stable1 14

### **4. 测试优化后的策略**

@@ -0,0 +1,5 @@
+
+<<<<<<< HEAD
+=======
+freqtrade backtesting --strategy FreqaiExampleStrategy --strategy-path freqtrade/templates --config config_examples/config_freqai.example.json --timerange 20230101-20230401
+>>>>>>> Snippet

4. **清理缓存**：

@@ -0,0 +1,5 @@
+
+<<<<<<< HEAD
+=======
+   rm -rf /freqtrade/user_data/models/test62/
+>>>>>>> Snippet

5. **重新训练**：

@@ -0,0 +1,5 @@
+
+<<<<<<< HEAD
+=======
+   freqtrade trade --config config_examples/config_freqai.okx.json --strategy FreqaiExampleStrategy
+>>>>>>> Snippet

config_examples/config_freqai.okx.json

@@ -2,16 +2,16 @@
     "$schema": "https://schema.freqtrade.io/schema.json",
     "trading_mode": "spot",
     "margin_mode": "isolated",
-    "max_open_trades": 4,
+    "max_open_trades": 3,
     "stake_currency": "USDT",
-    "stake_amount": 150,
+    "stake_amount": 100,
     "tradable_balance_ratio": 1,
     "fiat_display_currency": "USD",
     "dry_run": true,
-    "timeframe": "3m",
+    "timeframe": "15m",
     "dry_run_wallet": 1000,
     "cancel_open_orders_on_exit": true,
-    "stoploss": -0.05,
+    "stoploss": -0.1,
     "unfilledtimeout": {
         "entry": 5,
         "exit": 15
@@ -30,12 +30,13 @@
         },
         "ccxt_async_config": {
             "enableRateLimit": true,
-	          "rateLimit": 500,
+            "rateLimit": 500,
             "timeout": 20000
         },
         "pair_whitelist": [
             "BTC/USDT",
-            "SOL/USDT"
+            "SOL/USDT",
+            "ETH/USDT"
         ],
         "pair_blacklist": []
     },
@@ -61,50 +62,45 @@
     ],
     "freqai": {
         "enabled": true,
+        "model_path": "/freqtrade/user_data/models",
         "data_kitchen": {
             "fillna": "ffill"
         },
-        "freqaimodel": "CatboostClassifier",
-        "purge_old_models": 2,
-        "train_period_days": 15,
-        "identifier": "test62",
-        "train_period_days": 30,
-        "backtest_period_days": 10,
+        "freqaimodel": "XGBoostRegressor",
+        "model_training_parameters": {
+            "n_estimators": 300,
+            "learning_rate": 0.03,
+            "max_depth": 6,
+            "subsample": 0.8,
+            "colsample_bytree": 0.8,
+            "reg_lambda": 1.0,
+            "objective": "reg:squarederror",
+            "eval_metric": "rmse",
+            "early_stopping_rounds": 20
+        },
+        "train_period_days": 730,
+        "backtest_period_days": 90,
         "live_retrain_hours": 0,
         "feature_selection": {
-          "method": "recursive_elimination"
+            "method": "recursive_elimination"
         },
         "feature_parameters": {
-            "include_timeframes": [
-                "3m",
-                "15m",
-                "1h"
-            ],
-            "include_corr_pairlist": [
-                "BTC/USDT",
-                "SOL/USDT"
-            ],
-            "label_period_candles": 20,
+            "include_timeframes": ["15m", "1h", "4h"],
+            "include_corr_pairlist": ["BTC/USDT", "SOL/USDT", "ETH/USDT"],
+            "label_period_candles": 60,
             "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
+            "use_SVM_to_remove_outliers": true,
+            "SVM_parameters": {
+                "nu": 0.1
+            },
+            "DI_threshold": 0,
+            "indicator_periods_candles": [14, 20]
         },
         "data_split_parameters": {
-            "test_size": 0.2
-        },
-        "model_training_parameters": {
-            "n_estimators": 100,
-            "learning_rate": 0.05,
-            "max_depth": 5,
-            "num_leaves": 31
+            "test_size": 0.2,
+            "shuffle": true
         }
     },
     "api_server": {
@@ -128,3 +124,4 @@
         "loglevel": "DEBUG"
     }
 }
+

docker-compose.yml

@@ -64,9 +64,10 @@ services:
     command: >
        backtesting
         --logfile /freqtrade/user_data/logs/freqtrade.log
-        --freqaimodel LightGBMRegressor
+        --freqaimodel XGBoostRegressor
         --config /freqtrade/config_examples/config_freqai.okx.json
         --config /freqtrade/templates/FreqaiExampleStrategy.json
         --strategy-path /freqtrade/templates
         --strategy FreqaiExampleStrategy
-        --timerange 20240920-20250420
+        --timerange 20250320-20250420
+        --cache none

freqtrade/templates/FreqaiExampleHybridStrategy.py

@@ -52,7 +52,9 @@ class FreqaiExampleHybridStrategy(IStrategy):
             "random_state": 1
         },
         "model_training_parameters": {
-            "n_estimators": 800
+            "n_estimators": 200,
+            "max_depth": 5,
+            "learning_rate": 0.05
         }
     },
 
@@ -122,13 +124,11 @@ class FreqaiExampleHybridStrategy(IStrategy):
         """
 
         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
+            qtpylib.typical_price(dataframe), window=period, stds=2
         )
         dataframe["bb_lowerband-period"] = bollinger["lower"]
         dataframe["bb_middleband-period"] = bollinger["mid"]
@@ -137,13 +137,6 @@ class FreqaiExampleHybridStrategy(IStrategy):
         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
 
@@ -177,8 +170,7 @@ class FreqaiExampleHybridStrategy(IStrategy):
         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(
@@ -209,10 +201,10 @@ class FreqaiExampleHybridStrategy(IStrategy):
         dataframe["%-hour_of_day"] = dataframe["date"].dt.hour
         return dataframe
     def set_freqai_targets(self, dataframe: DataFrame, metadata: dict, **kwargs) -> DataFrame:
+        """
+        Redefined target variable to predict whether the price will increase or decrease in the future.
+        """
         logger.info(f"Setting FreqAI targets for pair: {metadata['pair']}")
-        logger.info(f"DataFrame shape: {dataframe.shape}")
-        logger.info(f"Available columns: {list(dataframe.columns)}")
-        logger.info(f"First few rows:\n{dataframe[['date', 'close']].head().to_string()}")
         
         if "close" not in dataframe.columns:
             logger.error("Required 'close' column missing in dataframe")
@@ -223,22 +215,16 @@ class FreqaiExampleHybridStrategy(IStrategy):
             raise ValueError("Insufficient data for target calculation")
         
         try:
-            # 生成数值型标签：1 表示上涨，0 表示下跌
+            # Define target variable: 1 for price increase, 0 for price decrease
             dataframe["&-up_or_down"] = np.where(
-                dataframe["close"].shift(-50) > dataframe["close"],
-                1.0,  # 数值型标签
-                0.0
+                dataframe["close"].shift(-50) > dataframe["close"], 1, 0
             )
+            # Ensure target variable is a 2D array
+            dataframe["&-up_or_down"] = dataframe["&-up_or_down"].values.reshape(-1, 1)
         except Exception as e:
             logger.error(f"Failed to create &-up_or_down column: {str(e)}")
             raise
         
-        logger.info(f"Target column head:\n{dataframe[['&-up_or_down']].head().to_string()}")
-        
-        if "&-up_or_down" not in dataframe.columns:
-            logger.error("FreqAI failed to generate the &-up_or_down column")
-            raise KeyError("FreqAI failed to generate the &-up_or_down column")
-        
         logger.info("FreqAI targets set successfully")
         return dataframe
 

freqtrade/templates/FreqaiExampleStrategy.py

@@ -1,5 +1,6 @@
 import logging
 import numpy as np
+import pandas as pd
 from functools import reduce
 import talib.abstract as ta
 from pandas import DataFrame
@@ -9,241 +10,280 @@ from freqtrade.strategy import IStrategy, IntParameter, DecimalParameter
 logger = logging.getLogger(__name__)
 
 class FreqaiExampleStrategy(IStrategy):
-    # 移除硬编码的 minimal_roi 和 stoploss，改为动态适配
-    minimal_roi = {}  # 将在 populate_indicators 中动态生成
-    stoploss = 0.0   # 将在 populate_indicators 中动态设置
+    """
+    FreqAI-based trading strategy using XGBoostRegressor for regression-based price movement prediction.
+    Optimized for short-term trading on spot markets (BTC/USDT, ETH/USDT, SOL/USDT).
+    Key improvements:
+    - Fixed KeyError in populate_entry_trend by using pd.concat for conditions
+    - Dynamic ATR-based stop-loss and ROI
+    - Enhanced feature engineering with cross-timeframe indicators
+    - Standardized and transformed target values to amplify signals
+    - Disabled DI filtering to resolve datasieve warnings
+    """
+
+    # Strategy parameters
+    minimal_roi = {}
+    stoploss = 0.0
     trailing_stop = True
     process_only_new_candles = True
     use_exit_signal = True
     startup_candle_count: int = 40
     can_short = False
+    timeframe = "15m"
 
