Debugging+++

services/market_services.py

@@ -73,8 +73,17 @@ def get_market_prediction(model, df_full, commodity, last_known_date):
     """
     Iteratively predicts the next 180 days.
     """
-    print(f"--- PREDICTION STARTED FOR {commodity} ---") # DEBUG PRINT
+    print(f"--- PREDICTION STARTED FOR {commodity} ---")
     
+    # --- FIX START: DISABLE FEATURE NAME CHECK ---
+    # This tells XGBoost: "Don't check column names, just trust the order of numbers I give you"
+    try:
+        booster = model.get_booster()
+        booster.feature_names = None
+    except Exception:
+        pass # If it fails, we proceed anyway
+    # --- FIX END ---
+
     df_commodity = df_full[df_full['commodity'] == commodity]
     df_daily = df_commodity.groupby(df_commodity.index).agg({'modal_price': 'mean'})
     
@@ -95,29 +104,20 @@ def get_market_prediction(model, df_full, commodity, last_known_date):
         if target_row[feature_names].isna().any():
             continue
 
-        # --- CRITICAL FIX SECTION ---
-        # 1. Extract values
+        # 1. Extract values as a plain Numpy Array
+        # Reshape to (1, 11) -> 1 row, 11 features
         input_values = target_row[feature_names].values.reshape(1, -1)
         
-        # 2. Create DataFrame
-        input_df = pd.DataFrame(input_values, columns=feature_names)
-        
-        # 3. DEBUG: Check if we are passing a DataFrame
-        # If you don't see this print in your terminal, the old code is still running!
-        if date == future_dates[0]: 
-            print("TYPE CHECK:", type(input_df))
-            print("COLUMNS CHECK:", input_df.columns.tolist())
-
-        # 4. Predict
-        prediction = model.predict(input_df)[0]
-        # -----------------------------
+        # 2. Predict using the Numpy Array directly (Faster & Safer now)
+        # Since we disabled feature_names check, this will now work.
+        prediction = model.predict(input_values)[0]
         
         df_extended.loc[date, 'modal_price'] = prediction
     
     daily_forecast_df = df_extended.loc[future_dates].copy()
     daily_forecast_df.rename(columns={'modal_price': 'forecast'}, inplace=True)
     
-    print("--- PREDICTION SUCCESS ---") # DEBUG PRINT
+    print("--- PREDICTION SUCCESS ---")
     return daily_forecast_df