1. 数据集

2. 实现

2.1 代码

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 bayesian_demo():
    '''
    朴素贝叶斯-文本分类
    :return:
    '''
    # 1. 获取数据
    news = fetch_20newsgroups(subset='all')

    # 2. 划分数据集
    x_train, x_test, y_train, y_test = train_test_split(news.data, news.target, test_size=0.2)

    # 3. 特征工程
    transfer = TfidfVectorizer()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.transform(x_test)

    # 4. 朴素贝叶斯算法预估器流程
    estimator = MultinomialNB()
    estimator.fit(x_train, y_train)

    # 5. 模型评估
    # 5.1 直接对比真实值、预测值
    y_predict = estimator.predict(x_test)
    print('y_predic:\n', y_predict)
    print('直接对比真实值与预测值：\n', y_test == y_predict)

    # 5.2 计算准确率
    score = estimator.score(x_test,y_test)
    print('准确率为：\n', score)

if __name__ == '__main__':
    bayesian_demo()

2.2 结果