merged

2025-05-19 10:45:49 +00:00 · 2025-05-19 10:45:49 +00:00 · 4e512554ba
commit 4e512554ba
parent c6581649da ae7fea6dc0
16 changed files with 509 additions and 2626 deletions
--- a/.gitignore
+++ b/.gitignore
@ -1,5 +1,4 @@
 # Freqtrade rules
-config*.json
 *.sqlite
 *.sqlite-shm
 *.sqlite-wal
--- a/2
+++ b/2
@ -1,2 +0,0 @@
-https://www.freqtrade.io/en/stable/strategy/custom-stakeamount/
-
--- a/config_examples/config.json
+++ b/config_examples/config.json
@ -0,0 +1,84 @@
+{
+    "exchange": {
+        "name": "okx",
+        "key": "your_api_key",
+        "secret": "your_api_secret",
+        "ccxt_config": {
+            "enableRateLimit": true,
+            "defaultType": "spot",
+            "rateLimit": 2000,
+            "timeout": 30000
+        },
+        "pair_whitelist": ["OKB/USDT", "SOL/USDT"]
+    },
+    "pairlists": [
+        {
+            "method": "StaticPairList"
+        }
+    ],
+    "timeframe": "15m",
+    "strategy": "NostalgiaForInfinityV8",
+    "freqai": {
+        "enabled": true,
+        "freqaimodel": "LightGBMRegressor",
+        "train_period_days": 7,
+        "backtest_period_days": 0.2,
+        "feature_parameters": {
+            "include_timeframes": ["15m"],
+            "include_corr_pairlist": ["OKB/USDT", "SOL/USDT"],
+            "label_period_candles": 4,
+            "include_shifted_candles": 0,
+            "indicator_periods_candles": [5, 10, 20],
+            "include_default_features": ["close", "open", "high", "low", "volume", "rsi", "ema", "sma"],
+            "DI_threshold": 0.3
+        },
+        "data_split_parameters": {
+            "test_size": 0.2,
+            "shuffle": false
+        },
+        "model_training_parameters": {
+            "n_estimators": 100,
+            "learning_rate": 0.1,
+            "num_leaves": 15,
+            "verbose": -1
+        }
+    },
+    "order_types": {
+        "entry": "market",
+        "exit": "market",
+        "stoploss": "limit",
+        "stoploss_on_exchange": false
+    },
+    "order_time_in_force": {
+        "entry": "gtc",
+        "exit": "gtc"
+    },
+    "entry_pricing": {
+        "price_side": "other",
+        "use_order_book": false,
+        "price_last_balance": 0.0
+    },
+    "exit_pricing": {
+        "price_side": "other",
+        "use_order_book": false
+    },
+    "use_exit_signal": true,
+    "exit_profit_only": false,
+    "ignore_roi_if_entry_signal": false,
+    "stoploss": -0.05,
+    "minimal_roi": {
+        "0": 0.06,
+        "30": 0.04,
+        "60": 0.02,
+        "120": 0
+    },
+    "stake_currency": "USDT",
+    "stake_amount": 150,
+    "max_open_trades": 4,
+    "unfilledtimeout": {
+        "entry": 5,
+        "exit": 15,
+        "unit": "minutes"
+    },
+    "fee": 0.0008
+}
--- a/config_examples/config_freqai.okx.json
+++ b/config_examples/config_freqai.okx.json
@ -1,128 +0,0 @@
-{
-    "$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"
-    }
-}
--- a/docker-compose.yml
+++ b/docker-compose.yml
@ -31,24 +31,36 @@ services:
