07 机器学习 - 朴素贝叶斯分类算法(案例二)

利用大量邮件先验数据，使用朴素贝叶斯分类算法来自动识别垃圾邮件。

python实现：

#过滤垃圾邮件
def textParse(bigString):      #正则表达式进行文本解析
    import re
    listOfTokens = re.split(r'\W*',bigString)
    return [tok.lower() for tok in listOfTokens if len(tok) > 2]

def spamTest():
    docList = []; classList = []; fullText = []
    for i in range(1,26):                          #导入并解析文本文件
        wordList = textParse(open('email/spam/%d.txt' % i).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
        wordList = textParse(open('email/ham/%d.txt' % i).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = createVocabList(docList)
    trainingSet = range(50);testSet = []
    for i in range(10):                         #随机构建训练集
        randIndex = int(random.uniform(0,len(trainingSet)))
        testSet.append(trainingSet[randIndex])    #随机挑选一个文档索引号放入测试集
        del(trainingSet[randIndex])              #将该文档索引号从训练集中剔除
    trainMat = []; trainClasses = []
    for docIndex in trainingSet:
        trainMat.append(setOfWords2Vec(vocabList, docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V, p1V, pSpam = trainNB0(array(trainMat), array(trainClasses))
    errorCount = 0
    for docIndex in testSet:              #对测试集进行分类
        wordVector = setOfWords2Vec(vocabList, docList[docIndex])
        if classifyNB(array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
            errorCount += 1
    print 'the error rate is: ', float(errorCount)/len(testSet)