phyer/myTestFreqAI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

result12.md

Browse Source
This commit is contained in:
zhangkun9038@dingtalk.com 2025-05-30 11:17:47 +08:00
parent 8dfbdc254f
commit e2b7fe5dcf
4 changed files with 2326 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2220
chat/result12.md Normal file
View File

File diff suppressed because it is too large Load Diff

2
config_examples/freqaiprimer.json
View File

@ -37,7 +37,7 @@
"rateLimit": 3000,
"timeout": 20000
},
"pair_whitelist": ["BTC/USDT", "ETH/USDT", "SOL/USDT", "DOT/USDT", "OKB/USDT", "TON/USDT"],
"pair_whitelist": ["BTC/USDT", "TON/USDT", "DOT/USDT", "XRP/USDT", "OKB/USDT", "SOL/USDT", "DOGE/USDT", "WCT/USDT", "TRUMP/USDT", "SUI/USDT", "PEPE/USDT", "TRB/USDT", "MASK/USDT", "UNI/USDT", "KAITO/USDT"],
"pair_blacklist": []
},
"entry_pricing": {

10
freqtrade/templates/freqaiprimer.json
View File

@ -12,16 +12,18 @@
},
"protection": {},
"roi": {
"0": 0.17099999999999999,
"8": 0.022,
"14": 0.014,
"0": 0.07,
"6": 0.022,
"12": 0.01,
"21": 0
},
"stoploss": {
"stoploss": -0.075
},
"trailing": {
"trailing_stop": false
"trailing_stop": true,
"trailing_stop_positive": 0.01,
"trailing_stop_positive_offset": 0.015
}
},
"ft_stratparam_v": 1,

