了解更多关注微信公众号“木下学Python”吧~
import jieba.analyse
tags = jieba.analyse.extract_tags(content,topK=num,withWeight=True)
for item in tags:
print(item[0]+'\t'+str(item[1]*1000))
content为文本信息,topK为提取关键词的个数,withWeight为关键词的权重
分词常用函数
import jieba
import wordcloud
with open('liulangdiqiu.txt','r',encoding='utf-8') as f:
txt = f.read()
ls = jieba.lcut(txt)
txt = ' '.join(ls)
w = wordcloud.WordCloud( width = 1000,height = 700,
font_path = 'msyh.ttc',)
w.generate(txt)
w.to_file('comments.png')