#英文词频统计
def getText():
path = r"E:\DLNL\Emma.txt"
with open(path,'r') as f:
txt = f.read()
txt = txt.lower()
olds = '!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\''
for old in olds:
txt = txt.replace(old, ' ')
return txt
EmmaText = getText()
words = EmmaText.split()
counts={}
tingci= ['and','to','the','of','a','i','it','is','he','she','in','her']
#从全文列表删除停词
# for ci in tingci:
# while ci in words:
# words.remove(ci)
for word in words:
counts[word] = counts.get(word,0)+1
#从字典删除停词
# for word in tingci:
# del(counts[word])
items = list(counts.items())
items.sort(key = lambda x:x[1],reverse=True)
for i in range(10):
print(items[i])
04-10
6273
![](https://csdnimg.cn/release/blogv2/dist/pc/img/readCountWhite.png)
06-13
“相关推荐”对你有帮助么?
-
非常没帮助
-
没帮助
-
一般
-
有帮助
-
非常有帮助
提交