机器学习实战——文本分类

朴素贝叶斯

优点：在数据较少的情况下仍然有效，可以处理多类别问题。

缺点：对输入数据的准备方式较为敏感。

适用数据类型：标称型数据

核心思想：选择高概率对应的类别。

条件概率：

代码：

from numpy import *
def loadDataSet():
    postingList=[['my','dog','has','flea',\
                  'probelms','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] #0正常，1侮辱,对应postingList的属性
    return postingList,classVec

def createVocabList(dataSet):
    vocabSet=set([]) #创建一个空集
    for document in dataSet:
        vocabSet=vocabSet|set(document) #创建两个集合的并集
    return list(vocabSet)
def setOfWords2Vec(vocabList,inputSet): #vocabList词汇表，inputSet输入的文档
    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) #侮辱性文档的概率
    p0Num=ones(numWords);p1Num=ones(numWords)
    p0Denom=2.0;p1Denom=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)
    p0Vect=log(p0Num/p0Denom)
    return p0Vect,p1Vect,pAbusive

def classifyNB(vec2Classify,p0Vec,p1Vec,pClass1):
    p1=sum(vec2Classify*p1Vec)+log(pClass1) #计算相乘后的概率
    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 postoinDoc in listOPosts:
        trainMat.append(setOfWords2Vec(myVocabList,postoinDoc))
    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))

if __name__ == '__main__':
    testingNB()
    # listOPosts,listClasses=loadDataSet()
    # myVocabList=createVocabList(listOPosts) #单词列表
    # trainMat=[]
    # for postoinDoc in listOPosts:
    #     trainMat.append(setOfWords2Vec(myVocabList,postoinDoc)) #句子分词后的单词在单词列表中出现的矩阵
    # # print(trainMat)
    # p0V,p1V,pAb=trainNB0(trainMat,listClasses)
    # print(p0V)
    # print(p1V)
    # print(pAb)
    # print(myVocabList)
    # print(setOfWords2Vec(myVocabList,listOPosts[0]))
    # print(setOfWords2Vec(myVocabList, listOPosts[3]))