樸素貝葉斯分類器

from numpy import *

def loadDataSet():
    postingList = 【測試數據集】
    classVec = [1, 0, 1, 0, 1, 0]  # 1 stands for insulting message,0 stands for normal statement
    return postingList, classVec

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 trainNB0(trainMatrix, trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory) / float(numTrainDocs)

        p0Num = ones(numWords); p1Num = ones(numWords)
    p0Denom = 2.0; p1Denom = 2.0 # maybe avoid 1/1

    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)
    p0Vect = log(p0Num / p0Denom)

    return p0Vect, p1Vect, pAbusive
def setOfWords2Vec(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] = 1
        else:
            print ("數據：%s 不在數據集中" % word)
    return returnVec

def createVocabList(dataSet):
    vocabSet = set([])
    for document in dataSet:
        vocabSet = vocabSet | set(document)
    return list(vocabSet)



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 = 【測試集】
    thisDoc = array(setOfWords2Vec(myVocabList,testEntry))
    print (testEntry,'被分類爲： ',classifyNB(thisDoc,p0V,p1V,pAb))
    testEntry =【測試集】
    thisDoc = array(setOfWords2Vec(myVocabList,testEntry))
    print (testEntry,'被分類爲： ',classifyNB(thisDoc,p0V,p1V,pAb))

作者：WangB