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

download.sh 重要更新

Browse Source
This commit is contained in:
Ubuntu 2025-07-09 16:37:42 +08:00
parent aba0b61d36
commit dd742d6079
3 changed files with 55 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
.output.log.swp Normal file
View File

Binary file not shown.

93
freqtrade/templates/freqaiprimer.py
View File

@ -173,24 +173,19 @@ class FreqaiPrimer(IStrategy):
return avg_stochrsi > threshold
def is_bearish_market(self, dataframe: DataFrame, metadata: dict, timeframe: str = "4h") -> pd.Series:
"""
判断 4h 时间框架是否为熊市，返回布尔 Series
条件：
a. 价格远低于布林带中轨
b. STOCHRSI 超过90
c. 看跌蜡烛图形态（看跌吞没、乌云盖顶、射击之星，或 STOCHRSI 最近10周期均值>85）
d. 成交量显著下降
"""
pair = metadata.get('pair', 'Unknown')
logger.debug(f"[{pair}] 开始计算 4h 熊市信号")
# 防御性检查
required_columns = ['close_4h', 'high_4h', 'low_4h', 'open_4h', 'stochrsi_k_4h', 'stochrsi_d_4h', 'bb_middle_4h', 'volume_z_score_4h']
required_columns = ['close_4h', 'high_4h', 'low_4h', 'open_4h', 'stochrsi_k_4h', 'stochrsi_d_4h', 'bb_middle_4h']
missing = [col for col in required_columns if col not in dataframe.columns]
if missing:
logger.error(f"[{pair}] 缺少必要列：{missing}，返回全 False")
return pd.Series([False] * len(dataframe), index=dataframe.index)
# 检查 volume_z_score_4h 是否存在
has_volume_z_score = 'volume_z_score_4h' in dataframe.columns and not dataframe['volume_z_score_4h'].isna().all()
# 条件 a：价格远低于布林带中轨（低于中轨 1% 以上）
cond_a = dataframe['close_4h'] < dataframe['bb_middle_4h'] * 0.99
@ -205,40 +200,38 @@ class FreqaiPrimer(IStrategy):
prev_open = open_4h.shift(1)
prev_close = close_4h.shift(1)
# 看跌吞没形态
cond_engulfing = (
(prev_close > prev_open) &
(close_4h < open_4h) &
(close_4h < prev_open) &
(open_4h > prev_close)
)
# 乌云盖顶
cond_dark_cloud_cover = (
(prev_close > prev_open) &
(open_4h > prev_close) &
(close_4h < (prev_open + prev_close) / 2) &
(close_4h < open_4h)
)
# 射击之星
body = abs(open_4h - close_4h)
upper_wick = high_4h - np.maximum(open_4h, close_4h)
lower_wick = np.minimum(open_4h, close_4h) - low_4h
cond_shooting_star = (upper_wick > 2 * body) & (lower_wick < body) & (close_4h < open_4h)
# STOCHRSI 最近10周期均值>85
cond_stochrsi_high = self.is_stochrsi_overbought(dataframe, period=10, threshold=85)
cond_c = cond_engulfing | cond_dark_cloud_cover | cond_shooting_star | cond_stochrsi_high
# 条件 d：成交量显著下降（volume_z_score < -1.0）
cond_d = dataframe['volume_z_score_4h'] < -1.0
# 条件 d：成交量显著下降
cond_d = dataframe['volume_z_score_4h'] < -1.0 if has_volume_z_score else pd.Series([False] * len(dataframe), index=dataframe.index)
# 综合熊市信号（至少满足两个条件以提高稳定性）
# 综合熊市信号（至少满足两个条件）
bearish_signal = (cond_a & cond_b) | (cond_a & cond_c) | (cond_b & cond_c) | (cond_a & cond_d)
logger.debug(f"[{pair}] 熊市信号生成完成，满足条件的 K 线数：{bearish_signal.sum()}")
# 记录每个条件的触发情况
logger.debug(f"[{pair}] 熊市信号 - 条件a (价格低于布林中轨): {cond_a.mean():.2%}, "
f"条件b (STOCHRSI>90): {cond_b.mean():.2%}, "
f"条件c (看跌形态): {cond_c.mean():.2%}, "
f"条件d (成交量下降): {cond_d.mean():.2%}, "
f"总熊市信号触发率: {bearish_signal.mean():.2%}")
