中英文统计

fo=open("sunstr.txt","r",encoding="utf-8")
sunstr=fo.read().lower()
for ch in ",.":
    sunstr.replace(ch," ")
sunstr = sunstr.split();
sunstrset = set(sunstr)

dic = {}
for i in sunstrset:
    dic[i] = sunstr.count(i)
print(dic)


for key in dic:
    print(key,dic[key]);

wcList = list(dic.items())

def tskeSecond(elem):
    return elem[1]

wcList.sort(key=tskeSecond,reverse=True)
print(wcList)

def getTxt():
    txt = open("sunstr.txt").read()
    txt = txt.lower()
    for ch in ‘!"@#$%^&*()+,-./:;<=>?@[\\]_`~{|}‘:
        txt.replace(ch," ")
    return txt
# sunstr = sunstr.replace(","," ")

sunstr = getTxt().split()
sunstrset = set(sunstr)

dic = {}
for i in sunstrset:
    dic[i] = sunstr.count(i)
print(dic)


for key in dic:
    print(key,dic[key]);

wcList = list(dic.items())

def tskeSecond(elem):
    return elem[1]

wcList.sort(key=tskeSecond,reverse=True)
print(wcList)

import jieba
word =open("123.txt","r",encoding="utf-8").read()
 
for ch in "，。“”":
    word = word.replace(ch,"")
 
word = jieba.cut(word)
word = list(word)
print(word)
 
 
wordset =set(word)
worddic ={}
 
for i in wordset:
    worddic[i]= word.count(i)
print(worddic)
 
wcList = list(worddic.items())
wcList.sort(key=lambda x:x[1],reverse=True)
print(wcList)