    # Default command used when running `docker compose up`

    # --freqaimodel XGBoostRegressor
-    # commangd: >
-    #      # 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 FreqaiExampleHybridStrategy
-      # --strategy-path /freqtrade/templates
+    # 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
    # command: >
    #   backtesting
    #     --logfile /freqtrade/user_data/logs/freqtrade.log
-    #     --freqaimodel XGBoostRegressor
+    #     --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: >
    #   hyperopt
    #     --logfile /freqtrade/user_data/logs/freqtrade.log
--- a/filter.py
+++ b/filter.py
@ -0,0 +1,7 @@
+with open('output.log', 'r') as input_file, open('output_filted.log', 'w') as output_file:
+    for line in input_file:
+        if "validation_0" in line:
+            if "[99]" in line:
+                output_file.write(line)
+        else:
+            output_file.write(line)
--- a/freqtrade/templates/chat.md
+++ b/freqtrade/templates/chat.md
@ -0,0 +1,85 @@
+> 请把当前策略的运行逻辑进行梳理和讲解
+
+我来为您梳理和讲解这个策略的运行逻辑。这是一个基于 FreqAI 的机器学习交易策略，主要使用 RSI 指标和机器学习模型进行交易决策。以下是策略的主要逻辑：
+
+### 1. 策略配置
+```python
+minimal_roi = {
+    "0": 0.02,
+    "7": 0.01,
+    "13": 0.005,
+    "60": 0
+}
+stoploss = 0.0
+trailing_stop = True
+```
+- 设置了静态的 ROI 目标
+- 启用了追踪止损
+
+### 2. 特征工程
+策略通过多个方法构建特征：
+- `feature_engineering_expand_all`: 计算 RSI 和布林带宽度
+- `feature_engineering_expand_basic`: 计算价格变化百分比
+- `feature_engineering_standard`: 计算波动率和时间特征
+
+### 3. 目标变量设置
+在 `set_freqai_targets` 方法中：
+- 使用未来 `label_period_candles` 周期的 RSI 值作为目标变量
+- 计算并标准化波动率特征
+
+### 4. 指标计算
+`populate_indicators` 方法中计算了多个技术指标：
+- RSI
+- 波动率
+- TEMA（三重指数移动平均线）
+- 布林带下轨
+- 未来价格方向（up_or_down）
+
+### 5. 机器学习模型
+使用 LightGBM 回归模型：
+```python
+freqai_info = {
+    "model": "LightGBMRegressor",
+    "feature_parameters": {...},
+    "data_split_parameters": {...},
+    "model_training_parameters": {...}
+}
+```
+- 模型预测买入和卖出的 RSI 值
+- 使用 SOL/USDT 作为相关交易对
+
+### 6. 入场逻辑
+`populate_entry_trend` 方法中：
+- 当实际 RSI 上穿预测的买入 RSI 时
+- TEMA 指标向上
+- 交易量大于 0
+- 模型预测结果为 1
+- 未来价格方向为上涨
+
+### 7. 出场逻辑
+`populate_exit_trend` 方法中：
+- 当实际 RSI 上穿预测的卖出 RSI 时
+- 或价格下跌超过 2%
+- 或价格跌破布林带下轨
+- 或持有时间超过 1 天
+
+### 8. 交易确认
+`confirm_trade_entry` 方法：
+- 检查当前价格是否在可接受范围内
+- 记录交易确认信息
+
+### 策略特点
+1. 机器学习驱动：使用 LightGBM 模型预测 RSI 值
+2. 多特征融合：结合技术指标、波动率和时间特征
+3. 风险控制：设置了 ROI 目标和追踪止损
+4. 动态调整：通过机器学习模型动态调整交易信号
+
+### 运行流程
+1. 数据准备：获取历史数据，计算技术指标
+2. 特征工程：构建机器学习特征
+3. 模型训练：使用历史数据训练 LightGBM 模型
+4. 信号生成：根据模型预测结果生成交易信号
+5. 交易执行：根据入场和出场逻辑执行交易
+6. 风险控制：根据 ROI 和止损规则管理仓位
+
+这个策略结合了传统技术分析和机器学习方法，通过模型预测来增强交易信号的准确性，同时保持了严格的风险控制机制。
--- a/freqtrade/templates/freqaiprimer.py
+++ b/freqtrade/templates/freqaiprimer.py
@ -1,277 +0,0 @@
-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)
-
-            dataframe["&-buy_rsi"] = ta.RSI(dataframe, timeperiod=14)
-            dataframe["&-buy_rsi"] = dataframe["&-buy_rsi"].shift(-label_period).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"]
-        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["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
