代码改变世界

期末综合大作业:词频统计

2018-06-20 21:11  陈俊宇A  阅读(164)  评论(0)    收藏  举报
f=open('z.txt',mode='r',encoding='utf-8')
fText=f.read()
f.close()

replacelist=['?' ',' '.' ';' "'" '!''\n','\ufeff']
for c in replacelist:
    fText=fText.replace(c,' ')
fText=fText.replace(' ',' ')
print(fText)

print(fText.split(' '))
fList=fText.split(' ')

fSet=set(fList)
print(fList)
fDict={}
for word in fSet:
    fDict[word]=fList.count(word)
    print(fDict)
    for d in fDict:
        print(d,fDict[d])

wordCountList=list(fDict.items())
print(wordCountList)
wordCountList.sort(key=lambda x:x[1],reverse=True)
print(wordCountList)

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

fCountFile=open('fCount.txt',mode='a',encoding='utf-8')
for i in range(len(wordCountList)):
    fCountFile.write(str(wordCountList[i][1])+' '+wordCountList[i][0]+'\n')
fCountFile.close()