期末综合大作业:词频统计
#1. letFile = open('let.txt',mode="r",encoding='utf-8') letText = letFile.read() letFile.close() print(letText) #2. replaceList = [',','.',"'",'\n'] for c in replaceList: letText = letText.replace(c,' ') print(letText) #3. print(letText.split(' ')) letList = letText.split(' ') #4. letSet = set(letList) print(letSet) letDict = {} for word in letSet: letDict[word] = letList.count(word) print(letDict) for d in letDict: print(d,letDict[d]) #5. wordCountList = list(letDict.items()) print(wordCountList) wordCountList.sort(key=lambda x:x[1],reverse=True) print(wordCountList) #6. for i in range(20): print(wordCountList) #7. letCountFile = open('letCount.txt',mode='a',encoding='utf-8') for i in range(len(wordCountList)): letCountFile.write(str(wordCountList[i][1])+' '+wordCountList[i][0]+'\n') letCountFile.close()
posted on 2018-06-20 21:04 2han92hu0m1n9 阅读(131) 评论(0) 收藏 举报
浙公网安备 33010602011771号