朴素贝叶斯算法的python实现

下面是脚本之家 jb51.cc 通过网络收集整理的代码片段。

脚本之家小编现在分享给大家，也给大家做个参考。

#coding=utf-8
from numpy import *
def loadDataSet():
    postingList=[['my','dog','has','flea','problems','help','please'],['maybe','not','take','him','to','park','stupid'],['my','dalmation','is','so','cute','I','love','him'],['stop','posting','stupid','worthless','garbage'],['mr','licks','ate','my','steak','how','stop',['quit','buying','food','stupid']]
    classVec = [0,1,1]    #1 is abusive,0 not
    return postingList,classVec
#创建一个带有所有单词的列表
def createVocabList(dataSet):
    vocabSet = set([])
    for document in dataSet:
        vocabSet = vocabSet | set(document)
    return list(vocabSet)
     
def setOfWords2Vec(vocabList,inputSet):
    retVocabList = [0] * len(vocabList)
    for word in inputSet:
        if word in vocabList:
            retVocabList[vocabList.index(word)] = 1
        else:
            print 'word ',word,'not in dict'
    return retVocabList
#另一种模型    
def bagOfWords2VecMN(vocabList,inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1
    return returnVec
def trainNB0(trainMatrix,trainCatergory):
    numTrainDoc = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCatergory)/float(numTrainDoc)
    #防止多个概率的成绩当中的一个为0
    p0Num = ones(numWords)
    p1Num = ones(numWords)
    p0Denom = 2.0
    p1Denom = 2.0
    for i in range(numTrainDoc):
        if trainCatergory[i] == 1:
            p1Num +=trainMatrix[i]
            p1Denom += sum(trainMatrix[i])
        else:
            p0Num +=trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
    p1Vect = log(p1Num/p1Denom)#处于精度的考虑，否则很可能到限归零
    p0Vect = log(p0Num/p0Denom)
    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 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','dalmation']
    thisDoc = array(setOfWords2Vec(myVocabList,testEntry))
    print testEntry,'classified as: ',classifyNB(thisDoc,p0V,pAb)
    testEntry = ['stupid','garbage']
    thisDoc = array(setOfWords2Vec(myVocabList,pAb)
     
     
def main():
    testingNB()
     
if __name__ == '__main__':
    main()

以上是脚本之家(jb51.cc)为你收集整理的全部代码内容，希望文章能够帮你解决所遇到的程序开发问题。

如果觉得脚本之家网站内容还不错，欢迎将脚本之家网站推荐给程序员好友。

（编辑：安卓应用网）

【声明】本站内容均来自网络，其相关言论仅代表作者个人观点，不代表本站立场。若无意侵犯到您的权利，请及时与联系站长删除相关内容!