从文本中构建词向量

妖狐艹你老母 2022-06-04 08:48 187阅读 0赞

词表到向量的转换函数：

def loadDataSet():
        postingList = [['my', 'dog', 'has', 'flea', 'problems', 'help', 'please'],
                       ['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'],
                       ['my', 'dalmation', 'is', 'so', 'cute', 'I', 'love', 'him'],
                       ['stop', 'posting', 'stupid', 'wprthless', 'garbage'],
                       ['mr', 'licks', 'ate', 'my', 'steak', 'how', 'to', 'stop', 'him'],
                       ['quit', 'buying', 'worthless', 'dog', 'food', 'stupid']] #进行词条切分后的文档集合
        classVec = [0, 1, 0, 1, 0, 1] #1表示侮辱性文字，0表示正常言论
        return postingList, classVec
    
    def createVocabList(dataSet):
        vocabSet = set([]) #创建一个空子集
        for document in dataSet:
            vocabSet = vocabSet | set(document)  #set子集并运算，创建一个不重复词列表
        return list(vocabSet)
    
    #检查某个词是否在vocabList中
    def setOfWords2Vec(vocabList, inputSet): #vocabList词汇表，inputSet输入文档
        returnVec = [0]*len(vocabList) #创建一个与vocabList等长的0向量
        for word in inputSet:
            if word in vocabList:
                returnVec[vocabList.index(word)] = 1 #相应的位置置1
            else: print("the word: %s is not in my Vocabulary!" % word)
        return returnVec
    
    
    listOPosts, listClasses = loadDataSet()
    myVocabList = createVocabList(listOPosts)
    print(myVocabList)
    print(setOfWords2Vec(myVocabList, listOPosts[0]))
    
    >>['park', 'flea', 'dalmation', 'to', 'stop', 'love', 'dog', 'problems', 'posting', 'help', 'garbage', 'him', 'not', 'is', 'stupid', 'mr', 'buying', 'how', 'quit', 'I', 'food', 'ate', 'steak', 'cute', 'licks', 'wprthless', 'my', 'so', 'take', 'worthless', 'maybe', 'please', 'has']
    >>[0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1]