朴素贝叶斯算法

最新推荐文章于 2021-05-28 14:30:03 发布

彼得暹罗猫

最新推荐文章于 2021-05-28 14:30:03 发布

阅读量288

点赞数

分类专栏：机器学习算法

本文链接：https://blog.youkuaiyun.com/Gage_0209/article/details/81563958

版权

机器学习算法专栏收录该内容

3 篇文章

订阅专栏

def loadDataSet():
    postingList = [['my', 'dog', 'has', 'flea', 'problem', '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]
    return postingList, classVec

def createVocabList(dataSet):
    vocabSet = set([])
    for document in dataSet:
        vocabSet = vocabSet | set(document)
    return 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

def trainNB0(trainMatrix, trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    p1Num = ones(numWords)
    p0Num = ones(numWords)
    p1Denom = 2.0
    p0Denom = 2.0
    for i in range(numTrainDocs):
        if trainategory[i] = 1:
            p1Num += trainMatrix[i]
            p1Denom += 1
        else:
            p0Num += trainMatrix[i]
            p0Denom += 1
    p1Vect = log(p1Num / p1Denom)
    p0Vect = log(p0Num / p0Denom)
    return p0Vect, p1Vect, pAbusive

def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)
    p0 = sum(vec2Classify * p0Vec) + log(1-pClass1)
    if p1 > p0:
        return 1
    else:
        return 0

def testingNB():
    listOPosts, listClasses = loadDataSet()
    myVocabList = createVocabList(listOPosts)
    trainMat = []
    for postinDoc in listOPosts:
        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
    p0V, p1V, pAb = trainNB0(array(trainMat), array(listClasses))
    testEntry = ['love', 'my', 'dalmation']
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    print testEntry, 'classified as: ', classifyNB(thisDoc, p0V, p1V, pAb)
    testEntry = ['stupid', 'garbage']
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))