s12_run_xgboost_only_train_create.py 文件源码

def run_train_with_model(train, features, model_path):
    start_time = time.time()

    gbm = xgb.Booster()
    gbm.load_model(model_path)

    print("Validating...")
    check = gbm.predict(xgb.DMatrix(train[features]))
    score = roc_auc_score(train['isDuplicate'].values, check)
    validation_df = pd.DataFrame({'itemID_1': train['itemID_1'].values, 'itemID_2': train['itemID_2'].values,
                                  'isDuplicate': train['isDuplicate'].values, 'probability': check})
    print('AUC score value: {:.6f}'.format(score))

    imp = get_importance(gbm, features)
    print('Importance array: ', imp)

    print('Prediction time: {} minutes'.format(round((time.time() - start_time)/60, 2)))
    return validation_df, score