Update preprocess.py

preprocess.py

@@ -24,10 +24,19 @@ def parse(csv_path):
     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
 
+    # Extract datetime features
+    X['DateTime'] = pd.to_datetime(X['DateTime'])
+    X['DayOfWeek'] = X['DateTime'].dt.dayofweek
+    X['Month'] = X['DateTime'].dt.month
+    X['Hour'] = X['DateTime'].dt.hour
+    X = X.drop('DateTime', axis=1)
+
+    
     # Normalize numerical features
     scaler = MinMaxScaler()
     numerical_features = ['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])
+    X[numerical_features] = scaler.fit_transform(X[numerical_features])
+    data = pd.concat([X, y.to_frame(name="is_click")], axis=1)
     data.to_csv('data/03 normalize.csv', index=False)