_0-rmse:0.14510 validation_1-rmse:0.11614 +[91] validation_0-rmse:0.14516 validation_1-rmse:0.11514 +[92] validation_0-rmse:0.14480 validation_1-rmse:0.11455 +[93] validation_0-rmse:0.14475 validation_1-rmse:0.11414 +[94] validation_0-rmse:0.14443 validation_1-rmse:0.11374 +[95] validation_0-rmse:0.14409 validation_1-rmse:0.11331 +[96] validation_0-rmse:0.14391 validation_1-rmse:0.11240 +[97] validation_0-rmse:0.14303 validation_1-rmse:0.11154 +[98] validation_0-rmse:0.14274 validation_1-rmse:0.11114 +[99] validation_0-rmse:0.14246 validation_1-rmse:0.11071 +2025-04-29 01:55:46,544 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.71 secs) -------------------- +2025-04-29 01:55:46,544 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:47,092 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-02-10 00:00:00 to 2025-03-12 00:00:00, 8/11 trains +2025-04-29 01:55:47,092 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1741737600_prediction.feather +2025-04-29 01:55:47,100 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:47,107 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:55:47,109 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079166 +1 0.003285 50.079166 +2 0.001898 50.079166 +3 0.000484 50.079166 +4 0.001688 50.079166 +2025-04-29 01:55:47,115 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:47,122 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:55:47,123 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.102027 +1 0.003285 50.102027 +2 0.001898 50.102027 +3 0.000484 50.102027 +4 0.001688 50.102027 +2025-04-29 01:55:47,128 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1741737600/cb_btc_1741737600 +2025-04-29 01:55:47,129 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:47,145 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:47,145 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-10 to 2025-03-11 -------------------- +2025-04-29 01:55:51,987 - datasieve.pipeline - INFO - DI tossed 18 predictions for being too far from training data. +2025-04-29 01:55:51,989 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:51,989 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.26738 validation_1-rmse:0.26816 +[1] validation_0-rmse:0.26268 validation_1-rmse:0.26258 +[2] validation_0-rmse:0.25808 validation_1-rmse:0.25725 +[3] validation_0-rmse:0.25395 validation_1-rmse:0.25212 +[4] validation_0-rmse:0.24987 validation_1-rmse:0.24723 +[5] validation_0-rmse:0.24633 validation_1-rmse:0.24263 +[6] validation_0-rmse:0.24308 validation_1-rmse:0.23814 +[7] validation_0-rmse:0.23959 validation_1-rmse:0.23402 +[8] validation_0-rmse:0.23612 validation_1-rmse:0.22977 +[9] validation_0-rmse:0.23322 validation_1-rmse:0.22577 +[10] validation_0-rmse:0.23012 validation_1-rmse:0.22207 +[11] validation_0-rmse:0.22730 validation_1-rmse:0.21843 +[12] validation_0-rmse:0.22453 validation_1-rmse:0.21489 +[13] validation_0-rmse:0.22236 validation_1-rmse:0.21145 +[14] validation_0-rmse:0.22000 validation_1-rmse:0.20841 +[15] validation_0-rmse:0.21744 validation_1-rmse:0.20529 +[16] validation_0-rmse:0.21556 validation_1-rmse:0.20225 +[17] validation_0-rmse:0.21331 validation_1-rmse:0.19932 +[18] validation_0-rmse:0.21171 validation_1-rmse:0.19643 +[19] validation_0-rmse:0.21051 validation_1-rmse:0.19382 +[20] validation_0-rmse:0.20880 validation_1-rmse:0.19128 +[21] validation_0-rmse:0.20711 validation_1-rmse:0.18854 +[22] validation_0-rmse:0.20538 validation_1-rmse:0.18612 +[23] validation_0-rmse:0.20350 validation_1-rmse:0.18381 +[24] validation_0-rmse:0.20234 validation_1-rmse:0.18144 +[25] validation_0-rmse:0.20081 validation_1-rmse:0.17917 +[26] validation_0-rmse:0.19918 validation_1-rmse:0.17714 +[27] validation_0-rmse:0.19804 validation_1-rmse:0.17496 +[28] validation_0-rmse:0.19662 validation_1-rmse:0.17304 +[29] validation_0-rmse:0.19580 validation_1-rmse:0.17082 +[30] validation_0-rmse:0.19454 validation_1-rmse:0.16901 +[31] validation_0-rmse:0.19331 validation_1-rmse:0.16691 +[32] validation_0-rmse:0.19234 validation_1-rmse:0.16517 +[33] validation_0-rmse:0.19118 validation_1-rmse:0.16354 +[34] validation_0-rmse:0.19024 validation_1-rmse:0.16175 +[35] validation_0-rmse:0.18915 validation_1-rmse:0.16020 +[36] validation_0-rmse:0.18823 validation_1-rmse:0.15865 +[37] validation_0-rmse:0.18756 validation_1-rmse:0.15712 +[38] validation_0-rmse:0.18698 validation_1-rmse:0.15541 +[39] validation_0-rmse:0.18643 validation_1-rmse:0.15395 +[40] validation_0-rmse:0.18562 validation_1-rmse:0.15265 +[41] validation_0-rmse:0.18516 validation_1-rmse:0.15124 +[42] validation_0-rmse:0.18421 validation_1-rmse:0.14979 +[43] validation_0-rmse:0.18360 validation_1-rmse:0.14850 +[44] validation_0-rmse:0.18275 validation_1-rmse:0.14733 +[45] validation_0-rmse:0.18253 validation_1-rmse:0.14597 +[46] validation_0-rmse:0.18183 validation_1-rmse:0.14470 +[47] validation_0-rmse:0.18111 validation_1-rmse:0.14361 +[48] validation_0-rmse:0.18060 validation_1-rmse:0.14243 +[49] validation_0-rmse:0.18001 validation_1-rmse:0.14134 +[50] validation_0-rmse:0.17953 validation_1-rmse:0.14030 +[51] validation_0-rmse:0.17899 validation_1-rmse:0.13927 +[52] validation_0-rmse:0.17830 validation_1-rmse:0.13817 +[53] validation_0-rmse:0.17770 validation_1-rmse:0.13720 +[54] validation_0-rmse:0.17702 validation_1-rmse:0.13629 +[55] validation_0-rmse:0.17650 validation_1-rmse:0.13531 +[56] validation_0-rmse:0.17625 validation_1-rmse:0.13440 +[57] validation_0-rmse:0.17580 validation_1-rmse:0.13352 +[58] validation_0-rmse:0.17530 validation_1-rmse:0.13268 +[59] validation_0-rmse:0.17486 validation_1-rmse:0.13166 +[60] validation_0-rmse:0.17438 validation_1-rmse:0.13071 +[61] validation_0-rmse:0.17387 validation_1-rmse:0.12991 +[62] validation_0-rmse:0.17356 validation_1-rmse:0.12914 +[63] validation_0-rmse:0.17311 validation_1-rmse:0.12839 +[64] validation_0-rmse:0.17265 validation_1-rmse:0.12767 +[65] validation_0-rmse:0.17209 validation_1-rmse:0.12682 +[66] validation_0-rmse:0.17197 validation_1-rmse:0.12595 +[67] validation_0-rmse:0.17157 validation_1-rmse:0.12506 +[68] validation_0-rmse:0.17131 validation_1-rmse:0.12439 +[69] validation_0-rmse:0.17088 validation_1-rmse:0.12371 +[70] validation_0-rmse:0.17038 validation_1-rmse:0.12298 +[71] validation_0-rmse:0.17009 validation_1-rmse:0.12235 +[72] validation_0-rmse:0.16979 validation_1-rmse:0.12172 +[73] validation_0-rmse:0.16934 validation_1-rmse:0.12118 +[74] validation_0-rmse:0.16902 validation_1-rmse:0.12050 +[75] validation_0-rmse:0.16881 validation_1-rmse:0.11988 +[76] validation_0-rmse:0.16846 validation_1-rmse:0.11928 +[77] validation_0-rmse:0.16809 validation_1-rmse:0.11846 +[78] validation_0-rmse:0.16774 validation_1-rmse:0.11791 +[79] validation_0-rmse:0.16745 validation_1-rmse:0.11738 +[80] validation_0-rmse:0.16717 validation_1-rmse:0.11683 +[81] validation_0-rmse:0.16702 validation_1-rmse:0.11599 +[82] validation_0-rmse:0.16677 validation_1-rmse:0.11535 +[83] validation_0-rmse:0.16649 validation_1-rmse:0.11468 +[84] validation_0-rmse:0.16605 validation_1-rmse:0.11415 +[85] validation_0-rmse:0.16591 validation_1-rmse:0.11350 +[86] validation_0-rmse:0.16560 validation_1-rmse:0.11303 +[87] validation_0-rmse:0.16531 validation_1-rmse:0.11259 +[88] validation_0-rmse:0.16504 validation_1-rmse:0.11185 +[89] validation_0-rmse:0.16485 validation_1-rmse:0.11134 +[90] validation_0-rmse:0.16463 validation_1-rmse:0.11083 +[91] validation_0-rmse:0.16436 validation_1-rmse:0.11041 +[92] validation_0-rmse:0.16412 validation_1-rmse:0.10988 +[93] validation_0-rmse:0.16388 validation_1-rmse:0.10942 +[94] validation_0-rmse:0.16391 validation_1-rmse:0.10881 +[95] validation_0-rmse:0.16357 validation_1-rmse:0.10838 +[96] validation_0-rmse:0.16358 validation_1-rmse:0.10796 +[97] validation_0-rmse:0.16338 validation_1-rmse:0.10756 +[98] validation_0-rmse:0.16339 validation_1-rmse:0.10688 +[99] validation_0-rmse:0.16321 validation_1-rmse:0.10649 +2025-04-29 01:55:52,741 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.61 secs) -------------------- +2025-04-29 01:55:52,742 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:53,285 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-02-20 00:00:00 to 2025-03-22 00:00:00, 9/11 trains +2025-04-29 01:55:53,286 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1742601600_prediction.feather +2025-04-29 01:55:53,291 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:53,298 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:55:53,300 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.102027 +1 0.003285 50.102027 +2 0.001898 50.102027 +3 0.000484 50.102027 +4 0.001688 50.102027 +2025-04-29 01:55:53,309 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:53,316 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:55:53,318 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079967 +1 0.003285 50.079967 +2 0.001898 50.079967 +3 0.000484 50.079967 +4 0.001688 50.079967 +2025-04-29 01:55:53,322 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1742601600/cb_btc_1742601600 +2025-04-29 01:55:53,323 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:53,339 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:53,340 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-20 to 2025-03-21 -------------------- +2025-04-29 01:55:58,184 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:55:58,185 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.26992 validation_1-rmse:0.26756 +[1] validation_0-rmse:0.26551 validation_1-rmse:0.26201 +[2] validation_0-rmse:0.26111 validation_1-rmse:0.25656 +[3] validation_0-rmse:0.25690 validation_1-rmse:0.25154 +[4] validation_0-rmse:0.25291 validation_1-rmse:0.24683 +[5] validation_0-rmse:0.24933 validation_1-rmse:0.24228 +[6] validation_0-rmse:0.24598 validation_1-rmse:0.23796 +[7] validation_0-rmse:0.24252 validation_1-rmse:0.23392 +[8] validation_0-rmse:0.23953 validation_1-rmse:0.22978 +[9] validation_0-rmse:0.23634 validation_1-rmse:0.22592 +[10] validation_0-rmse:0.23330 validation_1-rmse:0.22229 +[11] validation_0-rmse:0.23059 validation_1-rmse:0.21875 +[12] validation_0-rmse:0.22799 validation_1-rmse:0.21546 +[13] validation_0-rmse:0.22565 validation_1-rmse:0.21212 +[14] validation_0-rmse:0.22329 validation_1-rmse:0.20904 +[15] validation_0-rmse:0.22111 validation_1-rmse:0.20604 +[16] validation_0-rmse:0.21894 validation_1-rmse:0.20318 +[17] validation_0-rmse:0.21715 validation_1-rmse:0.20021 +[18] validation_0-rmse:0.21499 validation_1-rmse:0.19735 +[19] validation_0-rmse:0.21283 validation_1-rmse:0.19480 +[20] validation_0-rmse:0.21109 validation_1-rmse:0.19209 +[21] validation_0-rmse:0.20904 validation_1-rmse:0.18969 +[22] validation_0-rmse:0.20762 validation_1-rmse:0.18718 +[23] validation_0-rmse:0.20580 validation_1-rmse:0.18498 +[24] validation_0-rmse:0.20434 validation_1-rmse:0.18262 +[25] validation_0-rmse:0.20267 validation_1-rmse:0.18048 +[26] validation_0-rmse:0.20106 validation_1-rmse:0.17844 +[27] validation_0-rmse:0.19945 validation_1-rmse:0.17647 +[28] validation_0-rmse:0.19813 validation_1-rmse:0.17443 +[29] validation_0-rmse:0.19669 validation_1-rmse:0.17264 +[30] validation_0-rmse:0.19541 validation_1-rmse:0.17054 +[31] validation_0-rmse:0.19401 validation_1-rmse:0.16881 +[32] validation_0-rmse:0.19263 validation_1-rmse:0.16719 +[33] validation_0-rmse:0.19134 validation_1-rmse:0.16560 +[34] validation_0-rmse:0.18996 validation_1-rmse:0.16365 +[35] validation_0-rmse:0.18864 validation_1-rmse:0.16211 +[36] validation_0-rmse:0.18752 validation_1-rmse:0.16069 +[37] validation_0-rmse:0.18652 validation_1-rmse:0.15898 +[38] validation_0-rmse:0.18540 validation_1-rmse:0.15751 +[39] validation_0-rmse:0.18429 validation_1-rmse:0.15616 +[40] validation_0-rmse:0.18317 validation_1-rmse:0.15475 +[41] validation_0-rmse:0.18215 validation_1-rmse:0.15324 +[42] validation_0-rmse:0.18119 validation_1-rmse:0.15199 +[43] validation_0-rmse:0.18008 validation_1-rmse:0.15057 +[44] validation_0-rmse:0.17926 validation_1-rmse:0.14942 +[45] validation_0-rmse:0.17841 validation_1-rmse:0.14813 +[46] validation_0-rmse:0.17755 validation_1-rmse:0.14700 +[47] validation_0-rmse:0.17672 validation_1-rmse:0.14572 +[48] validation_0-rmse:0.17586 validation_1-rmse:0.14466 +[49] validation_0-rmse:0.17511 validation_1-rmse:0.14354 +[50] validation_0-rmse:0.17440 validation_1-rmse:0.14236 +[51] validation_0-rmse:0.17354 validation_1-rmse:0.14130 +[52] validation_0-rmse:0.17281 validation_1-rmse:0.14035 +[53] validation_0-rmse:0.17210 validation_1-rmse:0.13942 +[54] validation_0-rmse:0.17136 validation_1-rmse:0.13843 +[55] validation_0-rmse:0.17045 validation_1-rmse:0.13715 +[56] validation_0-rmse:0.16971 validation_1-rmse:0.13629 +[57] validation_0-rmse:0.16900 validation_1-rmse:0.13511 +[58] validation_0-rmse:0.16834 validation_1-rmse:0.13426 +[59] validation_0-rmse:0.16763 validation_1-rmse:0.13323 +[60] validation_0-rmse:0.16702 validation_1-rmse:0.13242 +[61] validation_0-rmse:0.16639 validation_1-rmse:0.13164 +[62] validation_0-rmse:0.16586 validation_1-rmse:0.13079 +[63] validation_0-rmse:0.16527 validation_1-rmse:0.13006 +[64] validation_0-rmse:0.16458 validation_1-rmse:0.12914 +[65] validation_0-rmse:0.16396 validation_1-rmse:0.12841 +[66] validation_0-rmse:0.16332 validation_1-rmse:0.12742 +[67] validation_0-rmse:0.16290 validation_1-rmse:0.12665 +[68] validation_0-rmse:0.16248 validation_1-rmse:0.12584 +[69] validation_0-rmse:0.16192 validation_1-rmse:0.12503 +[70] validation_0-rmse:0.16128 validation_1-rmse:0.12435 +[71] validation_0-rmse:0.16078 validation_1-rmse:0.12371 +[72] validation_0-rmse:0.16032 validation_1-rmse:0.12311 +[73] validation_0-rmse:0.15998 validation_1-rmse:0.12241 +[74] validation_0-rmse:0.15959 validation_1-rmse:0.12184 +[75] validation_0-rmse:0.15922 validation_1-rmse:0.12121 +[76] validation_0-rmse:0.15877 validation_1-rmse:0.12064 +[77] validation_0-rmse:0.15830 validation_1-rmse:0.11981 +[78] validation_0-rmse:0.15791 validation_1-rmse:0.11927 +[79] validation_0-rmse:0.15751 validation_1-rmse:0.11859 +[80] validation_0-rmse:0.15716 validation_1-rmse:0.11795 +[81] validation_0-rmse:0.15680 validation_1-rmse:0.11740 +[82] validation_0-rmse:0.15624 validation_1-rmse:0.11683 +[83] validation_0-rmse:0.15578 validation_1-rmse:0.11632 +[84] validation_0-rmse:0.15553 validation_1-rmse:0.11586 +[85] validation_0-rmse:0.15471 validation_1-rmse:0.11513 +[86] validation_0-rmse:0.15444 validation_1-rmse:0.11465 +[87] validation_0-rmse:0.15417 validation_1-rmse:0.11406 +[88] validation_0-rmse:0.15387 validation_1-rmse:0.11359 +[89] validation_0-rmse:0.15359 validation_1-rmse:0.11319 +[90] validation_0-rmse:0.15332 validation_1-rmse:0.11269 +[91] validation_0-rmse:0.15301 validation_1-rmse:0.11221 +[92] validation_0-rmse:0.15258 validation_1-rmse:0.11176 +[93] validation_0-rmse:0.15231 validation_1-rmse:0.11135 +[94] validation_0-rmse:0.15202 validation_1-rmse:0.11093 +[95] validation_0-rmse:0.15185 validation_1-rmse:0.11041 +[96] validation_0-rmse:0.15173 validation_1-rmse:0.11000 +[97] validation_0-rmse:0.15150 validation_1-rmse:0.10961 +[98] validation_0-rmse:0.15114 validation_1-rmse:0.10917 +[99] validation_0-rmse:0.15096 validation_1-rmse:0.10882 +2025-04-29 01:55:59,097 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.77 secs) -------------------- +2025-04-29 01:55:59,098 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:55:59,706 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-03-02 00:00:00 to 2025-04-01 00:00:00, 10/11 trains +2025-04-29 01:55:59,706 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1743465600_prediction.feather +2025-04-29 01:55:59,715 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:59,723 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:55:59,725 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.079967 +1 0.003285 50.079967 +2 0.001898 50.079967 +3 0.000484 50.079967 +4 0.001688 50.079967 +2025-04-29 01:55:59,732 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:55:59,739 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:55:59,741 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.024153 +1 0.003285 50.024153 +2 0.001898 50.024153 +3 0.000484 50.024153 +4 0.001688 50.024153 +2025-04-29 01:55:59,745 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1743465600/cb_btc_1743465600 +2025-04-29 01:55:59,746 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:55:59,762 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:55:59,762 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-02 to 2025-03-31 -------------------- +2025-04-29 01:56:04,571 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:56:04,571 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.28468 validation_1-rmse:0.28491 +[1] validation_0-rmse:0.27961 validation_1-rmse:0.27914 +[2] validation_0-rmse:0.27524 validation_1-rmse:0.27370 +[3] validation_0-rmse:0.27054 validation_1-rmse:0.26858 +[4] validation_0-rmse:0.26601 validation_1-rmse:0.26362 +[5] validation_0-rmse:0.26219 validation_1-rmse:0.25896 +[6] validation_0-rmse:0.25814 validation_1-rmse:0.25450 +[7] validation_0-rmse:0.25500 validation_1-rmse:0.25026 +[8] validation_0-rmse:0.25145 validation_1-rmse:0.24602 +[9] validation_0-rmse:0.24843 validation_1-rmse:0.24213 +[10] validation_0-rmse:0.24527 validation_1-rmse:0.23824 +[11] validation_0-rmse:0.24238 validation_1-rmse:0.23440 +[12] validation_0-rmse:0.23940 validation_1-rmse:0.23096 +[13] validation_0-rmse:0.23630 validation_1-rmse:0.22764 +[14] validation_0-rmse:0.23385 validation_1-rmse:0.22440 +[15] validation_0-rmse:0.23099 validation_1-rmse:0.22128 +[16] validation_0-rmse:0.22865 validation_1-rmse:0.21801 +[17] validation_0-rmse:0.22620 validation_1-rmse:0.21515 +[18] validation_0-rmse:0.22375 validation_1-rmse:0.21210 +[19] validation_0-rmse:0.22142 validation_1-rmse:0.20925 +[20] validation_0-rmse:0.21927 validation_1-rmse:0.20663 +[21] validation_0-rmse:0.21720 validation_1-rmse:0.20416 +[22] validation_0-rmse:0.21528 validation_1-rmse:0.20170 +[23] validation_0-rmse:0.21330 validation_1-rmse:0.19913 +[24] validation_0-rmse:0.21136 validation_1-rmse:0.19693 +[25] validation_0-rmse:0.21002 validation_1-rmse:0.19438 +[26] validation_0-rmse:0.20807 validation_1-rmse:0.19222 +[27] validation_0-rmse:0.20636 validation_1-rmse:0.19016 +[28] validation_0-rmse:0.20439 validation_1-rmse:0.18763 +[29] validation_0-rmse:0.20276 validation_1-rmse:0.18559 +[30] validation_0-rmse:0.20114 validation_1-rmse:0.18380 +[31] validation_0-rmse:0.19965 validation_1-rmse:0.18163 +[32] validation_0-rmse:0.19833 validation_1-rmse:0.17955 +[33] validation_0-rmse:0.19688 validation_1-rmse:0.17782 +[34] validation_0-rmse:0.19558 validation_1-rmse:0.17614 +[35] validation_0-rmse:0.19420 validation_1-rmse:0.17451 +[36] validation_0-rmse:0.19297 validation_1-rmse:0.17293 +[37] validation_0-rmse:0.19169 validation_1-rmse:0.17111 +[38] validation_0-rmse:0.19038 validation_1-rmse:0.16943 +[39] validation_0-rmse:0.18941 validation_1-rmse:0.16798 +[40] validation_0-rmse:0.18828 validation_1-rmse:0.16657 +[41] validation_0-rmse:0.18724 validation_1-rmse:0.16485 +[42] validation_0-rmse:0.18620 validation_1-rmse:0.16347 +[43] validation_0-rmse:0.18525 validation_1-rmse:0.16204 +[44] validation_0-rmse:0.18429 validation_1-rmse:0.16073 +[45] validation_0-rmse:0.18324 validation_1-rmse:0.15951 +[46] validation_0-rmse:0.18250 validation_1-rmse:0.15797 +[47] validation_0-rmse:0.18157 validation_1-rmse:0.15682 +[48] validation_0-rmse:0.18069 validation_1-rmse:0.15566 +[49] validation_0-rmse:0.18002 validation_1-rmse:0.15440 +[50] validation_0-rmse:0.17914 validation_1-rmse:0.15322 +[51] validation_0-rmse:0.17842 validation_1-rmse:0.15220 +[52] validation_0-rmse:0.17756 validation_1-rmse:0.15107 +[53] validation_0-rmse:0.17668 validation_1-rmse:0.15007 +[54] validation_0-rmse:0.17596 validation_1-rmse:0.14866 +[55] validation_0-rmse:0.17525 validation_1-rmse:0.14775 +[56] validation_0-rmse:0.17467 validation_1-rmse:0.14653 +[57] validation_0-rmse:0.17390 validation_1-rmse:0.14564 +[58] validation_0-rmse:0.17326 validation_1-rmse:0.14478 +[59] validation_0-rmse:0.17273 validation_1-rmse:0.14356 +[60] validation_0-rmse:0.17218 validation_1-rmse:0.14269 +[61] validation_0-rmse:0.17157 validation_1-rmse:0.14186 +[62] validation_0-rmse:0.17120 validation_1-rmse:0.14083 +[63] validation_0-rmse:0.17069 validation_1-rmse:0.14002 +[64] validation_0-rmse:0.17012 validation_1-rmse:0.13912 +[65] validation_0-rmse:0.16942 validation_1-rmse:0.13834 +[66] validation_0-rmse:0.16914 validation_1-rmse:0.13720 +[67] validation_0-rmse:0.16856 validation_1-rmse:0.13648 +[68] validation_0-rmse:0.16800 validation_1-rmse:0.13569 +[69] validation_0-rmse:0.16796 validation_1-rmse:0.13472 +[70] validation_0-rmse:0.16737 validation_1-rmse:0.13405 +[71] validation_0-rmse:0.16686 validation_1-rmse:0.13342 +[72] validation_0-rmse:0.16639 validation_1-rmse:0.13270 +[73] validation_0-rmse:0.16648 validation_1-rmse:0.13149 +[74] validation_0-rmse:0.16609 validation_1-rmse:0.13086 +[75] validation_0-rmse:0.16560 validation_1-rmse:0.13025 +[76] validation_0-rmse:0.16530 validation_1-rmse:0.12925 +[77] validation_0-rmse:0.16492 validation_1-rmse:0.12824 +[78] validation_0-rmse:0.16451 validation_1-rmse:0.12770 +[79] validation_0-rmse:0.16414 validation_1-rmse:0.12710 +[80] validation_0-rmse:0.16377 validation_1-rmse:0.12654 +[81] validation_0-rmse:0.16338 validation_1-rmse:0.12595 +[82] validation_0-rmse:0.16317 validation_1-rmse:0.12490 +[83] validation_0-rmse:0.16249 validation_1-rmse:0.12361 +[84] validation_0-rmse:0.16217 validation_1-rmse:0.12307 +[85] validation_0-rmse:0.16178 validation_1-rmse:0.12255 +[86] validation_0-rmse:0.16149 validation_1-rmse:0.12206 +[87] validation_0-rmse:0.16113 validation_1-rmse:0.12155 +[88] validation_0-rmse:0.16049 validation_1-rmse:0.12061 +[89] validation_0-rmse:0.16008 validation_1-rmse:0.11990 +[90] validation_0-rmse:0.15955 validation_1-rmse:0.11882 +[91] validation_0-rmse:0.15927 validation_1-rmse:0.11842 +[92] validation_0-rmse:0.15891 validation_1-rmse:0.11796 +[93] validation_0-rmse:0.15880 validation_1-rmse:0.11730 +[94] validation_0-rmse:0.15829 validation_1-rmse:0.11631 +[95] validation_0-rmse:0.15809 validation_1-rmse:0.11584 +[96] validation_0-rmse:0.15778 validation_1-rmse:0.11544 +[97] validation_0-rmse:0.15763 validation_1-rmse:0.11504 +[98] validation_0-rmse:0.15724 validation_1-rmse:0.11438 +[99] validation_0-rmse:0.15694 validation_1-rmse:0.11396 +2025-04-29 01:56:05,520 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.77 secs) -------------------- +2025-04-29 01:56:05,521 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:06,027 - freqtrade.freqai.freqai_interface - INFO - Training BTC/USDT, 1/2 pairs from 2025-03-12 00:00:00 to 2025-04-11 00:00:00, 11/11 trains +2025-04-29 01:56:06,027 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_btc_1744329600_prediction.feather +2025-04-29 01:56:06,037 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:56:06,045 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:56:06,046 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.024153 +1 0.003285 50.024153 +2 0.001898 50.024153 +3 0.000484 50.024153 +4 0.001688 50.024153 +2025-04-29 01:56:06,057 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：BTC/USDT +2025-04-29 01:56:06,064 - FreqaiExampleStrategy - INFO - 目标列形状：(66770,) +2025-04-29 01:56:06,065 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.003572 50.093162 +1 0.003285 50.093162 +2 0.001898 50.093162 +3 0.000484 50.093162 +4 0.001688 50.093162 +2025-04-29 01:56:06,070 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-BTC_1744329600/cb_btc_1744329600 +2025-04-29 01:56:06,071 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training BTC/USDT -------------------- +2025-04-29 01:56:06,087 - freqtrade.freqai.data_kitchen - INFO - BTC/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:06,088 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-12 to 2025-04-10 -------------------- +2025-04-29 01:56:10,904 - datasieve.pipeline - INFO - DI tossed 2001 predictions for being too far from training data. +2025-04-29 01:56:10,907 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 75 features +2025-04-29 01:56:10,907 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.32950 validation_1-rmse:0.29220 +[1] validation_0-rmse:0.32402 validation_1-rmse:0.28580 +[2] validation_0-rmse:0.31922 validation_1-rmse:0.27974 +[3] validation_0-rmse:0.31450 validation_1-rmse:0.27409 +[4] validation_0-rmse:0.30969 validation_1-rmse:0.26866 +[5] validation_0-rmse:0.30585 validation_1-rmse:0.26346 +[6] validation_0-rmse:0.30202 validation_1-rmse:0.25855 +[7] validation_0-rmse:0.29888 validation_1-rmse:0.25375 +[8] validation_0-rmse:0.29520 validation_1-rmse:0.24919 +[9] validation_0-rmse:0.29164 validation_1-rmse:0.24487 +[10] validation_0-rmse:0.28843 validation_1-rmse:0.24072 +[11] validation_0-rmse:0.28514 validation_1-rmse:0.23667 +[12] validation_0-rmse:0.28114 validation_1-rmse:0.23279 +[13] validation_0-rmse:0.27740 validation_1-rmse:0.22909 +[14] validation_0-rmse:0.27421 validation_1-rmse:0.22543 +[15] validation_0-rmse:0.27115 validation_1-rmse:0.22210 +[16] validation_0-rmse:0.26820 validation_1-rmse:0.21859 +[17] validation_0-rmse:0.26549 validation_1-rmse:0.21528 +[18] validation_0-rmse:0.26254 validation_1-rmse:0.21226 +[19] validation_0-rmse:0.25967 validation_1-rmse:0.20927 +[20] validation_0-rmse:0.25735 validation_1-rmse:0.20641 +[21] validation_0-rmse:0.25470 validation_1-rmse:0.20366 +[22] validation_0-rmse:0.25265 validation_1-rmse:0.20073 +[23] validation_0-rmse:0.25054 validation_1-rmse:0.19819 +[24] validation_0-rmse:0.24806 validation_1-rmse:0.19573 +[25] validation_0-rmse:0.24570 validation_1-rmse:0.19304 +[26] validation_0-rmse:0.24361 validation_1-rmse:0.19076 +[27] validation_0-rmse:0.24148 validation_1-rmse:0.18853 +[28] validation_0-rmse:0.24014 validation_1-rmse:0.18621 +[29] validation_0-rmse:0.23792 validation_1-rmse:0.18410 +[30] validation_0-rmse:0.23603 validation_1-rmse:0.18203 +[31] validation_0-rmse:0.23421 validation_1-rmse:0.17990 +[32] validation_0-rmse:0.23264 validation_1-rmse:0.17800 +[33] validation_0-rmse:0.23087 validation_1-rmse:0.17616 +[34] validation_0-rmse:0.22949 validation_1-rmse:0.17427 +[35] validation_0-rmse:0.22857 validation_1-rmse:0.17234 +[36] validation_0-rmse:0.22690 validation_1-rmse:0.17065 +[37] validation_0-rmse:0.22566 validation_1-rmse:0.16898 +[38] validation_0-rmse:0.22462 validation_1-rmse:0.16738 +[39] validation_0-rmse:0.22376 validation_1-rmse:0.16567 +[40] validation_0-rmse:0.22232 validation_1-rmse:0.16410 +[41] validation_0-rmse:0.22105 validation_1-rmse:0.16265 +[42] validation_0-rmse:0.22006 validation_1-rmse:0.16111 +[43] validation_0-rmse:0.21847 validation_1-rmse:0.15976 +[44] validation_0-rmse:0.21782 validation_1-rmse:0.15824 +[45] validation_0-rmse:0.21641 validation_1-rmse:0.15686 +[46] validation_0-rmse:0.21552 validation_1-rmse:0.15554 +[47] validation_0-rmse:0.21459 validation_1-rmse:0.15417 +[48] validation_0-rmse:0.21339 validation_1-rmse:0.15293 +[49] validation_0-rmse:0.21255 validation_1-rmse:0.15176 +[50] validation_0-rmse:0.21192 validation_1-rmse:0.15047 +[51] validation_0-rmse:0.21115 validation_1-rmse:0.14910 +[52] validation_0-rmse:0.21072 validation_1-rmse:0.14774 +[53] validation_0-rmse:0.20992 validation_1-rmse:0.14670 +[54] validation_0-rmse:0.20839 validation_1-rmse:0.14541 +[55] validation_0-rmse:0.20753 validation_1-rmse:0.14442 +[56] validation_0-rmse:0.20648 validation_1-rmse:0.14328 +[57] validation_0-rmse:0.20564 validation_1-rmse:0.14229 +[58] validation_0-rmse:0.20473 validation_1-rmse:0.14137 +[59] validation_0-rmse:0.20418 validation_1-rmse:0.14011 +[60] validation_0-rmse:0.20341 validation_1-rmse:0.13923 +[61] validation_0-rmse:0.20258 validation_1-rmse:0.13839 +[62] validation_0-rmse:0.20230 validation_1-rmse:0.13723 +[63] validation_0-rmse:0.20075 validation_1-rmse:0.13546 +[64] validation_0-rmse:0.20007 validation_1-rmse:0.13467 +[65] validation_0-rmse:0.19937 validation_1-rmse:0.13387 +[66] validation_0-rmse:0.19875 validation_1-rmse:0.13296 +[67] validation_0-rmse:0.19709 validation_1-rmse:0.13137 +[68] validation_0-rmse:0.19675 validation_1-rmse:0.13042 +[69] validation_0-rmse:0.19617 validation_1-rmse:0.12968 +[70] validation_0-rmse:0.19560 validation_1-rmse:0.12900 +[71] validation_0-rmse:0.19492 validation_1-rmse:0.12834 +[72] validation_0-rmse:0.19319 validation_1-rmse:0.12681 +[73] validation_0-rmse:0.19272 validation_1-rmse:0.12612 +[74] validation_0-rmse:0.19230 validation_1-rmse:0.12535 +[75] validation_0-rmse:0.19170 validation_1-rmse:0.12474 +[76] validation_0-rmse:0.19058 validation_1-rmse:0.12338 +[77] validation_0-rmse:0.19010 validation_1-rmse:0.12279 +[78] validation_0-rmse:0.18961 validation_1-rmse:0.12223 +[79] validation_0-rmse:0.18960 validation_1-rmse:0.12156 +[80] validation_0-rmse:0.18882 validation_1-rmse:0.12038 +[81] validation_0-rmse:0.18819 validation_1-rmse:0.11975 +[82] validation_0-rmse:0.18789 validation_1-rmse:0.11916 +[83] validation_0-rmse:0.18738 validation_1-rmse:0.11864 +[84] validation_0-rmse:0.18718 validation_1-rmse:0.11801 +[85] validation_0-rmse:0.18600 validation_1-rmse:0.11698 +[86] validation_0-rmse:0.18572 validation_1-rmse:0.11653 +[87] validation_0-rmse:0.18534 validation_1-rmse:0.11603 +[88] validation_0-rmse:0.18478 validation_1-rmse:0.11508 +[89] validation_0-rmse:0.18430 validation_1-rmse:0.11459 +[90] validation_0-rmse:0.18447 validation_1-rmse:0.11396 +[91] validation_0-rmse:0.18424 validation_1-rmse:0.11352 +[92] validation_0-rmse:0.18367 validation_1-rmse:0.11307 +[93] validation_0-rmse:0.18333 validation_1-rmse:0.11265 +[94] validation_0-rmse:0.18313 validation_1-rmse:0.11216 +[95] validation_0-rmse:0.18275 validation_1-rmse:0.11157 +[96] validation_0-rmse:0.18275 validation_1-rmse:0.11106 +[97] validation_0-rmse:0.18248 validation_1-rmse:0.11068 +[98] validation_0-rmse:0.18220 validation_1-rmse:0.11033 +[99] validation_0-rmse:0.18198 validation_1-rmse:0.10994 +2025-04-29 01:56:11,705 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training BTC/USDT (5.63 secs) -------------------- +2025-04-29 01:56:11,706 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:12,255 - FreqaiExampleStrategy - INFO - 动态参数：buy_rsi=39.26145316407591, sell_rsi=59.26145316407591, stoploss=-0.15, trailing_stop_positive=0.05 +2025-04-29 01:56:12,275 - FreqaiExampleStrategy - INFO - up_or_down 值统计： +up_or_down +1 33535 +0 33236 +2025-04-29 01:56:12,276 - FreqaiExampleStrategy - INFO - do_predict 值统计： +do_predict +0.0 35773 +1.0 30998 +2025-04-29 01:56:12,279 - FreqaiExampleStrategy - INFO - 处理交易对：SOL/USDT +2025-04-29 01:56:12,281 - freqtrade.freqai.freqai_interface - INFO - Training 11 timeranges +2025-04-29 01:56:12,282 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2024-12-02 00:00:00 to 2025-01-01 00:00:00, 1/11 trains +2025-04-29 01:56:12,283 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1735689600_prediction.feather +2025-04-29 01:56:12,334 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 5m to 8690 +2025-04-29 01:56:12,335 - freqtrade.data.dataprovider - INFO - Loading data for SOL/USDT 5m from 2024-12-01 19:50:00 to 2025-04-20 00:00:00 +2025-04-29 01:56:12,422 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 1h to 770 +2025-04-29 01:56:12,422 - freqtrade.data.dataprovider - INFO - Loading data for SOL/USDT 1h from 2024-11-29 22:00:00 to 2025-04-20 00:00:00 +2025-04-29 01:56:12,518 - freqtrade.data.dataprovider - INFO - Increasing startup_candle_count for freqai on 3m to 14450 +2025-04-29 01:56:12,519 - freqtrade.data.dataprovider - INFO - Loading data for BTC/USDT 3m from 2024-12-01 21:30:00 to 2025-04-20 00:00:00 +2025-04-29 01:56:13,040 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:13,046 - FreqaiExampleStrategy - INFO - 目标列形状：(14450,) +2025-04-29 01:56:13,047 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.58814 +1 0.003044 49.58814 +2 0.000465 49.58814 +3 -0.000380 49.58814 +4 0.002829 49.58814 +2025-04-29 01:56:13,052 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:13,057 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:56:13,059 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.68088 +1 0.003044 49.68088 +2 0.000465 49.68088 +3 -0.000380 49.68088 +4 0.002829 49.68088 +2025-04-29 01:56:13,066 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1735689600/cb_sol_1735689600 +2025-04-29 01:56:13,066 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:13,095 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:13,096 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-02 to 2024-12-31 -------------------- +2025-04-29 01:56:18,126 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:18,126 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.30164 validation_1-rmse:0.29585 +[1] validation_0-rmse:0.29609 validation_1-rmse:0.28921 +[2] validation_0-rmse:0.29103 validation_1-rmse:0.28298 +[3] validation_0-rmse:0.28604 validation_1-rmse:0.27706 +[4] validation_0-rmse:0.28108 validation_1-rmse:0.27129 +[5] validation_0-rmse:0.27670 validation_1-rmse:0.26609 +[6] validation_0-rmse:0.27234 validation_1-rmse:0.26092 +[7] validation_0-rmse:0.26874 validation_1-rmse:0.25593 +[8] validation_0-rmse:0.26461 validation_1-rmse:0.25118 +[9] validation_0-rmse:0.26074 validation_1-rmse:0.24677 +[10] validation_0-rmse:0.25745 validation_1-rmse:0.24239 +[11] validation_0-rmse:0.25460 validation_1-rmse:0.23832 +[12] validation_0-rmse:0.25121 validation_1-rmse:0.23441 +[13] validation_0-rmse:0.24825 validation_1-rmse:0.23068 +[14] validation_0-rmse:0.24580 validation_1-rmse:0.22694 +[15] validation_0-rmse:0.24286 validation_1-rmse:0.22346 +[16] validation_0-rmse:0.24051 validation_1-rmse:0.22006 +[17] validation_0-rmse:0.23821 validation_1-rmse:0.21690 +[18] validation_0-rmse:0.23549 validation_1-rmse:0.21383 +[19] validation_0-rmse:0.23335 validation_1-rmse:0.21087 +[20] validation_0-rmse:0.23089 validation_1-rmse:0.20804 +[21] validation_0-rmse:0.22918 validation_1-rmse:0.20505 +[22] validation_0-rmse:0.22716 validation_1-rmse:0.20240 +[23] validation_0-rmse:0.22562 validation_1-rmse:0.19981 +[24] validation_0-rmse:0.22385 validation_1-rmse:0.19723 +[25] validation_0-rmse:0.22201 validation_1-rmse:0.19473 +[26] validation_0-rmse:0.22016 validation_1-rmse:0.19245 +[27] validation_0-rmse:0.21834 validation_1-rmse:0.19024 +[28] validation_0-rmse:0.21671 validation_1-rmse:0.18789 +[29] validation_0-rmse:0.21493 validation_1-rmse:0.18579 +[30] validation_0-rmse:0.21385 validation_1-rmse:0.18351 +[31] validation_0-rmse:0.21216 validation_1-rmse:0.18156 +[32] validation_0-rmse:0.21088 validation_1-rmse:0.17941 +[33] validation_0-rmse:0.20953 validation_1-rmse:0.17754 +[34] validation_0-rmse:0.20805 validation_1-rmse:0.17575 +[35] validation_0-rmse:0.20648 validation_1-rmse:0.17399 +[36] validation_0-rmse:0.20515 validation_1-rmse:0.17220 +[37] validation_0-rmse:0.20382 validation_1-rmse:0.17031 +[38] validation_0-rmse:0.20257 validation_1-rmse:0.16871 +[39] validation_0-rmse:0.20125 validation_1-rmse:0.16718 +[40] validation_0-rmse:0.20005 validation_1-rmse:0.16574 +[41] validation_0-rmse:0.19885 validation_1-rmse:0.16415 +[42] validation_0-rmse:0.19789 validation_1-rmse:0.16270 +[43] validation_0-rmse:0.19680 validation_1-rmse:0.16130 +[44] validation_0-rmse:0.19564 validation_1-rmse:0.15993 +[45] validation_0-rmse:0.19480 validation_1-rmse:0.15854 +[46] validation_0-rmse:0.19376 validation_1-rmse:0.15728 +[47] validation_0-rmse:0.19290 validation_1-rmse:0.15568 +[48] validation_0-rmse:0.19223 validation_1-rmse:0.15445 +[49] validation_0-rmse:0.19129 validation_1-rmse:0.15330 +[50] validation_0-rmse:0.19035 validation_1-rmse:0.15194 +[51] validation_0-rmse:0.18948 validation_1-rmse:0.15082 +[52] validation_0-rmse:0.18882 validation_1-rmse:0.14945 +[53] validation_0-rmse:0.18801 validation_1-rmse:0.14840 +[54] validation_0-rmse:0.18707 validation_1-rmse:0.14736 +[55] validation_0-rmse:0.18637 validation_1-rmse:0.14635 +[56] validation_0-rmse:0.18571 validation_1-rmse:0.14542 +[57] validation_0-rmse:0.18497 validation_1-rmse:0.14413 +[58] validation_0-rmse:0.18443 validation_1-rmse:0.14297 +[59] validation_0-rmse:0.18375 validation_1-rmse:0.14203 +[60] validation_0-rmse:0.18319 validation_1-rmse:0.14111 +[61] validation_0-rmse:0.18266 validation_1-rmse:0.14030 +[62] validation_0-rmse:0.18185 validation_1-rmse:0.13914 +[63] validation_0-rmse:0.18145 validation_1-rmse:0.13831 +[64] validation_0-rmse:0.18135 validation_1-rmse:0.13720 +[65] validation_0-rmse:0.18075 validation_1-rmse:0.13643 +[66] validation_0-rmse:0.18020 validation_1-rmse:0.13560 +[67] validation_0-rmse:0.17951 validation_1-rmse:0.13485 +[68] validation_0-rmse:0.17888 validation_1-rmse:0.13414 +[69] validation_0-rmse:0.17850 validation_1-rmse:0.13343 +[70] validation_0-rmse:0.17798 validation_1-rmse:0.13224 +[71] validation_0-rmse:0.17751 validation_1-rmse:0.13133 +[72] validation_0-rmse:0.17711 validation_1-rmse:0.13062 +[73] validation_0-rmse:0.17701 validation_1-rmse:0.12966 +[74] validation_0-rmse:0.17648 validation_1-rmse:0.12872 +[75] validation_0-rmse:0.17611 validation_1-rmse:0.12806 +[76] validation_0-rmse:0.17573 validation_1-rmse:0.12732 +[77] validation_0-rmse:0.17528 validation_1-rmse:0.12664 +[78] validation_0-rmse:0.17478 validation_1-rmse:0.12605 +[79] validation_0-rmse:0.17432 validation_1-rmse:0.12518 +[80] validation_0-rmse:0.17391 validation_1-rmse:0.12466 +[81] validation_0-rmse:0.17358 validation_1-rmse:0.12398 +[82] validation_0-rmse:0.17315 validation_1-rmse:0.12342 +[83] validation_0-rmse:0.17260 validation_1-rmse:0.12276 +[84] validation_0-rmse:0.17220 validation_1-rmse:0.12222 +[85] validation_0-rmse:0.17182 validation_1-rmse:0.12176 +[86] validation_0-rmse:0.17152 validation_1-rmse:0.12124 +[87] validation_0-rmse:0.17103 validation_1-rmse:0.12046 +[88] validation_0-rmse:0.17085 validation_1-rmse:0.11974 +[89] validation_0-rmse:0.17053 validation_1-rmse:0.11930 +[90] validation_0-rmse:0.17018 validation_1-rmse:0.11888 +[91] validation_0-rmse:0.17011 validation_1-rmse:0.11810 +[92] validation_0-rmse:0.16980 validation_1-rmse:0.11762 +[93] validation_0-rmse:0.16956 validation_1-rmse:0.11689 +[94] validation_0-rmse:0.16923 validation_1-rmse:0.11641 +[95] validation_0-rmse:0.16912 validation_1-rmse:0.11579 +[96] validation_0-rmse:0.16878 validation_1-rmse:0.11530 +[97] validation_0-rmse:0.16857 validation_1-rmse:0.11489 +[98] validation_0-rmse:0.16824 validation_1-rmse:0.11442 +[99] validation_0-rmse:0.16824 validation_1-rmse:0.11403 +2025-04-29 01:56:19,586 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.52 secs) -------------------- +2025-04-29 01:56:19,587 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:20,174 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2024-12-12 00:00:00 to 2025-01-11 00:00:00, 2/11 trains +2025-04-29 01:56:20,175 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1736553600_prediction.feather +2025-04-29 01:56:20,179 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:20,185 - FreqaiExampleStrategy - INFO - 目标列形状：(19250,) +2025-04-29 01:56:20,186 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.68088 +1 0.003044 49.68088 +2 0.000465 49.68088 +3 -0.000380 49.68088 +4 0.002829 49.68088 +2025-04-29 01:56:20,192 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:20,197 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:56:20,199 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.97721 +1 0.003044 49.97721 +2 0.000465 49.97721 +3 -0.000380 49.97721 +4 0.002829 49.97721 +2025-04-29 01:56:20,204 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1736553600/cb_sol_1736553600 +2025-04-29 01:56:20,205 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:20,227 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:20,228 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-12 to 2025-01-10 -------------------- +2025-04-29 01:56:25,109 - datasieve.pipeline - INFO - DI tossed 5 predictions for being too far from training data. +2025-04-29 01:56:25,112 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:25,112 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.29597 validation_1-rmse:0.29016 +[1] validation_0-rmse:0.29075 validation_1-rmse:0.28391 +[2] validation_0-rmse:0.28602 validation_1-rmse:0.27798 +[3] validation_0-rmse:0.28062 validation_1-rmse:0.27213 +[4] validation_0-rmse:0.27647 validation_1-rmse:0.26682 +[5] validation_0-rmse:0.27188 validation_1-rmse:0.26144 +[6] validation_0-rmse:0.26781 validation_1-rmse:0.25655 +[7] validation_0-rmse:0.26412 validation_1-rmse:0.25180 +[8] validation_0-rmse:0.25994 validation_1-rmse:0.24709 +[9] validation_0-rmse:0.25649 validation_1-rmse:0.24277 +[10] validation_0-rmse:0.25332 validation_1-rmse:0.23850 +[11] validation_0-rmse:0.24999 validation_1-rmse:0.23452 +[12] validation_0-rmse:0.24687 validation_1-rmse:0.23072 +[13] validation_0-rmse:0.24432 validation_1-rmse:0.22694 +[14] validation_0-rmse:0.24128 validation_1-rmse:0.22341 +[15] validation_0-rmse:0.23869 validation_1-rmse:0.21969 +[16] validation_0-rmse:0.23628 validation_1-rmse:0.21635 +[17] validation_0-rmse:0.23354 validation_1-rmse:0.21326 +[18] validation_0-rmse:0.23123 validation_1-rmse:0.21007 +[19] validation_0-rmse:0.22919 validation_1-rmse:0.20707 +[20] validation_0-rmse:0.22705 validation_1-rmse:0.20418 +[21] validation_0-rmse:0.22505 validation_1-rmse:0.20149 +[22] validation_0-rmse:0.22285 validation_1-rmse:0.19887 +[23] validation_0-rmse:0.22084 validation_1-rmse:0.19631 +[24] validation_0-rmse:0.21877 validation_1-rmse:0.19389 +[25] validation_0-rmse:0.21748 validation_1-rmse:0.19133 +[26] validation_0-rmse:0.21557 validation_1-rmse:0.18870 +[27] validation_0-rmse:0.21374 validation_1-rmse:0.18648 +[28] validation_0-rmse:0.21183 validation_1-rmse:0.18432 +[29] validation_0-rmse:0.21047 validation_1-rmse:0.18209 +[30] validation_0-rmse:0.20873 validation_1-rmse:0.17990 +[31] validation_0-rmse:0.20717 validation_1-rmse:0.17795 +[32] validation_0-rmse:0.20564 validation_1-rmse:0.17599 +[33] validation_0-rmse:0.20428 validation_1-rmse:0.17421 +[34] validation_0-rmse:0.20290 validation_1-rmse:0.17229 +[35] validation_0-rmse:0.20161 validation_1-rmse:0.17047 +[36] validation_0-rmse:0.20018 validation_1-rmse:0.16878 +[37] validation_0-rmse:0.19923 validation_1-rmse:0.16688 +[38] validation_0-rmse:0.19796 validation_1-rmse:0.16534 +[39] validation_0-rmse:0.19668 validation_1-rmse:0.16355 +[40] validation_0-rmse:0.19543 validation_1-rmse:0.16204 +[41] validation_0-rmse:0.19441 validation_1-rmse:0.16062 +[42] validation_0-rmse:0.19344 validation_1-rmse:0.15910 +[43] validation_0-rmse:0.19256 validation_1-rmse:0.15759 +[44] validation_0-rmse:0.19154 validation_1-rmse:0.15625 +[45] validation_0-rmse:0.19048 validation_1-rmse:0.15494 +[46] validation_0-rmse:0.18937 validation_1-rmse:0.15366 +[47] validation_0-rmse:0.18865 validation_1-rmse:0.15236 +[48] validation_0-rmse:0.18784 validation_1-rmse:0.15112 +[49] validation_0-rmse:0.18704 validation_1-rmse:0.14998 +[50] validation_0-rmse:0.18625 validation_1-rmse:0.14874 +[51] validation_0-rmse:0.18541 validation_1-rmse:0.14763 +[52] validation_0-rmse:0.18456 validation_1-rmse:0.14659 +[53] validation_0-rmse:0.18383 validation_1-rmse:0.14530 +[54] validation_0-rmse:0.18315 validation_1-rmse:0.14420 +[55] validation_0-rmse:0.18234 validation_1-rmse:0.14321 +[56] validation_0-rmse:0.18181 validation_1-rmse:0.14206 +[57] validation_0-rmse:0.18109 validation_1-rmse:0.14106 +[58] validation_0-rmse:0.18033 validation_1-rmse:0.13996 +[59] validation_0-rmse:0.17964 validation_1-rmse:0.13905 +[60] validation_0-rmse:0.17921 validation_1-rmse:0.13820 +[61] validation_0-rmse:0.17865 validation_1-rmse:0.13731 +[62] validation_0-rmse:0.17795 validation_1-rmse:0.13648 +[63] validation_0-rmse:0.17737 validation_1-rmse:0.13559 +[64] validation_0-rmse:0.17680 validation_1-rmse:0.13483 +[65] validation_0-rmse:0.17628 validation_1-rmse:0.13408 +[66] validation_0-rmse:0.17588 validation_1-rmse:0.13303 +[67] validation_0-rmse:0.17530 validation_1-rmse:0.13228 +[68] validation_0-rmse:0.17478 validation_1-rmse:0.13153 +[69] validation_0-rmse:0.17439 