-    # 参数定义：FreqAI 动态适配 buy_rsi 和 sell_rsi，禁用 Hyperopt 优化
-    buy_rsi = IntParameter(low=10, high=50, default=27, space="buy", optimize=False, load=True)
-    sell_rsi = IntParameter(low=50, high=90, default=59, space="sell", optimize=False, load=True)
+    # Hyperopt parameters
+    buy_rsi = IntParameter(low=10, high=50, default=30, space="buy", optimize=True, load=True)
+    sell_rsi = IntParameter(low=50, high=90, default=70, space="sell", optimize=True, load=True)
+    roi_0 = DecimalParameter(low=0.01, high=0.1, default=0.05, space="roi", optimize=True, load=True)
+    roi_15 = DecimalParameter(low=0.005, high=0.05, default=0.03, space="roi", optimize=True, load=True)
+    roi_30 = DecimalParameter(low=0.001, high=0.03, default=0.01, space="roi", optimize=True, load=True)
+    stoploss_param = DecimalParameter(low=-0.2, high=-0.05, default=-0.1, space="stoploss", optimize=True, load=True)
 
-    # 为 Hyperopt 优化添加 ROI 和 stoploss 参数
-    roi_0 = DecimalParameter(low=0.01, high=0.2, default=0.038, space="roi", optimize=True, load=True)
-    roi_15 = DecimalParameter(low=0.005, high=0.1, default=0.027, space="roi", optimize=True, load=True)
-    roi_30 = DecimalParameter(low=0.001, high=0.05, default=0.009, space="roi", optimize=True, load=True)
-    stoploss_param = DecimalParameter(low=-0.35, high=-0.1, default=-0.182, space="stoploss", optimize=True, load=True)
-
-    # FreqAI 配置
+    # FreqAI configuration
     freqai_info = {
-        "model": "LightGBMRegressor",
+        "model": "XGBoostRegressor",
+        "return_type": "raw",  # Use raw regression predictions
         "feature_parameters": {
-            "include_timeframes": ["5m", "15m", "1h"],
-            "include_corr_pairlist": [],
-            "label_period_candles": 12,
-            "include_shifted_candles": 3,
+            "include_timeframes": ["15m", "1h", "4h"],
+            "include_corr_pairlist": ["BTC/USDT", "SOL/USDT", "ETH/USDT"],
+            "label_period_candles": 60,  # Extended prediction horizon
+            "include_shifted_candles": 2,
+            "weight_factor": 0.9,
+            "principal_component_analysis": False,
+            "use_SVM_to_remove_outliers": True,
+            "SVM_parameters": {"nu": 0.1},
+            "DI_threshold": 0,  # Disable DI filtering
+            "indicator_periods_candles": [14, 20]
         },
         "data_split_parameters": {
             "test_size": 0.2,
-            "shuffle": False,
+            "shuffle": True,
         },
         "model_training_parameters": {
-            "n_estimators": 100,
-            "learning_rate": 0.1,
-            "num_leaves": 31,
-            "verbose": -1,
+            "n_estimators": 300,
+            "learning_rate": 0.03,
+            "max_depth": 6,
+            "subsample": 0.8,
+            "colsample_bytree": 0.8,
+            "reg_lambda": 1.0,
+            "objective": "reg:squarederror",
+            "eval_metric": "rmse",
+            "early_stopping_rounds": 20,
+            "verbose": 0,
         },
+        "data_kitchen": {
+            "feature_parameters": {
+                "DI_threshold": 0  # Ensure DI filtering is disabled
+            }
+        }
     }
 
-    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 calculate_macd(self, dataframe: DataFrame) -> DataFrame:
+        """Calculate MACD indicators and handle exceptions."""
+        try:
+            macd = ta.MACD(dataframe, fastperiod=12, slowperiod=26, signalperiod=9)
+            dataframe["macd"] = macd["macd"].replace([np.inf, -np.inf], np.nan).ffill().fillna(0)
+            dataframe["macdsignal"] = macd["macdsignal"].replace([np.inf, -np.inf], np.nan).ffill().fillna(0)
+            logger.info("MACD calculated successfully.")
+        except Exception as e:
+            logger.error(f"Error calculating MACD: {str(e)}")
+            dataframe["macd"] = np.nan
+            dataframe["macdsignal"] = np.nan
+        return dataframe
 
