python第四次作业

q = open('遇见.txt', 'r', encoding='utf-8').read()
wordsls = jieba.lcut(q)
wcdict = {}
for word in wordsls:
    if len(word) == 1:
        continue
    else:
        wcdict[word] = wcdict.get(word, 0) + 1

wcls = list(wcdict.items())
wcls.sort(key=lambda x: x[1], reverse=True)
print(wcls)
for i in range(7):
    print(wcls[i])

　　

 

#准备utf-8编码的文本文件，通过文件读取字符串str
fo=open('because of you.txt','r',encoding='utf-8')
stra = fo.read().lower()
fo.close()
print(stra)

sep=',.;!'
for ch in sep:
    stra = stra.replace(ch,'')#进行预处理，清除掉sep中存在的标点符号
print(stra)

strList=stra.split('')
print(len(strList),strList)#分解提取单词，转化为列表list

strSet = set(strList)
print(len(strSet),strSet)#转化为集合

strDict={}
for world in strSet:
    strDict[world] = strList.count(world)
print(len(strDict),strDict)#转化为字典，计算上一个集合中每个单词出现的次数

wcList=list(strDict.items())
print(wcList)#将字典中的目录转化为列表输出
wcList.sort(key=lambda x:x[1],reverse= True)
print(wcList) #按降序输出

e = {'a','the','an','and','i','or','of'}
strSet = strSet - e
print(len(strSet),strSet) #排除语法型词汇，代词、冠词、连词等无语义词

for i in range(20):
    print(wcList[i]) #TOP20输出