中英文词频统计

q =open('111.txt','r',encoding='utf-8')
a = q.read().lower()
q.close()
d= a.replace(',',' ')
c=d.replace("'" ,' ')
e = c.split()
print(e)
j=set(e)
exclude={'a','the','i','you','in','do','but','that','net','if','a','m','it'}
j=j-exclude
print(j)
h={}
for g in j:
    h[g]=e.count(g)
for key in h:
    print(key,h[key])
i=list(h.items())
print(i)
i.sort(key=lambda x:x[1],reverse=False)
print(i)

　　

 

import jieba
q =open('333.txt','r',encoding='utf-8').read()
wordsls=jieba.lcut(q)
wcdict={}
for word in wordsls:
    if len (word)==1:
        continue
    else:wcdict[word]=wcdict.get(word,0)+1

wcls=list(wcdict.items())
wcls.sort(key=lambda x:x[1],reverse=True)
print(wcls)
for i in range(7):
    print(wcls[i])