user_logging_tests.py 文件源码

def test_verify_features_finds_no_missing_features_when_none_are_missing():
        np.random.seed(0)

        df_titanic_train, df_titanic_test = utils.get_titanic_binary_classification_dataset()

        column_descriptions = {
            'survived': 'output'
            , 'embarked': 'categorical'
            , 'pclass': 'categorical'
            , 'sex': 'categorical'
        }


        ml_predictor = Predictor(type_of_estimator='classifier', column_descriptions=column_descriptions)
        ml_predictor.train(df_titanic_train, verify_features=True)

        file_name = ml_predictor.save(str(random.random()))

        with open(file_name, 'rb') as read_file:
            saved_ml_pipeline = dill.load(read_file)
        os.remove(file_name)

        missing_features = saved_ml_pipeline.named_steps['final_model'].verify_features(df_titanic_test)
        print('missing_features')
        print(missing_features)


        print("len(missing_features['prediction_not_training'])")
        print(len(missing_features['prediction_not_training']))
        print("len(missing_features['training_not_prediction'])")
        print(len(missing_features['training_not_prediction']))
        assert len(missing_features['prediction_not_training']) == 0
        assert len(missing_features['training_not_prediction']) == 0