一。基本原理

贝叶斯公式

 二。在文本分类中的情况

 sklearn实现

 1 from sklearn.datasets import fetch_20newsgroups
 2 from sklearn.model_selection import train_test_split
 3 from sklearn.feature_extraction.text import TfidfVectorizer
 4 from sklearn.naive_bayes import MultinomialNB
 5
 6 def news_classification():
 7     """
 8     朴素贝叶斯对新闻进行分类
 9     :return:
10     """
11     #1.获取数据
12     news=fetch_20newsgroups("c:/new",subset="all")
13     #print(news)
14     #2.划分数据集
15     x_train,x_test,y_train,y_test=train_test_split(news.data,news.target)
16     #  print(x_train)
17     #3.特征工程:文本特征抽取-tfidf
18     transfer=TfidfVectorizer()
19     x_train=transfer.fit_transform(x_train)
20     x_test=transfer.transform(x_test)
21     #4.朴素贝叶斯预估器'
22     estimator=MultinomialNB()
23     estimator.fit(x_train,y_train)
24     #5.模型评估
25     y_predict=estimator.predict(x_test)
26     print(y_predict)
27     print("直接比对真实值和预测值:\n",y_predict==y_test)
28     #方法2:直接计算准确率
29     score=estimator.score(x_test,y_test)
30     print("准确率为:",score)
31 if __name__ == "__main__":
32     news_classification()
01-03 09:07