第四周作业

#英文统计词频

fo = open(‘yingwen.txt‘, ‘r‘, encoding=‘utf-8‘)
str = fo.read()  #通过文件读取字符串 str
fo.close()
print(str)

##预处理标点符号
str = str.replace(‘.‘,‘‘)
print(str)

##预处理特殊字符
sep = ‘.,:‘‘;?!-_‘
for ch in sep:
    str = str.replace(ch,‘‘)
    print(str)

#分解提取单词 list
strlist = str.split()
print(len(strlist),strlist)

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

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

##词频排序list.sort(key=)
Dict = dict(strDict)
DictList = list(Dict.items())
print(DictList)
DictList.sort(key=lambda x:x[1],reverse = True)
print(DictList)

#排除语法型词汇，代词、冠词、连词等无语义词
strSet = set(strSet)
exclude = {‘a‘,‘and‘,‘the‘,‘i‘,‘you‘}
exset = strSet-exclude
print(len(exset),exset)

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

#中文词频统计

fo = open(‘水浒传.txt‘, ‘r‘, encoding=‘utf-8‘)
strhu = fo.read()  #通过文件读取字符串 str
fo.close()
print(strhu)

#特殊符号处理
sep = ‘，。？！；：‘’“”‘
for sh in sep:
    strhu = strhu.replace(sh,‘‘)
    print(strhu)

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

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

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

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

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