英文词频统计

英文词频统计

def gettext(filename):#设置函数，方便下次使用
    with open('hamlet.txt','r')as fr:#打开同路径文件
        content=fr.read()
    content=content.lower()
    fset=set()
    for i in content:#找出不属于英文的符号
        if  not 'a'<=i<='z':
            fset.add(i)   
    #print(fset)
    for i in fset:#将符号替换为空格
        content=content.replace(i,' ')
    return content
filename='hamlet.txt'
words=gettext(filename)
ls=words.split()
counts={}
for word  in  ls:
    counts[word]=counts.get(word,0)+1
excludes=['the','and','to','of','a','my','in','you']
for word in excludes:
    del counts[word]#这三行是为了去出一些词频，可以不用
lst=list(counts.items())
lst.sort(key=lambda x:x[1],reverse=True)#排序
for i in range(10):#选出前十名
    key,value=lst[i]
    print('{0:<10}{1:>5}'.format(key,value))