update

app.py

@@ -36,6 +36,10 @@ FEATURE_COLUMNS = CATEGORICAL_COLUMNS + NUMERICAL_COLUMNS
 import pandas as pd
 from sklearn.preprocessing import LabelEncoder, StandardScaler
 
+import pandas as pd
+import numpy as np
+from sklearn.preprocessing import LabelEncoder, StandardScaler
+
 
 def preprocess_input(input_df):
     """
@@ -76,27 +80,38 @@ def preprocess_input(input_df):
     required_columns = ["age_level", "gender", "product", "city_development_index"]
     if not all(col in input_df.columns for col in required_columns):
         print("🛑 Missing required columns for aggregations. Skipping aggregation steps.")
-        return input_df
-
-    # Aggregation: Age & Gender vs Product
-    input_df = compute_aggregations(input_df, ["age_level", "gender", "product"], {
-        "campaign_id": "nunique",
-        "webpage_id": "nunique"
-    }, suffix="age_sex_prod")
+    else:
+        # Aggregation: Age & Gender vs Product
+        input_df = compute_aggregations(input_df, ["age_level", "gender", "product"], {
+            "campaign_id": "nunique",
+            "webpage_id": "nunique"
+        }, suffix="age_sex_prod")
+
+        # Aggregation: City, Age, Product
+        input_df = compute_aggregations(input_df, ["city_development_index", "age_level", "product"], {
+            "campaign_id": "nunique",
+            "webpage_id": "nunique"
+        }, suffix="city_age_prod")
+
+    # 🚀 Step 4: Add Missing Aggregated Columns with Default Values
+    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"
+    ]
 
-    # Aggregation: City, Age, Product
-    input_df = compute_aggregations(input_df, ["city_development_index", "age_level", "product"], {
-        "campaign_id": "nunique",
-        "webpage_id": "nunique"
-    }, suffix="city_age_prod")
+    for col in aggregated_features:
+        if col not in input_df.columns:
+            input_df[col] = 0  # Fill missing aggregated columns with default values
 
-    # 🚀 Step 4: Ensure Categorical Features Are Strings
+    # 🚀 Step 5: Ensure Categorical Features Are Strings
     categorical_columns = ["gender", "product", "campaign_id", "webpage_id"]
 
     for col in categorical_columns:
         input_df[col] = input_df[col].astype(str).fillna("missing")
 
-    # 🚀 Step 5: Encode Categorical Features as Integers
+    # 🚀 Step 6: Encode Categorical Features as Integers
     label_encoders = {}
     for col in categorical_columns:
         le = LabelEncoder()
@@ -105,7 +120,7 @@ def preprocess_input(input_df):
         label_encoders[col] = le
         input_df[col] = input_df[col].map(lambda x: le.transform([x])[0] if x in le.classes_ else -1)
 
-    # 🚀 Step 6: Normalize Numerical Features
+    # 🚀 Step 7: Normalize Numerical Features
     numerical_columns = [
         "age_level", "city_development_index", "user_group_id", "user_depth", "var_1",
         "click_sum_age_sex_prod", "click_count_age_sex_prod",
@@ -121,6 +136,7 @@ def preprocess_input(input_df):
 
     return input_df
 
+
 def download_model(filename, local_path):
     """Download model from Hugging Face and move it to the correct location."""
     temp_path = hf_hub_download(repo_id=MODEL_REPO, filename=filename, local_dir=MODEL_DIR)