return bearish_signal
def trailing_space(self):
@ -283,30 +276,36 @@ class FreqaiPrimer(IStrategy):
dataframe_4h = self.dp.get_pair_dataframe(pair=pair, timeframe="4h")
if dataframe_4h.empty or len(dataframe_4h) < 50:
logger.warning(f"[{pair}] 4h 数据为空或不足（{len(dataframe_4h)} 根K线），初始化空列")
for col in ['open_4h', 'high_4h', 'low_4h', 'close_4h', 'stochrsi_k_4h', 'stochrsi_d_4h',
for col in ['open_4h', 'high_4h', 'low_4h', 'close_4h', 'stochrsi_k_4h', 'stochrsi_d_4h',
'bb_upper_4h', 'bb_middle_4h', 'bb_lower_4h', 'volume_z_score_4h']:
dataframe[col] = np.nan
else:
# 计算 4h 指标
stochrsi_4h = ta.STOCHRSI(dataframe_4h, timeperiod=14, fastk_period=3, fastd_period=3)
dataframe_4h['stochrsi_k'] = stochrsi_4h['fastk']
dataframe_4h['stochrsi_d'] = stochrsi_4h['fastd']
real = ta.TYPPRICE(dataframe_4h)
upperband, middleband, lowerband = ta.BBANDS(real, timeperiod=20, nbdevup=2.0, nbdevdn=2.0)
dataframe_4h['bb_upper_4h'] = upperband
dataframe_4h['bb_middle_4h'] = middleband
dataframe_4h['bb_lower_4h'] = lowerband
dataframe_4h['volume_mean_20_4h'] = dataframe_4h["volume"].rolling(20).mean()
dataframe_4h['volume_std_20_4h'] = dataframe_4h["volume"].rolling(20).std()
dataframe_4h['volume_z_score_4h'] = (dataframe_4h["volume"] - dataframe_4h['volume_mean_20_4h']) / dataframe_4h['volume_std_20_4h']
if len(dataframe_4h) >= 20: # 确保有足够数据计算 rolling(20)
stochrsi_4h = ta.STOCHRSI(dataframe_4h, timeperiod=14, fastk_period=3, fastd_period=3)
dataframe_4h['stochrsi_k'] = stochrsi_4h['fastk']
dataframe_4h['stochrsi_d'] = stochrsi_4h['fastd']
real = ta.TYPPRICE(dataframe_4h)
upperband, middleband, lowerband = ta.BBANDS(real, timeperiod=20, nbdevup=2.0, nbdevdn=2.0)
dataframe_4h['bb_upper_4h'] = upperband
dataframe_4h['bb_middle_4h'] = middleband
dataframe_4h['bb_lower_4h'] = lowerband
dataframe_4h['volume_mean_20_4h'] = dataframe_4h["volume"].rolling(20).mean()
dataframe_4h['volume_std_20_4h'] = dataframe_4h["volume"].rolling(20).std()
dataframe_4h['volume_z_score_4h'] = (dataframe_4h["volume"] - dataframe_4h['volume_mean_20_4h']) / dataframe_4h['volume_std_20_4h']
# 清理 NaN 和无穷值
dataframe_4h['volume_z_score_4h'] = dataframe_4h['volume_z_score_4h'].replace([np.inf, -np.inf], 0).ffill().fillna(0)
else:
logger.warning(f"[{pair}] 4h 数据不足以计算 volume_z_score_4h（{len(dataframe_4h)} 根K线，需至少20根）")
dataframe_4h['volume_z_score_4h'] = np.nan
# 映射 4h 数据到主时间框架
for col in ['open', 'high', 'low', 'close', 'stochrsi_k', 'stochrsi_d', 'bb_upper_4h', 'bb_middle_4h', 'bb_lower_4h', 'volume_z_score']:
for col in ['open', 'high', 'low', 'close', 'stochrsi_k', 'stochrsi_d', 'bb_upper_4h', 'bb_middle_4h', 'bb_lower_4h', 'volume_z_score_4h']:
if col in dataframe_4h.columns:
dataframe[f"{col}_4h" if not col.endswith('_4h') else col] = dataframe_4h[col].reindex(dataframe.index, method='ffill').bfill()
dataframe[col if col.endswith('_4h') else f"{col}_4h"] = dataframe_4h[col].reindex(dataframe.index, method='ffill').bfill()
else:
logger.warning(f"[{pair}] 4h 数据缺少列 {col}，初始化为空")
