朴素贝叶斯算法对新闻进行分类

from sklearn.datasets import fetch_20newsgroups

# 加载数据
news = fetch_20newsgroups(data_home=r'E:\jupyter--workspace',subset='all')

Downloading 20news dataset. This may take a few minutes.
Downloading dataset from https://ndownloader.figshare.com/files/5975967 (14 MB)

from sklearn.model_selection import train_test_split

# 数据划分
x_train,x_test,y_train,y_test = train_test_split(news.data,news.target)

from sklearn.feature_extraction.text import TfidfVectorizer

# 文本特征抽取
transfer = TfidfVectorizer()
x_train=transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)

from sklearn.naive_bayes import MultinomialNB

# 构建朴素贝叶斯算法预估器
estimator = MultinomialNB()
estimator.fit(x_train,y_train)

MultinomialNB(alpha=1.0, class_prior=None, fit_prior=True)

# 评估模型
y_predict = estimator.predict(x_test)
print('真实值与预测值对吧：\n',y_predict==y_test)

真实值与预测值对吧：
 [ True False  True ... False  True  True]

# 计算准确率
score = estimator.score(x_test,y_test)
print("准确率:\n", score)

准确率:
 0.8378607809847198