     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.replace([np.inf, -np.inf], 0, inplace=True)
-        dataframe.ffill(inplace=True)
-        dataframe.fillna(0, inplace=True)
-        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.replace([np.inf, -np.inf], 0, inplace=True)
-        dataframe.fillna(method='ffill', inplace=True)
-        dataframe.fillna(0, inplace=True)
-        return dataframe
-
-    def feature_engineering_standard(self, dataframe: DataFrame, metadata: dict, **kwargs) -> DataFrame:
-        dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek
-        dataframe["%-hour_of_day"] = dataframe["date"].dt.hour
-        dataframe.replace([np.inf, -np.inf], 0, inplace=True)
-        dataframe.fillna(method='ffill', inplace=True)
-        dataframe.fillna(0, inplace=True)
-        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"]
-            # 生成 %-volatility 特征
-            dataframe["%-volatility"] = dataframe["close"].pct_change().rolling(20).std()
-            
-            # 单一回归目标
-            dataframe["&-buy_rsi"] = ta.RSI(dataframe, timeperiod=14).shift(-label_period)
-            
-            # 数据清理
-            for col in ["&-buy_rsi", "%-volatility"]:
-                dataframe[col].replace([np.inf, -np.inf], 0, inplace=True)
-                dataframe[col].fillna(method='ffill', inplace=True)
-                dataframe[col].fillna(0, inplace=True)
-                if dataframe[col].isna().any():
-                    logger.warning(f"目标列 {col} 仍包含 NaN，检查数据生成逻辑")
-        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']}")
-        dataframe = self.freqai.start(dataframe, metadata, self)
-        
-        # 计算传统指标
+        """Enhanced feature engineering with cross-timeframe and momentum indicators."""
+        # Standard technical indicators
         dataframe["rsi"] = ta.RSI(dataframe, timeperiod=14)
+        dataframe["sma20"] = ta.SMA(dataframe["close"], timeperiod=20)
+        dataframe["ema50"] = ta.EMA(dataframe["close"], timeperiod=50)
+        dataframe["atr"] = ta.ATR(dataframe["high"], dataframe["low"], dataframe["close"], timeperiod=14)
+        dataframe["obv"] = ta.OBV(dataframe["close"], dataframe["volume"])
+        dataframe["adx"] = ta.ADX(dataframe["high"], dataframe["low"], dataframe["close"], timeperiod=14)
+        dataframe["momentum"] = ta.MOM(dataframe["close"], timeperiod=14)
+        dataframe["price_sma_diff"] = (dataframe["close"] - dataframe["sma20"]) / dataframe["sma20"]
+
+        # 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["tema"] = ta.TEMA(dataframe, timeperiod=9)
+        dataframe["bb_width"] = (bollinger["upper"] - bollinger["lower"]) / bollinger["mid"]
 
-        # 生成 up_or_down 信号（非 FreqAI 目标）
-        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
-        )
+        # Cross-timeframe features
+        for tf in ["1h", "4h"]:
+            tf_data = self.dp.get_pair_dataframe(pair=metadata["pair"], timeframe=tf)
+            if not tf_data.empty:
+                dataframe[f"rsi_{tf}"] = ta.RSI(tf_data, timeperiod=14)
+                bollinger_tf = qtpylib.bollinger_bands(qtpylib.typical_price(tf_data), window=20, stds=2)
+                dataframe[f"bb_width_{tf}"] = (bollinger_tf["upper"] - bollinger_tf["lower"]) / bollinger_tf["mid"]
 
