第四次

strHello='''...'''.lower()
fo = open('C:\\Users\Administrator\Desktop\hello.txt', 'r', encoding='utf-8')
hello = fo.read()
fo.close()
print(hello)
sep = ''',?'''
for ch in sep:
    strHello = strHello.replace(ch, '')

    strList = strHello.split()
    print(len(strList),strList)
    strSet = set(strList)
    exclude = {'i', 'in', 'the''anymore'}
    strSet = strSet-exclude

    print(len(strSet),strSet)

    strDict = {}
    for hello in strSet:
        strDict[hello] = strList.count(hello)

        print(strDict.items())

wcList = list(strDict.items())
wcList.sort()
print(strDict.items())
print(wcList[:20])

　　

import jieba
fo = open('C:\\Users\Administrator\Desktop\hi.txt','r',encoding='utf-8')
strho = fo.read()  #通过文件读取字符串 str
fo.close()
print(strho)

#对文本进行预处理
sep = '，。？！；：‘’“” "" '
for sh in sep:
    strho = strho.replace(sh,'')
    print(strho)

#单词计数字典 set
strset  = set(strho)
print(len(strset),strset)


##单词计数dict
strDict={}
for word in strset:
    strDict[word]=strho.count(word)
    print(len(strDict),strDict)

#把字典转换为列表
hlouList = list(strDict.items())
print(hlouList)

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

#.输出TOP(20)
for i in range(20):
    print(hlouList[i])

　　

转载于:https://www.cnblogs.com/liuyonghe/p/9789986.html