樸素貝葉斯python實現，貝葉斯python

樸素貝葉斯python實現，貝葉斯python

機率論是很多機器學習演算法基礎，樸素貝葉斯分類器之所以稱為樸素，是因為整個形式化過程中只做最原始、簡單的假設。（這個假設：問題中有很多特徵，我們簡單假設一個個特徵是獨立的，該假設稱做條件獨立性，其實往往實際問題中不是完全獨立的，這時需要用到另外一種方法叫做貝葉斯網路），後面利用樸素貝葉斯方法，我們應用在垃圾郵件過濾問題當中去。

貝葉斯決策理論的分類方法：

優點：資料較少仍然有效，可以處理多類別問題。

缺點：對於輸入資料的準備方式較為敏感，我理解就是開始要準備每個已經分類好的樣本集

資料類型：標稱型資料（nominal values provide only enough information to distiguish one object from another = 或者|=)

理論基礎就是我們在數理統計課程中學到的那個貝葉斯公式這裡不再複述，我們通過計算條件機率進行分類。

Python進行文本分類：

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]    #1 is abusive, 0 not    return postingList,classVec                 def createVocabList(dataSet):    vocabSet = set([])  #create empty set    for document in dataSet:        vocabSet = vocabSet | set(document) #union of the two sets    return list(vocabSet)def setOfWords2Vec(vocabList, inputSet):    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

第一個函數loadDataSet()建立樣本資料，每個樣本資料進行了分類，1為侮辱言論0 為正常言論。

下一個函數則是建立所有文檔中出現不重複單詞的列表。

第三個函數set轉為向量，如果單詞出現向量中為1，沒出現為0。

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

這個函數中進行了兩個最佳化需要注意：初始化矩陣為1，避免因為某個特性下機率為0 就導致整體機率為0 ，還有一個就是機率進行乘法過後數值會比較小，取log方便比較。

測試代碼函數部分：

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 0def 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)

應用部分：使用樸素貝葉斯過濾垃圾郵件，使用到交叉驗證。

資料準備會有spam檔案夾下面全部是標記的垃圾郵件，ham下是正常郵件。

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

textParse 接受字串進行解析為字串列表。

spamTest 在50封郵件中選取10篇郵件隨機播放為測試集交叉驗證。

所有代碼匯總在一個bayes.py檔案中：

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]    #1 is abusive, 0 not    return postingList,classVec                 def createVocabList(dataSet):    vocabSet = set([])  #create empty set    for document in dataSet:        vocabSet = vocabSet | set(document) #union of the two sets    return list(vocabSet)def setOfWords2Vec(vocabList, inputSet):    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 returnVecdef trainNB0(trainMatrix,trainCategory):    numTrainDocs = len(trainMatrix)    numWords = len(trainMatrix[0])    pAbusive = sum(trainCategory)/float(numTrainDocs)    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])    p1Vect = log(p1Num/p1Denom)          #change to log()    p0Vect = log(p0Num/p0Denom)          #change to log()    return p0Vect,p1Vect,pAbusivedef 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 0def 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 returnVecdef 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    if __name__ == "__main__":    listOPosts,listClasses = loadDataSet()    myVocabList = createVocabList(listOPosts)    print myVocabList    trainMat = []    for postinDoc in listOPosts:        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))    p0V,p1V,pAb = trainNB0(trainMat, listClasses)    testingNB()    spamTest()

 

 

樸素貝葉斯演算法問題

用這個來編軟體 ？ 我給你的提示，也是我現在在做的畢業設計，你用excel來實現你的計算，這個要比軟體來的方便，然後你在利用VB和你製作的excel進行互動。 生活中的具體應用不多
 
基於weka實現文本分類 中文短文本 不同演算法的結果差異較大 樸素貝葉斯明顯優於其他 問原因

樓主你好
對於文本分類，樸素貝葉斯或者貝葉斯信念網路 的效果是最好的 和一般的聚類分類是有區別的
樓主可以參閱 bug triage的相關文獻