Machine Learning in action --朴素贝叶斯(已勘误)

最近在自学机器学习，应导师要求，先把《Machine Learning with R》动手刷了一遍，感觉R真不能算是一门计算机语言，感觉也就是一个功能复杂的计算器。所以这次就决定使用经典教材《Machine Learning in action》。因为开学得换work station ，怕到时候代码又丢了，所以就索性开个博客，把代码上传上来。

因为书上的原代码有很多错误，并且网上的许多博客的代码也是没有改正的，这次我把修正过的代码po上来

edition：python3.5

talk is cheap show me the code

函数定义代码

#coding=utf-8from numpy import *#from math import logdef loadDataSet():#数据格式    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 侮辱性文字 ， 0 代表正常言论    return postingList,classVecdef createVocabList(dataSet):    #创建空集    vocabSet = set([])    for document in dataSet:        vocabSet = vocabSet | set(document)    return list(vocabSet)def setOfWords2Vec(vocabList, inputSet):    #创建一个长度为 len(vocabList)， 所含元素全为0的向量    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 Vocabulary"%word)    return returnVecdef trainNBO(trainMatrix, trainCategory):    numTrainDocs = len(trainMatrix) #矩阵行数    numWords = len(trainMatrix[0])#矩阵列数    #sum(trainCategory)表示label为1 的数量    pAbusive = sum(trainCategory) / float(numTrainDocs)#label为1的先验概率p(c1)    p0Num = ones(numWords) #列数    p1Num = ones(numWords)#列数    p0Denom = 2.0    p1Denom = 2.0    for i in range(numTrainDocs): #每一行        if trainCategory[i] == 1:            p1Num += trainMatrix[i]            p1Denom += sum(trainMatrix[i])        else:            p0Num += trainMatrix[i]            p0Denom += sum(trainMatrix[i])    p1Vect = log(p1Num / p1Denom)    p0Vect = log(p0Num / p0Denom)    return p0Vect, p1Vect, pAbusivedef classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):    p1 = sum(vec2Classify * p1Vec) + log(pClass1)    p0 = sum(vec2Classify * p0Vec) + log(1.0- pClass1)    if p1 > p0:        return 1    else:        return  0def textParse(bigString):    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, encoding='gbk', errors='ignore').read())        docList.append(wordList)        fullText.extend(wordList)        classList.append(1)        wordList = textParse(open('email/ham/%d.txt'%i, encoding='gbk', errors='ignore').read())        docList.append(wordList)        fullText.extend(wordList)        classList.append(0)    vocabList = createVocabList(docList)    trainingSet = list(range(50))    testSet = []    #随机构建训练集    for i in range(10):        randIndex = int(random.randint(0, len(trainingSet)))        testSet.append(trainingSet[randIndex])        del(trainingSet[randIndex])    trainMat = []    trainClasses = []    for docIndex in trainingSet:        trainMat.append(setOfWords2Vec(vocabList, docList[docIndex]))        trainClasses.append(classList[docIndex])    p0V, p1V, pSpam = trainNBO(array(trainMat), array(trainClasses))    errorCount = 0    #对测试集进行分类    for docIndex in testSet:        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))

在spamTest()中，主要有以下几个错误
1.’range’ object doesn’t support item deletion –>这是因为python3中中range不返回数组对象，而是返回range对象
改正方法：http://blog.csdn.net/dillon2015/article/details/52987792
1.UnicodeDecodeError: ‘gbk’ codec can’t decode byte 0xae in position 199: illegal multibyte sequence —> 这个具体什么原因，我也是一头乱麻，后来找了下，因为原文件是 gbk 格式，所以改成以下格式

wordList = textParse(open('email/spam/%d.txt'%i, encoding='gbk', errors='ignore').read())

上面代码块只是定义了主要的函数，离运行还差一点。由于书原文中，采用了使用 iPython 命令行的运行方式，但是博主比较懒，所以干脆舍弃掉原来的方式。

废话不多少，直接上代码

实验1

if __name__=="__main__":    listOPosts, listClasses = loadDataSet()    myVocabList = createVocabList(listOPosts)    print(sum(listClasses))    print(listClasses)    print(myVocabList)    vec1 = setOfWords2Vec(myVocabList, listOPosts[0])    vec2 = setOfWords2Vec(myVocabList, listOPosts[3])    print(vec1)    print(vec2)

实验2 ：

if __name__ == "__main__":     listOPosts, listClasses = loadDataSet()    myVocabList = createVocabList(listOPosts)    trainMat = []    for postinDoc in listOPosts:        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))    p0V, p1V ,pAb = trainNBO(trainMat, listClasses)    print(p0V)    print(p1V)    print(pAb)

实验3 ：

if __name__ == "__main__":    listOPosts, listClasses = loadDataSet()    myVocabList = createVocabList(listOPosts)    trainMat = []    for postinDoc in listOPosts:        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))    p0V, p1V ,pAb = trainNBO(trainMat, listClasses)    testEntry = ['love','my','dalmation']    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))    print(testEntry , 'classified as :', classifyNB(thisDoc, p0V, p1V, pAb))

更多请戳github
https://github.com/Edgis/Machine-learning-in-action/blob/master/bayes.py