data.py 文件源码

def newsgroups(*, path=None, key=None, limit=None):
    """
    Return a list of newsgroup messages from the 20 newsgroups dataset.

    Arguments:
     - path(str): Unused in this case. Dataset is managed by sklearn.
     - key(str): Unused.
     - limit(int): Unused.
    """
    # This is going to download the dataset the first time we
    # run this function. Ideally we can populate these datasets
    # ahead of time.
    from sklearn.datasets import fetch_20newsgroups
    if limit:
        return fetch_20newsgroups(subset='train').data[:limit]
    return fetch_20newsgroups(subset='train').data