机器学习实战ch04

>>> import bayes
>>> listOPosts,listClasses=bayes.loadDataSet()
>>> listOPosts
[['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']]
>>> listClasses
[0, 1, 0, 1, 0, 1]
>>> myVocabList=bayes.createVocabList(listOPosts)
>>> myVocabList
['cute', 'love', 'help', 'garbage', 'quit', 'I', 'problems', 'is', 'park', 'stop', 'flea', 'dalmation', 'licks', 'food', 'not', 'him', 'buying', 'posting', 'has', 'worthless', 'ate', 'to', 'maybe', 'please', 'dog', 'how', 'stupid', 'so', 'take', 'mr', 'steak', 'my']
>>> bayes.setOfWords2Vec(myVocabList,listOPosts[0])
[0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1]
>>> trainMat=[]
>>> for postinDoc in listOPosts:
...     trainMat.append(bayes.setOfWords2Vec(myVocabList,postinDoc))
... 
>>> trainMat
[[0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1], [0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 0, 0, 0], [1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1], [0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1], [0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0]]

上面运行的程序中listOPosts中有六句话，把每句话的单词拆分开来。listClasses表示着这六句话是侮辱类还是非侮辱类，比如第一句话：my dog has flea problems help please，是非侮辱类，所以标为0。myVocabList是listOPosts六句话的所有单词的集合，setOfWords2Vec函数使listOPosts中的句子由myVocabList来表示，比如listOPosts[0]中有help这个单词，那么myVocabList[2]就是1。而trianMat就是listOPosts中的六句话全部用myVocabList来表示。

def trainNB0(trainMatrix,trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    p0Num = zeros(numWords); p1Num = zeros(numWords)      #change to ones() 
    p0Denom = 0; p1Denom = 0                        #change to 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         #change to log()
    p0Vect = p0Num/p0Denom          #change to log()
    return p0Vect,p1Vect,pAbusive	

该函数的输入参数是：

>>> p0V,p1V,pAb=bayes.trainNB0(trainMat,listClasses)

sum(trainCategory)代表的是侮辱性的句子的条数，float(numTrainDocs)是总的句子的条数，pAbusive就是输入的样本中侮辱性句子所占的比例，这里为0.5。numWords是所有单词集合的个数，接下来的for语句中一个句子一个句子进行分析，p1Num是一个具有numWords个元素的列表，如果一个句子是侮辱性的，那么trainMatrix中跟句子相关的列表会累加起来。p0Num是一个具有numWords个元素的列表，如果一个句子是非侮辱性的，那么trainMatrix中跟句子相关的列表会累加起来。从p1V和p0V可以看出相应单词在侮辱性或非侮辱性句子中出现的比例。如p1V[26]是stupid，表示在所有侮辱性句子的单词中，这个词所占的比例是0.15789474。 

>>> p0V
array([ 0.04166667,  0.04166667,  0.04166667,  0.        ,  0.        ,
        0.04166667,  0.04166667,  0.04166667,  0.        ,  0.04166667,
        0.04166667,  0.04166667,  0.04166667,  0.        ,  0.        ,
        0.08333333,  0.        ,  0.        ,  0.04166667,  0.        ,
        0.04166667,  0.04166667,  0.        ,  0.04166667,  0.04166667,
        0.04166667,  0.        ,  0.04166667,  0.        ,  0.04166667,
        0.04166667,  0.125     ])
>>> sum(p0V)
0.99999999999999967
>>> p1V
array([ 0.        ,  0.        ,  0.        ,  0.05263158,  0.05263158,
        0.        ,  0.        ,  0.        ,  0.05263158,  0.05263158,
        0.        ,  0.        ,  0.        ,  0.05263158,  0.05263158,
        0.05263158,  0.05263158,  0.05263158,  0.        ,  0.10526316,
        0.        ,  0.05263158,  0.05263158,  0.        ,  0.10526316,
        0.        ,  0.15789474,  0.        ,  0.05263158,  0.        ,
        0.        ,  0.        ])
>>> sum(p1V)
0.99999999999999978

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 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)

上面testingNB()函数中将love my dalmation转化成由myVocabList表示的数组，然后分别与p0V和p1V相乘，看哪个值大，就判定这句话是什么类型的。
bagOfWords2VecMN函数和setOfWords2Vec函数的区别在于用

            returnVec[vocabList.index(word)] += 1

替换

            returnVec[vocabList.index(word)] = 1

因为输入的句子中有可能有相同的单词。

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 = range(50); testSet=[]           #create test set
    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))
    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]
    print 'the error rate is: ',float(errorCount)/len(testSet)
    #return vocabList,fullText

上面的第一个函数textParse将邮件的句子拆分成单词。spamTest函数中的docList相当于前面的 listOPosts，classList相当于前面的listClasses，spam和ham文件夹中各有25封邮件，将这50封邮件拆成单词，并存放于docList中。spam中的邮件标为1，ham中邮件标为0，记录在classList中。vocabList包含了50封邮件中的所有拆分的单词。然后50封邮件中随机抽取10封为测试邮件testSet，其余40封为trainingSet。由trainingSet中的邮件做成trainMat和trainingClasses，然后得到p0V，p1V和pSpam。接下来用p0V，p1V和pSpam三个参数对testSet中的10封邮件进行测试，根据测出的结果（0或1）与已知的结果比较，得出错误的概率。

>>> ny=feedparser.parse('http://newyork.craigslist.org/search/stp/index.rss')
>>> sf=feedparser.parse('http://sfbay.craigslist.org/search/stp/index.rss')
>>> sf['entries']
[]
>>> ny['entries']
[]
>>> import bayes
>>> vocaList,pSF,pNY=bayes.localWords(ny,sf)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "bayes.py", line 142, in localWords
    testSet.append(trainingSet[randIndex])
IndexError: list index out of range

上面的程序运行起来和书中的不一样，可能是RSS修改了书中ny['entries']的长度为100，但是这里该长度为0。所以程序中运行的参数trainingSet变成了0，所以报错了。