机器学习实战之朴素贝叶斯进行文档分类（Python 代码版）

　　　　贝叶斯是搞概率论的。学术圈上有个贝叶斯学派。看起来吊吊的。关于贝叶斯是个啥网上有很多资料。想必读者基本都明了。我这里只简单概括下：贝叶斯分类其实就是基于先验概率的基础上的一种分类法，核心公式就是条件概率。举个俗气的例子，通过我们的以往观察，鲤鱼中尾巴是红色的占比达90%，鲫鱼中尾巴是红色的占比只有1%不到，那么新来了一条小鱼，他是鲤鱼还是鲫鱼呢？我看一下他的尾巴，发现是红色，根据过去的先验概率经验，它是鲤鱼的概率比较大，我认为它是鲤鱼。

　　这当时是个最简单的例子，实践中的问题就复杂了。比如说特征不止是尾巴红不红，还有鱼嘴巴大不大，鱼肥不肥，鱼身子长还是宽，各种，而且不是一个特征就能分辨出来的，还需要多方分析，然后贝爷感觉这个那个的真麻烦，就先假定每个特征都是独立的，如果一条鱼红尾巴大嘴巴肥得很还是长身子，就这样求她是鲤鱼的概率：鲤鱼中红尾巴0.9*鲤鱼中大嘴巴0.3*鲤鱼中肥猪0.6*鲤鱼中长身子0.4=0.27*0.24.。。。。

　　闲话少扯。上代码分析。我代码干的不是鱼的分类了，而是一篇文档。

　　

from numpy import * 
def loadDataSet():#这个函数呢，他建立了一个敏感词典，并打了标签，共6个词集合，其中2、4、6词集合中的词是敏感词
    postingList = [['my','dog','has','flea',\
                    'problems','help','please'],
                   ['maybe','not','take','him',\
                    'to','dog','park','stupid'],
                    ['my','dalmation','is','so','cute',\
                     'T','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):#这个函数呢，它是把输入的dataset（就是一个新文档嘛）进行分解处理，返回的是这个文档没有重复词的列表
    vocabSet = set([])
    for document in dataSet:
        vocabSet = vocabSet | set(document)
    return list(vocabSet)

def setOfWords2Vec(vocabList,inputSet):#这个函数呢，他就是根据输入的新文档，和词汇表，来对新文档打标签，看他有多少敏感词，只要是出现了词汇表里的词，就将标签打1，没有就默认为0
    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):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix)
    pAbusive = sum(trainCategory) / float(numTrainDocs)
    p0Num = zeros(numWords)
    p1Num= zeros(numWords)
    p0Denom = 0.0;p1Denom = 0.0
    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,pClass1):
    p1= sum(vec2Classify * p1Vec) + log(pClass1)
    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else :
        return 0
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 bagOfWords2VecMN(vocabList,inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] +=1
    return returnVec
def 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('E:/数据挖掘/MLiA_SourceCode/machinelearninginaction/Ch04/email/spam/%d.txt' % i).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
     #   print('zhe li de i shi %d,',  i)
        wordList = textParse(open('E:/数据挖掘/MLiA_SourceCode/machinelearninginaction/Ch04/email/ham/%d.txt' % i).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = createVocabList(docList)
    trainingSet = list(range(50));testSet=[]
    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:
        trainMat.append(setOfWords2Vec(vocabList,docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses))
    errorCount=0
    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))