朴素贝叶斯算法

# 朴素贝叶斯算法
# coding=utf-8
from sklearn.datasets import fetch_20newsgroups
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
print("*"*100)


def naviebayes():
    """
    朴素贝叶斯
    :return:
    """
    news = fetch_20newsgroups(subset='all')
    # print(news)

    # 数据分割
    x_train, x_test, y_train, y_test = train_test_split(news.data, news.target,test_size=0.25)

    # 对数据进行特征值抽取
    tf = TfidfVectorizer()
    x_train = tf.fit_transform(x_train)
    print(tf.get_feature_names())
    x_test = tf.transform(x_test)

    # 朴素贝叶斯算法
    mlt = MultinomialNB(alpha=1.0)

    print(x_train.toarray())

    mlt.fit(x_train, y_train)

    y_predict = mlt.predict(x_test)

    print(y_predict)

    sc = mlt.score(x_test, y_test)

    print(sc)

    return None


if __name__ == "__main__":
    naviebayes()