朴素贝叶斯项目实战

from sklearn.datasets import load_iris,fetch_20newsgroups,load_boston
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.feature_extraction.text import TfidfVectorizer
import pandas as pd
from sklearn.naive_bayes import MultinomialNB  #朴素贝叶斯算法


def process_news():
    # 获取新闻数据
    news=fetch_20newsgroups(subset="all")
    # print(news)
    # 将数据分割为训练集测试集
    x_train,x_text,y_train,y_text=train_test_split(news.data,news.target,test_size=0.25)
    # print("训练集特征值目标值")
    # print(x_train,y_train)
    # print("测试集特征值目标值")
    #对数据进行特征抽取
    tf=TfidfVectorizer()
    x_train=tf.fit_transform(x_train)
    print(tf.get_feature_names())
    tf.x_text=tf.transform(x_text)


    #进行朴素贝叶斯算法预测
    mlt=MultinomialNB(alpha=1.0)
    print(x_train)
    mlt.fit(x_train,y_train)
    y_predict=mlt.predict(x_text)
    print("预测文章的类型为",y_predict)
    print("准确率：",mlt.score(x_text,y_text))
def main():
    process_news()


if __name__ == '__main__':
    main()

运行结果：