datasets.py 文件源码

def load_newsgroups():
    from sklearn.feature_extraction.text import TfidfVectorizer
    from sklearn.datasets import fetch_20newsgroups
    newsgroups = fetch_20newsgroups(subset='all', remove=('headers', 'footers', 'quotes'))

    vectorizer = TfidfVectorizer(max_features=2000, dtype=np.float64, sublinear_tf=True)
    x_sparse = vectorizer.fit_transform(newsgroups.data)
    x = np.asarray(x_sparse.todense())
    y = newsgroups.target
    print('News group data shape ', x.shape)
    print("News group number of clusters: ", np.unique(y).size)
    return x, y