dataset.py 文件源码

def load_uci_german_credits(path, n_train):
    if not os.path.isfile(path):
        data_dir = os.path.dirname(path)
        if not os.path.exists(os.path.dirname(path)):
            os.makedirs(data_dir)
        download_dataset('https://archive.ics.uci.edu/ml/'
                         'machine-learning-databases/statlog/'
                         'german/german.data-numeric', path)

    n_dims = 24
    data = np.loadtxt(path)

    x_train = data[:n_train, :n_dims]
    y_train = data[:n_train, n_dims] - 1
    x_test = data[n_train:, :n_dims]
    y_test = data[n_train:, n_dims] - 1

    return x_train, y_train, x_test, y_test