机器学习：贝叶斯

利用朴素贝叶斯方法，进行垃圾邮件分类，email文件夹下包含了25个正常留言和25个非正常留言的数据，训练一个贝叶斯分类器，并测试分类器。

bayes.py包含了所有函数的实现，需要做的是，明白各个函数的功能作用及输入输出，在脚本中完成函数的调用，给出要求的格式的结果。

from numpy import *
import csv
import random
random.seed(21860251)

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 is abusive, 0 not
    return postingList, classVec


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):  # 对比词汇表和输入的所有单词
    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):  # trainMatrix是文档矩阵 trainCategory是文档类别标签构成的向量
    numTrainDocs = len(trainMatrix)  # 文档矩阵的长度
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory) / float(numTrainDocs)

    p0Num = ones(numWords)  # 初始化概率
    p1Num = ones(numWords)
    p0Denom = 2.0
    p1Denom = 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 classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)  # element-wise mult
    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else:
        return 0


def bagOfWords2VecMN(vocabList, inputSet):  # 朴素贝叶斯词带模型
    returnVec = [0] * len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1  # 加1
    return returnVec


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))
    print(testEntry, 'classified as: ', classifyNB(thisDoc, p0V, p1V, pAb))


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 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))
    testSet = []  # create test set 随机构建测试集
    for i in range(10):
        randIndex = int(random.uniform(0, len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del (trainingSet[randIndex])

    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))

    out = open('test_result.csv', 'w', newline='')
    csv_write = csv.writer(out, dialect='excel')
    csv_write.writerow(['testSet', 'predict_value', 'truth'])

    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])
        test_result_list = [docIndex, classifyNB(array(wordVector), p0V, p1V, pSpam), classList[docIndex]]
        csv_write.writerow(test_result_list) # 以覆盖方式来写入csv文件中
    print('the error rate is: ', float(errorCount) / len(testSet))
    # return vocabList,fullText

testSet	predict_value	truth
9	0	0
34	1	1
3	1	0
31	1	0
10	1	1
42	1	1
18	1	1
21	0	0
36	1	1
14	1	1