朴素贝叶斯算法对新闻进行分类

#!/usr/bin/python
# 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


def nb_news():
    #朴素贝叶斯对新闻进行分类

    #获取数据
    news = fetch_20newsgroups(subset="all")

    #划分数据
    x_train, x_test, y_train, y_test = train_test_split(news.data, news.target)

    #特征工程:文本特征提取
    transfer = TfidfVectorizer()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.transform(x_test)

    #朴素贝叶斯算法估计
    estimator = MultinomialNB()
    estimator.fit(x_train, y_train)

    #模型评估
    y_predict = estimator.predict(x_test)
    print "y_predict:\n", y_predict
    print "对比真实值和预测值:\n", y_test == y_predict

    # 方法二：计算正确率
    score = estimator.score(x_test, y_test)
    print "准确率：\n", score

    return None

nb_news()