update

app.py

@@ -222,53 +222,53 @@ if uploaded_file:
 
     xgb_preds = xgb.predict(input_df[xgb_training_features])
 
-    # 🔥 List of features RandomForest was trained with
-    rf_training_features = [
-        "age_level", "gender", "product", "campaign_id", "webpage_id",
-        "product_category_1", "product_category_2", "user_group_id",
-        "user_depth", "city_development_index", "var_1",
-        "click_sum_age_sex_prod", "click_count_age_sex_prod",
-        "unique_campaigns_age_sex_prod", "unique_webpages_age_sex_prod",
-        "click_sum_city_age_prod", "click_count_city_age_prod",
-        "unique_campaigns_city_age_prod", "unique_webpages_city_age_prod"
-    ]
-
-    # ✅ Ensure all training features exist in `input_df`
-    for col in rf_training_features:
-        if col not in input_df.columns:
-            input_df[col] = 0  # Default missing columns to 0
-
-    # Get intersection of trained features and current input_df columns
-    common_features = list(set(rf.feature_names_in_) & set(input_df.columns))
-
-    # Select only the matching features
-    input_df_rf = input_df[common_features]
-
-    # Predict without needing to add missing features
-    rf_preds = rf.predict(input_df_rf)
-
-
-    print("RF Model Trained Features:", rf.feature_names_in_)
-    print("Input Data Features:", input_df_rf.columns.tolist())
-
-    # Debugging: Check for missing or extra features
-    missing_features = set(rf.feature_names_in_) - set(input_df_rf.columns)
-    extra_features = set(input_df_rf.columns) - set(rf.feature_names_in_)
-
-    print("Missing Features in Input:", missing_features)
-    print("Extra Features in Input:", extra_features)
-    # ✅ Make Predictions with RandomForest
-    rf_preds = rf.predict(input_df_rf)
+    # # 🔥 List of features RandomForest was trained with
+    # rf_training_features = [
+    #     "age_level", "gender", "product", "campaign_id", "webpage_id",
+    #     "product_category_1", "product_category_2", "user_group_id",
+    #     "user_depth", "city_development_index", "var_1",
+    #     "click_sum_age_sex_prod", "click_count_age_sex_prod",
+    #     "unique_campaigns_age_sex_prod", "unique_webpages_age_sex_prod",
+    #     "click_sum_city_age_prod", "click_count_city_age_prod",
+    #     "unique_campaigns_city_age_prod", "unique_webpages_city_age_prod"
+    # ]
+    #
+    # # ✅ Ensure all training features exist in `input_df`
+    # for col in rf_training_features:
+    #     if col not in input_df.columns:
+    #         input_df[col] = 0  # Default missing columns to 0
+    #
+    # # Get intersection of trained features and current input_df columns
+    # common_features = list(set(rf.feature_names_in_) & set(input_df.columns))
+    #
+    # # Select only the matching features
+    # input_df_rf = input_df[common_features]
+    #
+    # # Predict without needing to add missing features
+    # rf_preds = rf.predict(input_df_rf)
+    #
+    #
+    # print("RF Model Trained Features:", rf.feature_names_in_)
+    # print("Input Data Features:", input_df_rf.columns.tolist())
+    #
+    # # Debugging: Check for missing or extra features
+    # missing_features = set(rf.feature_names_in_) - set(input_df_rf.columns)
+    # extra_features = set(input_df_rf.columns) - set(rf.feature_names_in_)
+    #
+    # print("Missing Features in Input:", missing_features)
+    # print("Extra Features in Input:", extra_features)
+    # # ✅ Make Predictions with RandomForest
+    # rf_preds = rf.predict(input_df_rf)
 
     catboost_probs = catboost.predict_proba(input_df)[:, 1]
     xgb_probs = xgb.predict_proba(input_df)[:, 1]
-    rf_probs = rf.predict_proba(input_df)[:, 1]
+    #rf_probs = rf.predict_proba(input_df)[:, 1]
 
     # Combine results
     predictions_df = pd.DataFrame({
         "CatBoost": catboost_preds,
         "XGBoost": xgb_preds,
-        "RandomForest": rf_preds
+      #  "RandomForest": rf_preds
     })
 
     # Apply "at least one model predicts 1" rule
@@ -278,7 +278,7 @@ if uploaded_file:
     probabilities_df = pd.DataFrame({
         "CatBoost_Prob": catboost_probs,
         "XGBoost_Prob": xgb_probs,
-        "RandomForest_Prob": rf_probs
+      #  "RandomForest_Prob": rf_probs
     })
 
     # Save results