-        # 动态设置参数
-        if "&-buy_rsi" in dataframe.columns:
-            # 派生其他目标
-            dataframe["&-sell_rsi"] = dataframe["&-buy_rsi"] + 30
-            dataframe["%-volatility"] = dataframe["close"].pct_change().rolling(20).std()
-            dataframe["&-stoploss"] = -0.1 - (dataframe["%-volatility"] * 10).clip(0, 0.25)
-            dataframe["&-roi_0"] = (dataframe["close"].shift(-label_period) / dataframe["close"] - 1).clip(0, 0.2)
-            
-            # 限制预测值，添加平滑
-            dataframe["buy_rsi_pred"] = dataframe["&-buy_rsi"].rolling(5).mean().clip(10, 50)
-            dataframe["buy_rsi_pred"].fillna(dataframe["buy_rsi_pred"].mean(), inplace=True)
-            if dataframe["buy_rsi_pred"].isna().any():
-                logger.warning("buy_rsi_pred 列包含 NaN，已填充为默认值")
-            dataframe["sell_rsi_pred"] = dataframe["&-sell_rsi"].rolling(5).mean().clip(50, 90)
-            dataframe["sell_rsi_pred"].fillna(dataframe["sell_rsi_pred"].mean(), inplace=True)
-            if dataframe["sell_rsi_pred"].isna().any():
-                logger.warning("sell_rsi_pred 列包含 NaN，已填充为默认值")
-            dataframe["stoploss_pred"] = dataframe["&-stoploss"].clip(-0.35, -0.1)
-            dataframe["stoploss_pred"].fillna(dataframe["stoploss_pred"].mean(), inplace=True)
-            if dataframe["stoploss_pred"].isna().any():
-                logger.warning("stoploss_pred 列包含 NaN，已填充为默认值")
-            dataframe["roi_0_pred"] = dataframe["&-roi_0"].clip(0.01, 0.2)
-            dataframe["roi_0_pred"].fillna(dataframe["roi_0_pred"].mean(), inplace=True)
-            if dataframe["roi_0_pred"].isna().any():
-                logger.warning("roi_0_pred 列包含 NaN，已填充为默认值")
-                        
-            # 检查预测值
-            for col in ["buy_rsi_pred", "sell_rsi_pred", "stoploss_pred", "roi_0_pred", "&-sell_rsi", "&-stoploss", "&-roi_0"]:
-                if dataframe[col].isna().any():
-                    logger.warning(f"列 {col} 包含 NaN，填充为默认值")
-                    dataframe[col].fillna(dataframe[col].mean(), inplace=True)
-            
-            # 动态追踪止盈
-            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)
-            
-            # 设置策略级参数
-            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(dataframe["trailing_stop_positive"].iloc[-1])
-            self.trailing_stop_positive_offset = float(dataframe["trailing_stop_positive_offset"].iloc[-1])
-            
-            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}")
-        
-        dataframe.replace([np.inf, -np.inf], 0, inplace=True)
-        dataframe.fillna(method='ffill', inplace=True)
-        dataframe.fillna(0, inplace=True)
-        
-        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()}")
+        # Correlated pair features
+        if metadata["pair"] == "SOL/USDT":
+            btc_data = self.dp.get_pair_dataframe(pair="BTC/USDT", timeframe=self.timeframe)
+            if not btc_data.empty:
+                dataframe["btc_rsi"] = ta.RSI(btc_data, timeperiod=14)
+                dataframe["btc_price_change"] = btc_data["close"].pct_change()
+                dataframe["btc_volatility"] = btc_data["close"].pct_change().rolling(20).std()
 
+        # Data cleaning
+        for col in dataframe.columns:
+            if dataframe[col].dtype in ["float64", "int64"]:
+                dataframe[col] = dataframe[col].replace([np.inf, -np.inf], np.nan).ffill().fillna(dataframe[col].median())
+        logger.info(f"Feature engineering completed, features: {len(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 feature_engineering_expand_basic(self, dataframe: DataFrame, metadata: dict, **kwargs) -> DataFrame:
+        """Basic feature engineering for FreqAI."""
+        dataframe["%-pct-change"] = dataframe["close"].pct_change()
+        dataframe["%-raw_volume"] = dataframe["volume"]
+        dataframe["%-raw_price"] = dataframe["close"]
+        for col in dataframe.columns:
+            if dataframe[col].dtype in ["float64", "int64"]:
+                dataframe[col] = dataframe[col].replace([np.inf, -np.inf], np.nan).ffill().fillna(dataframe[col].median())
+        return dataframe
 