validation_1-rmse:0.13081 +[70] validation_0-rmse:0.17401 validation_1-rmse:0.12991 +[71] validation_0-rmse:0.17347 validation_1-rmse:0.12911 +[72] validation_0-rmse:0.17304 validation_1-rmse:0.12838 +[73] validation_0-rmse:0.17254 validation_1-rmse:0.12774 +[74] validation_0-rmse:0.17207 validation_1-rmse:0.12656 +[75] validation_0-rmse:0.17185 validation_1-rmse:0.12571 +[76] validation_0-rmse:0.17126 validation_1-rmse:0.12512 +[77] validation_0-rmse:0.17096 validation_1-rmse:0.12447 +[78] validation_0-rmse:0.17064 validation_1-rmse:0.12381 +[79] validation_0-rmse:0.17024 validation_1-rmse:0.12300 +[80] validation_0-rmse:0.16989 validation_1-rmse:0.12244 +[81] validation_0-rmse:0.16955 validation_1-rmse:0.12180 +[82] validation_0-rmse:0.16924 validation_1-rmse:0.12129 +[83] validation_0-rmse:0.16931 validation_1-rmse:0.12037 +[84] validation_0-rmse:0.16888 validation_1-rmse:0.11970 +[85] validation_0-rmse:0.16845 validation_1-rmse:0.11914 +[86] validation_0-rmse:0.16809 validation_1-rmse:0.11840 +[87] validation_0-rmse:0.16766 validation_1-rmse:0.11760 +[88] validation_0-rmse:0.16741 validation_1-rmse:0.11714 +[89] validation_0-rmse:0.16707 validation_1-rmse:0.11667 +[90] validation_0-rmse:0.16683 validation_1-rmse:0.11592 +[91] validation_0-rmse:0.16643 validation_1-rmse:0.11537 +[92] validation_0-rmse:0.16621 validation_1-rmse:0.11455 +[93] validation_0-rmse:0.16611 validation_1-rmse:0.11396 +[94] validation_0-rmse:0.16587 validation_1-rmse:0.11350 +[95] validation_0-rmse:0.16563 validation_1-rmse:0.11308 +[96] validation_0-rmse:0.16535 validation_1-rmse:0.11237 +[97] validation_0-rmse:0.16487 validation_1-rmse:0.11173 +[98] validation_0-rmse:0.16461 validation_1-rmse:0.11133 +[99] validation_0-rmse:0.16437 validation_1-rmse:0.11096 +2025-04-29 01:56:26,510 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.30 secs) -------------------- +2025-04-29 01:56:26,511 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:27,072 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2024-12-22 00:00:00 to 2025-01-21 00:00:00, 3/11 trains +2025-04-29 01:56:27,073 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1737417600_prediction.feather +2025-04-29 01:56:27,079 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:27,085 - FreqaiExampleStrategy - INFO - 目标列形状：(24050,) +2025-04-29 01:56:27,086 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.97721 +1 0.003044 49.97721 +2 0.000465 49.97721 +3 -0.000380 49.97721 +4 0.002829 49.97721 +2025-04-29 01:56:27,094 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:27,100 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:56:27,102 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.941408 +1 0.003044 49.941408 +2 0.000465 49.941408 +3 -0.000380 49.941408 +4 0.002829 49.941408 +2025-04-29 01:56:27,108 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1737417600/cb_sol_1737417600 +2025-04-29 01:56:27,109 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:27,130 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:27,131 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2024-12-22 to 2025-01-20 -------------------- +2025-04-29 01:56:32,206 - datasieve.pipeline - INFO - DI tossed 1523 predictions for being too far from training data. +2025-04-29 01:56:32,209 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:32,210 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.30838 validation_1-rmse:0.28356 +[1] validation_0-rmse:0.30280 validation_1-rmse:0.27752 +[2] validation_0-rmse:0.29759 validation_1-rmse:0.27179 +[3] validation_0-rmse:0.29330 validation_1-rmse:0.26614 +[4] validation_0-rmse:0.28936 validation_1-rmse:0.26091 +[5] validation_0-rmse:0.28544 validation_1-rmse:0.25581 +[6] validation_0-rmse:0.28151 validation_1-rmse:0.25102 +[7] validation_0-rmse:0.27790 validation_1-rmse:0.24636 +[8] validation_0-rmse:0.27429 validation_1-rmse:0.24196 +[9] validation_0-rmse:0.27104 validation_1-rmse:0.23770 +[10] validation_0-rmse:0.26762 validation_1-rmse:0.23356 +[11] validation_0-rmse:0.26472 validation_1-rmse:0.22966 +[12] validation_0-rmse:0.26219 validation_1-rmse:0.22601 +[13] validation_0-rmse:0.25924 validation_1-rmse:0.22234 +[14] validation_0-rmse:0.25634 validation_1-rmse:0.21888 +[15] validation_0-rmse:0.25379 validation_1-rmse:0.21545 +[16] validation_0-rmse:0.25117 validation_1-rmse:0.21221 +[17] validation_0-rmse:0.24877 validation_1-rmse:0.20902 +[18] validation_0-rmse:0.24653 validation_1-rmse:0.20604 +[19] validation_0-rmse:0.24404 validation_1-rmse:0.20315 +[20] validation_0-rmse:0.24194 validation_1-rmse:0.20032 +[21] validation_0-rmse:0.23966 validation_1-rmse:0.19765 +[22] validation_0-rmse:0.23804 validation_1-rmse:0.19481 +[23] validation_0-rmse:0.23599 validation_1-rmse:0.19230 +[24] validation_0-rmse:0.23384 validation_1-rmse:0.18993 +[25] validation_0-rmse:0.23196 validation_1-rmse:0.18756 +[26] validation_0-rmse:0.23057 validation_1-rmse:0.18506 +[27] validation_0-rmse:0.22854 validation_1-rmse:0.18283 +[28] validation_0-rmse:0.22705 validation_1-rmse:0.18071 +[29] validation_0-rmse:0.22557 validation_1-rmse:0.17851 +[30] validation_0-rmse:0.22394 validation_1-rmse:0.17644 +[31] validation_0-rmse:0.22213 validation_1-rmse:0.17452 +[32] validation_0-rmse:0.22064 validation_1-rmse:0.17267 +[33] validation_0-rmse:0.21905 validation_1-rmse:0.17084 +[34] validation_0-rmse:0.21806 validation_1-rmse:0.16880 +[35] validation_0-rmse:0.21693 validation_1-rmse:0.16700 +[36] validation_0-rmse:0.21537 validation_1-rmse:0.16520 +[37] validation_0-rmse:0.21417 validation_1-rmse:0.16362 +[38] validation_0-rmse:0.21282 validation_1-rmse:0.16204 +[39] validation_0-rmse:0.21137 validation_1-rmse:0.16047 +[40] validation_0-rmse:0.20994 validation_1-rmse:0.15897 +[41] validation_0-rmse:0.20878 validation_1-rmse:0.15747 +[42] validation_0-rmse:0.20766 validation_1-rmse:0.15604 +[43] validation_0-rmse:0.20666 validation_1-rmse:0.15444 +[44] validation_0-rmse:0.20566 validation_1-rmse:0.15316 +[45] validation_0-rmse:0.20496 validation_1-rmse:0.15162 +[46] validation_0-rmse:0.20394 validation_1-rmse:0.15038 +[47] validation_0-rmse:0.20277 validation_1-rmse:0.14909 +[48] validation_0-rmse:0.20176 validation_1-rmse:0.14793 +[49] validation_0-rmse:0.20072 validation_1-rmse:0.14681 +[50] validation_0-rmse:0.20058 validation_1-rmse:0.14528 +[51] validation_0-rmse:0.19970 validation_1-rmse:0.14419 +[52] validation_0-rmse:0.19887 validation_1-rmse:0.14284 +[53] validation_0-rmse:0.19809 validation_1-rmse:0.14182 +[54] validation_0-rmse:0.19725 validation_1-rmse:0.14076 +[55] validation_0-rmse:0.19636 validation_1-rmse:0.13981 +[56] validation_0-rmse:0.19615 validation_1-rmse:0.13853 +[57] validation_0-rmse:0.19540 validation_1-rmse:0.13757 +[58] validation_0-rmse:0.19460 validation_1-rmse:0.13664 +[59] validation_0-rmse:0.19418 validation_1-rmse:0.13553 +[60] validation_0-rmse:0.19382 validation_1-rmse:0.13445 +[61] validation_0-rmse:0.19302 validation_1-rmse:0.13363 +[62] validation_0-rmse:0.19218 validation_1-rmse:0.13270 +[63] validation_0-rmse:0.19154 validation_1-rmse:0.13183 +[64] validation_0-rmse:0.19083 validation_1-rmse:0.13105 +[65] validation_0-rmse:0.19005 validation_1-rmse:0.13008 +[66] validation_0-rmse:0.18929 validation_1-rmse:0.12932 +[67] validation_0-rmse:0.18885 validation_1-rmse:0.12851 +[68] validation_0-rmse:0.18837 validation_1-rmse:0.12781 +[69] validation_0-rmse:0.18790 validation_1-rmse:0.12711 +[70] validation_0-rmse:0.18732 validation_1-rmse:0.12617 +[71] validation_0-rmse:0.18682 validation_1-rmse:0.12552 +[72] validation_0-rmse:0.18669 validation_1-rmse:0.12448 +[73] validation_0-rmse:0.18617 validation_1-rmse:0.12382 +[74] validation_0-rmse:0.18587 validation_1-rmse:0.12322 +[75] validation_0-rmse:0.18544 validation_1-rmse:0.12261 +[76] validation_0-rmse:0.18524 validation_1-rmse:0.12162 +[77] validation_0-rmse:0.18486 validation_1-rmse:0.12098 +[78] validation_0-rmse:0.18443 validation_1-rmse:0.12021 +[79] validation_0-rmse:0.18415 validation_1-rmse:0.11963 +[80] validation_0-rmse:0.18393 validation_1-rmse:0.11866 +[81] validation_0-rmse:0.18344 validation_1-rmse:0.11809 +[82] validation_0-rmse:0.18307 validation_1-rmse:0.11748 +[83] validation_0-rmse:0.18257 validation_1-rmse:0.11699 +[84] validation_0-rmse:0.18216 validation_1-rmse:0.11643 +[85] validation_0-rmse:0.18188 validation_1-rmse:0.11595 +[86] validation_0-rmse:0.18168 validation_1-rmse:0.11502 +[87] validation_0-rmse:0.18148 validation_1-rmse:0.11451 +[88] validation_0-rmse:0.18093 validation_1-rmse:0.11378 +[89] validation_0-rmse:0.18054 validation_1-rmse:0.11332 +[90] validation_0-rmse:0.18024 validation_1-rmse:0.11285 +[91] validation_0-rmse:0.17982 validation_1-rmse:0.11241 +[92] validation_0-rmse:0.17950 validation_1-rmse:0.11185 +[93] validation_0-rmse:0.17918 validation_1-rmse:0.11123 +[94] validation_0-rmse:0.17882 validation_1-rmse:0.11072 +[95] validation_0-rmse:0.17881 validation_1-rmse:0.10986 +[96] validation_0-rmse:0.17832 validation_1-rmse:0.10941 +[97] validation_0-rmse:0.17800 validation_1-rmse:0.10897 +[98] validation_0-rmse:0.17774 validation_1-rmse:0.10859 +[99] validation_0-rmse:0.17746 validation_1-rmse:0.10819 +2025-04-29 01:56:33,558 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.45 secs) -------------------- +2025-04-29 01:56:33,558 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:34,118 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-01 00:00:00 to 2025-01-31 00:00:00, 4/11 trains +2025-04-29 01:56:34,119 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1738281600_prediction.feather +2025-04-29 01:56:34,124 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:34,130 - FreqaiExampleStrategy - INFO - 目标列形状：(28850,) +2025-04-29 01:56:34,131 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.941408 +1 0.003044 49.941408 +2 0.000465 49.941408 +3 -0.000380 49.941408 +4 0.002829 49.941408 +2025-04-29 01:56:34,137 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:34,143 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:56:34,144 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.830756 +1 0.003044 49.830756 +2 0.000465 49.830756 +3 -0.000380 49.830756 +4 0.002829 49.830756 +2025-04-29 01:56:34,149 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1738281600/cb_sol_1738281600 +2025-04-29 01:56:34,150 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:34,173 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:34,173 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-01 to 2025-01-30 -------------------- +2025-04-29 01:56:39,271 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:39,271 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.29494 validation_1-rmse:0.28739 +[1] validation_0-rmse:0.28930 validation_1-rmse:0.28164 +[2] validation_0-rmse:0.28437 validation_1-rmse:0.27613 +[3] validation_0-rmse:0.27990 validation_1-rmse:0.27106 +[4] validation_0-rmse:0.27541 validation_1-rmse:0.26617 +[5] validation_0-rmse:0.27070 validation_1-rmse:0.26147 +[6] validation_0-rmse:0.26683 validation_1-rmse:0.25687 +[7] validation_0-rmse:0.26280 validation_1-rmse:0.25263 +[8] validation_0-rmse:0.25916 validation_1-rmse:0.24830 +[9] validation_0-rmse:0.25540 validation_1-rmse:0.24420 +[10] validation_0-rmse:0.25186 validation_1-rmse:0.24022 +[11] validation_0-rmse:0.24829 validation_1-rmse:0.23647 +[12] validation_0-rmse:0.24504 validation_1-rmse:0.23286 +[13] validation_0-rmse:0.24183 validation_1-rmse:0.22943 +[14] validation_0-rmse:0.23870 validation_1-rmse:0.22619 +[15] validation_0-rmse:0.23587 validation_1-rmse:0.22274 +[16] validation_0-rmse:0.23325 validation_1-rmse:0.21951 +[17] validation_0-rmse:0.23045 validation_1-rmse:0.21650 +[18] validation_0-rmse:0.22792 validation_1-rmse:0.21367 +[19] validation_0-rmse:0.22524 validation_1-rmse:0.21092 +[20] validation_0-rmse:0.22293 validation_1-rmse:0.20804 +[21] validation_0-rmse:0.22055 validation_1-rmse:0.20549 +[22] validation_0-rmse:0.21831 validation_1-rmse:0.20307 +[23] validation_0-rmse:0.21601 validation_1-rmse:0.20062 +[24] validation_0-rmse:0.21372 validation_1-rmse:0.19810 +[25] validation_0-rmse:0.21154 validation_1-rmse:0.19580 +[26] validation_0-rmse:0.20966 validation_1-rmse:0.19369 +[27] validation_0-rmse:0.20790 validation_1-rmse:0.19130 +[28] validation_0-rmse:0.20602 validation_1-rmse:0.18921 +[29] validation_0-rmse:0.20418 validation_1-rmse:0.18723 +[30] validation_0-rmse:0.20236 validation_1-rmse:0.18525 +[31] validation_0-rmse:0.20057 validation_1-rmse:0.18324 +[32] validation_0-rmse:0.19900 validation_1-rmse:0.18144 +[33] validation_0-rmse:0.19744 validation_1-rmse:0.17941 +[34] validation_0-rmse:0.19608 validation_1-rmse:0.17767 +[35] validation_0-rmse:0.19467 validation_1-rmse:0.17605 +[36] validation_0-rmse:0.19313 validation_1-rmse:0.17422 +[37] validation_0-rmse:0.19156 validation_1-rmse:0.17260 +[38] validation_0-rmse:0.19020 validation_1-rmse:0.17103 +[39] validation_0-rmse:0.18884 validation_1-rmse:0.16948 +[40] validation_0-rmse:0.18767 validation_1-rmse:0.16797 +[41] validation_0-rmse:0.18636 validation_1-rmse:0.16647 +[42] validation_0-rmse:0.18512 validation_1-rmse:0.16505 +[43] validation_0-rmse:0.18403 validation_1-rmse:0.16340 +[44] validation_0-rmse:0.18290 validation_1-rmse:0.16210 +[45] validation_0-rmse:0.18189 validation_1-rmse:0.16085 +[46] validation_0-rmse:0.18090 validation_1-rmse:0.15966 +[47] validation_0-rmse:0.17992 validation_1-rmse:0.15841 +[48] validation_0-rmse:0.17901 validation_1-rmse:0.15728 +[49] validation_0-rmse:0.17817 validation_1-rmse:0.15582 +[50] validation_0-rmse:0.17697 validation_1-rmse:0.15458 +[51] validation_0-rmse:0.17607 validation_1-rmse:0.15349 +[52] validation_0-rmse:0.17516 validation_1-rmse:0.15235 +[53] validation_0-rmse:0.17425 validation_1-rmse:0.15131 +[54] validation_0-rmse:0.17347 validation_1-rmse:0.15032 +[55] validation_0-rmse:0.17275 validation_1-rmse:0.14932 +[56] validation_0-rmse:0.17211 validation_1-rmse:0.14834 +[57] validation_0-rmse:0.17131 validation_1-rmse:0.14741 +[58] validation_0-rmse:0.17072 validation_1-rmse:0.14617 +[59] validation_0-rmse:0.16999 validation_1-rmse:0.14528 +[60] validation_0-rmse:0.16934 validation_1-rmse:0.14416 +[61] validation_0-rmse:0.16887 validation_1-rmse:0.14321 +[62] validation_0-rmse:0.16842 validation_1-rmse:0.14213 +[63] validation_0-rmse:0.16765 validation_1-rmse:0.14130 +[64] validation_0-rmse:0.16691 validation_1-rmse:0.14048 +[65] validation_0-rmse:0.16629 validation_1-rmse:0.13956 +[66] validation_0-rmse:0.16565 validation_1-rmse:0.13882 +[67] validation_0-rmse:0.16530 validation_1-rmse:0.13793 +[68] validation_0-rmse:0.16467 validation_1-rmse:0.13710 +[69] validation_0-rmse:0.16436 validation_1-rmse:0.13621 +[70] validation_0-rmse:0.16377 validation_1-rmse:0.13542 +[71] validation_0-rmse:0.16334 