pythonのjiebaモジュール高周波語統計

482 ワード

import jieba

txt = open('gaopin.txt','r').read()
words = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:
        continue
    else:
        counts[word] = counts.get(word,0) + 1
        
items = list(counts.items())

items.sort(key=lambda x : x[1],reverse=True)
#items.sort(reverse = True)
for i in range(20):
    word ,count =items[i]
    print(word,count)
#    print('{0:<10}{1:>5}'.format(word,count))