综合练习：词频统计

Posted 2020-10-28 097黄大贞

f=open(\'/Users/Administrator/Desktop/we.txt\',\'r\')
text=f.read()
f.close()
print(text)

rep = \'\'\',.!:?\'\'\'
exclude={\'a\',\'the\',\'for\',\'in\',\'i\',\'my\',\'that\',\'of\',\'have\',\'and\',\'had\',\'it\',\'are\'}
for c in rep:
     str=text.replace(c,"")
str=str.lower().split()
for i in str:
     print(i)

dict01={}
wordset=set(str)-exclude
for w in wordset:
    dict01[w]=str.count(w)
# set01 = set(str)
# print(set01)
# for item in set01:
#     dict01.update({item:str.count(item)})
# print(dict01)
for c in str:
    dict01[c]=dict01.get(c,0)+1
for w in exclude:
    dict01.pop(w)
dictlist=dict01.items()
dictlist=sorted(dict01.items(),key=lambda d:d[1],reverse=True)
for c in range(10):
    print(dictlist[c])