基础python统计词频,未考虑到删除停用词
# 词频统计
def getText():#处理文件
txt=open("English.txt","r").read()
txt = txt.lower()#将英文全部变为小写
for ch in '!"#$&*+,-./:;<=>?@[\\]^_{}|':
txt = txt.replace(ch," ")
return txt
myTxt = getText()
words = myTxt.split()#将字符分割为列表
counts={} #新建一个空字典
for word in words:
counts[word] = counts.get(word,0)+1
items = list(counts.items())#将字典中的键值对变为列表
items.sort(key=lambda x:x[1],reverse=True)#按词语个数从大往小排序
for i in range(20):#打印词频在前20位的单词
word,count = items[i]
print("{0:<10}{1:>5}".format(word,count))