使用朴素贝叶斯进行文档分类（二）

'''
@代码作者: Peter
'''
from numpy import *
def loadDataSet():
    #获取训练集
    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(侮辱性文档), 0 not
    return postingList,classVec
                 
def createVocabList(dataSet):
    '''集合去重'''
    vocabSet = set([])  #create empty set
    for document in dataSet:
        vocabSet = vocabSet | set(document) #union of the two sets
    return sorted(list(vocabSet))

def setOfWords2Vec(vocabList, inputSet):
    #词集模型
    #将文档转换成向量,有则为1，无则为0
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] = 1
        else: print('''单词: "%s" 不在词汇表中!''' % word)
    return returnVec

def trainNB0(trainMatrix,trainCategory):
    #计算p(wi|c1) 和 p(wi|c0) 
    numTrainDocs = len(trainMatrix)#训练集文档数
    numWords = len(trainMatrix[0])##训练集每篇文档单词数
    #因为1 is abusive(侮辱性文档), 0 not， 所有sum(trainCategory)表示侮辱性文档的数量
    pAbusive = sum(trainCategory)/float(numTrainDocs) #侮辱性文档的概率
    
    '''利用贝叶斯分类器对文档分类时，要计算多个概率的乘积以获得文档属于
类别的概率：计算 p(w0|c1)*p(w1|c1)*...*p(wn|c1), 如果其中一个概率为0，在最后的乘积为0
为了降低这种影响，可以将所以此的出现次数初始化为1，并将分母初始化为2'''
    p0Num = ones(numWords); p1Num = ones(numWords)      #change to ones() 
    p0Denom = 2.0; p1Denom = 2.0                        #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])
    #防止多个很小的数相乘下溢出的问题（四舍五入后为0），取对数,乘法变加法:
    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):
    #词袋模型
    #将文档转换成向量,有则加1，无则为0。 词袋法，计算词频
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 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)) 
    label = classifyNB(thisDoc,p0V,p1V,pAb)
    print (testEntry,'classified as: ', label, "  （侮辱性文字）" if label==1 else "（非侮辱性文字）")
    
    testEntry = ['stupid', 'garbage','cat']
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    label = classifyNB(thisDoc,p0V,p1V,pAb)
    print (testEntry,'classified as: ', label, " （侮辱性文字）" if label==1 else "（非侮辱性文字)")


if __name__ =="__main__":
    listOPosts, listClasses = loadDataSet()
    myVocabList = createVocabList(listOPosts)
    trainMat = []
    for postinDoc in listOPosts:
        trainMat.append(setOfWords2Vec(myVocabList,postinDoc))#此处用的是词集模型
    print(myVocabList)
    print(trainMat) ;print()
    print()
    p0v, p1v , pAb =trainNB0(trainMat, listClasses)
    print(p0v); print(p1v); print(pAb);print()
    testingNB()

'''
def textParse(bigString):
    #文本解析，将长字符串解析为词向量。input is big string, output is word list
    import re
    listOfTokens = re.split(r'\W*', bigString)
    #单词全部转换为小写。 舍弃长度小于2的单词（认为它们干扰分类结果）。
    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(创建单词表）
    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

def calcMostFreq(vocabList,fullText):
    #计算出30个高频词
    import operator
    freqDict = {}
    for token in vocabList:
        freqDict[token]=fullText.count(token)
    sortedFreq = sorted(freqDict.iteritems(), key=operator.itemgetter(1), reverse=True) 
    return sortedFreq[:30]      

def localWords(feed1,feed0):
    import feedparser
    docList=[]; classList = []; fullText =[]
    minLen = min(len(feed1['entries']),len(feed0['entries']))
    for i in range(minLen):
        wordList = textParse(feed1['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1) #NY is class 1
        wordList = textParse(feed0['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = createVocabList(docList)#create vocabulary
    top30Words = calcMostFreq(vocabList,fullText)   #去除30个高频词
    for pairW in top30Words:
        if pairW[0] in vocabList: vocabList.remove(pairW[0])
    trainingSet = range(2*minLen); testSet=[]           #create test set
    for i in range(20):
        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( 'the error rate is: ',float(errorCount)/len(testSet))
    return vocabList,p0V,p1V

def getTopWords(ny,sf):
    import operator
    vocabList,p0V,p1V=localWords(ny,sf)
    topNY=[]; topSF=[]
    for i in range(len(p0V)):
        if p0V[i] > -6.0 : topSF.append((vocabList[i],p0V[i]))
        if p1V[i] > -6.0 : topNY.append((vocabList[i],p1V[i]))
    sortedSF = sorted(topSF, key=lambda pair: pair[1], reverse=True)
    print( "SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**")
    for item in sortedSF:
        print (item[0])
    sortedNY = sorted(topNY, key=lambda pair: pair[1], reverse=True)
    print ("NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**")
    for item in sortedNY:
        print( item[0])
spamTest()
'''