base.py 文件源码

def mnist(missingness="mcar", thr=0.2):
    """ Loads corrupted MNIST

    Parameters
    ----------
    missingness: ('mcar', 'mar', 'mnar')
        Type of missigness you want in your dataset
    th: float between [0,1]
        Percentage of missing data in generated data

    Returns
    -------
    numpy.ndarray
    """
    from sklearn.datasets import fetch_mldata
    dataset = fetch_mldata('MNIST original')
    corruptor = Corruptor(dataset.data, thr=thr)
    data = getattr(corruptor, missingness)()
    return {"X": data, "Y": dataset.target}