update

app.py

@@ -55,9 +55,8 @@ def preprocess_input(input_df):
         "webpage_id": "nunique"
     }).reset_index()
 
-    # Rename columns after aggregation
+    # Fix renaming: Remove columns that are missing
     age_sex_product_agg.columns = ["age_level", "gender", "product",
-                                   "click_sum_age_sex_prod", "click_count_age_sex_prod",
                                    "unique_campaigns_age_sex_prod", "unique_webpages_age_sex_prod"]
 
     input_df = input_df.merge(age_sex_product_agg, on=["age_level", "gender", "product"], how="left")
@@ -68,44 +67,36 @@ def preprocess_input(input_df):
         "webpage_id": "nunique"
     }).reset_index()
 
-    # Rename columns after aggregation
+    # Fix renaming: Remove columns that are missing
     city_age_product_agg.columns = ["city_development_index", "age_level", "product",
-                                    "click_sum_city_age_prod", "click_count_city_age_prod",
                                     "unique_campaigns_city_age_prod", "unique_webpages_city_age_prod"]
+
     input_df = input_df.merge(city_age_product_agg, on=["city_development_index", "age_level", "product"], how="left")
     input_df.fillna(0, inplace=True)
+
+    # Feature List (Removed click_sum and click_count)
     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",
-
-                # Include Aggregated Features
-                "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"]
 
-    target = "is_click"
-
     categorical_columns = ["gender", "product", "campaign_id", "webpage_id"]
 
     # ===========================
     #  ENCODE CATEGORICAL FEATURES
     # ===========================
 
-    # Convert categorical features to category type
-    for col in categorical_columns:
-        input_df[col] = input_df[col].astype("category")
-
-    # Encode categorical variables consistently
     label_encoders = {}
     for col in categorical_columns:
         le = LabelEncoder()
-        input_df[col] = input_df[col].astype(str).map(lambda s: le.transform([s])[0] if s in le.classes_ else -1)
+        input_df[col] = le.fit_transform(input_df[col].astype(str))  # Apply transformation correctly
+        label_encoders[col] = le  # Store encoder for reference
 
     # Normalize numerical features
     numerical_columns = [col for col in features if col not in categorical_columns]
     scaler = StandardScaler()
-    input_df[numerical_columns] = scaler.transform(input_df[numerical_columns])
+    input_df[numerical_columns] = scaler.fit_transform(input_df[numerical_columns])
 
     return input_df