10.15作业

fo= open('C:\\Users\Administrator\Desktop\zz.txt','r',encoding="utf-8")    #从同一目录下读取文件
strgc = fo.read() #小写
fo.close()
print(strgc)

seq ='.,'
for ch in seq:
      strgc=strgc.replace(ch," ")       #用for循环replace函数将.和,替换成空格
print(strgc)

strList = strgc.split()             #拆分
print(len(strList),strList)    #分隔一个一个单词并统计英文单词个数
strSet = set(strList)      #将列表转化成集合
exclude={"and","if","a","or","in","the"}
strSet=strSet-exclude              #去掉排除语法型词汇，代词、冠词、连词等无语义词
print(strSet)

strDict={}
for word in strSet:                #再将集合转化成字典来统计每个单词出现次数
    strDict[word] = strList.count(word)     #只有列表可以统计
print(len(strDict),strDict)

wclist =list(strDict.items())      #以列表返回可遍历的(键, 值) 元组数组
wclist.sort()                     #简单排序
print(strDict.items())

#def takeSecond(elem):        #定义函数
#   x=elem[1]
#    return x
#wclist.sort(key=takeSecond,reverse=True)  #排序，默认升序，reverse=true降序  法①
wclist.sort(key=lambda  x:x[1],reverse=True)     #方法② 用lambda函数排序
print(wclist)

for i in range(20):     #输出前20个
    print(wclist[i])

import jieba

fo = open ('C:\\Users\Administrator\Desktop\\xs.txt', 'r', encoding='utf-8')
x = fo.read ()
fo.close ()
print (x)

sep = '，。？！；：“”‘’-——<_/>'
for en in sep:
   x = x.replace (en, '')

zhaung = list (jieba.cut_for_search (x))

strSet = set (x)
# print(len(strSet), strSet)

strDict = dict ()
for word in strSet:
    strDict[word] = x.count (word)
    # print(len(strDict), strDict)


wcList = list (strDict.items ())
# print(wcList)
wcList.sort (key=lambda x: x[1], reverse=True)
# print(wcList)

for i in range (20):
    print (wcList[i])

转载于:https://www.cnblogs.com/zhanglk/p/9789444.html