-    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
+    def feature_engineering_standard(self, dataframe: DataFrame, metadata: dict, **kwargs) -> DataFrame:
+        """Standard feature engineering for temporal features."""
+        dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek
+        dataframe["%-hour_of_day"] = dataframe["date"].dt.hour
+        for col in dataframe.columns:
+            if dataframe[col].dtype in ["float64", "int64"]:
+                dataframe[col] = dataframe[col].replace([np.inf, -np.inf], np.nan).ffill().fillna(dataframe[col].median())
+        return dataframe
+
+    def set_freqai_targets(self, dataframe: DataFrame, metadata: dict, **kwargs) -> DataFrame:
+        """Set FreqAI prediction targets with standardized and transformed values."""
+        logger.info(f"Setting FreqAI targets for pair: {metadata['pair']}")
+        if "close" not in dataframe.columns:
+            logger.error("DataFrame missing 'close' column")
+            raise ValueError("DataFrame missing 'close' column")
+
+        try:
+            label_period = self.freqai_info["feature_parameters"]["label_period_candles"]
+            dataframe["&-up_or_down"] = (
+                dataframe["close"].shift(-label_period) - dataframe["close"]
+            ) / dataframe["close"]
+            # Standardize target values
+            dataframe["&-up_or_down"] = (
+                dataframe["&-up_or_down"] - dataframe["&-up_or_down"].mean()
+            ) / dataframe["&-up_or_down"].std()
+            # Apply logarithmic transformation to amplify signals
+            dataframe["&-up_or_down"] = np.log1p(dataframe["&-up_or_down"].abs()) * np.sign(dataframe["&-up_or_down"])
+            dataframe["&-up_or_down"] = dataframe["&-up_or_down"].replace([np.inf, -np.inf], np.nan).ffill().fillna(0)
+            dataframe["&-buy_rsi"] = ta.RSI(dataframe, timeperiod=14)
+            dataframe["%-volatility"] = dataframe["close"].pct_change().rolling(20).std()
+
+            for col in ["&-buy_rsi", "&-up_or_down", "%-volatility"]:
+                dataframe[col] = dataframe[col].replace([np.inf, -np.inf], np.nan).ffill().fillna(dataframe[col].median())
+        except Exception as e:
+            logger.error(f"Failed to create FreqAI targets: {str(e)}")
+            raise
+        logger.info(f"Target column shape: {dataframe['&-up_or_down'].shape}")
+        logger.info(f"Target preview:\n{dataframe[['&-up_or_down', '&-buy_rsi']].head().to_string()}")
+        return dataframe
+
+    def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
+        """Populate indicators and dynamic strategy parameters."""
+        logger.info(f"Processing pair: {metadata['pair']}")
+        dataframe = self.freqai.start(dataframe, metadata, self)
+
+        # Calculate technical indicators
+        dataframe["rsi"] = ta.RSI(dataframe, timeperiod=14)
+        dataframe["atr"] = ta.ATR(dataframe["high"], dataframe["low"], dataframe["close"], 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 = self.calculate_macd(dataframe)
+
+        # Dynamic parameter settings
+        if "&-buy_rsi" in dataframe.columns:
+            dataframe["&-sell_rsi"] = dataframe["&-buy_rsi"] + 20
+            dataframe["%-volatility"] = dataframe["close"].pct_change().rolling(20).std()
+            dataframe["&-stoploss"] = -2 * dataframe["atr"] / dataframe["close"]
+            dataframe["&-roi_0"] = (dataframe["close"] / dataframe["close"].shift(10) - 1).clip(0, 0.1).fillna(0)
+
+            # Dynamic predictions
+            dataframe["buy_rsi_pred"] = dataframe["rsi"].rolling(window=10).mean().clip(20, 50).fillna(dataframe["rsi"].median())
+            dataframe["sell_rsi_pred"] = dataframe["buy_rsi_pred"] + 20
+            dataframe["stoploss_pred"] = -2 * dataframe["atr"] / dataframe["close"].clip(-0.2, -0.05)
