Machine_Learning_in_Action04 - Naive_Bayes

Naive Bayes

使用概率分布进行分类

学习朴素贝叶斯分类器

解析 RSS 源数据

使用朴素贝叶斯来分析区域态度

目录

• Naive Bayes
  • 基于贝叶斯决策理论的分类方法
  • 使用朴素贝叶斯进行文档分类
  • 文本分类实例
  • 垃圾邮件分类

• 从最简单的概率分来开始
• 然后在此基础上加入一些假设
• 然后学习朴素贝叶斯分类

基于贝叶斯决策理论的分类方法

• 朴素贝叶斯优点：
  • 可以处理少量数据，可以处理多分类
• 缺点：
  • 对数据敏感
• 朴素贝叶斯是贝叶斯理论的一个子集

使用朴素贝叶斯进行文档分类

在文档分类中，整个文档是一个实例，特征就是文档中的字词。

朴素贝叶斯是文档分类问题常用的方法。

• 朴素贝叶斯的一般步骤
  • 收集数据：可以使用任何方法，我们使用RSS源数据
  • 准备：数值型或布尔型数据
  • 分析：由于特征太多，画特征图可能没用。画直方图效果更好
  • 训练：计算独立特征的条件概率
  • 测试：计算误差
    • 应用：可以在任何场景中使用朴素贝叶斯分类器，不一定是文本

文本分类实例

import numpy as np

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([])
    for document in dataSet:
        vocabSet = vocabSet | set(document)
    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

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

def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + np.log(pClass1)
    p0 = sum(vec2Classify * p0Vec) + np.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(np.array(trainMat),np.array(listClasses))
    testEntry = ['love', 'my', 'dalmation']
    thisDoc = np.array(setOfWords2Vec(myVocabList, testEntry))
    print(testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))
    testEntry = ['stupid', 'garbage']
    thisDoc = np.array(setOfWords2Vec(myVocabList, testEntry))
    print(testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))


if __name__ == '__main__':
    # dataSet, classes = loadDataSet()
    # vocabs = createVocabList(dataSet)
    # print(vocabs)
    # trainMat=[]
    # for postinDoc in dataSet:
    #     trainMat.append(setOfWords2Vec(vocabs, postinDoc))
    # p0V,p1V,pAb=trainNB0(trainMat, classes)
    # print(p0V, p1V, pAb)

    testingNB()

垃圾邮件分类

## bag of word
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('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)
    trainingSet = list(range(50)); testSet=[]
    for i in range(10):
        randIndex = int(np.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(np.array(trainMat),np.array(trainClasses))
    errorCount = 0
    for docIndex in testSet:
        wordVector = setOfWords2Vec(vocabList, docList[docIndex])
        if classifyNB(np.array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
            errorCount += 1
    print('the error rate is: ',float(errorCount)/len(testSet))

if __name__ == '__main__':
    spamTest()