吴裕雄--天生自然python机器学习：使用朴素贝叶斯过滤垃圾邮件

使用朴素贝叶斯解决一些现实生活中
的问题时，需要先从文本内容得到字符串列表，然后生成词向量。

准备数据：切分文本

测试算法：使用朴素贝叶斯进行交叉验证

文件解析及完整的垃圾邮件测试函数

def createVocabList(dataSet):

    vocabSet = set([])  #create empty set

    for document in dataSet:

        vocabSet = vocabSet | set(document) #union of the two sets

    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

def bagOfWords2VecMN(vocabList, inputSet):

    returnVec = [0]*len(vocabList)

    for word in inputSet:

        if word in vocabList:

            returnVec[vocabList.index(word)] += 1

    return returnVec

def textParse(bigString):    #input is big string, #output is word list

    import re

    listOfTokens = re.split(r'\W*', bigString)

    return [tok.lower() for tok in listOfTokens if len(tok) > 2]

def trainNB0(trainMatrix,trainCategory):

    numTrainDocs = len(trainMatrix)

    numWords = len(trainMatrix[0])

    pAbusive = sum(trainCategory)/float(numTrainDocs)

    p0Num = ones(numWords)

    p1Num = ones(numWords)      #change to ones()

    p0Denom = 2.0

    p1Denom = 2.0                        #change to 2.0

    for i in range(numTrainDocs):

        if trainCategory[i] == 1:

            p1Num += trainMatrix[i]

            p1Denom += sum(trainMatrix[i])

        else:

            p0Num += trainMatrix[i]

            p0Denom += sum(trainMatrix[i])

    p1Vect = log(p1Num/p1Denom)          #change to log()

    p0Vect = log(p0Num/p0Denom)          #change to log()

    return p0Vect,p1Vect,pAbusive

def aloneIndex(datasetLen):

    a = []

    while(True):

        randIndex = int(random.uniform(0,len(trainingSet)))

        a.append(randIndex)

        if(len(set(a))==10):

            break

    return a

def spamTest():

    docList=[]

    classList = []

    fullText =[]

    for i in range(1,26):

        wordList = textParse(open('F:\\machinelearninginaction\\Ch04\\email\\spam\\%d.txt' % i).read())

        docList.append(wordList)

        fullText.extend(wordList)

        classList.append(1)

        wordList = textParse(open('F:\\machinelearninginaction\\Ch04\\email\\ham\\%d.txt' % i).read())

        docList.append(wordList)

        fullText.extend(wordList)

        classList.append(0)

    vocabList = createVocabList(docList)#create vocabulary

    trainingSet = range(50)

    testSet = aloneIndex(trainingSet) #create test set

    trainingSetT = []

    for i in range(len(trainingSet)):

        for j in range(len(testSet)):

            if(testSet[j] != trainingSet[i]):

                trainingSetT.append(trainingSet[i])

    trainingSet = trainingSetT

    trainMat=[]

    trainClasses = []

    for docIndex in trainingSet:#train the classifier (get probs) trainNB0

        trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))

        trainClasses.append(classList[docIndex])

    p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses))

    errorCount = 0

    for docIndex in testSet:        #classify the remaining items

        wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])

        if(classifyNB(array(wordVector),p0V,p1V,pSpam) != classList[docIndex]):

            errorCount += 1

            print("classification error",docList[docIndex])

    print('the error rate is: ',float(errorCount)/len(testSet))

spamTest()