--- a/run.sh
+++ b/run.sh
@ -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
--- a/temp_validation.log
+++ b/temp_validation.log
--- a/tests/config_test_comments.json
+++ b/tests/config_test_comments.json
@ -0,0 +1,129 @@
+{
+    /* Single-line C-style comment */
+    "max_open_trades": 3,
+    /*
+     * Multi-line C-style comment
+     */
+    "stake_currency": "BTC",
+    "stake_amount": 0.05,
+    "fiat_display_currency": "USD", // C++-style comment
+    "amount_reserve_percent": 0.05, // And more, tabs before this comment
+    "dry_run": false,
+    "timeframe": "5m",
+    "trailing_stop": false,
+    "trailing_stop_positive": 0.005,
+    "trailing_stop_positive_offset": 0.0051,
+    "trailing_only_offset_is_reached": false,
+    "minimal_roi": {
+        "40": 0.0,
+        "30": 0.01,
+        "20": 0.02,
+        "0": 0.04
+    },
+    "stoploss": -0.10,
+    "unfilledtimeout": {
+        "buy": 10,
+        "sell": 30, // Trailing comma should also be accepted now
+    },
+    "bid_strategy": {
+        "use_order_book": false,
+        "ask_last_balance": 0.0,
+        "order_book_top": 1,
+        "check_depth_of_market": {
+            "enabled": false,
+            "bids_to_ask_delta": 1
+        }
+    },
+    "ask_strategy": {
+        "use_order_book": false,
+        "order_book_min": 1,
+        "order_book_max": 9
+    },
+    "order_types": {
+        "buy": "limit",
+        "sell": "limit",
+        "stoploss": "market",
+        "stoploss_on_exchange": false,
+        "stoploss_on_exchange_interval": 60
+    },
+    "order_time_in_force": {
+        "buy": "gtc",
+        "sell": "gtc"
+    },
+    "pairlist": {
+        "method": "VolumePairList",
+        "config": {
+            "number_assets": 20,
+            "sort_key": "quoteVolume",
+            "precision_filter": false
+        }
+    },
+    "exchange": {
+        "name": "binance",
+        "sandbox": false,
+        "key": "your_exchange_key",
+        "secret": "your_exchange_secret",
+        "password": "",
+        "ccxt_config": {
+            "enableRateLimit": true
+        },
+        "ccxt_async_config": {
+            "enableRateLimit": false,
+            "rateLimit": 500,
+            "aiohttp_trust_env": false
+        },
+        "pair_whitelist": [
+            "ETH/BTC",
+            "LTC/BTC",
+            "ETC/BTC",
+            "DASH/BTC",
+            "ZEC/BTC",
+            "XLM/BTC",
+            "NXT/BTC",
+            "TRX/BTC",
+            "ADA/BTC",
+            "XMR/BTC"
+        ],
+        "pair_blacklist": [
+            "DOGE/BTC"
+        ],
+        "outdated_offset": 5,
+        "markets_refresh_interval": 60
+    },
+    "edge": {
+        "enabled": false,
+        "process_throttle_secs": 3600,
+        "calculate_since_number_of_days": 7,
+        "allowed_risk": 0.01,
+        "stoploss_range_min": -0.01,
+        "stoploss_range_max": -0.1,
+        "stoploss_range_step": -0.01,
+        "minimum_winrate": 0.60,
