Iteration 20

app.py

@@ -27,18 +27,18 @@ def load_reference_data(player_id):
     """Load reference prediction data and input features"""
     try:
         # Read the full CSV to get both input features and prediction
-        ref_df = pd.read_csv(f"{player_id}.csv", encoding='utf-8')
+        ref_df = pd.read_csv(f"{player_id}.csv", encoding='utf-8', index_col=0)
         
-        # Extract the features
-        features = ref_df[ref_df.index != 'Predicted_Cost']
-        print("\nReference features:")
-        print(features)
+        # Remove the prediction row and convert to a proper format
+        features = ref_df[ref_df.index != 'Predicted_Cost'].iloc[:, 0]
+        prediction = ref_df.loc['Predicted_Cost', f"{player_id}_S34"]
         
-        # Get the prediction from the last row
-        prediction = ref_df.iloc[-1][f"{player_id}_S34"]
-        print(f"Reference prediction: {prediction}")
+        print("\nReference data loaded:")
+        for idx in ['mmr', 'p1', 'p2', 'p3', 'p4', 'p5', 'count', 'mean', 'std', 'min', 'max', 'sum']:
+            if idx in features.index:
+                print(f"{idx}: {features[idx]}")
         
-        return features, prediction
+        return features, float(prediction)
     except Exception as e:
         print(f"Could not load reference data: {e}")
         return None, None
@@ -144,12 +144,15 @@ def predict_cost(user_id, mmr, comf_1, comf_2, comf_3, comf_4, comf_5):
         
         print("\nComparing processed data with reference:")
         if reference_features is not None:
-            for col in processed_data.columns:
-                if col in reference_features.index:
-                    print(f"{col}:")
-                    print(f"  Our value: {processed_data[col].iloc[0]}")
-                    print(f"  Ref value: {reference_features.loc[col, player_id + '_S34']}")
-        
+            our_data = processed_data.iloc[0]
+            for idx in ['mmr', 'p1', 'p2', 'p3', 'p4', 'p5', 'count', 'mean', 'std', 'min', 'max', 'sum']:
+                our_val = our_data[idx]
+                ref_val = reference_features[idx] if idx in reference_features.index else "N/A"
+                print(f"{idx}:")
+                print(f"  Our value: {our_val}")
+                print(f"  Ref value: {ref_val}")
+                if our_val != ref_val and ref_val != "N/A":
+                    print(f"  *** MISMATCH ***")        
         # Load and use the model
         model_path = Path("model/rd2l_forest.onnx")
         if not model_path.exists():