文件方式实现完整的英文词频统计实例

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

str=str.lower()

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

#排除语法型词汇
dict={}
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‘])
keys=set(words)-ecp 

#创建计数字典
for i in keys:
    dict[i]=words.count(i)
#将字典转换为列表,以便后序排序
items=list(dict.items()) 

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

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