文件方式实现完整的英文词频统计实例

fo=open(‘test.txt‘,‘r‘) #读入待分析的字符串
str=fo.read()
fo.close()

for i in ‘,.?!"\n--‘: #分解提取单词
    str=str.replace(i,‘ ‘)
words=str.split(‘ ‘)

for i in keys:    #创建计数字典
    dict[i]=words.count(i)

dict={}         #排除语法型词汇
ecp=set([‘‘,‘a‘,‘an‘,‘the‘,‘and‘,‘to‘,‘in‘,‘on‘,‘of‘,‘for‘,‘i‘,‘our‘,‘us‘,‘into‘,‘her‘,‘we‘,
         ‘when‘,‘their‘,‘my‘,‘from‘,‘them‘,‘with‘,‘after‘,‘would‘,‘was‘,‘had‘,‘that‘,‘while‘,
         ‘his‘,‘she‘,‘up‘,‘it‘,‘they‘,‘so‘,‘by‘])

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

print(‘输出TOP20:‘)
for i in range(20):
   print(items[i])