+        "minimum_expectancy": 0.20,
+        "min_trade_number": 10,
+        "max_trade_duration_minute": 1440,
+        "remove_pumps": false
+    },
+    "telegram": {
+        // We can now comment out some settings
+        //        "enabled": true,
+        "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,
+        "username": "freqtrader",
+        "password": "SuperSecurePassword"
+    },
+    "db_url": "sqlite:///tradesv3.sqlite",
+    "initial_state": "running",
+    "forcebuy_enable": false,
+    "internals": {
+        "process_throttle_secs": 5
+    },
+    "strategy": "DefaultStrategy",
+    "strategy_path": "user_data/strategies/"
+}
--- a/tools/download.sh
+++ b/tools/download.sh
@ -60,11 +60,14 @@ if [[ "$@" == *"--timerange"* ]] && [[ "$@" == *"--days"* ]]; then
 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=$(get_csv_param_value "--timeframe" "$@")
@ -75,18 +78,22 @@ if [[ -z "$pairs" ]]; then
 fi

 if [[ -z "$timeframe" ]]; then
-  timeframe="3m,5m,15m,30m,1h,4h,6h,12h,1d"
+  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"
+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 $timerange"
+  cmd+=" --timerange='$timerange'"
 elif [[ -n "$days" ]]; then
-  cmd+=" --days $days"
+  cmd+=" --days=$days"
 fi

 # Execute the command
-eval $cmd
+eval "$cmd"
--- a/tools/dryrun.sh
+++ b/tools/dryrun.sh
@ -1,4 +1,26 @@
 #!/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
@ -33,7 +55,6 @@ if [ ! -f ".env" ]; then
  echo ""
  exit 1
 fi
-
 # 加载 .env 文件中的变量
 export $(grep -v '^#' .env | xargs)
 # 设置默认值
--- a/tools/mergeme.sh
+++ b/tools/mergeme.sh
@ -0,0 +1,42 @@
+#!/bin/bash
+
+set -e # 出错立即停止
+
+# 获取参数
+source_branch=$1
+target_branch=$2
+
+# 确保传入了两个参数
+if [ -z "$source_branch" ] || [ -z "$target_branch" ]; then
+  echo "❌ 使用方法: $0 <源分支> <目标分支>"
+  echo "示例: $0 theforce-noai-test base"
+  exit 1
+fi
+
+# 定位到 Git 仓库根目录
+cd "$(git rev-parse --show-toplevel)"
+
+# 获取当前分支名
+current_branch=$(git rev-parse --abbrev-ref HEAD)
+
+# 如果当前不在 source_branch 上，则切换过去
+if [ "$current_branch" != "$source_branch" ]; then
+  echo "🔄 当前在分支 '$current_branch'，正在切换到 '$source_branch'"
+  git checkout "$source_branch"
+fi
+
+echo "📥 正在拉取 '$source_branch' 的最新代码..."
+git pull origin "$source_branch"
+
+echo "📥 正在拉取目标分支 '$target_branch' 的最新代码..."
+git fetch origin "$target_branch"
+
+echo "🔄 正在合并 '$target_branch' 到 '$source_branch'"
+git merge "origin/$target_branch" -m "Merge branch '$target_branch' into $source_branch"
+
+# 如果有冲突，需要手动解决，脚本会在此处中断
+
+echo "📤 正在推送合并后的代码到远程 '$source_branch'"
+git push origin "$source_branch"
+
+echo "✅ 合并完成并已推送到远程分支 '$source_branch'"
--- a/tools/mergetemp.sh
+++ b/tools/mergetemp.sh
@ -0,0 +1,11 @@
+#!/bin/bash
+
+source_branch=$0
+dest_branch=$1
+path=$3
+cd $path
+git reset --hard
+git checkout $dest_branch
+git pull
+git checkout $source_branch
+git merge $dest_branch
--- a/tools/view_feather.py
+++ 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)
				`@ -1,2 +0,0 @@`
				`https://www.freqtrade.io/en/stable/strategy/custom-stakeamount/`