Update preprocess.py

preprocess.py

@@ -19,12 +19,13 @@ def parse(csv_path):
     data.to_csv('data/02 drop_duplicates.csv', index=False)
     
     # Step 2: Define the feature columns (X) and target column (y)
-    X = data[["name", "attendance percentage", "average sleep time", "average screen time"]]  # Feature columns
-    y = data["grade"]  # Target column
+    # X = data[["name", "attendance percentage", "average sleep time", "average screen time"]]  # Feature columns
+    X = data[["DateTime","product","campaign_id","webpage_id","product_category_1","product_category_2","user_group_id","gender","age_level","user_depth","city_development_index","var_1"]]  # Feature columns
+    y = data["is_click"]  # Target column
 
     # Normalize numerical features
     scaler = MinMaxScaler()
-    numerical_features = ['user_depth', 'age_level', 'city_development_index', 'var_1']
+    numerical_features = ['product','campaign_id','webpage_id','user_depth',"product_category_1","product_category_2","user_group_id", 'age_level',"user_depth", 'city_development_index', 'var_1']
     data[numerical_features] = scaler.fit_transform(data[numerical_features])
     data.to_csv('data/03 normalize.csv', index=False)