向量的构建过程如下所示
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‘,‘worthless‘,‘garbage‘],
                     [‘mr‘,‘licks‘,‘ate‘,‘my‘,‘steak‘,‘how‘,                     ‘to‘,‘stop‘,‘him‘],
                     [‘quit‘,‘buying‘,‘worthless‘,‘dog‘,‘food‘,‘stupid‘]]
    
    classVec = [0,1,0,1,0,1]  #1代表侮辱性文字，0,代表正常言论
    return postingList,classVec
    
def createVocabList(dataSet):
    vocabSet = set([])
    for document in dataSet:
        vocabSet = vocabSet | set(document)
    return list(vocabSet)
            
def setOfWords2Vec(vocabList,inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] = 1 
        else:print ("the word: %s is not in my Vocabulary") % word
    return returnVec

在cmd的doc命令行中调用的python命令如下所示
import bayes
listOPosts,listClasses = bayes.loadDataSet()
myVocabList = bayes.createVocabList(listOPosts)
myVocabList

程序运行的结果如下所示