python-autosklearn-sequence-usage

import sklearn.model_selection
import sklearn.datasets
import sklearn.metrics
import autosklearn.classification


def main():
    X, y = sklearn.datasets.load_breast_cancer(return_X_y=True)
    X_train, X_test, y_train, y_test = \
        sklearn.model_selection.train_test_split(X, y, random_state=1)

    automl = autosklearn.classification.AutoSklearnClassifier(
    	# 寻找合适模型所用的时间
        time_left_for_this_task=120,
        # 每一个机器学习模型所用的时间
        per_run_time_limit=30,
        tmp_folder='/tmp/autosklearn_sequential_example_tmp',
        output_folder='/tmp/autosklearn_sequential_example_out',
        # 集成模型中模型数量
        ensemble_size=0,
        delete_tmp_folder_after_terminate=False,
    )
    automl.fit(X_train, y_train, dataset_name='breast_cancer')
    automl.fit_ensemble(y_train, ensemble_size=50)

    print(automl.show_models())
    predictions = automl.predict(X_test)
    print(automl.sprint_statistics())
    print("Accuracy score", sklearn.metrics.accuracy_score(y_test, predictions))


if __name__ == '__main__':
    main()