Create data_prep.py

data_prep.py

@@ -0,0 +1,65 @@
+# data_prep.py
+
+
+# example: recency from last_purchase_days_ago (if exists)
+if 'last_purchase_days_ago' in df.columns:
+df['recency'] = df['last_purchase_days_ago']
+else:
+df['recency'] = np.nan
+
+
+# example: tenure from signup_date
+if 'signup_date' in df.columns:
+df['signup_date'] = pd.to_datetime(df['signup_date'], errors='coerce')
+df['tenure_days'] = (pd.Timestamp('today') - df['signup_date']).dt.days.fillna(df['signup_date'].median())
+else:
+df['tenure_days'] = np.nan
+
+
+# keep numeric features and encode categorical later
+return df
+
+
+
+
+def prepare_features(df: pd.DataFrame, cat_cols=None, save_encoder_path=None):
+df = df.copy()
+if cat_cols is None:
+cat_cols = [c for c in df.columns if df[c].dtype == 'object']
+
+
+num_cols = [c for c in df.columns if pd.api.types.is_numeric_dtype(df[c])]
+
+
+# One-hot encode categories (simple)
+if len(cat_cols) > 0:
+encoder = OneHotEncoder(handle_unknown='ignore', sparse=False)
+cat_mat = encoder.fit_transform(df[cat_cols].astype(str))
+cat_df = pd.DataFrame(cat_mat, columns=encoder.get_feature_names_out(cat_cols), index=df.index)
+features = pd.concat([df[num_cols], cat_df], axis=1)
+if save_encoder_path:
+joblib.dump(encoder, save_encoder_path)
+else:
+features = df[num_cols]
+
+
+return features.fillna(0)
+
+
+
+
+if __name__ == '__main__':
+import argparse
+parser = argparse.ArgumentParser()
+parser.add_argument('--input', default='data/customers_example.csv')
+parser.add_argument('--out_features', default='data/features.parquet')
+parser.add_argument('--save_encoder', default='data/ohe.joblib')
+args = parser.parse_args()
+
+
+df = load_data(args.input)
+df = basic_clean(df)
+df = feature_engineer(df)
+features = prepare_features(df, save_encoder_path=args.save_encoder)
+features.to_parquet(args.out_features)
+print('Saved features to', args.out_features)