中文词频统计

import jieba

txt = open(‘wkz.txt‘, ‘r‘, encoding=‘UTF-8‘).read()

for i in ‘，。！？：“”……（）你我他她是没有一什么这为那这‘:
    txt = txt.replace(i, ‘‘)
words = list(jieba.cut(txt))

dic = {}
for i in words:
    if len(i) == 1:
        continue
    else:
        dic[i] = dic.get(i, 0) + 1

wc = list(dic.items())
wc.sort(key=lambda x: x[1], reverse=True)
# print(a)

for i in range(20):
    print(wc[i])