+            dataframe["roi_0_pred"] = dataframe["&-roi_0"].clip(0.01, 0.1).fillna(dataframe["&-roi_0"].mean())
+
+            for col in ["&-stoploss", "&-roi_0", "buy_rsi_pred", "sell_rsi_pred", "stoploss_pred", "roi_0_pred"]:
+                dataframe[col] = dataframe[col].replace([np.inf, -np.inf], np.nan).ffill().fillna(dataframe[col].mean())
+
+            # Set strategy parameters
+            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(dataframe["stoploss_pred"].iloc[-1])
+            self.minimal_roi = {
+                0: float(self.roi_0.value) + (dataframe["atr"].iloc[-1] / dataframe["close"].iloc[-1]),
+                15: float(self.roi_15.value) * 0.8,
+                30: float(self.roi_30.value) * 0.5,
+                60: 0
+            }
+            # Dynamic trailing stop
+            self.trailing_stop_positive = float(1.5 * dataframe["atr"].iloc[-1] / dataframe["close"].iloc[-1])
+            self.trailing_stop_positive_offset = float(2.5 * dataframe["atr"].iloc[-1] / dataframe["close"].iloc[-1])
+
+        # Data cleaning
+        dataframe.ffill(inplace=True)
+        dataframe.fillna(dataframe.mean(numeric_only=True), inplace=True)
+        logger.info(f"&-up_or_down stats:\n{dataframe['&-up_or_down'].describe().to_string()}")
+        return dataframe
+
+    def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
+        """Generate entry signals with relaxed conditions."""
+        # Validate required columns
+        required_cols = ["rsi", "buy_rsi_pred", "volume", "bb_middleband", "macd", "macdsignal", "&-up_or_down"]
+        if not all(col in dataframe.columns for col in required_cols):
+            logger.error(f"Missing required columns: {set(required_cols) - set(dataframe.columns)}")
+            return dataframe
+
+        dataframe = self.calculate_macd(dataframe)
+        enter_long_conditions = [
+            dataframe["rsi"] < dataframe["buy_rsi_pred"],
+            dataframe["volume"] > dataframe["volume"].rolling(window=10).mean() * 1.0,
+            dataframe["close"] > dataframe["bb_middleband"],
+            dataframe["macd"] > dataframe["macdsignal"],
+            dataframe["&-up_or_down"] > (0.001 if metadata["pair"] == "BTC/USDT" else 0.0015)  # Lower threshold for BTC
         ]
-        if exit_long_conditions:
-            df.loc[
-                reduce(lambda x, y: x & y, exit_long_conditions),
-                "exit_long"
-            ] = 1
-        return df
+        # Combine conditions into a DataFrame
+        conditions_df = pd.concat(enter_long_conditions, axis=1)
+        dataframe.loc[conditions_df.sum(axis=1) >= 3, ["enter_long", "enter_tag"]] = (1, "long")
+        return dataframe
+
+    def populate_exit_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
+        """Generate exit signals with confirmation."""
+        # Validate required columns
+        required_cols = ["rsi", "sell_rsi_pred", "bb_middleband", "macd", "macdsignal", "&-up_or_down"]
+        if not all(col in dataframe.columns for col in required_cols):
+            logger.error(f"Missing required columns: {set(required_cols) - set(dataframe.columns)}")
+            return dataframe
+
+        exit_long_conditions = [
+            dataframe["rsi"] > dataframe["sell_rsi_pred"],
+            dataframe["close"] < dataframe["bb_middleband"],
+            dataframe["macd"] < dataframe["macdsignal"],
+            dataframe["&-up_or_down"] < -0.005
+        ]
+        # Combine conditions into a DataFrame
+        conditions_df = pd.concat(exit_long_conditions, axis=1)
+        # Require confirmation: at least 3 conditions met for two consecutive candles
+        exit_signal = (conditions_df.sum(axis=1) >= 3) & (conditions_df.shift(1).sum(axis=1) >= 3)
+        dataframe.loc[exit_signal, "exit_long"] = 1
+        return dataframe
 
