Debugging

app.py

@@ -56,10 +56,14 @@ def process_player_data(player_id, mmr, comf_1, comf_2, comf_3, comf_4, comf_5):
         # Read the example row from prediction_data_prepped.csv to get the expected structure
         try:
             pred_data = pd.read_csv("prediction_data_prepped.csv")
+            print("\nReference columns from prediction_data_prepped.csv:")
+            print(sorted(pred_data.columns.tolist()))
+            print(f"Number of reference columns: {len(pred_data.columns)}")
+            
             if not pred_data.empty:
                 # Get column structure from the first row
                 for col in pred_data.columns:
-                    if col not in player_data:
+                    if col not in player_data and col != 'Predicted_Cost':  # Skip the target variable
                         player_data[col] = 0
         except Exception as e:
             print(f"Warning - Error reading prediction data template: {str(e)}")
@@ -86,30 +90,32 @@ def process_player_data(player_id, mmr, comf_1, comf_2, comf_3, comf_4, comf_5):
         # Convert to DataFrame for consistency with training
         df = pd.DataFrame([player_data])
         
-        # Load reference data structure if available
-        try:
-            ref_data = pd.read_csv("result_prediction_data_prepped.csv")
-            if not ref_data.empty:
-                # Get all columns from reference data
-                for col in ref_data.columns:
-                    if col not in df.columns:
-                        df[col] = 0
-                # Reorder columns to match reference data
-                df = df[ref_data.columns]
-        except Exception as e:
-            print(f"Warning - Error matching reference data structure: {str(e)}")
-            
-        # Final check for required columns
-        if FEATURE_COLUMNS:
-            for col in FEATURE_COLUMNS:
-                if col not in df.columns:
-                    df[col] = 0
-            # Reorder columns to match model input
-            df = df[FEATURE_COLUMNS]
+        # Print out the columns we have in our processed data
+        print("\nProcessed data columns:")
+        print(sorted(df.columns.tolist()))
+        print(f"Number of processed columns: {len(df.columns)}")
         
-        print(f"Processed data columns: {df.columns.tolist()}")
-        print(f"Number of features: {len(df.columns)}")
+        # Find missing columns
+        expected_cols = set(pred_data.columns) - {'Predicted_Cost'}  # Remove target variable
+        actual_cols = set(df.columns)
+        
+        missing_cols = expected_cols - actual_cols
+        extra_cols = actual_cols - expected_cols
+        
+        if missing_cols:
+            print("\nMissing columns:")
+            print(sorted(list(missing_cols)))
+            
+        if extra_cols:
+            print("\nExtra columns:")
+            print(sorted(list(extra_cols)))
+            
+        # Ensure we have all needed columns and remove any extras
+        for col in missing_cols:
+            df[col] = 0
+        df = df[list(expected_cols)]
         
+        print(f"\nFinal number of columns: {len(df.columns)}")
         return df
     except Exception as e:
         return f"Error processing player data: {str(e)}"