RL training in NN working

NN/utils/data_interface.py

@@ -303,6 +303,76 @@ class DataInterface:
         """
         return len(self.timeframes) * 5  # OHLCV features for each timeframe
 
+    def get_features(self, timeframe, n_candles=1000):
+        """
+        Get feature data with technical indicators for a specific timeframe.
+        
+        Args:
+            timeframe (str): Timeframe to get features for ('1m', '5m', etc.)
+            n_candles (int): Number of candles to get
+            
+        Returns:
+            np.ndarray: Array of feature data including technical indicators
+                        and the close price as the last column
+        """
+        # Get historical data
+        df = self.get_historical_data(timeframe=timeframe, n_candles=n_candles)
+        
+        if df is None or df.empty:
+            logger.error(f"No data available for {self.symbol} {timeframe}")
+            return None
+            
+        # Add technical indicators
+        df = self.add_technical_indicators(df)
+        
+        # Drop NaN values that might have been introduced by indicators
+        df = df.dropna()
+        
+        # Extract features (all columns except timestamp)
+        features = df.drop('timestamp', axis=1).values
+        
+        logger.info(f"Prepared {len(features)} {timeframe} feature rows with {features.shape[1]} features")
+        return features
+        
+    def add_technical_indicators(self, df):
+        """
+        Add technical indicators to the dataframe.
+        
+        Args:
+            df (pd.DataFrame): DataFrame with OHLCV data
+            
+        Returns:
+            pd.DataFrame: DataFrame with added technical indicators
+        """
+        # Make a copy to avoid modifying the original
+        df_copy = df.copy()
+        
+        # Basic price indicators
+        df_copy['returns'] = df_copy['close'].pct_change()
+        df_copy['log_returns'] = np.log(df_copy['close']/df_copy['close'].shift(1))
+        
+        # Moving Averages
+        df_copy['sma_7'] = ta.trend.sma_indicator(df_copy['close'], window=7)
+        df_copy['sma_25'] = ta.trend.sma_indicator(df_copy['close'], window=25)
+        df_copy['sma_99'] = ta.trend.sma_indicator(df_copy['close'], window=99)
+        
+        # MACD
+        macd = ta.trend.MACD(df_copy['close'])
+        df_copy['macd'] = macd.macd()
+        df_copy['macd_signal'] = macd.macd_signal()
+        df_copy['macd_diff'] = macd.macd_diff()
+        
+        # RSI
+        df_copy['rsi'] = ta.momentum.rsi(df_copy['close'], window=14)
+        
+        # Bollinger Bands
+        bollinger = ta.volatility.BollingerBands(df_copy['close'])
+        df_copy['bb_high'] = bollinger.bollinger_hband()
+        df_copy['bb_low'] = bollinger.bollinger_lband()
+        df_copy['bb_pct'] = bollinger.bollinger_pband()
+        
+        return df_copy
+
     def calculate_pnl(self, predictions, actual_prices, position_size=1.0):
         """
         Robust PnL calculator that handles:
@@ -557,33 +627,33 @@ class DataInterface:
         # Calculate technical indicators
         try:
             # Add RSI (14)
-            df['rsi'] = ta.rsi(df['close'], length=14)
+            df['rsi'] = ta.momentum.rsi(df['close'], window=14)
             
             # Add MACD
-            macd = ta.macd(df['close'])
-            df['macd'] = macd['MACD_12_26_9']
-            df['macd_signal'] = macd['MACDs_12_26_9']
-            df['macd_hist'] = macd['MACDh_12_26_9']
+            macd = ta.trend.MACD(df['close'])
+            df['macd'] = macd.macd()
+            df['macd_signal'] = macd.macd_signal()
+            df['macd_hist'] = macd.macd_diff()
             
             # Add Bollinger Bands
-            bbands = ta.bbands(df['close'], length=20)
-            df['bb_upper'] = bbands['BBU_20_2.0']
-            df['bb_middle'] = bbands['BBM_20_2.0']
-            df['bb_lower'] = bbands['BBL_20_2.0']
+            bbands = ta.volatility.BollingerBands(df['close'])
+            df['bb_upper'] = bbands.bollinger_hband()
+            df['bb_middle'] = bbands.bollinger_mavg()
+            df['bb_lower'] = bbands.bollinger_lband()
             
             # Add ATR (Average True Range)
-            df['atr'] = ta.atr(df['high'], df['low'], df['close'], length=14)
+            df['atr'] = ta.volatility.average_true_range(df['high'], df['low'], df['close'], window=14)
             
             # Add moving averages
-            df['sma_20'] = ta.sma(df['close'], length=20)
-            df['sma_50'] = ta.sma(df['close'], length=50)
-            df['ema_20'] = ta.ema(df['close'], length=20)
+            df['sma_20'] = ta.trend.sma_indicator(df['close'], window=20)
+            df['sma_50'] = ta.trend.sma_indicator(df['close'], window=50)
+            df['ema_20'] = ta.trend.ema_indicator(df['close'], window=20)
             
             # Add OBV (On-Balance Volume)
-            df['obv'] = ta.obv(df['close'], df['volume'])
+            df['obv'] = ta.volume.on_balance_volume(df['close'], df['volume'])
             
             # Add momentum indicators
-            df['mom'] = ta.mom(df['close'], length=10)
+            df['mom'] = ta.momentum.roc(df['close'], window=10)
             
             # Normalize price to previous close
             df['close_norm'] = df['close'] / df['close'].shift(1) - 1