plot.py 文件源码

def newsgroups_class_distrib():
    from sklearn.datasets import fetch_20newsgroups
    ngroup_test = fetch_20newsgroups(subset='test', remove=('headers', 'footers', 'quotes'), categories=None)
    ngroup_train = fetch_20newsgroups(subset='train', remove=('headers', 'footers', 'quotes'), categories=None)
    test_data = ngroup_test.data
    train_data = ngroup_train.data
    test_groups = ngroup_test.target
    train_groups = ngroup_train.target

    n = 2000
    train_groups = train_groups[:n]
    test_groups = test_groups[:n]

    plt.figure()
    plt.hist(train_groups, 20, normed=True, range=(0, 19))
    plt.title("train groups")

    plt.figure()
    plt.hist(test_groups, 20, normed=True, range=(0, 19))
    plt.title("test groups")

    plt.show()