python统计单词、中文字个数与频率

有时候我们想统计一下单词的个数，比如四六级，在四六级中出现的高频词汇，统计一下我们日常说话的常用字等。利用所学知识编写。

import operator
#这里是初始文档
f = open('word.txt','r',encoding='utf-8')
speech_etxt = f.read()

#接下来这一段是为了处理中文的切分，给中文添加空格。
#添加空格,a 代表追加
f2 =open('newWord.txt','a+',encoding='utf-8')
i = 0
for i in range(len(speech_etxt)):
    s = speech_etxt[i]+' '
    f2.write(s)
f.close()
f2.close()



f3 = open('newWord.txt','r',encoding='utf-8')
txt = f3.read()
speech = txt.split(' ')
# 利用字典进行处理单词统计
dic = {}
for word in speech:
    if word not in dic:
        dic[word] = 1
    else:
        dic[word] = dic[word] + 1

swd = sorted(dic.items(),key=operator.itemgetter(1),reverse=True)
f1 =open('out.txt','w',encoding='utf-8')
w = 0
m = []
for k,v in swd:
    w = w + 1
    a = k
    b = str(v)
    m += a
    str1 = a+': '+b+'\n'
    f1.write(str1)


print(w)
print(m)