机器学习实战——练习（朴素贝叶斯——垃圾邮件过滤）

朴素贝叶斯——垃圾邮件过滤

描述：
有50封邮件，其中垃圾邮件25封，有用邮件25封，垃圾邮件类别记为1，有用邮件类别记为0，现在需要过滤邮件。
实验思路：

• 首先，处理下邮件的形式，文本处理成向量
• 然后，随机将邮件分成训练集和测试集，比例4:1
• 训练集拿出来训练，得到两个类别的概率分布
• 测试集拿出来测试，概率带进来计算类别，并计算错误率

# 输入字符串，输出单词列表
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]


# 每次随机选40篇训练，10篇测试
def spamTest():
    docList = []
    classList = []
    fullText = []
    for i in range(1, 26):
        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)  # create vocabulary
    trainingSet = list(range(50))
    # print(trainingSet)
    testSet = []  # create test set
    # 随机选10个测试样本，40个训练样本
    for i in range(10):
        randIndex = int(random.uniform(0, len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del (trainingSet[randIndex])
    # print(testSet)
    # print(trainingSet)
    # 训练40个邮件，得到概率分布
    trainMat = []
    trainClasses = []
    for docIndex in trainingSet:       # train the classifier (get probs) trainNB0
        trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
        trainClasses.append(classList[docIndex])
    # print(trainMat)
    # print(trainClasses)
    p0V, p1V, pSpam = trainNB0(array(trainMat), array(trainClasses))
    errorCount = 0
    # 将训练得到的概率代入测试中，计算错误率
    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))
    # return vocabList,fullText