机器学习经典算法3-朴素贝叶斯

一、算法简要

        贝叶斯是从统计概率的角度来进行分类，确切来说是条件概率，例如要猜是哪一类动物，该动物具备的特征是：四条腿、高度超过x米、哺乳动物，那么在这些特征前提下，计算其为哪种动物的概率。

二、算法一般流程

      1.数据的收集

      2.数据的准备：数值型或布尔型

      3.分析数据

      4.训练算法：计算不同的独立特征的条件概率

      5.测试算法：计算错误率

      6.使用算法：以实际应用为驱动

三、朴素贝叶斯伪代码

      1.计算各个独立特征在各个分类中的条件概率

      2.计算各类别出现的概率

      3.对于特定的特征输入，计算其相应属于特定分类的条件概率

      4.选择条件概率最大的类别作为该输入类别进行返回

四、代码实现与示例

      trainBN0中计算各个独立特征在不同分类中的条件概率和各类别的概率（为了更好的计算，避免独立特征条件概率为0，将所有词出现的次数初始化为1，同时将分母初始化为2---即p0Num=ones(numWords) p1Num=ones(numWords) p0Denom=2.0 p1Denom=2.0）；setOfWords2Vec根据字典形成相应的vector（vector中只有0和1，对词出现的次数多少不区分），而bagOfWords2VecMN中则进行了区分；在classifyNB中进行条件概率计算时，进行了一些log转换。

from numpy import *
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]
    return postingList, classVec
def createVocabList(dataSet):
    vocaSet = set([])
    for doc in dataSet:
        vocaSet = vocaSet | set(doc)
    return list(vocaSet)
def setOfWords2Vec(vocabList, inputSet):
    returnVec=[]
    for doc in inputSet:
        tmpVec = [0]*len(vocabList)
        for word in doc:
            if word in vocabList:
                tmpVec[vocabList.index(word)]=1
            else:
                print "the word: %s is not in my vacobulary!"%word
        returnVec.append(tmpVec)
    return returnVec
def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = []
    for doc in inputSet:
        tmpVec = [0]*len(vocabList)
        for word in doc:
            if word in vocabList:
                if word in vocabList:
                    tmpVec[vocabList.index(word)]+=1
                else:
                    print "the word: %s is not in my vacobulary"%word
        returnVec.append(tmpVec)
    return returnVec
def trainNB0(trainMatrix, trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    '''
    p0Num = zeros(numWords)
    p1Num = zeros(numWords)
    '''
    p0Num = ones(numWords)
    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 = p1Num/p1Denom
    p0Vect = p0Num/p0Denom
    return p0Vect, p1Vect, pAbusive
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass):
    p1 = sum(vec2Classify*p1Vec)+log(pClass)
    p0 = sum(vec2Classify*p0Vec)+log(1.0-pClass)
    if p1>p0:
        return 1
    else:
        return 0
def testingNB():
    listOPosts, listClasses = loadDataSet()
    myVocabList = createVocabList(listOPosts)
    trainMat = setOfWords2Vec(myVocabList,listOPosts)
    p0V, p1V, pAb = trainNB0(array(trainMat),array(listClasses))
    result = []
    testSet=[['love','my', 'dalmation'],['stupid','garbage']]
    testVec = setOfWords2Vec(myVocabList, testSet)
    for test in testVec:
        tmp_r = classifyNB(test, p0V, p1V, pAb)
        result.append(tmp_r)
    for i in range(len(testSet)):
        print testSet[i]
        print "The class of it is: "+str(result[i])
testingNB()