期末综合大作业:词频统计1

f=open('son.txt',mode='r',encoding='utf-8')
fText = f.read()

print(fText)

replaceList = ['?',',','.',';']
for c in replaceList:
fText = fText.replace(c,' ')

print(fText)

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

sonSet = set(bigList)
print(sonSet)

bigDict = {}
for word in sonSet:
bigDict[word] = bigList.count(word)
print(bigDict)

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

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

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

posted @ 2018-06-20 20:35  吴树生  阅读(95)  评论(0编辑  收藏  举报