Python利用jieba獲取中文詞匯等

import jieba
import os
import jieba.analyse

data = cleaned_comments # 數據來源於評論數據
seg = jieba.lcut(data)
print(seg)

# 增加自定義詞表庫
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)

# 抽取出現次數最多的詞匯
extracttext = jieba.analyse.extract_tags(data, topK=20,withWeight=False, allowPOS=())
print(extracttext)

 

待續。。。