     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:
+        """Confirm trade entry to avoid slippage."""
         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
         return True
+

请啊!

@@ -0,0 +1,233 @@
+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 FreqaiExampleStrategy(IStrategy):
+    # 移除硬编码的 minimal_roi 和 stoploss，改为动态适配
+    minimal_roi = {}  # 将在 populate_indicators 中动态生成
+    stoploss = 0.0   # 将在 populate_indicators 中动态设置
+    trailing_stop = True
+    process_only_new_candles = True
+    use_exit_signal = True
+    startup_candle_count: int = 40
+    can_short = False
+
+    # 参数定义：FreqAI 动态适配 buy_rsi 和 sell_rsi，禁用 Hyperopt 优化
+    buy_rsi = IntParameter(low=10, high=50, default=27, space="buy", optimize=False, load=True)
+    sell_rsi = IntParameter(low=50, high=90, default=59, space="sell", optimize=False, load=True)
+
+    # 为 Hyperopt 优化添加 ROI 和 stoploss 参数
+    roi_0 = DecimalParameter(low=0.01, high=0.2, default=0.038, space="roi", optimize=True, load=True)
+    roi_15 = DecimalParameter(low=0.005, high=0.1, default=0.027, space="roi", optimize=True, load=True)
+    roi_30 = DecimalParameter(low=0.001, high=0.05, default=0.009, space="roi", optimize=True, load=True)
+    stoploss_param = DecimalParameter(low=-0.35, high=-0.1, default=-0.182, space="stoploss", optimize=True, load=True)
+
+    # FreqAI 配置
+    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": 100,
+            "learning_rate": 0.1,
+            "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.replace([np.inf, -np.inf], 0, inplace=True)
+        dataframe.ffill(inplace=True)
+        dataframe.fillna(0, inplace=True)
+        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.replace([np.inf, -np.inf], 0, inplace=True)
+        dataframe.fillna(method='ffill', inplace=True)
+        dataframe.fillna(0, inplace=True)
+        return dataframe
+
+    def feature_engineering_standard(self, dataframe: DataFrame, metadata: dict, **kwargs) -> DataFrame:
+        dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek
+        dataframe["%-hour_of_day"] = dataframe["date"].dt.hour
+        dataframe.replace([np.inf, -np.inf], 0, inplace=True)
+        dataframe.fillna(method='ffill', inplace=True)
+        dataframe.fillna(0, inplace=True)
+        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"]
+            # 生成 %-volatility 特征
+            dataframe["%-volatility"] = dataframe["close"].pct_change().rolling(20).std()
+            
+            # 单一回归目标
+            # 移除对未来的数据依赖
+            dataframe["&-buy_rsi"] = ta.RSI(dataframe, timeperiod=14)
+            
+            # 数据清理
+            for col in ["&-buy_rsi", "%-volatility"]:
+                dataframe[col].replace([np.inf, -np.inf], 0, inplace=True)
+                dataframe[col].fillna(method='ffill', inplace=True)
+                dataframe[col].fillna(0, inplace=True)
+                if dataframe[col].isna().any():
+                    logger.warning(f"目标列 {col} 仍包含 NaN，检查数据生成逻辑")
+        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']}")
+        dataframe = self.freqai.start(dataframe, metadata, self)
+        
+        # 计算传统指标
+        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)
+        
+        # 生成 up_or_down 信号（非 FreqAI 目标）
+        label_period = self.freqai_info["feature_parameters"]["label_period_candles"]
+        # 使用历史数据生成 up_or_down 信号
+        dataframe["up_or_down"] = np.where(
+            dataframe["close"] > dataframe["close"].shift(1), 1, 0
+        )
+        
+        # 动态设置参数
+        if "&-buy_rsi" in dataframe.columns:
+            # 派生其他目标
+            dataframe["&-sell_rsi"] = dataframe["&-buy_rsi"] + 30
+            dataframe["%-volatility"] = dataframe["close"].pct_change().rolling(20).std()
+            dataframe["&-stoploss"] = -0.1 - (dataframe["%-volatility"] * 10).clip(0, 0.25)
+            dataframe["&-roi_0"] = (dataframe["close"] / dataframe["close"].shift(label_period) - 1).clip(0, 0.2)
+            
+            # 简化动态参数生成逻辑
+            dataframe["buy_rsi_pred"] = dataframe["&-buy_rsi"].clip(10, 50)
+            dataframe["sell_rsi_pred"] = dataframe["&-buy_rsi"] + 30
+            dataframe["stoploss_pred"] = -0.1 - (dataframe["%-volatility"] * 10).clip(0, 0.25)
+            dataframe["roi_0_pred"] = dataframe["&-roi_0"].clip(0.01, 0.2)
+                        
+            # 检查预测值
+            for col in ["buy_rsi_pred", "sell_rsi_pred", "stoploss_pred", "roi_0_pred", "&-sell_rsi", "&-stoploss", "&-roi_0"]:
+                if dataframe[col].isna().any():
+                    logger.warning(f"列 {col} 包含 NaN，填充为默认值")
+                    dataframe[col].fillna(dataframe[col].mean(), inplace=True)
+            
+            # 更保守的止损和止盈设置
+            dataframe["trailing_stop_positive"] = (dataframe["roi_0_pred"] * 0.3).clip(0.01, 0.2)
+            dataframe["trailing_stop_positive_offset"] = (dataframe["roi_0_pred"] * 0.5).clip(0.01, 0.3)
+            
+            # 设置策略级参数
+            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(dataframe["trailing_stop_positive"].iloc[-1])
+            self.trailing_stop_positive_offset = float(dataframe["trailing_stop_positive_offset"].iloc[-1])
+            
+            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}")
+        
+        dataframe.replace([np.inf, -np.inf], 0, inplace=True)
+        dataframe.fillna(method='ffill', inplace=True)
+        dataframe.fillna(0, inplace=True)
+        
+        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()}")
+        
+        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["volume"] > 0
+        ]
+        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["volume"] > 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:
+        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
+        return True