s11_run_xgboost_only_test.py 文件源码

def run_test_with_model(train, test, 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({'isDuplicate': train['isDuplicate'].values, 'probability': check})
    # print(validation_df)
    print('AUC score value: {:.6f}'.format(score))
    # score1 = roc_auc_score(validation_df['isDuplicate'].values, validation_df['probability'])
    # print('AUC score check value: {:.6f}'.format(score1))


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

    print("Predict test set...")
    test_prediction = gbm.predict(xgb.DMatrix(test[features]))

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