python+sklearn+基于贝叶斯实现商品评论情感分类

最新推荐文章于 2023-10-30 21:30:42 发布

走在下雨天的人

最新推荐文章于 2023-10-30 21:30:42 发布

阅读量1.7k

点赞数

分类专栏：机器学习

本文链接：https://blog.csdn.net/qq_42988748/article/details/83181763

版权

理论参考：朴素贝叶斯理论推导与三种常见模型

import jieba
import jieba.posseg as pseg
import json
import re
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB,BernoulliNB,GaussianNB
from sklearn.model_selection import train_test_split
from sklearn import metrics

def StopWordsList():
    filepath = 'E:\数据挖掘学习\FAQ\stopwords.txt'
    wlst = [w.strip() for w in open(filepath, 'r', encoding='utf8').readlines()]
    return wlst

def seg_sentence(sentence, stop_words):
    stop_flag = ['x', 'c', 'u', 'd', 'p', 't', 'uj', 'm', 'f', 'r']  # 过滤数字m
    sentence_seged = pseg.cut(re.sub('\n', '', sentence))
    outstr = []
    for word, flag in