KaiquanMah/DSIP

1import argparse2import pandas as pd3import joblib4 5 6def run_prediction():7    input_path = "data/X_test_1st.csv"8    output_path = "results/predictions.csv"9    model_path = "model/best_model.pkl"10 11    # Load data and model12    df = pd.read_csv(input_path)13    model = joblib.load(model_path)14 15    # Preprocessing16    features = [17        'product_category_1',18        'product_category_2',19        'user_depth',20        'age_level',21        'city_development_index',22        'var_1',23        'gender'24    ]25 26    X = df[features]27    X = pd.get_dummies(X, columns=['gender'], drop_first=True)28 29    # Predict30    predictions = model.predict(X)31 32    # Save predictions33    df['predictions'] = predictions34    df.to_csv(output_path, index=False)35    print(f"Predictions saved to {output_path}")36 37 38    39# def main():40#     parser = argparse.ArgumentParser()41#     parser.add_argument('--model-path', type=str, required=True, help='Path to the trained model')42#     parser.add_argument('--input-data', type=str, required=True, help='Path to input data for prediction')43#     args = parser.parse_args()44 45#     print(f"Loading model from {args.model_path}")46#     print(f"Predicting on data from {args.input_data}")47#     # Add prediction logic here48 49# if __name__ == '__main__':50#     main()