dataframe[f"{col}_4h" if not col.endswith('_4h') else col] = np.nan
dataframe[col if col.endswith('_4h') else f"{col}_4h"] = np.nan
# 数据清理：处理 NaN 和无穷值
for col in ["ema200", "bb_upperband", "bb_middleband", "bb_lowerband", "rsi", "volume_z_score",
@ -398,10 +397,13 @@ class FreqaiPrimer(IStrategy):
self.stats_logged = True
return dataframe
def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
pair = metadata.get('pair', 'Unknown')
conditions = []
logger.info(f"[{pair}] populate_entry_trend 被调用，数据行数：{len(dataframe)}，时间：{dataframe.index[-1]}")
# 记录 enter_long 信号统计
logger.info(f"[{pair}] enter_long 信号总数：{dataframe['enter_long'].sum() if 'enter_long' in dataframe.columns else 0}")
# 获取市场趋势得分
trend_score = self.get_market_trend(dataframe=dataframe, metadata=metadata)
@ -416,11 +418,9 @@ class FreqaiPrimer(IStrategy):
stochrsi_max = 45
stochrsi_threshold = self.linear_map(trend_score, 0, 100, stochrsi_max, stochrsi_min)
# 计算熊市信号
# 计算熊市信号和 STOCHRSI 超买信号
bearish_signal = self.is_bearish_market(dataframe, metadata, timeframe="4h")
bearish_signal_aligned = bearish_signal.reindex(dataframe.index, method='ffill').fillna(False)
# 计算 STOCHRSI 超买信号
stochrsi_overbought = self.is_stochrsi_overbought(dataframe, period=10, threshold=85)
stochrsi_overbought_aligned = stochrsi_overbought.reindex(dataframe.index, method='ffill').fillna(True)
@ -434,6 +434,12 @@ class FreqaiPrimer(IStrategy):
cond6 = ~bearish_signal_aligned
cond7 = ~stochrsi_overbought_aligned
# 记录 cond6 和 cond7 的触发情况
logger.debug(f"[{pair}] cond6 (非熊市) 触发率: {(~bearish_signal_aligned).mean():.2%}, "
f"熊市信号 K 线数: {bearish_signal_aligned.sum()}")
logger.debug(f"[{pair}] cond7 (STOCHRSI 非超买) 触发率: {(~stochrsi_overbought_aligned).mean():.2%}, "
f"STOCHRSI 超买 K 线数: {stochrsi_overbought_aligned.sum()}")
buy_condition = cond1 & cond2 & cond3 & cond4 & cond5 & cond6 & cond7
conditions.append(buy_condition)
@ -465,6 +471,13 @@ class FreqaiPrimer(IStrategy):
else:
logger.debug(f"[{pair}] 无有效买入条件")
logger.debug(f"[{pair}] 各条件触发率 - "
f"cond1: {cond1.mean():.2%}, "
f"cond2: {cond2.mean():.2%}, "
f"cond3: {cond3.mean():.2%}, "
f"cond4: {cond4.mean():.2%}, "
f"cond5: {cond5.mean():.2%}, "
f"buy_condition: {buy_condition.mean():.2%}")
return dataframe
def populate_exit_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame:

3
tools/download.sh
View File

@ -74,7 +74,8 @@ timeframe=$(get_csv_param_value "--timeframe" "$@")
# Use default values if parameters are not provided
if [[ -z "$pairs" ]]; then
pairs="BTC/USDT,OKB/USDT,TON/USDT,DOT/USDT,SOL/USDT,XRP/USDT"
#"pair_whitelist": ["BTC/USDT" "TON/USDT" "DOT/USDT" "XRP/USDT" "OKB/USDT" "SOL/USDT" "DOGE/USDT" "WCT/USDT" "TRUMP/USDT" "SUI/USDT" "PEPE/USDT" "TRB/USDT" "MASK/USDT" "UNI/USDT" "KAITO/USDT"],
pairs="BTC/USDT" "TON/USDT" "DOT/USDT" "XRP/USDT" "OKB/USDT" "SOL/USDT" "DOGE/USDT" "WCT/USDT" "TRUMP/USDT" "SUI/USDT" "PEPE/USDT" "TRB/USDT" "MASK/USDT" "UNI/USDT" "KAITO/USDT"
fi
if [[ -z "$timeframe" ]]; then