Checking onboardin flow - fix 4

services/training/app/ml/prophet_manager.py

@@ -18,6 +18,7 @@ import joblib
 from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
 import json
 from pathlib import Path
+import math
 
 from app.core.config import settings
 
@@ -177,8 +178,16 @@ class BakeryProphetManager:
         """Prepare data for Prophet training"""
         prophet_data = df.copy()
         
-        # Ensure ds column is datetime
-        prophet_data['ds'] = pd.to_datetime(prophet_data['ds'])
+        # Prophet column mapping
+        if 'date' in prophet_data.columns:
+            prophet_data['ds'] = prophet_data['date']
+        if 'quantity' in prophet_data.columns:
+            prophet_data['y'] = prophet_data['quantity']
+    
+        # ✅ CRITICAL FIX: Remove timezone from ds column
+        if 'ds' in prophet_data.columns:
+            prophet_data['ds'] = pd.to_datetime(prophet_data['ds']).dt.tz_localize(None)
+            logger.info(f"Removed timezone from ds column")
         
         # Handle missing values in target
         if prophet_data['y'].isna().any():
@@ -345,7 +354,14 @@ class BakeryProphetManager:
             rmse = np.sqrt(mse)
             
             # MAPE (Mean Absolute Percentage Error)
-            mape = np.mean(np.abs((y_true - y_pred) / y_true)) * 100
+            non_zero_mask = y_true != 0
+            if np.sum(non_zero_mask) == 0:
+                mape = 0.0  # Return 0 instead of Infinity
+            else:
+                mape_values = np.abs((y_true[non_zero_mask] - y_pred[non_zero_mask]) / y_true[non_zero_mask])
+                mape = np.mean(mape_values) * 100
+                if math.isinf(mape) or math.isnan(mape):
+                    mape = 0.0
             
             # R-squared
             r2 = r2_score(y_true, y_pred)