10.15作业

fo = open('C:\\Users\Administrator\Desktop\song.txt', 'r', encoding='utf-8')
sss = fo.read()
fo.close()
print(sss)
sss=sss.lower()#大写转小写
#print(sss)
sss=sss.replace(',','')#去除标点符号
sss=sss.replace('.','')
sss=sss.replace('?','')
sss=sss.replace(':','')
sss=sss.replace('!','')
sss=sss.lstrip()#去除空格
print(sss)
print("将歌词分隔一个一个的单词为：")
str=sss.split()
print(str)
print("统计每个单词出现的次数为：")
strset=set(str)
abc=dict()
for word in strset:
    abc[word]=str.count(word)#遍历处理
wordlist = list(abc.items())#items格式转换
wordlist.sort(key=lambda x:x[1],reverse=True)     #用lambda函数排序
for i in range (20):
    print (wordlist[i])

　　

 

import jieba
fo = open('C:\\Users\\Administrator\\Desktop\\hello.txt', 'r',encoding='gb2312')
sss=fo.read()
print(sss)
strbn = sss #通过文件读取字符串 str
fo.close()
print(strbn)

#单词计数
strSet = set(strbn)
print(len(strSet),strSet)

strDict ={}
for word in strSet:
    strDict[word] = strbn.count(word)

print(len(strDict),strDict)

wcList = list(strDict.items())
wcList.sort()
print(strDict.items())

#词频排序
wcList.sort(key=lambda x:x[1],reverse=True)
print(wcList)

#输出top20
for s in range(20):
    print(wcList[s])

　　

 

转载于:https://www.cnblogs.com/yysa/p/9789381.html