词频统计

f=open('ghost.txt','r')
news=f.read()
f.close()

sep=''':;""'',.?!-'''
exclude={'the','me','you','my','of','to','in','will','for','and','from'}

for c in sep:
    news=news.replace(c,'')

wordList=news.lower().split()
wordDict={}


'''
for i in wordList:
    wordDict[i]=wordDict.get(i,0)+1
'''

wordSet=set(wordList) - exclude
for i in wordSet:
    wordDict[i]=wordList.count(i)

dictList=list(wordDict.items())
dictList.sort(key=lambda x:x[1],reverse=True)

f=open('result.txt','a')
for i in range(20):
    f.write(dictList[i][0]+' '+str(dictList[i][1])+'\n')
f.close()

 

 

PS.这是经过分析后的结果