import jieba

import os

import jieba.analyse

data = cleaned_comments # 数据来源于评论数据

seg = jieba.lcut(data)

print(seg)

# 增加自定义词表库

mydict = os.getcwd()+"/mydict.txt"

jieba.load_userdict(mydict)

seg = jieba.lcut(data)

print(seg)

import jieba.posseg as pseg

posseg = pseg.lcut(data)

print(posseg)

# 抽取出现次数最多的词汇

extracttext = jieba.analyse.extract_tags(data, topK=20,withWeight=False, allowPOS=())

print(extracttext)