validation_1-rmse:0.13463 +[72] validation_0-rmse:0.16280 validation_1-rmse:0.13394 +[73] validation_0-rmse:0.16230 validation_1-rmse:0.13328 +[74] validation_0-rmse:0.16156 validation_1-rmse:0.13246 +[75] validation_0-rmse:0.16122 validation_1-rmse:0.13151 +[76] validation_0-rmse:0.16080 validation_1-rmse:0.13080 +[77] validation_0-rmse:0.16033 validation_1-rmse:0.13015 +[78] validation_0-rmse:0.15992 validation_1-rmse:0.12951 +[79] validation_0-rmse:0.15950 validation_1-rmse:0.12888 +[80] validation_0-rmse:0.15909 validation_1-rmse:0.12822 +[81] validation_0-rmse:0.15875 validation_1-rmse:0.12744 +[82] validation_0-rmse:0.15831 validation_1-rmse:0.12683 +[83] validation_0-rmse:0.15786 validation_1-rmse:0.12626 +[84] validation_0-rmse:0.15747 validation_1-rmse:0.12572 +[85] validation_0-rmse:0.15724 validation_1-rmse:0.12495 +[86] validation_0-rmse:0.15695 validation_1-rmse:0.12442 +[87] validation_0-rmse:0.15664 validation_1-rmse:0.12382 +[88] validation_0-rmse:0.15651 validation_1-rmse:0.12326 +[89] validation_0-rmse:0.15629 validation_1-rmse:0.12256 +[90] validation_0-rmse:0.15596 validation_1-rmse:0.12196 +[91] validation_0-rmse:0.15559 validation_1-rmse:0.12141 +[92] validation_0-rmse:0.15511 validation_1-rmse:0.12088 +[93] validation_0-rmse:0.15487 validation_1-rmse:0.12033 +[94] validation_0-rmse:0.15472 validation_1-rmse:0.11975 +[95] validation_0-rmse:0.15438 validation_1-rmse:0.11924 +[96] validation_0-rmse:0.15408 validation_1-rmse:0.11882 +[97] validation_0-rmse:0.15382 validation_1-rmse:0.11819 +[98] validation_0-rmse:0.15350 validation_1-rmse:0.11777 +[99] validation_0-rmse:0.15331 validation_1-rmse:0.11727 +2025-04-29 01:56:40,600 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.45 secs) -------------------- +2025-04-29 01:56:40,601 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:41,171 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-11 00:00:00 to 2025-02-10 00:00:00, 5/11 trains +2025-04-29 01:56:41,172 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1739145600_prediction.feather +2025-04-29 01:56:41,177 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:41,183 - FreqaiExampleStrategy - INFO - 目标列形状：(33650,) +2025-04-29 01:56:41,185 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.830756 +1 0.003044 49.830756 +2 0.000465 49.830756 +3 -0.000380 49.830756 +4 0.002829 49.830756 +2025-04-29 01:56:41,193 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:41,200 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:56:41,201 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.714422 +1 0.003044 49.714422 +2 0.000465 49.714422 +3 -0.000380 49.714422 +4 0.002829 49.714422 +2025-04-29 01:56:41,206 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1739145600/cb_sol_1739145600 +2025-04-29 01:56:41,207 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:41,228 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:41,229 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-11 to 2025-02-09 -------------------- +2025-04-29 01:56:46,277 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:46,278 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.29889 validation_1-rmse:0.30153 +[1] validation_0-rmse:0.29317 validation_1-rmse:0.29483 +[2] validation_0-rmse:0.28819 validation_1-rmse:0.28860 +[3] validation_0-rmse:0.28336 validation_1-rmse:0.28273 +[4] validation_0-rmse:0.27885 validation_1-rmse:0.27694 +[5] validation_0-rmse:0.27448 validation_1-rmse:0.27155 +[6] validation_0-rmse:0.27020 validation_1-rmse:0.26634 +[7] validation_0-rmse:0.26629 validation_1-rmse:0.26134 +[8] validation_0-rmse:0.26241 validation_1-rmse:0.25653 +[9] validation_0-rmse:0.25876 validation_1-rmse:0.25192 +[10] validation_0-rmse:0.25559 validation_1-rmse:0.24747 +[11] validation_0-rmse:0.25223 validation_1-rmse:0.24337 +[12] validation_0-rmse:0.24904 validation_1-rmse:0.23934 +[13] validation_0-rmse:0.24639 validation_1-rmse:0.23548 +[14] validation_0-rmse:0.24353 validation_1-rmse:0.23187 +[15] validation_0-rmse:0.24076 validation_1-rmse:0.22837 +[16] validation_0-rmse:0.23849 validation_1-rmse:0.22484 +[17] validation_0-rmse:0.23581 validation_1-rmse:0.22147 +[18] validation_0-rmse:0.23342 validation_1-rmse:0.21814 +[19] validation_0-rmse:0.23133 validation_1-rmse:0.21509 +[20] validation_0-rmse:0.22937 validation_1-rmse:0.21187 +[21] validation_0-rmse:0.22713 validation_1-rmse:0.20902 +[22] validation_0-rmse:0.22509 validation_1-rmse:0.20631 +[23] validation_0-rmse:0.22312 validation_1-rmse:0.20373 +[24] validation_0-rmse:0.22123 validation_1-rmse:0.20076 +[25] validation_0-rmse:0.21951 validation_1-rmse:0.19837 +[26] validation_0-rmse:0.21751 validation_1-rmse:0.19562 +[27] validation_0-rmse:0.21589 validation_1-rmse:0.19309 +[28] validation_0-rmse:0.21422 validation_1-rmse:0.19091 +[29] validation_0-rmse:0.21272 validation_1-rmse:0.18879 +[30] validation_0-rmse:0.21119 validation_1-rmse:0.18660 +[31] validation_0-rmse:0.20982 validation_1-rmse:0.18468 +[32] validation_0-rmse:0.20829 validation_1-rmse:0.18239 +[33] validation_0-rmse:0.20681 validation_1-rmse:0.18048 +[34] validation_0-rmse:0.20548 validation_1-rmse:0.17869 +[35] validation_0-rmse:0.20431 validation_1-rmse:0.17665 +[36] validation_0-rmse:0.20297 validation_1-rmse:0.17483 +[37] validation_0-rmse:0.20174 validation_1-rmse:0.17311 +[38] validation_0-rmse:0.20060 validation_1-rmse:0.17153 +[39] validation_0-rmse:0.19951 validation_1-rmse:0.16958 +[40] validation_0-rmse:0.19848 validation_1-rmse:0.16805 +[41] validation_0-rmse:0.19745 validation_1-rmse:0.16652 +[42] validation_0-rmse:0.19647 validation_1-rmse:0.16509 +[43] validation_0-rmse:0.19570 validation_1-rmse:0.16325 +[44] validation_0-rmse:0.19473 validation_1-rmse:0.16187 +[45] validation_0-rmse:0.19397 validation_1-rmse:0.16012 +[46] validation_0-rmse:0.19314 validation_1-rmse:0.15887 +[47] validation_0-rmse:0.19196 validation_1-rmse:0.15723 +[48] validation_0-rmse:0.19096 validation_1-rmse:0.15595 +[49] validation_0-rmse:0.19009 validation_1-rmse:0.15468 +[50] validation_0-rmse:0.18931 validation_1-rmse:0.15355 +[51] validation_0-rmse:0.18864 validation_1-rmse:0.15207 +[52] validation_0-rmse:0.18786 validation_1-rmse:0.15101 +[53] validation_0-rmse:0.18690 validation_1-rmse:0.14960 +[54] validation_0-rmse:0.18614 validation_1-rmse:0.14859 +[55] validation_0-rmse:0.18550 validation_1-rmse:0.14756 +[56] validation_0-rmse:0.18475 validation_1-rmse:0.14647 +[57] validation_0-rmse:0.18405 validation_1-rmse:0.14545 +[58] validation_0-rmse:0.18346 validation_1-rmse:0.14415 +[59] validation_0-rmse:0.18277 validation_1-rmse:0.14321 +[60] validation_0-rmse:0.18219 validation_1-rmse:0.14221 +[61] validation_0-rmse:0.18158 validation_1-rmse:0.14129 +[62] validation_0-rmse:0.18100 validation_1-rmse:0.14043 +[63] validation_0-rmse:0.18059 validation_1-rmse:0.13920 +[64] validation_0-rmse:0.17997 validation_1-rmse:0.13842 +[65] validation_0-rmse:0.17941 validation_1-rmse:0.13754 +[66] validation_0-rmse:0.17881 validation_1-rmse:0.13652 +[67] validation_0-rmse:0.17823 validation_1-rmse:0.13576 +[68] validation_0-rmse:0.17784 validation_1-rmse:0.13468 +[69] validation_0-rmse:0.17735 validation_1-rmse:0.13396 +[70] validation_0-rmse:0.17687 validation_1-rmse:0.13311 +[71] validation_0-rmse:0.17628 validation_1-rmse:0.13225 +[72] validation_0-rmse:0.17599 validation_1-rmse:0.13154 +[73] validation_0-rmse:0.17542 validation_1-rmse:0.13080 +[74] validation_0-rmse:0.17497 validation_1-rmse:0.13013 +[75] validation_0-rmse:0.17456 validation_1-rmse:0.12954 +[76] validation_0-rmse:0.17416 validation_1-rmse:0.12864 +[77] validation_0-rmse:0.17369 validation_1-rmse:0.12802 +[78] validation_0-rmse:0.17345 validation_1-rmse:0.12735 +[79] validation_0-rmse:0.17302 validation_1-rmse:0.12672 +[80] validation_0-rmse:0.17254 validation_1-rmse:0.12609 +[81] validation_0-rmse:0.17248 validation_1-rmse:0.12527 +[82] validation_0-rmse:0.17210 validation_1-rmse:0.12470 +[83] validation_0-rmse:0.17196 validation_1-rmse:0.12398 +[84] validation_0-rmse:0.17189 validation_1-rmse:0.12334 +[85] validation_0-rmse:0.17155 validation_1-rmse:0.12280 +[86] validation_0-rmse:0.17124 validation_1-rmse:0.12230 +[87] validation_0-rmse:0.17103 validation_1-rmse:0.12178 +[88] validation_0-rmse:0.17086 validation_1-rmse:0.12118 +[89] validation_0-rmse:0.17064 validation_1-rmse:0.12049 +[90] validation_0-rmse:0.17029 validation_1-rmse:0.11993 +[91] validation_0-rmse:0.16981 validation_1-rmse:0.11942 +[92] validation_0-rmse:0.16950 validation_1-rmse:0.11894 +[93] validation_0-rmse:0.16937 validation_1-rmse:0.11833 +[94] validation_0-rmse:0.16928 validation_1-rmse:0.11786 +[95] validation_0-rmse:0.16899 validation_1-rmse:0.11735 +[96] validation_0-rmse:0.16869 validation_1-rmse:0.11693 +[97] validation_0-rmse:0.16843 validation_1-rmse:0.11650 +[98] validation_0-rmse:0.16829 validation_1-rmse:0.11591 +[99] validation_0-rmse:0.16802 validation_1-rmse:0.11547 +2025-04-29 01:56:47,778 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.57 secs) -------------------- +2025-04-29 01:56:47,779 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:48,320 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-21 00:00:00 to 2025-02-20 00:00:00, 6/11 trains +2025-04-29 01:56:48,321 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1740009600_prediction.feather +2025-04-29 01:56:48,327 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:48,333 - FreqaiExampleStrategy - INFO - 目标列形状：(38450,) +2025-04-29 01:56:48,334 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.714422 +1 0.003044 49.714422 +2 0.000465 49.714422 +3 -0.000380 49.714422 +4 0.002829 49.714422 +2025-04-29 01:56:48,346 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:48,353 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:56:48,354 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.626186 +1 0.003044 49.626186 +2 0.000465 49.626186 +3 -0.000380 49.626186 +4 0.002829 49.626186 +2025-04-29 01:56:48,361 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1740009600/cb_sol_1740009600 +2025-04-29 01:56:48,361 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:48,383 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:48,383 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-21 to 2025-02-19 -------------------- +2025-04-29 01:56:53,532 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:56:53,533 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.29357 validation_1-rmse:0.28852 +[1] validation_0-rmse:0.28850 validation_1-rmse:0.28219 +[2] validation_0-rmse:0.28292 validation_1-rmse:0.27618 +[3] validation_0-rmse:0.27862 validation_1-rmse:0.27046 +[4] validation_0-rmse:0.27383 validation_1-rmse:0.26510 +[5] validation_0-rmse:0.27018 validation_1-rmse:0.25989 +[6] validation_0-rmse:0.26615 validation_1-rmse:0.25477 +[7] validation_0-rmse:0.26234 validation_1-rmse:0.25007 +[8] validation_0-rmse:0.25794 validation_1-rmse:0.24560 +[9] validation_0-rmse:0.25417 validation_1-rmse:0.24109 +[10] validation_0-rmse:0.25083 validation_1-rmse:0.23700 +[11] validation_0-rmse:0.24683 validation_1-rmse:0.23303 +[12] validation_0-rmse:0.24384 validation_1-rmse:0.22908 +[13] validation_0-rmse:0.24093 validation_1-rmse:0.22542 +[14] validation_0-rmse:0.23743 validation_1-rmse:0.22186 +[15] validation_0-rmse:0.23484 validation_1-rmse:0.21841 +[16] validation_0-rmse:0.23215 validation_1-rmse:0.21525 +[17] validation_0-rmse:0.22951 validation_1-rmse:0.21206 +[18] validation_0-rmse:0.22658 validation_1-rmse:0.20906 +[19] validation_0-rmse:0.22440 validation_1-rmse:0.20615 +[20] validation_0-rmse:0.22193 validation_1-rmse:0.20314 +[21] validation_0-rmse:0.22009 validation_1-rmse:0.20016 +[22] validation_0-rmse:0.21755 validation_1-rmse:0.19751 +[23] validation_0-rmse:0.21578 validation_1-rmse:0.19498 +[24] validation_0-rmse:0.21440 validation_1-rmse:0.19241 +[25] validation_0-rmse:0.21229 validation_1-rmse:0.19006 +[26] validation_0-rmse:0.21038 validation_1-rmse:0.18780 +[27] validation_0-rmse:0.20897 validation_1-rmse:0.18529 +[28] validation_0-rmse:0.20703 validation_1-rmse:0.18313 +[29] validation_0-rmse:0.20556 validation_1-rmse:0.18091 +[30] validation_0-rmse:0.20384 validation_1-rmse:0.17884 +[31] validation_0-rmse:0.20281 validation_1-rmse:0.17690 +[32] validation_0-rmse:0.20169 validation_1-rmse:0.17483 +[33] validation_0-rmse:0.20012 validation_1-rmse:0.17300 +[34] validation_0-rmse:0.19876 validation_1-rmse:0.17106 +[35] validation_0-rmse:0.19755 validation_1-rmse:0.16934 +[36] validation_0-rmse:0.19649 validation_1-rmse:0.16752 +[37] validation_0-rmse:0.19501 validation_1-rmse:0.16586 +[38] validation_0-rmse:0.19423 validation_1-rmse:0.16418 +[39] validation_0-rmse:0.19297 validation_1-rmse:0.16264 +[40] validation_0-rmse:0.19162 validation_1-rmse:0.16092 +[41] validation_0-rmse:0.19049 validation_1-rmse:0.15952 +[42] validation_0-rmse:0.18925 validation_1-rmse:0.15810 +[43] validation_0-rmse:0.18845 validation_1-rmse:0.15638 +[44] validation_0-rmse:0.18730 validation_1-rmse:0.15506 +[45] validation_0-rmse:0.18661 validation_1-rmse:0.15357 +[46] validation_0-rmse:0.18563 validation_1-rmse:0.15226 +[47] validation_0-rmse:0.18473 validation_1-rmse:0.15101 +[48] validation_0-rmse:0.18399 validation_1-rmse:0.14957 +[49] validation_0-rmse:0.18304 validation_1-rmse:0.14841 +[50] validation_0-rmse:0.18219 validation_1-rmse:0.14717 +[51] validation_0-rmse:0.18131 validation_1-rmse:0.14599 +[52] validation_0-rmse:0.18043 validation_1-rmse:0.14492 +[53] validation_0-rmse:0.17966 validation_1-rmse:0.14388 +[54] validation_0-rmse:0.17901 validation_1-rmse:0.14274 +[55] validation_0-rmse:0.17850 validation_1-rmse:0.14134 +[56] validation_0-rmse:0.17764 validation_1-rmse:0.14035 +[57] validation_0-rmse:0.17682 validation_1-rmse:0.13937 +[58] validation_0-rmse:0.17604 validation_1-rmse:0.13844 +[59] validation_0-rmse:0.17526 validation_1-rmse:0.13754 +[60] validation_0-rmse:0.17488 validation_1-rmse:0.13621 +[61] validation_0-rmse:0.17432 validation_1-rmse:0.13530 +[62] validation_0-rmse:0.17345 validation_1-rmse:0.13439 +[63] validation_0-rmse:0.17284 validation_1-rmse:0.13358 +[64] validation_0-rmse:0.17213 validation_1-rmse:0.13278 +[65] validation_0-rmse:0.17164 validation_1-rmse:0.13175 +[66] validation_0-rmse:0.17098 validation_1-rmse:0.13088 +[67] validation_0-rmse:0.17049 validation_1-rmse:0.13002 +[68] validation_0-rmse:0.17000 validation_1-rmse:0.12918 +[69] validation_0-rmse:0.16969 validation_1-rmse:0.12815 +[70] validation_0-rmse:0.16917 validation_1-rmse:0.12746 +[71] validation_0-rmse:0.16857 validation_1-rmse:0.12678 +[72] validation_0-rmse:0.16830 validation_1-rmse:0.12595 +[73] validation_0-rmse:0.16793 validation_1-rmse:0.12522 +[74] validation_0-rmse:0.16752 validation_1-rmse:0.12457 +[75] validation_0-rmse:0.16704 validation_1-rmse:0.12395 +[76] validation_0-rmse:0.16668 validation_1-rmse:0.12316 +[77] validation_0-rmse:0.16621 validation_1-rmse:0.12251 +[78] validation_0-rmse:0.16591 validation_1-rmse:0.12185 +[79] validation_0-rmse:0.16550 validation_1-rmse:0.12115 +[80] validation_0-rmse:0.16506 validation_1-rmse:0.12055 +[81] validation_0-rmse:0.16467 validation_1-rmse:0.12001 +[82] validation_0-rmse:0.16422 validation_1-rmse:0.11944 +[83] validation_0-rmse:0.16379 validation_1-rmse:0.11892 +[84] validation_0-rmse:0.16344 validation_1-rmse:0.11825 +[85] validation_0-rmse:0.16317 validation_1-rmse:0.11766 +[86] validation_0-rmse:0.16289 validation_1-rmse:0.11712 +[87] validation_0-rmse:0.16271 validation_1-rmse:0.11639 +[88] validation_0-rmse:0.16236 validation_1-rmse:0.11591 +[89] validation_0-rmse:0.16210 validation_1-rmse:0.11515 +[90] validation_0-rmse:0.16170 validation_1-rmse:0.11457 +[91] validation_0-rmse:0.16149 validation_1-rmse:0.11411 +[92] validation_0-rmse:0.16132 validation_1-rmse:0.11360 +[93] validation_0-rmse:0.16108 validation_1-rmse:0.11292 +[94] validation_0-rmse:0.16077 validation_1-rmse:0.11247 +[95] validation_0-rmse:0.16040 validation_1-rmse:0.11205 +[96] validation_0-rmse:0.16017 validation_1-rmse:0.11157 +[97] validation_0-rmse:0.15988 validation_1-rmse:0.11117 +[98] validation_0-rmse:0.15964 validation_1-rmse:0.11074 +[99] validation_0-rmse:0.15958 validation_1-rmse:0.11029 +2025-04-29 01:56:54,862 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.50 secs) -------------------- +2025-04-29 01:56:54,863 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:56:55,419 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-01-31 00:00:00 to 2025-03-02 00:00:00, 7/11 trains +2025-04-29 01:56:55,420 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1740873600_prediction.feather +2025-04-29 01:56:55,426 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:55,433 - FreqaiExampleStrategy - INFO - 目标列形状：(43250,) +2025-04-29 01:56:55,435 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.626186 +1 0.003044 49.626186 +2 0.000465 49.626186 +3 -0.000380 49.626186 +4 0.002829 49.626186 +2025-04-29 01:56:55,445 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:56:55,452 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:56:55,453 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.568812 +1 0.003044 49.568812 +2 0.000465 49.568812 +3 -0.000380 49.568812 +4 0.002829 49.568812 +2025-04-29 01:56:55,459 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1740873600/cb_sol_1740873600 +2025-04-29 01:56:55,459 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:56:55,481 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:56:55,482 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-01-31 to 2025-03-01 -------------------- +2025-04-29 01:57:00,566 - datasieve.pipeline - INFO - DI tossed 2417 predictions for being too far from training data. +2025-04-29 01:57:00,569 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:00,570 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.33058 validation_1-rmse:0.29214 +[1] validation_0-rmse:0.32414 validation_1-rmse:0.28558 +[2] validation_0-rmse:0.31832 validation_1-rmse:0.27962 +[3] validation_0-rmse:0.31280 validation_1-rmse:0.27380 +[4] validation_0-rmse:0.30679 validation_1-rmse:0.26829 +[5] validation_0-rmse:0.30182 validation_1-rmse:0.26306 +[6] validation_0-rmse:0.29686 validation_1-rmse:0.25797 +[7] validation_0-rmse:0.29291 validation_1-rmse:0.25323 +[8] validation_0-rmse:0.28868 validation_1-rmse:0.24871 +[9] validation_0-rmse:0.28559 validation_1-rmse:0.24437 +[10] validation_0-rmse:0.28262 validation_1-rmse:0.24018 +[11] validation_0-rmse:0.27890 validation_1-rmse:0.23606 +[12] validation_0-rmse:0.27663 validation_1-rmse:0.23225 +[13] validation_0-rmse:0.27306 validation_1-rmse:0.22870 +[14] validation_0-rmse:0.26948 validation_1-rmse:0.22493 +[15] validation_0-rmse:0.26663 validation_1-rmse:0.22157 +[16] validation_0-rmse:0.26427 validation_1-rmse:0.21817 +[17] validation_0-rmse:0.26195 validation_1-rmse:0.21492 +[18] validation_0-rmse:0.25856 validation_1-rmse:0.21177 +[19] validation_0-rmse:0.25606 validation_1-rmse:0.20861 +[20] validation_0-rmse:0.25343 validation_1-rmse:0.20580 +[21] validation_0-rmse:0.25243 validation_1-rmse:0.20301 +[22] validation_0-rmse:0.25066 validation_1-rmse:0.20027 +[23] validation_0-rmse:0.24864 validation_1-rmse:0.19761 +[24] validation_0-rmse:0.24630 validation_1-rmse:0.19522 +[25] validation_0-rmse:0.24491 validation_1-rmse:0.19283 +[26] validation_0-rmse:0.24339 validation_1-rmse:0.19036 +[27] validation_0-rmse:0.24108 validation_1-rmse:0.18818 +[28] validation_0-rmse:0.23976 validation_1-rmse:0.18592 +[29] validation_0-rmse:0.23882 validation_1-rmse:0.18348 +[30] validation_0-rmse:0.23676 validation_1-rmse:0.18142 +[31] validation_0-rmse:0.23520 validation_1-rmse:0.17945 +[32] validation_0-rmse:0.23395 validation_1-rmse:0.17754 +[33] validation_0-rmse:0.23229 validation_1-rmse:0.17545 +[34] validation_0-rmse:0.23073 validation_1-rmse:0.17360 +[35] validation_0-rmse:0.22951 validation_1-rmse:0.17182 +[36] validation_0-rmse:0.22806 validation_1-rmse:0.16995 +[37] validation_0-rmse:0.22713 validation_1-rmse:0.16834 +[38] validation_0-rmse:0.22541 validation_1-rmse:0.16668 +[39] validation_0-rmse:0.22393 validation_1-rmse:0.16509 +[40] validation_0-rmse:0.22282 validation_1-rmse:0.16343 +[41] validation_0-rmse:0.22168 validation_1-rmse:0.16185 +[42] validation_0-rmse:0.22085 validation_1-rmse:0.16046 +[43] validation_0-rmse:0.21991 validation_1-rmse:0.15907 +[44] validation_0-rmse:0.21833 validation_1-rmse:0.15756 +[45] validation_0-rmse:0.21710 validation_1-rmse:0.15618 +[46] validation_0-rmse:0.21619 validation_1-rmse:0.15490 +[47] validation_0-rmse:0.21518 validation_1-rmse:0.15345 +[48] validation_0-rmse:0.21402 validation_1-rmse:0.15221 +[49] validation_0-rmse:0.21305 validation_1-rmse:0.15086 +[50] validation_0-rmse:0.21229 validation_1-rmse:0.14968 +[51] validation_0-rmse:0.21119 validation_1-rmse:0.14854 +[52] validation_0-rmse:0.21019 validation_1-rmse:0.14745 +[53] validation_0-rmse:0.20924 validation_1-rmse:0.14637 +[54] validation_0-rmse:0.20982 validation_1-rmse:0.14517 +[55] validation_0-rmse:0.20888 validation_1-rmse:0.14405 +[56] validation_0-rmse:0.20806 validation_1-rmse:0.14305 +[57] validation_0-rmse:0.20822 validation_1-rmse:0.14169 +[58] validation_0-rmse:0.20741 validation_1-rmse:0.14071 +[59] validation_0-rmse:0.20663 validation_1-rmse:0.13976 +[60] validation_0-rmse:0.20602 validation_1-rmse:0.13882 +[61] validation_0-rmse:0.20523 validation_1-rmse:0.13776 +[62] validation_0-rmse:0.20558 validation_1-rmse:0.13689 +[63] validation_0-rmse:0.20501 validation_1-rmse:0.13605 +[64] validation_0-rmse:0.20348 validation_1-rmse:0.13462 +[65] validation_0-rmse:0.20273 validation_1-rmse:0.13382 +[66] validation_0-rmse:0.20203 validation_1-rmse:0.13306 +[67] validation_0-rmse:0.20166 validation_1-rmse:0.13228 +[68] validation_0-rmse:0.20002 validation_1-rmse:0.13102 +[69] validation_0-rmse:0.19928 validation_1-rmse:0.13021 +[70] validation_0-rmse:0.19870 validation_1-rmse:0.12946 +[71] validation_0-rmse:0.19830 validation_1-rmse:0.12876 +[72] validation_0-rmse:0.19814 validation_1-rmse:0.12801 +[73] validation_0-rmse:0.19798 validation_1-rmse:0.12711 +[74] validation_0-rmse:0.19746 validation_1-rmse:0.12649 +[75] validation_0-rmse:0.19701 validation_1-rmse:0.12588 +[76] validation_0-rmse:0.19555 validation_1-rmse:0.12467 +[77] validation_0-rmse:0.19514 validation_1-rmse:0.12407 +[78] validation_0-rmse:0.19468 validation_1-rmse:0.12347 +[79] validation_0-rmse:0.19439 validation_1-rmse:0.12277 +[80] validation_0-rmse:0.19473 validation_1-rmse:0.12220 +[81] validation_0-rmse:0.19448 validation_1-rmse:0.12154 +[82] validation_0-rmse:0.19418 validation_1-rmse:0.12086 +[83] validation_0-rmse:0.19370 validation_1-rmse:0.12030 +[84] validation_0-rmse:0.19346 validation_1-rmse:0.11976 +[85] validation_0-rmse:0.19322 validation_1-rmse:0.11879 +[86] validation_0-rmse:0.19282 validation_1-rmse:0.11819 +[87] validation_0-rmse:0.19226 validation_1-rmse:0.11770 +[88] validation_0-rmse:0.19187 validation_1-rmse:0.11719 +[89] validation_0-rmse:0.19145 validation_1-rmse:0.11671 +[90] validation_0-rmse:0.19134 validation_1-rmse:0.11619 +[91] validation_0-rmse:0.19030 validation_1-rmse:0.11531 +[92] validation_0-rmse:0.18998 validation_1-rmse:0.11487 +[93] validation_0-rmse:0.18945 validation_1-rmse:0.11445 +[94] validation_0-rmse:0.18919 validation_1-rmse:0.11395 +[95] validation_0-rmse:0.18862 validation_1-rmse:0.11324 +[96] validation_0-rmse:0.18824 validation_1-rmse:0.11283 +[97] validation_0-rmse:0.18778 validation_1-rmse:0.11225 +[98] validation_0-rmse:0.18755 validation_1-rmse:0.11186 +[99] validation_0-rmse:0.18742 validation_1-rmse:0.11149 +2025-04-29 01:57:02,441 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.98 secs) -------------------- +2025-04-29 01:57:02,442 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:02,968 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-02-10 00:00:00 to 2025-03-12 00:00:00, 8/11 trains +2025-04-29 01:57:02,968 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1741737600_prediction.feather +2025-04-29 01:57:02,980 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:02,987 - FreqaiExampleStrategy - INFO - 目标列形状：(48050,) +2025-04-29 01:57:02,989 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.568812 +1 0.003044 49.568812 +2 0.000465 49.568812 +3 -0.000380 49.568812 +4 0.002829 49.568812 +2025-04-29 01:57:03,001 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:03,007 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:57:03,009 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.623338 +1 0.003044 49.623338 +2 0.000465 49.623338 +3 -0.000380 49.623338 +4 0.002829 49.623338 +2025-04-29 01:57:03,014 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1741737600/cb_sol_1741737600 +2025-04-29 01:57:03,015 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:03,042 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:03,042 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-10 to 2025-03-11 -------------------- +2025-04-29 01:57:08,138 - datasieve.pipeline - INFO - DI tossed 3 predictions for being too far from training data. +2025-04-29 01:57:08,141 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:08,141 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.25025 validation_1-rmse:0.24842 +[1] validation_0-rmse:0.24557 validation_1-rmse:0.24302 +[2] validation_0-rmse:0.24132 validation_1-rmse:0.23806 +[3] validation_0-rmse:0.23733 validation_1-rmse:0.23332 +[4] validation_0-rmse:0.23376 validation_1-rmse:0.22859 +[5] validation_0-rmse:0.23049 validation_1-rmse:0.22444 +[6] validation_0-rmse:0.22702 validation_1-rmse:0.22025 +[7] validation_0-rmse:0.22380 validation_1-rmse:0.21631 +[8] validation_0-rmse:0.22066 validation_1-rmse:0.21250 +[9] validation_0-rmse:0.21772 validation_1-rmse:0.20892 +[10] validation_0-rmse:0.21473 validation_1-rmse:0.20536 +[11] validation_0-rmse:0.21219 validation_1-rmse:0.20211 +[12] validation_0-rmse:0.20968 validation_1-rmse:0.19897 +[13] validation_0-rmse:0.20730 validation_1-rmse:0.19597 +[14] validation_0-rmse:0.20552 validation_1-rmse:0.19281 +[15] validation_0-rmse:0.20361 validation_1-rmse:0.18992 +[16] validation_0-rmse:0.20165 validation_1-rmse:0.18721 +[17] validation_0-rmse:0.19948 validation_1-rmse:0.18463 +[18] validation_0-rmse:0.19807 validation_1-rmse:0.18193 +[19] validation_0-rmse:0.19703 validation_1-rmse:0.17939 +[20] validation_0-rmse:0.19569 validation_1-rmse:0.17683 +[21] validation_0-rmse:0.19388 validation_1-rmse:0.17462 +[22] validation_0-rmse:0.19219 validation_1-rmse:0.17240 +[23] validation_0-rmse:0.19062 validation_1-rmse:0.17026 +[24] validation_0-rmse:0.18933 validation_1-rmse:0.16813 +[25] validation_0-rmse:0.18829 validation_1-rmse:0.16598 +[26] validation_0-rmse:0.18704 validation_1-rmse:0.16411 +[27] validation_0-rmse:0.18563 validation_1-rmse:0.16221 +[28] validation_0-rmse:0.18446 validation_1-rmse:0.16034 +[29] validation_0-rmse:0.18316 validation_1-rmse:0.15841 +[30] validation_0-rmse:0.18192 validation_1-rmse:0.15674 +[31] validation_0-rmse:0.18091 validation_1-rmse:0.15479 +[32] validation_0-rmse:0.18003 validation_1-rmse:0.15312 +[33] validation_0-rmse:0.17886 validation_1-rmse:0.15150 +[34] validation_0-rmse:0.17786 validation_1-rmse:0.14997 +[35] validation_0-rmse:0.17692 validation_1-rmse:0.14855 +[36] validation_0-rmse:0.17613 validation_1-rmse:0.14709 +[37] validation_0-rmse:0.17547 validation_1-rmse:0.14549 +[38] validation_0-rmse:0.17467 validation_1-rmse:0.14404 +[39] validation_0-rmse:0.17393 validation_1-rmse:0.14267 +[40] validation_0-rmse:0.17348 validation_1-rmse:0.14118 +[41] validation_0-rmse:0.17258 validation_1-rmse:0.13993 +[42] validation_0-rmse:0.17168 validation_1-rmse:0.13871 +[43] validation_0-rmse:0.17077 validation_1-rmse:0.13757 +[44] validation_0-rmse:0.17015 validation_1-rmse:0.13621 +[45] validation_0-rmse:0.16924 validation_1-rmse:0.13509 +[46] validation_0-rmse:0.16833 validation_1-rmse:0.13401 +[47] validation_0-rmse:0.16756 validation_1-rmse:0.13297 +[48] validation_0-rmse:0.16717 validation_1-rmse:0.13198 +[49] validation_0-rmse:0.16664 validation_1-rmse:0.13081 +[50] validation_0-rmse:0.16615 validation_1-rmse:0.12979 +[51] validation_0-rmse:0.16541 validation_1-rmse:0.12879 +[52] validation_0-rmse:0.16478 validation_1-rmse:0.12767 +[53] validation_0-rmse:0.16408 validation_1-rmse:0.12675 +[54] validation_0-rmse:0.16363 validation_1-rmse:0.12571 +[55] validation_0-rmse:0.16320 validation_1-rmse:0.12485 +[56] validation_0-rmse:0.16253 validation_1-rmse:0.12398 +[57] validation_0-rmse:0.16192 validation_1-rmse:0.12307 +[58] validation_0-rmse:0.16149 validation_1-rmse:0.12229 +[59] validation_0-rmse:0.16137 validation_1-rmse:0.12128 +[60] validation_0-rmse:0.16117 validation_1-rmse:0.12045 +[61] validation_0-rmse:0.16064 validation_1-rmse:0.11966 +[62] validation_0-rmse:0.16050 validation_1-rmse:0.11890 +[63] validation_0-rmse:0.16003 validation_1-rmse:0.11809 +[64] validation_0-rmse:0.15969 validation_1-rmse:0.11739 +[65] validation_0-rmse:0.15922 validation_1-rmse:0.11661 +[66] validation_0-rmse:0.15868 validation_1-rmse:0.11577 +[67] validation_0-rmse:0.15830 validation_1-rmse:0.11509 +[68] validation_0-rmse:0.15789 validation_1-rmse:0.11446 +[69] validation_0-rmse:0.15733 validation_1-rmse:0.11372 +[70] validation_0-rmse:0.15694 validation_1-rmse:0.11307 +[71] validation_0-rmse:0.15692 validation_1-rmse:0.11224 +[72] validation_0-rmse:0.15659 validation_1-rmse:0.11166 +[73] validation_0-rmse:0.15634 validation_1-rmse:0.11111 +[74] validation_0-rmse:0.15595 validation_1-rmse:0.11056 +[75] validation_0-rmse:0.15579 validation_1-rmse:0.10985 +[76] validation_0-rmse:0.15543 validation_1-rmse:0.10903 +[77] validation_0-rmse:0.15500 validation_1-rmse:0.10848 +[78] validation_0-rmse:0.15499 validation_1-rmse:0.10778 +[79] validation_0-rmse:0.15471 validation_1-rmse:0.10721 +[80] validation_0-rmse:0.15442 validation_1-rmse:0.10666 +[81] validation_0-rmse:0.15416 validation_1-rmse:0.10608 +[82] validation_0-rmse:0.15388 validation_1-rmse:0.10560 +[83] validation_0-rmse:0.15368 validation_1-rmse:0.10498 +[84] validation_0-rmse:0.15346 validation_1-rmse:0.10449 +[85] validation_0-rmse:0.15329 validation_1-rmse:0.10392 +[86] validation_0-rmse:0.15302 validation_1-rmse:0.10347 +[87] validation_0-rmse:0.15270 validation_1-rmse:0.10303 +[88] validation_0-rmse:0.15259 validation_1-rmse:0.10258 +[89] validation_0-rmse:0.15269 validation_1-rmse:0.10204 +[90] validation_0-rmse:0.15239 validation_1-rmse:0.10159 +[91] validation_0-rmse:0.15204 validation_1-rmse:0.10116 +[92] validation_0-rmse:0.15175 validation_1-rmse:0.10070 +[93] validation_0-rmse:0.15167 validation_1-rmse:0.10017 +[94] validation_0-rmse:0.15154 validation_1-rmse:0.09982 +[95] validation_0-rmse:0.15122 validation_1-rmse:0.09932 +[96] validation_0-rmse:0.15119 validation_1-rmse:0.09880 +[97] validation_0-rmse:0.15112 validation_1-rmse:0.09842 +[98] validation_0-rmse:0.15095 validation_1-rmse:0.09807 +[99] validation_0-rmse:0.15075 validation_1-rmse:0.09770 +2025-04-29 01:57:09,614 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.60 secs) -------------------- +2025-04-29 01:57:09,615 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:10,150 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-02-20 00:00:00 to 2025-03-22 00:00:00, 9/11 trains +2025-04-29 01:57:10,151 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1742601600_prediction.feather +2025-04-29 01:57:10,159 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:10,167 - FreqaiExampleStrategy - INFO - 目标列形状：(52850,) +2025-04-29 01:57:10,168 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.623338 +1 0.003044 49.623338 +2 0.000465 49.623338 +3 -0.000380 49.623338 +4 0.002829 49.623338 +2025-04-29 01:57:10,181 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:10,188 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:57:10,190 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.644115 +1 0.003044 49.644115 +2 0.000465 49.644115 +3 -0.000380 49.644115 +4 0.002829 49.644115 +2025-04-29 01:57:10,195 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1742601600/cb_sol_1742601600 +2025-04-29 01:57:10,196 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:10,218 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:10,218 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-02-20 to 2025-03-21 -------------------- +2025-04-29 01:57:15,185 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:15,186 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.24126 validation_1-rmse:0.24985 +[1] validation_0-rmse:0.23710 validation_1-rmse:0.24457 +[2] validation_0-rmse:0.23323 validation_1-rmse:0.23968 +[3] validation_0-rmse:0.22960 validation_1-rmse:0.23491 +[4] validation_0-rmse:0.22600 validation_1-rmse:0.23038 +[5] validation_0-rmse:0.22255 validation_1-rmse:0.22616 +[6] validation_0-rmse:0.21946 validation_1-rmse:0.22213 +[7] validation_0-rmse:0.21640 validation_1-rmse:0.21827 +[8] validation_0-rmse:0.21381 validation_1-rmse:0.21453 +[9] validation_0-rmse:0.21110 validation_1-rmse:0.21092 +[10] validation_0-rmse:0.20854 validation_1-rmse:0.20742 +[11] validation_0-rmse:0.20586 validation_1-rmse:0.20418 +[12] validation_0-rmse:0.20373 validation_1-rmse:0.20097 +[13] validation_0-rmse:0.20156 validation_1-rmse:0.19779 +[14] validation_0-rmse:0.19934 validation_1-rmse:0.19493 +[15] validation_0-rmse:0.19739 validation_1-rmse:0.19211 +[16] validation_0-rmse:0.19537 validation_1-rmse:0.18929 +[17] validation_0-rmse:0.19333 validation_1-rmse:0.18671 +[18] validation_0-rmse:0.19163 validation_1-rmse:0.18396 +[19] validation_0-rmse:0.18975 validation_1-rmse:0.18157 +[20] validation_0-rmse:0.18799 validation_1-rmse:0.17903 +[21] validation_0-rmse:0.18612 validation_1-rmse:0.17673 +[22] validation_0-rmse:0.18451 validation_1-rmse:0.17454 +[23] validation_0-rmse:0.18299 validation_1-rmse:0.17225 +[24] validation_0-rmse:0.18150 validation_1-rmse:0.17025 +[25] validation_0-rmse:0.18016 validation_1-rmse:0.16803 +[26] validation_0-rmse:0.17866 validation_1-rmse:0.16614 +[27] validation_0-rmse:0.17732 validation_1-rmse:0.16429 +[28] validation_0-rmse:0.17619 validation_1-rmse:0.16247 +[29] validation_0-rmse:0.17494 validation_1-rmse:0.16080 +[30] validation_0-rmse:0.17391 validation_1-rmse:0.15889 +[31] validation_0-rmse:0.17282 validation_1-rmse:0.15724 +[32] validation_0-rmse:0.17156 validation_1-rmse:0.15548 +[33] validation_0-rmse:0.17054 validation_1-rmse:0.15393 +[34] validation_0-rmse:0.16943 validation_1-rmse:0.15244 +[35] validation_0-rmse:0.16841 validation_1-rmse:0.15088 +[36] validation_0-rmse:0.16736 validation_1-rmse:0.14950 +[37] validation_0-rmse:0.16647 validation_1-rmse:0.14797 +[38] validation_0-rmse:0.16544 validation_1-rmse:0.14641 +[39] validation_0-rmse:0.16454 validation_1-rmse:0.14508 +[40] validation_0-rmse:0.16357 validation_1-rmse:0.14380 +[41] validation_0-rmse:0.16266 validation_1-rmse:0.14261 +[42] validation_0-rmse:0.16198 validation_1-rmse:0.14134 +[43] validation_0-rmse:0.16105 validation_1-rmse:0.14019 +[44] validation_0-rmse:0.16046 validation_1-rmse:0.13896 +[45] validation_0-rmse:0.15963 validation_1-rmse:0.13773 +[46] validation_0-rmse:0.15899 validation_1-rmse:0.13662 +[47] validation_0-rmse:0.15822 validation_1-rmse:0.13555 +[48] validation_0-rmse:0.15757 validation_1-rmse:0.13452 +[49] validation_0-rmse:0.15688 validation_1-rmse:0.13322 +[50] validation_0-rmse:0.15627 validation_1-rmse:0.13206 +[51] validation_0-rmse:0.15558 validation_1-rmse:0.13110 +[52] validation_0-rmse:0.15493 validation_1-rmse:0.13017 +[53] validation_0-rmse:0.15429 validation_1-rmse:0.12924 +[54] validation_0-rmse:0.15365 validation_1-rmse:0.12838 +[55] validation_0-rmse:0.15303 validation_1-rmse:0.12741 +[56] validation_0-rmse:0.15258 validation_1-rmse:0.12653 +[57] validation_0-rmse:0.15202 validation_1-rmse:0.12569 +[58] validation_0-rmse:0.15142 validation_1-rmse:0.12478 +[59] validation_0-rmse:0.15106 validation_1-rmse:0.12392 +[60] validation_0-rmse:0.15049 validation_1-rmse:0.12297 +[61] validation_0-rmse:0.14990 validation_1-rmse:0.12223 +[62] validation_0-rmse:0.14932 validation_1-rmse:0.12144 +[63] validation_0-rmse:0.14876 validation_1-rmse:0.12071 +[64] validation_0-rmse:0.14826 validation_1-rmse:0.12000 +[65] validation_0-rmse:0.14788 validation_1-rmse:0.11931 +[66] validation_0-rmse:0.14753 validation_1-rmse:0.11842 +[67] validation_0-rmse:0.14714 validation_1-rmse:0.11776 +[68] validation_0-rmse:0.14665 validation_1-rmse:0.11706 +[69] validation_0-rmse:0.14655 validation_1-rmse:0.11614 +[70] validation_0-rmse:0.14616 validation_1-rmse:0.11556 +[71] validation_0-rmse:0.14579 validation_1-rmse:0.11478 +[72] validation_0-rmse:0.14533 validation_1-rmse:0.11418 +[73] validation_0-rmse:0.14491 validation_1-rmse:0.11358 +[74] validation_0-rmse:0.14448 validation_1-rmse:0.11300 +[75] validation_0-rmse:0.14446 validation_1-rmse:0.11235 +[76] validation_0-rmse:0.14414 validation_1-rmse:0.11173 +[77] validation_0-rmse:0.14371 validation_1-rmse:0.11116 +[78] validation_0-rmse:0.14344 validation_1-rmse:0.11066 +[79] validation_0-rmse:0.14321 validation_1-rmse:0.10996 +[80] validation_0-rmse:0.14280 validation_1-rmse:0.10942 +[81] validation_0-rmse:0.14250 validation_1-rmse:0.10885 +[82] validation_0-rmse:0.14222 validation_1-rmse:0.10837 +[83] validation_0-rmse:0.14184 validation_1-rmse:0.10787 +[84] validation_0-rmse:0.14140 validation_1-rmse:0.10731 +[85] validation_0-rmse:0.14114 validation_1-rmse:0.10683 +[86] validation_0-rmse:0.14100 validation_1-rmse:0.10625 +[87] validation_0-rmse:0.14077 validation_1-rmse:0.10574 +[88] validation_0-rmse:0.14048 validation_1-rmse:0.10534 +[89] validation_0-rmse:0.14010 validation_1-rmse:0.10485 +[90] validation_0-rmse:0.13990 validation_1-rmse:0.10443 +[91] validation_0-rmse:0.13956 validation_1-rmse:0.10400 +[92] validation_0-rmse:0.13949 validation_1-rmse:0.10341 +[93] validation_0-rmse:0.13930 validation_1-rmse:0.10298 +[94] validation_0-rmse:0.13905 validation_1-rmse:0.10254 +[95] validation_0-rmse:0.13884 validation_1-rmse:0.10211 +[96] validation_0-rmse:0.13867 validation_1-rmse:0.10167 +[97] validation_0-rmse:0.13859 validation_1-rmse:0.10114 +[98] validation_0-rmse:0.13839 validation_1-rmse:0.10078 +[99] validation_0-rmse:0.13818 validation_1-rmse:0.10038 +2025-04-29 01:57:16,538 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.34 secs) -------------------- +2025-04-29 01:57:16,539 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:17,068 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-03-02 00:00:00 to 2025-04-01 00:00:00, 10/11 trains +2025-04-29 01:57:17,069 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1743465600_prediction.feather +2025-04-29 01:57:17,084 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:17,092 - FreqaiExampleStrategy - INFO - 目标列形状：(57650,) +2025-04-29 01:57:17,094 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.644115 +1 0.003044 49.644115 +2 0.000465 49.644115 +3 -0.000380 49.644115 +4 0.002829 49.644115 +2025-04-29 01:57:17,108 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:17,115 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:57:17,117 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.601082 +1 0.003044 49.601082 +2 0.000465 49.601082 +3 -0.000380 49.601082 +4 0.002829 49.601082 +2025-04-29 01:57:17,124 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1743465600/cb_sol_1743465600 +2025-04-29 01:57:17,125 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:17,151 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:17,151 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-02 to 2025-03-31 -------------------- +2025-04-29 01:57:22,430 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:22,430 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.23717 validation_1-rmse:0.24954 +[1] validation_0-rmse:0.23311 validation_1-rmse:0.24432 +[2] validation_0-rmse:0.22894 validation_1-rmse:0.23928 +[3] validation_0-rmse:0.22483 validation_1-rmse:0.23452 +[4] validation_0-rmse:0.22141 validation_1-rmse:0.23005 +[5] validation_0-rmse:0.21750 validation_1-rmse:0.22575 +[6] validation_0-rmse:0.21419 validation_1-rmse:0.22161 +[7] validation_0-rmse:0.21074 validation_1-rmse:0.21764 +[8] validation_0-rmse:0.20776 validation_1-rmse:0.21374 +[9] validation_0-rmse:0.20479 validation_1-rmse:0.21020 +[10] validation_0-rmse:0.20193 validation_1-rmse:0.20664 +[11] validation_0-rmse:0.19915 validation_1-rmse:0.20326 +[12] validation_0-rmse:0.19683 validation_1-rmse:0.20013 +[13] validation_0-rmse:0.19459 validation_1-rmse:0.19705 +[14] validation_0-rmse:0.19243 validation_1-rmse:0.19415 +[15] validation_0-rmse:0.19013 validation_1-rmse:0.19115 +[16] validation_0-rmse:0.18828 validation_1-rmse:0.18836 +[17] validation_0-rmse:0.18621 validation_1-rmse:0.18557 +[18] validation_0-rmse:0.18402 validation_1-rmse:0.18302 +[19] validation_0-rmse:0.18198 validation_1-rmse:0.18050 +[20] validation_0-rmse:0.18015 validation_1-rmse:0.17803 +[21] validation_0-rmse:0.17857 validation_1-rmse:0.17575 +[22] validation_0-rmse:0.17681 validation_1-rmse:0.17350 +[23] validation_0-rmse:0.17537 validation_1-rmse:0.17132 +[24] validation_0-rmse:0.17377 validation_1-rmse:0.16919 +[25] validation_0-rmse:0.17225 validation_1-rmse:0.16720 +[26] validation_0-rmse:0.17072 validation_1-rmse:0.16529 +[27] validation_0-rmse:0.16931 validation_1-rmse:0.16310 +[28] validation_0-rmse:0.16784 validation_1-rmse:0.16126 +[29] validation_0-rmse:0.16650 validation_1-rmse:0.15940 +[30] validation_0-rmse:0.16512 validation_1-rmse:0.15771 +[31] validation_0-rmse:0.16392 validation_1-rmse:0.15605 +[32] validation_0-rmse:0.16287 validation_1-rmse:0.15428 +[33] validation_0-rmse:0.16159 validation_1-rmse:0.15277 +[34] validation_0-rmse:0.16033 validation_1-rmse:0.15125 +[35] validation_0-rmse:0.15910 validation_1-rmse:0.14974 +[36] validation_0-rmse:0.15821 validation_1-rmse:0.14832 +[37] validation_0-rmse:0.15733 validation_1-rmse:0.14664 +[38] validation_0-rmse:0.15624 validation_1-rmse:0.14525 +[39] validation_0-rmse:0.15518 validation_1-rmse:0.14395 +[40] validation_0-rmse:0.15451 validation_1-rmse:0.14267 +[41] validation_0-rmse:0.15396 validation_1-rmse:0.14127 +[42] validation_0-rmse:0.15309 validation_1-rmse:0.14006 +[43] validation_0-rmse:0.15219 validation_1-rmse:0.13890 +[44] validation_0-rmse:0.15156 validation_1-rmse:0.13749 +[45] validation_0-rmse:0.15061 validation_1-rmse:0.13637 +[46] validation_0-rmse:0.14982 validation_1-rmse:0.13528 +[47] validation_0-rmse:0.14918 validation_1-rmse:0.13414 +[48] validation_0-rmse:0.14840 validation_1-rmse:0.13312 +[49] validation_0-rmse:0.14802 validation_1-rmse:0.13212 +[50] validation_0-rmse:0.14738 validation_1-rmse:0.13089 +[51] validation_0-rmse:0.14671 validation_1-rmse:0.12994 +[52] validation_0-rmse:0.14604 validation_1-rmse:0.12894 +[53] validation_0-rmse:0.14534 validation_1-rmse:0.12802 +[54] validation_0-rmse:0.14464 validation_1-rmse:0.12718 +[55] validation_0-rmse:0.14423 validation_1-rmse:0.12625 +[56] validation_0-rmse:0.14371 validation_1-rmse:0.12531 +[57] validation_0-rmse:0.14321 validation_1-rmse:0.12446 +[58] validation_0-rmse:0.14279 validation_1-rmse:0.12346 +[59] validation_0-rmse:0.14234 validation_1-rmse:0.12257 +[60] validation_0-rmse:0.14194 validation_1-rmse:0.12181 +[61] validation_0-rmse:0.14176 validation_1-rmse:0.12077 +[62] validation_0-rmse:0.14120 validation_1-rmse:0.12003 +[63] validation_0-rmse:0.14073 validation_1-rmse:0.11932 +[64] validation_0-rmse:0.14023 validation_1-rmse:0.11862 +[65] validation_0-rmse:0.14001 validation_1-rmse:0.11791 +[66] validation_0-rmse:0.13966 validation_1-rmse:0.11720 +[67] validation_0-rmse:0.13920 validation_1-rmse:0.11644 +[68] validation_0-rmse:0.13872 validation_1-rmse:0.11560 +[69] validation_0-rmse:0.13831 validation_1-rmse:0.11494 +[70] validation_0-rmse:0.13808 validation_1-rmse:0.11425 +[71] validation_0-rmse:0.13762 validation_1-rmse:0.11348 +[72] validation_0-rmse:0.13725 validation_1-rmse:0.11284 +[73] validation_0-rmse:0.13681 validation_1-rmse:0.11225 +[74] validation_0-rmse:0.13629 validation_1-rmse:0.11165 +[75] validation_0-rmse:0.13595 validation_1-rmse:0.11109 +[76] validation_0-rmse:0.13585 validation_1-rmse:0.11023 +[77] validation_0-rmse:0.13541 validation_1-rmse:0.10972 +[78] validation_0-rmse:0.13505 validation_1-rmse:0.10920 +[79] validation_0-rmse:0.13465 validation_1-rmse:0.10861 +[80] validation_0-rmse:0.13433 validation_1-rmse:0.10810 +[81] validation_0-rmse:0.13409 validation_1-rmse:0.10744 +[82] validation_0-rmse:0.13377 validation_1-rmse:0.10695 +[83] validation_0-rmse:0.13353 validation_1-rmse:0.10641 +[84] validation_0-rmse:0.13337 validation_1-rmse:0.10588 +[85] validation_0-rmse:0.13329 validation_1-rmse:0.10533 +[86] validation_0-rmse:0.13296 validation_1-rmse:0.10488 +[87] validation_0-rmse:0.13264 validation_1-rmse:0.10442 +[88] validation_0-rmse:0.13247 validation_1-rmse:0.10394 +[89] validation_0-rmse:0.13216 validation_1-rmse:0.10351 +[90] validation_0-rmse:0.13188 validation_1-rmse:0.10297 +[91] validation_0-rmse:0.13145 validation_1-rmse:0.10203 +[92] validation_0-rmse:0.13122 validation_1-rmse:0.10157 +[93] validation_0-rmse:0.13102 validation_1-rmse:0.10118 +[94] validation_0-rmse:0.13060 validation_1-rmse:0.10033 +[95] validation_0-rmse:0.13033 validation_1-rmse:0.09981 +[96] validation_0-rmse:0.13016 validation_1-rmse:0.09933 +[97] validation_0-rmse:0.12995 validation_1-rmse:0.09894 +[98] validation_0-rmse:0.12972 validation_1-rmse:0.09860 +[99] validation_0-rmse:0.12954 validation_1-rmse:0.09825 +2025-04-29 01:57:23,725 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.60 secs) -------------------- +2025-04-29 01:57:23,726 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:24,305 - freqtrade.freqai.freqai_interface - INFO - Training SOL/USDT, 2/2 pairs from 2025-03-12 00:00:00 to 2025-04-11 00:00:00, 11/11 trains +2025-04-29 01:57:24,305 - freqtrade.freqai.data_kitchen - INFO - Could not find backtesting prediction file at +/freqtrade/user_data/models/test175/backtesting_predictions/cb_sol_1744329600_prediction.feather +2025-04-29 01:57:24,318 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:24,325 - FreqaiExampleStrategy - INFO - 目标列形状：(62450,) +2025-04-29 01:57:24,327 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.601082 +1 0.003044 49.601082 +2 0.000465 49.601082 +3 -0.000380 49.601082 +4 0.002829 49.601082 +2025-04-29 01:57:24,337 - FreqaiExampleStrategy - INFO - 设置 FreqAI 目标，交易对：SOL/USDT +2025-04-29 01:57:24,345 - FreqaiExampleStrategy - INFO - 目标列形状：(66770,) +2025-04-29 01:57:24,346 - FreqaiExampleStrategy - INFO - 目标列预览： + up_or_down &-buy_rsi +0 0.002704 49.729824 +1 0.003044 49.729824 +2 0.000465 49.729824 +3 -0.000380 49.729824 +4 0.002829 49.729824 +2025-04-29 01:57:24,352 - freqtrade.freqai.freqai_interface - INFO - Could not find model at /freqtrade/user_data/models/test175/sub-train-SOL_1744329600/cb_sol_1744329600 +2025-04-29 01:57:24,353 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Starting training SOL/USDT -------------------- +2025-04-29 01:57:24,376 - freqtrade.freqai.data_kitchen - INFO - SOL/USDT: dropped 0 training points due to NaNs in populated dataset 14400. +2025-04-29 01:57:24,376 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Training on data from 2025-03-12 to 2025-04-10 -------------------- +2025-04-29 01:57:29,392 - datasieve.pipeline - INFO - DI tossed 1948 predictions for being too far from training data. +2025-04-29 01:57:29,396 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 111 features +2025-04-29 01:57:29,396 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - Training model on 11520 data points +[0] validation_0-rmse:0.30616 validation_1-rmse:0.27906 +[1] validation_0-rmse:0.30021 validation_1-rmse:0.27322 +[2] validation_0-rmse:0.29443 validation_1-rmse:0.26757 +[3] validation_0-rmse:0.28911 validation_1-rmse:0.26205 +[4] validation_0-rmse:0.28365 validation_1-rmse:0.25699 +[5] validation_0-rmse:0.27823 validation_1-rmse:0.25219 +[6] validation_0-rmse:0.27295 validation_1-rmse:0.24748 +[7] validation_0-rmse:0.26797 validation_1-rmse:0.24295 +[8] validation_0-rmse:0.26320 validation_1-rmse:0.23854 +[9] validation_0-rmse:0.25898 validation_1-rmse:0.23437 +[10] validation_0-rmse:0.25517 validation_1-rmse:0.23021 +[11] validation_0-rmse:0.25113 validation_1-rmse:0.22639 +[12] validation_0-rmse:0.24762 validation_1-rmse:0.22270 +[13] validation_0-rmse:0.24393 validation_1-rmse:0.21915 +[14] validation_0-rmse:0.24169 validation_1-rmse:0.21579 +[15] validation_0-rmse:0.23898 validation_1-rmse:0.21236 +[16] validation_0-rmse:0.23539 validation_1-rmse:0.20924 +[17] validation_0-rmse:0.23364 validation_1-rmse:0.20621 +[18] validation_0-rmse:0.23062 validation_1-rmse:0.20322 +[19] validation_0-rmse:0.22764 validation_1-rmse:0.20024 +[20] validation_0-rmse:0.22488 validation_1-rmse:0.19731 +[21] validation_0-rmse:0.22211 validation_1-rmse:0.19445 +[22] validation_0-rmse:0.21952 validation_1-rmse:0.19188 +[23] validation_0-rmse:0.21699 validation_1-rmse:0.18935 +[24] validation_0-rmse:0.21549 validation_1-rmse:0.18686 +[25] validation_0-rmse:0.21310 validation_1-rmse:0.18454 +[26] validation_0-rmse:0.21118 validation_1-rmse:0.18198 +[27] validation_0-rmse:0.20904 validation_1-rmse:0.17979 +[28] validation_0-rmse:0.20726 validation_1-rmse:0.17755 +[29] validation_0-rmse:0.20511 validation_1-rmse:0.17547 +[30] validation_0-rmse:0.20336 validation_1-rmse:0.17335 +[31] validation_0-rmse:0.20172 validation_1-rmse:0.17144 +[32] validation_0-rmse:0.19983 validation_1-rmse:0.16961 +[33] validation_0-rmse:0.19794 validation_1-rmse:0.16759 +[34] validation_0-rmse:0.19658 validation_1-rmse:0.16581 +[35] validation_0-rmse:0.19492 validation_1-rmse:0.16409 +[36] validation_0-rmse:0.19347 validation_1-rmse:0.16229 +[37] validation_0-rmse:0.19225 validation_1-rmse:0.16064 +[38] validation_0-rmse:0.19083 validation_1-rmse:0.15877 +[39] validation_0-rmse:0.18921 validation_1-rmse:0.15720 +[40] validation_0-rmse:0.18766 validation_1-rmse:0.15572 +[41] validation_0-rmse:0.18652 validation_1-rmse:0.15414 +[42] validation_0-rmse:0.18519 validation_1-rmse:0.15277 +[43] validation_0-rmse:0.18396 validation_1-rmse:0.15125 +[44] validation_0-rmse:0.18264 validation_1-rmse:0.14968 +[45] validation_0-rmse:0.18134 validation_1-rmse:0.14841 +[46] validation_0-rmse:0.18026 validation_1-rmse:0.14717 +[47] validation_0-rmse:0.17900 validation_1-rmse:0.14594 +[48] validation_0-rmse:0.17815 validation_1-rmse:0.14460 +[49] validation_0-rmse:0.17713 validation_1-rmse:0.14344 +[50] validation_0-rmse:0.17609 validation_1-rmse:0.14232 +[51] validation_0-rmse:0.17502 validation_1-rmse:0.14112 +[52] validation_0-rmse:0.17414 validation_1-rmse:0.13991 +[53] validation_0-rmse:0.17317 validation_1-rmse:0.13889 +[54] validation_0-rmse:0.17267 validation_1-rmse:0.13770 +[55] validation_0-rmse:0.17175 validation_1-rmse:0.13665 +[56] validation_0-rmse:0.17087 validation_1-rmse:0.13573 +[57] validation_0-rmse:0.17001 validation_1-rmse:0.13483 +[58] validation_0-rmse:0.16920 validation_1-rmse:0.13384 +[59] validation_0-rmse:0.16869 validation_1-rmse:0.13280 +[60] validation_0-rmse:0.16790 validation_1-rmse:0.13189 +[61] validation_0-rmse:0.16689 validation_1-rmse:0.13093 +[62] validation_0-rmse:0.16600 validation_1-rmse:0.13007 +[63] validation_0-rmse:0.16548 validation_1-rmse:0.12921 +[64] validation_0-rmse:0.16482 validation_1-rmse:0.12837 +[65] validation_0-rmse:0.16397 validation_1-rmse:0.12747 +[66] validation_0-rmse:0.16316 validation_1-rmse:0.12669 +[67] validation_0-rmse:0.16267 validation_1-rmse:0.12587 +[68] validation_0-rmse:0.16204 validation_1-rmse:0.12501 +[69] validation_0-rmse:0.16159 validation_1-rmse:0.12422 +[70] validation_0-rmse:0.16090 validation_1-rmse:0.12354 +[71] validation_0-rmse:0.16026 validation_1-rmse:0.12282 +[72] validation_0-rmse:0.15986 validation_1-rmse:0.12206 +[73] validation_0-rmse:0.15919 validation_1-rmse:0.12129 +[74] validation_0-rmse:0.15875 validation_1-rmse:0.12061 +[75] validation_0-rmse:0.15829 validation_1-rmse:0.11966 +[76] validation_0-rmse:0.15790 validation_1-rmse:0.11864 +[77] validation_0-rmse:0.15732 validation_1-rmse:0.11802 +[78] validation_0-rmse:0.15696 validation_1-rmse:0.11739 +[79] validation_0-rmse:0.15615 validation_1-rmse:0.11660 +[80] validation_0-rmse:0.15556 validation_1-rmse:0.11593 +[81] validation_0-rmse:0.15516 validation_1-rmse:0.11531 +[82] validation_0-rmse:0.15466 validation_1-rmse:0.11437 +[83] validation_0-rmse:0.15422 validation_1-rmse:0.11383 +[84] validation_0-rmse:0.15382 validation_1-rmse:0.11332 +[85] validation_0-rmse:0.15350 validation_1-rmse:0.11244 +[86] validation_0-rmse:0.15310 validation_1-rmse:0.11180 +[87] validation_0-rmse:0.15277 validation_1-rmse:0.11119 +[88] validation_0-rmse:0.15228 validation_1-rmse:0.11060 +[89] validation_0-rmse:0.15192 validation_1-rmse:0.11011 +[90] validation_0-rmse:0.15144 validation_1-rmse:0.10956 +[91] validation_0-rmse:0.15092 validation_1-rmse:0.10913 +[92] validation_0-rmse:0.15058 validation_1-rmse:0.10847 +[93] validation_0-rmse:0.15017 validation_1-rmse:0.10803 +[94] validation_0-rmse:0.14984 validation_1-rmse:0.10702 +[95] validation_0-rmse:0.14967 validation_1-rmse:0.10629 +[96] validation_0-rmse:0.14914 validation_1-rmse:0.10587 +[97] validation_0-rmse:0.14882 validation_1-rmse:0.10545 +[98] validation_0-rmse:0.14853 validation_1-rmse:0.10454 +[99] validation_0-rmse:0.14837 validation_1-rmse:0.10398 +2025-04-29 01:57:30,474 - freqtrade.freqai.base_models.BaseRegressionModel - INFO - -------------------- Done training SOL/USDT (6.12 secs) -------------------- +2025-04-29 01:57:30,475 - freqtrade.freqai.freqai_interface - INFO - Saving metadata to disk. +2025-04-29 01:57:31,077 - FreqaiExampleStrategy - INFO - 动态参数：buy_rsi=50.0, sell_rsi=70.0, stoploss=-0.15, trailing_stop_positive=0.05 +2025-04-29 01:57:31,096 - FreqaiExampleStrategy - INFO - up_or_down 值统计： +up_or_down +0 33825 +1 32946 +2025-04-29 01:57:31,097 - FreqaiExampleStrategy - INFO - do_predict 值统计： +do_predict +0.0 36730 +1.0 30041 +2025-04-29 01:57:31,105 - freqtrade.optimize.backtesting - INFO - Backtesting with data from 2025-01-01 00:00:00 up to 2025-04-20 00:00:00 (109 days). +2025-04-29 01:57:31,109 - FreqaiExampleStrategy - ERROR - MACD 或 MACD 信号列缺失，无法生成买入信号。尝试重新计算 MACD 列。 +2025-04-29 01:57:31,111 - FreqaiExampleStrategy - INFO - MACD 列已成功重新计算。 +2025-04-29 01:57:31,193 - FreqaiExampleStrategy - ERROR - MACD 或 MACD 信号列缺失，无法生成买入信号。尝试重新计算 MACD 列。 +2025-04-29 01:57:31,195 - FreqaiExampleStrategy - INFO - MACD 列已成功重新计算。 +2025-04-29 01:57:33,776 - freqtrade.misc - INFO - dumping json to "/freqtrade/user_data/backtest_results/backtest-result-2025-04-29_01-57-33.meta.json" +Result for strategy FreqaiExampleStrategy + BACKTESTING REPORT +┏━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Pair ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ BTC/USDT │ 38 │ -0.39 │ -22.029 │ -2.2 │ 22:13:00 │ 5 32 1 13.2 │ +│ SOL/USDT │ 44 │ -1.94 │ -128.236 │ -12.82 │ 16:35:00 │ 12 26 6 27.3 │ +│ TOTAL │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└──────────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┘ + LEFT OPEN TRADES REPORT +┏━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Pair ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ TOTAL │ 0 │ 0.0 │ 0.000 │ 0.0 │ 0:00 │ 0 0 0 0 │ +└───────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┘ + ENTER TAG STATS +┏━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Enter Tag ┃ Entries ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ long │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +│ TOTAL │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└───────────┴─────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┘ + EXIT REASON STATS +┏━━━━━━━━━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Exit Reason ┃ Exits ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━━━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ roi │ 75 │ 0.07 │ 7.926 │ 0.79 │ 14:48:00 │ 17 58 0 100 │ +│ trailing_stop_loss │ 7 │ -15.04 │ -158.191 │ -15.82 │ 2 days, 18:13:00 │ 0 0 7 0 │ +│ TOTAL │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└────────────────────┴───────┴──────────────┴─────────────────┴──────────────┴──────────────────┴────────────────────────┘ + MIXED TAG STATS +┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Enter Tag ┃ Exit Reason ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ ('long', 'roi') │ │ 75 │ 0.07 │ 7.926 │ 0.79 │ 14:48:00 │ 17 58 0 100 │ +│ ('long', 'trailing_stop_loss') │ │ 7 │ -15.04 │ -158.191 │ -15.82 │ 2 days, 18:13:00 │ 0 0 7 0 │ +│ TOTAL │ │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ +└────────────────────────────────┴─────────────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────────┴────────────────────────┘ + SUMMARY METRICS +┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┓ +┃ Metric ┃ Value ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━┩ +│ Backtesting from │ 2025-01-01 00:00:00 │ +│ Backtesting to │ 2025-04-20 00:00:00 │ +│ Trading Mode │ Spot │ +│ Max open trades │ 2 │ +│ │ │ +│ Total/Daily Avg Trades │ 82 / 0.75 │ +│ Starting balance │ 1000 USDT │ +│ Final balance │ 849.735 USDT │ +│ Absolute profit │ -150.265 USDT │ +│ Total profit % │ -15.03% │ +│ CAGR % │ -42.03% │ +│ Sortino │ -252.56 │ +│ Sharpe │ -4.15 │ +│ Calmar │ -17.48 │ +│ SQN │ -2.60 │ +│ Profit factor │ 0.05 │ +│ Expectancy (Ratio) │ -1.83 (-0.79) │ +│ Avg. daily profit % │ -0.14% │ +│ Avg. stake amount │ 150 USDT │ +│ Total trade volume │ 24523.15 USDT │ +│ │ │ +│ Best Pair │ BTC/USDT -2.20% │ +│ Worst Pair │ SOL/USDT -12.82% │ +│ Best trade │ SOL/USDT 0.90% │ +│ Worst trade │ SOL/USDT -15.19% │ +│ Best day │ 1.76 USDT │ +│ Worst day │ -22.827 USDT │ +│ Days win/draw/lose │ 14 / 80 / 7 │ +│ Avg. Duration Winners │ 0:55:00 │ +│ Avg. Duration Loser │ 2 days, 18:13:00 │ +│ Max Consecutive Wins / Loss │ 2 / 16 │ +│ Rejected Entry signals │ 0 │ +│ Entry/Exit Timeouts │ 0 / 0 │ +│ │ │ +│ Min balance │ 849.735 USDT │ +│ Max balance │ 1000.508 USDT │ +│ Max % of account underwater │ 15.07% │ +│ Absolute Drawdown (Account) │ 15.07% │ +│ Absolute Drawdown │ 150.773 USDT │ +│ Drawdown high │ 0.508 USDT │ +│ Drawdown low │ -150.265 USDT │ +│ Drawdown Start │ 2025-01-06 19:48:00 │ +│ Drawdown End │ 2025-04-06 23:15:00 │ +│ Market change │ -26.79% │ +└─────────────────────────────┴─────────────────────┘ + +Backtested 2025-01-01 00:00:00 -> 2025-04-20 00:00:00 | Max open trades : 2 + STRATEGY SUMMARY +┏━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┓ +┃ Strategy ┃ Trades ┃ Avg Profit % ┃ Tot Profit USDT ┃ Tot Profit % ┃ Avg Duration ┃ Win Draw Loss Win% ┃ Drawdown ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━┩ +│ FreqaiExampleStrategy │ 82 │ -1.22 │ -150.265 │ -15.03 │ 19:12:00 │ 17 58 7 20.7 │ 150.773 USDT 15.07% │ +└───────────────────────┴────────┴──────────────┴─────────────────┴──────────────┴──────────────┴────────────────────────┴──────────────────────┘