imporve features

services/training/app/ml/enhanced_features.py

@@ -7,6 +7,7 @@ import pandas as pd
 import numpy as np
 from typing import Dict, List, Optional
 import structlog
+from shared.ml.feature_calculator import HistoricalFeatureCalculator
 
 logger = structlog.get_logger()
 
@@ -19,10 +20,12 @@ class AdvancedFeatureEngineer:
 
     def __init__(self):
         self.feature_columns = []
+        self.feature_calculator = HistoricalFeatureCalculator()
 
     def add_lagged_features(self, df: pd.DataFrame, lag_days: List[int] = None) -> pd.DataFrame:
         """
         Add lagged demand features for capturing recent trends.
+        Uses shared feature calculator for consistency with prediction service.
 
         Args:
             df: DataFrame with 'quantity' column
@@ -34,14 +37,20 @@ class AdvancedFeatureEngineer:
         if lag_days is None:
             lag_days = [1, 7, 14]
 
-        df = df.copy()
+        # Use shared calculator for consistent lag calculation
+        df = self.feature_calculator.calculate_lag_features(
+            df,
+            lag_days=lag_days,
+            mode='training'
+        )
 
+        # Update feature columns list
         for lag in lag_days:
             col_name = f'lag_{lag}_day'
-            df[col_name] = df['quantity'].shift(lag)
-            self.feature_columns.append(col_name)
+            if col_name not in self.feature_columns:
+                self.feature_columns.append(col_name)
 
-        logger.info(f"Added {len(lag_days)} lagged features", lags=lag_days)
+        logger.info(f"Added {len(lag_days)} lagged features (using shared calculator)", lags=lag_days)
         return df
 
     def add_rolling_features(
@@ -52,6 +61,7 @@ class AdvancedFeatureEngineer:
     ) -> pd.DataFrame:
         """
         Add rolling statistics (mean, std, max, min).
+        Uses shared feature calculator for consistency with prediction service.
 
         Args:
             df: DataFrame with 'quantity' column
@@ -67,24 +77,22 @@ class AdvancedFeatureEngineer:
         if features is None:
             features = ['mean', 'std', 'max', 'min']
 
-        df = df.copy()
+        # Use shared calculator for consistent rolling calculation
+        df = self.feature_calculator.calculate_rolling_features(
+            df,
+            windows=windows,
+            statistics=features,
+            mode='training'
+        )
 
+        # Update feature columns list
         for window in windows:
             for feature in features:
                 col_name = f'rolling_{feature}_{window}d'
+                if col_name not in self.feature_columns:
+                    self.feature_columns.append(col_name)
 
-                if feature == 'mean':
-                    df[col_name] = df['quantity'].rolling(window=window, min_periods=max(1, window // 2)).mean()
-                elif feature == 'std':
-                    df[col_name] = df['quantity'].rolling(window=window, min_periods=max(1, window // 2)).std()
-                elif feature == 'max':
-                    df[col_name] = df['quantity'].rolling(window=window, min_periods=max(1, window // 2)).max()
-                elif feature == 'min':
-                    df[col_name] = df['quantity'].rolling(window=window, min_periods=max(1, window // 2)).min()
-
-                self.feature_columns.append(col_name)
-
-        logger.info(f"Added rolling features", windows=windows, features=features)
+        logger.info(f"Added rolling features (using shared calculator)", windows=windows, features=features)
         return df
 
     def add_day_of_week_features(self, df: pd.DataFrame, date_column: str = 'date') -> pd.DataFrame:
@@ -203,6 +211,7 @@ class AdvancedFeatureEngineer:
     def add_trend_features(self, df: pd.DataFrame, date_column: str = 'date') -> pd.DataFrame:
         """
         Add trend-based features.
+        Uses shared feature calculator for consistency with prediction service.
 
         Args:
             df: DataFrame with date and quantity
@@ -211,27 +220,18 @@ class AdvancedFeatureEngineer:
         Returns:
             DataFrame with trend features
         """
-        df = df.copy()
+        # Use shared calculator for consistent trend calculation
+        df = self.feature_calculator.calculate_trend_features(
+            df,
+            mode='training'
+        )
 
-        # Days since start (linear trend proxy)
-        df['days_since_start'] = (df[date_column] - df[date_column].min()).dt.days
-
-        # Momentum indicators (recent change vs. older change)
-        if 'lag_1_day' in df.columns and 'lag_7_day' in df.columns:
-            df['momentum_1_7'] = df['lag_1_day'] - df['lag_7_day']
-            self.feature_columns.append('momentum_1_7')
-
-        if 'rolling_mean_7d' in df.columns and 'rolling_mean_30d' in df.columns:
-            df['trend_7_30'] = df['rolling_mean_7d'] - df['rolling_mean_30d']
-            self.feature_columns.append('trend_7_30')
-
-        # Velocity (rate of change)
-        if 'lag_1_day' in df.columns and 'lag_7_day' in df.columns:
-            df['velocity_week'] = (df['lag_1_day'] - df['lag_7_day']) / 7
-            self.feature_columns.append('velocity_week')
-
-        self.feature_columns.append('days_since_start')
+        # Update feature columns list
+        for feature_name in ['days_since_start', 'momentum_1_7', 'trend_7_30', 'velocity_week']:
+            if feature_name in df.columns and feature_name not in self.feature_columns:
+                self.feature_columns.append(feature_name)
 
+        logger.debug("Added trend features (using shared calculator)")
         return df
 
     def add_cyclical_encoding(self, df: pd.DataFrame) -> pd.DataFrame: