期末综合大作业:词频统计

#1.
bigFile = open('big.txt',mode='r',encoding='utf-8')
bigText=bigFile.read()
bigFile.close()
print(bigText)

#2.
replaceList=[',','.',"'",'\n']
for c in replaceList:
    bigText=bigText.replace(c,'')
print(bigText)
bigText=bigText.replace('','')

#3.
print(bigText.split(' '))
bigList = bigText.split(' ')

#4
bigSet=set(bigList)
print(bigList)

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

print(bigDict)
for d in bigDict:
    print(d,bigDict[d])

#5.
wordCountList=list(bigDict.items())
print(wordCountList)
wordCountList.sort(key=lambda x:x[1],reverse=True)
print(wordCountList)

#6.
for i in range(20):
    print(wordCountList[i])

#7.
bigCountFile=open('bigCount.txt',mode='a',encoding='utf-8')
for i in range(len(wordCountList)):
    bigCountFile.write(str(wordCountList[i][1])+''+wordCountList[i][0]+'\n')
bigCountFile.close()

posted @ 2018-06-20 21:34  朱靖萍  阅读(90)  评论(0编辑  收藏  举报