cnn_text_util.py 文件源码

def get_datasets_20newsgroup(subset='train', categories=None, shuffle=True, random_state=42):
    """
    Retrieve data from 20 newsgroups
    :param subset: train, test or all
    :param categories: List of newsgroup name
    :param shuffle: shuffle the list or not
    :param random_state: seed integer to shuffle the dataset
    :return: data and labels of the newsgroup
    """
    datasets = fetch_20newsgroups(subset=subset, categories=categories, shuffle=shuffle, random_state=random_state)
    return datasets