1 from sklearn.datasets import fetch_20newsgroups
2 from sklearn.feature_extraction.text import TfidfVectorizer
3 from sklearn.naive_bayes import MultinomialNB

 1 def article_category():
 2     categories = [‘alt.atheism‘, ‘soc.religion.christian‘, ‘comp.graphics‘, ‘sci.med‘]
 3     twenty_train = fetch_20newsgroups(subset=‘train‘, categories=categories)
 4     # print(twenty_train)
 5     print(twenty_train.data)
 6     print(twenty_train.target)
 7     # 将x训练集词频向量化
 8     tfidf_transformer = TfidfVectorizer()
 9     X_train_tfidf = tfidf_transformer.fit_transform(twenty_train.data)
10 
11     # 贝叶斯训练
12     clf = MultinomialNB(alpha=1.0).fit(X_train_tfidf, twenty_train.target)
13     docs_new = [‘Chemical reaction‘, ‘Intel CPU is good‘]
14 
15     # 将要预测的数据词频向量化
16     X_new_tfidf = tfidf_transformer.transform(docs_new)
17     # 预测
18     predicted = clf.predict(X_new_tfidf)
19     print(predicted)
20     for doc, category in zip(docs_new, predicted):
21         print(‘%r => %s‘ % (doc, twenty_train.target_names[category]))