朴素贝叶斯算法与垃圾邮件判断

机器学习 jinwei 1123℃ 0评论

机器学习之朴素贝叶斯算法进行垃圾邮件预测
贝叶斯决策优点包括在数据较少的情况下任然有效,可以处理多类别的问题,缺点是对于输入数据的准备方式较为敏感。

# coding: utf-8
#bayes.py
from numpy import zeros,array,ones,log,random

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
# 创建一个包含在所有文档中出现的不重复词的列表
def createVocabList(dataSet):
    vocabSet=set([])
    for document in dataSet:
        vocabSet = vocabSet| set(document)
    return list(vocabSet)
#将每一个inputSet转换为一个向量
def setOfWords2Vec(vocabList,inputSet):
    returnVec = [0] *len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] =1
        else:print ("不存在")
    return returnVec
#朴素贝叶斯分类器训练函数
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;
    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
# 朴素贝叶斯分类函数
def classifyNB(vec2Classify,p0Vec,p1Vec,pClass1):
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)
    p0 = sum(vec2Classify * p0Vec) + log(1-pClass1)
    if p1>p0:
        return 1
    else:
        return 0
#朴素贝叶斯词袋模型
def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1
    return returnVec
#测试
def testingNB():
    listOPosts,listClasses = loadDataSet()
    myVocabList = creatVocabList(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))
#文件解析以及完整的垃圾邮件测试函数
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())
        # print wordList
        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 = list(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))

 

转载请注明:沐雨语曦 » 朴素贝叶斯算法与垃圾邮件判断

喜欢 (0)
发表我的评论
取消评论

表情

Hi,您需要填写昵称和邮箱!

  • 昵称 (必填)
  • 邮箱 (必填)
  • 网址