Create utils.py

utils.py

@@ -0,0 +1,17 @@
+# create new features
+def create_new_features(df):
+    df['year_sold'] = df['date'].dt.year
+    df = df.drop(columns=['date'])
+    df['house_age'] = df['year_sold'] - df['yr_built']
+    df['years_since_renovation'] = df['year_sold'] - df['yr_renovated']
+    df.drop(columns=['year_sold'], inplace=True)
+    df['has_basement'] = df['sqft_basement'].apply(lambda x: 1 if x > 0 else 0)
+    return df
+
+def normalize(df, col, min_dict, max_dict):
+    numerical_features = ['bedrooms', 'bathrooms', 'sqft_living', 'sqft_lot', 'floors', 'waterfront',
+                          'view', 'condition', 'sqft_above', 'sqft_basement',
+                          'yr_built', 'yr_renovated', 'house_age', 'years_since_renovation']
+    
+    df[col] = df[col].apply(lambda x: (x-min_dict[col])/(max_dict[col]-min_dict[col]))
+    return df[col]