朴素贝叶斯

?
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
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
from sklearn.metrics import classification_report
 
 
def naviebayes():
    """
    朴素贝叶斯进行文本分类
    :return: None
    """
    news = fetch_20newsgroups(subset='all')
 
    # 进行数据分割
    x_train, x_test, y_train, y_test = train_test_split(news.data, news.target, test_size=0.25)
 
    # 对数据集进行特征抽取
    tf = TfidfVectorizer()
 
    # 以训练集当中的词的列表进行每篇文章重要性统计['a','b','c','d']
    x_train = tf.fit_transform(x_train)
 
    print(tf.get_feature_names())
 
    x_test = tf.transform(x_test)
 
    # 进行朴素贝叶斯算法的预测
    mlt = MultinomialNB(alpha=1.0)
 
    print(x_train.toarray())
 
    mlt.fit(x_train, y_train)
 
    y_predict = mlt.predict(x_test)
 
    print("预测的文章类别为：", y_predict)
 
    # 得出准确率
    print("准确率为：", mlt.score(x_test, y_test))
 
    print("每个类别的精确率和召回率：", classification_report(y_test, y_predict, target_names=news.target_names))
 
    return None
 
 
if __name__ == "__main__":
    naviebayes()