116
freqtrade/templates/freqaiprimer.py
View File

@ -18,8 +18,30 @@ class FreqaiPrimer(IStrategy):
- 不使用 Hyperopt 优化任何参数
- 使用 FreqAI 提供的趋势和波动率信号进行交易决策
"""
# 👇 添加在这里
PAIR_PARAMS = {
"BTC/USDT": {"volatility_factor": 1.0, "min_stop": -0.005},
"TON/USDT": {"volatility_factor": 1.3, "min_stop": -0.0035},
"DOGE/USDT": {"volatility_factor": 1.5, "min_stop": -0.003},
"DOT/USDT": {"volatility_factor": 1.3, "min_stop": -0.0035},
"XRP/USDT": {"volatility_factor": 1.35, "min_stop": -0.0032},
"OKB/USDT": {"volatility_factor": 0.9, "min_stop": -0.006},
"SOL/USDT": {"volatility_factor": 1.4, "min_stop": -0.0032},
"WCT/USDT": {"volatility_factor": 1.4, "min_stop": -0.004},
"TRUMP/USDT": {"volatility_factor": 1.4, "min_stop": -0.0035},
"SUI/USDT": {"volatility_factor": 1.6, "min_stop": -0.0025},
"PEPE/USDT": {"volatility_factor": 1.5, "min_stop": -0.0036},
"TRB/USDT": {"volatility_factor": 1.45, "min_stop": -0.004},
"MASK/USDT": {"volatility_factor": 1.65, "min_stop": -0.0045},
"UNI/USDT": {"volatility_factor": 1.45, "min_stop": -0.005},
"KAITO/USDT": {"volatility_factor": 1.45, "min_stop": -0.004},
}
use_custom_stoploss = True
trailing_stop = True
trailing_stop_positive = 0.005
trailing_stop_positive_offset = 0.01
trailing_only_offset_is_reached = True
plot_config = {
"main_plot": {},
"subplots": {
@ -115,7 +137,21 @@ class FreqaiPrimer(IStrategy):
# 4. 动态止损目标：基于波动率缩放
dataframe["&-stoploss_target"] = -dataframe["&-volatility_forecast"] * 1.2
# 5. 市场状态识别：判断当前是震荡、趋势、超买还是超卖
# 👇 新增：z-score 标准化模型输出
if self.freqai and hasattr(self.freqai, "data"):
labels_mean = self.freqai.data.labels_mean
labels_std = self.freqai.data.labels_std
mean_roi = labels_mean.get("&-roi_target", 0.01)
std_roi = labels_std.get("&-roi_target", 0.01)
mean_stop = labels_mean.get("&-stoploss_target", -0.01)
std_stop = labels_std.get("&-stoploss_target", 0.01)
# z-score 标准化
dataframe["&-roi_target_z"] = (dataframe["&-roi_target"] - mean_roi) / std_roi
dataframe["&-stoploss_target_z"] = (dataframe["&-stoploss_target"] - mean_stop) / std_stop
# 市场状态识别：判断当前是震荡、趋势、超买还是超卖
if "bb_upperband-period" in dataframe.columns and "bb_lowerband-period" in dataframe.columns:
dataframe["&-market_condition"] = np.select([
(dataframe["close"] > dataframe["bb_upperband-period"]),
@ -133,7 +169,6 @@ class FreqaiPrimer(IStrategy):
# 卖出信号（必须存在）
dataframe["&-sell_signal"] = np.where(dataframe["&-trend_strength"] < -0.01, 1, 0)
return dataframe
def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
@ -143,11 +178,22 @@ class FreqaiPrimer(IStrategy):
# FreqAI 提供的预测列
if "&-trend" in dataframe.columns:
dataframe["in_uptrend"] = dataframe["&-trend"] > 0.5
# 将 roi_target 存入 dataframe，供后续使用
if "&-roi_target" in dataframe.columns:
dataframe["&-roi_target"] = dataframe["&-roi_target"].ffill().fillna(0.01)
else:
dataframe["&-roi_target"] = 0.01
# 添加 trailing stop 参数到 dataframe
if "&-volatility_forecast" in dataframe.columns:
volatility = dataframe["&-volatility_forecast"].iloc[-1]
dataframe["trailing_stop_positive"] = max(0.003, volatility * 0.5)
dataframe["trailing_stop_positive_offset"] = max(0.006, volatility * 1.0)
else:
dataframe["trailing_stop_positive"] = 0.005
dataframe["trailing_stop_positive_offset"] = 0.01
return dataframe
def populate_entry_trend(self, df: DataFrame, metadata: dict) -> DataFrame:
@ -158,13 +204,13 @@ class FreqaiPrimer(IStrategy):
df["buy_threshold"] = df["&-buy_signal"].rolling(20).quantile(0.8)
buy_condition = (df["&-buy_signal"] >= df["buy_threshold"]) & (df["&-buy_signal"] > 0.4)
# 动态计算趋势强度的滚动均值和标准差
# 👇 新增：滚动 Z-score 趋势判断
window = 50
df["trend_mean"] = df["&-trend_strength"].rolling(window).mean()
df["trend_std"] = df["&-trend_strength"].rolling(window).std()
# 使用 z-score 判断趋势是否显著
df["z_score_trend"] = (df["&-trend_strength"] - df["trend_mean"]) / df["trend_std"]
# 只有当 z-score > 1 时才认为趋势显著
buy_condition &= (df["z_score_trend"] > 1)
# 打印模型统计信息用于调试
@ -232,30 +278,43 @@ class FreqaiPrimer(IStrategy):
# 获取预测的 ROI 目标
roi_target = last_candle.get("&-roi_target", 0.01)
# 获取模型输出统计信息用于自适应判断
mean_roi = 0.01
std_roi = 0.01
if self.freqai and hasattr(self.freqai, "data"):
labels_mean = self.freqai.data.labels_mean
labels_std = self.freqai.data.labels_std
mean_roi = labels_mean.get("&-roi_target", mean_roi)
std_roi = labels_std.get("&-roi_target", std_roi)
high_threshold = mean_roi + std_roi
low_threshold = mean_roi - std_roi
# 根据预测值生成新的 ROI 表
if roi_target > 0.05:
if roi_target > high_threshold:
new_minimal_roi = {
"0": roi_target * 1.0,
"10": roi_target * 0.8,
"30": roi_target * 0.5,
"60": roi_target * 0.2,
"120": 0.01
"120": 0.005
}
elif 0.02 <= roi_target <= 0.05:
elif low_threshold <= roi_target <= high_threshold:
new_minimal_roi = {
"0": roi_target * 1.0,
"20": roi_target * 0.7,
"60": roi_target * 0.3,
"120": 0.01
"120": 0.005
}
else:
new_minimal_roi = {
"0": max(0.01, roi_target),
"60": 0.01,
"180": 0.01
"0": max(0.005, roi_target),
"60": 0.005,
"180": 0.005
}
# 返回新的 minimal_roi
return new_minimal_roi
def custom_stoploss(self, pair: str, trade: Trade, current_time: datetime,
@ -268,10 +327,33 @@ class FreqaiPrimer(IStrategy):
dataframe, _ = self.dp.get_analyzed_dataframe(pair, self.timeframe)
last_candle = dataframe.iloc[-1]
# 获取预测的止损目标
stoploss_target = last_candle.get("&-stoploss_target", -0.01)
# 获取预测的止损目标（使用 z-score 版本）
stoploss_z = last_candle.get("&-stoploss_target_z", -1.0) # 默认值为 -1.0（一个标准差）
# 将 stoploss_target 转换为负数（因为 stoploss 是负值）
dynamic_stoploss = min(-0.005, stoploss_target) # 设置最小止损限制a
# 获取模型统计信息用于自适应判断
mean_stop = -0.01
std_stop = 0.01
if self.freqai and hasattr(self.freqai, "data"):
labels_mean = self.freqai.data.labels_mean
labels_std = self.freqai.data.labels_std
mean_stop = labels_mean.get("&-stoploss_target", mean_stop)
std_stop = labels_std.get("&-stoploss_target", std_stop)
# 获取币种特定参数
params = self.PAIR_PARAMS.get(pair, {"volatility_factor": 1.0, "min_stop": -0.005})
volatility_factor = params["volatility_factor"]
min_stop = params["min_stop"]
# 动态止损下限 = 平均值 - volatility_factor * 标准差
dynamic_min_stop = min(min_stop, mean_stop - volatility_factor * std_stop)
# 如果 z-score < -1，则说明当前止损偏移较大，适当放宽
if stoploss_z < -1.0:
dynamic_min_stop = min(dynamic_min_stop * 1.2, -0.003)
# 最终止损值 = 模型建议值 和 动态下限中的较小者
dynamic_stoploss = dynamic_min_stop
return dynamic_stoploss