用朴素贝叶斯算法对sklearn自带的新闻进行分类

from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.model_selection import train_test_split
def nb_news():
    #1)加载数据
    news=fetch_20newsgroups(data_home=r"D:\桌面上的文件\数据挖掘",subset="all")
    #2）数据划分
    x_train,x_test,y_train,y_test=train_test_split(news.data,news.target)
    #3)文本特征抽取
    transfer=TfidfVectorizer()
    transfer.fit_transform(x_train)
    transfer.transform(x_test)
    #4)构建朴素贝叶斯算法预估器
    estimator=MultinomialNB()
    estimator.fit(x_train,y_train)
    # 5)模型评估
    # 方法一：直接比对真实值和预测值
    y_predict = estimator.predict(x_test)
    print("结果：", y_predict)
    print("直接比对真实值和预测值", y_test == y_predict)
    # 方法二：计算准确率
    score = estimator.score(x_test, y_test)
    print("准确率为：", score)
    return None
if __name__ == '__main__':
    # 执行函数
    nb_news()