朴素贝叶斯案例流程
1、加载20类新闻数据，并进行分割
2、生成文章特征词
3、朴素贝叶斯estimator流程进行预估
代码
from sklearn.datasets import fetch_20newsgroupsfrom sklearn.model_selection import train_test_splitfrom sklearn.feature_extraction.text import TfidfVectorizerfrom sklearn.naive_bayes import MultinomialNBdef 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 Noneif __name__=="__main__":naviebayes()
P：
关于sklearn.datasets.fetch_20newsgroups的下载速度极慢的解决
/a/1190000016498146?utm_source=tag-newest
