python第四次作業
阿新 • • 發佈：2018-10-15
print item 字典 src tin you range 目錄 word
q = open(‘遇見.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])
#準備utf-8編碼的文本文件，通過文件讀取字符串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,‘‘)#進行預處理，清除掉sep中存在的標點符號
print(stra)
strList=stra.split(‘‘)
print(len(strList),strList)#分解提取單詞，轉化為列表list
strSet = set(strList)
print(len(strSet),strSet)#轉化為集合
strDict={}
for world in strSet:
strDict[world] = strList.count(world)
print(len(strDict),strDict)#轉化為字典，計算上一個集合中每個單詞出現的次數
wcList=list(strDict.items())
print(wcList)#將字典中的目錄轉化為列表輸出
wcList.sort(key=lambda x:x[1],reverse= True)
print(wcList) #按降序輸出
e = {‘a‘,‘the‘,‘an‘,‘and‘,‘i‘,‘or‘,‘of‘}
strSet = strSet - e
print(len(strSet),strSet) #排除語法型詞匯，代詞、冠詞、連詞等無語義詞
for i in range(20):
print(wcList[i]) #TOP20輸出
python第四次作業