期末综合

 

#1.
geciFile = open('geci.txt',mode="r",encoding='utf-8')
geciText = geciFile.read()
geciFile.close()
print(geciText)

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

#3.
print(geciText.split(' '))
geciList = geciText.split(' ')

#4.
geciSet = set(geciList)
print(geciSet)

geciDict = {}
for word in geciSet:
    geciDict[word] = geciList.count(word)

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

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

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

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