Hamlet文本下载链接:
链接:https://pan.baidu.com/s/1qiqoIXjNmjwtHU4tmK6Ktw
提取码:t956
#----Hamlet英文词频统计----
excludes={"the","and","of","you","a","i","my","in"}
def getText():
txt=open("hamlet.txt","r").read()
txt=txt.lower()
for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~':
txt=txt.replace(ch," ")#将文本中特殊字符替换为空格
return txt
hamletTxt=getText()
words=hamletTxt.split()
counts={}
for word in words:
counts[word]=counts.get(word,0)+1
for word in excludes:
del(counts[word])
items=list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)
for i in range(10):
word,count=items[i]
print("{0:<10}{1:>5}".format(word,count))
输出:
to 754
hamlet 462
it 416
that 391
is 340
not 314
lord 309
his 296
this 295
but 269