Add improvements

2026-01-12 14:24:14 +01:00
parent 6037faaf8c
commit 230bbe6a19
61 changed files with 1668 additions and 894 deletions
--- a/services/training/app/ml/data_processor.py
+++ b/services/training/app/ml/data_processor.py
@@ -1121,9 +1121,10 @@ class EnhancedBakeryDataProcessor:
                    output_columns=len(df.columns))

        # Fill NA values from lagged and rolling features
+        # IMPORTANT: Use forward_mean strategy to prevent data leakage (no backward fill)
        logger.debug("Starting NA value filling",
                    na_counts={col: df[col].isna().sum() for col in df.columns if df[col].isna().any()})
-        df = self.feature_engineer.fill_na_values(df, strategy='forward_backward')
+        df = self.feature_engineer.fill_na_values(df, strategy='forward_mean')
        logger.debug("NA value filling completed",
                    remaining_na_counts={col: df[col].isna().sum() for col in df.columns if df[col].isna().any()})