sklearn朴素贝叶斯

一。基本原理

贝叶斯公式

 二。在文本分类中的情况

 sklearn实现

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 news_classification():
    """
    朴素贝叶斯对新闻进行分类
    :return:
    """
    #1.获取数据
    news=fetch_20newsgroups("c:/new",subset="all")
    #print(news)
    #2.划分数据集
    x_train,x_test,y_train,y_test=train_test_split(news.data,news.target)
    #  print(x_train)
    #3.特征工程：文本特征抽取-tfidf
    transfer=TfidfVectorizer()
    x_train=transfer.fit_transform(x_train)
    x_test=transfer.transform(x_test)
    #4.朴素贝叶斯预估器'
    estimator=MultinomialNB()
    estimator.fit(x_train,y_train)
    #5.模型评估
    y_predict=estimator.predict(x_test)
    print(y_predict)
    print("直接比对真实值和预测值:
",y_predict==y_test)
    #方法2：直接计算准确率
    score=estimator.score(x_test,y_test)
    print("准确率为:",score)
if __name__ == "__main__":
    news_classification()