中文词频统计

中文词频统计

import jieba
txt = open('test.txt','r',encoding='utf-8').read()
words= list(jieba.cut(txt))

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

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

for i in range(10):
    print(wc[i])

import jieba
txt = open('test.txt','r',encoding='utf-8').read()
words= list(jieba.cut(txt))

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

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

for i in range(10):
    print(wc[i])