python-垃圾邮箱分类-贝叶斯方法

python-垃圾邮箱分类-贝叶斯方法

#公式
贝叶斯定理是关于随机事件A和B的条件概率（或边缘概率）的一则定理。以邮件过滤为例：

其中:

Pr(S|W) 为邮件为垃圾邮件(spam)的概率，在已知词汇W的条件下。
Pr(S) 为垃圾邮件的概率
Pr(W|S) 为垃圾邮件中，词汇W的概率

#朴素贝叶斯的优点和缺点
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：对于输入数据的准备方式较为敏感；由于朴素贝叶斯的“朴素”特点，所以会带来一些准确率上的损失
我们使用的邮件数据集是 Ling-spam，并编写一个垃圾邮件的过滤器
使用拉普拉斯平滑解决零概率问题；
对乘积结果取自然对数避免下溢出问题，采用自然对数进行处理不会有任何损失。

代码如下:

import numpy as npimport reimport random


"""
函数说明:将切分的实验样本词条整理成不重复的词条列表，也就是词汇表
Pa
"""def createVocabList(dataSet):
    vocabSet = set([])      for document in dataSet:
        vocabSet = vocabSet | set(document)  #
    return list(vocabSet)

"""
函数说明:根据vocabList词汇表，将inputSet向量化，向量的每个元素为1或0
"""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       
"""
函数说明:根据vocabList词汇表，构建词袋模型
"""def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = [0] * len(vocabList)  
for word in inputSet:                   
 if word in vocabList:         
            returnVec[vocabList.index(word)] += 1
    return returnVec  

"""
函数说明: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 = np.ones(numWords)
    p1Num = np.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 = np.log(p1Num / p1Denom)
p0Vect = np.log(p0Num / p0Denom)  
    return p0Vect, p1Vect, pAbusive  

"""
函数说明:朴素贝叶斯分类器分类函数
"""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
"""
函数说明:接收一个大字符串并将其解析为字符串列表
"""def textParse(bigString):  
listOfTokens = re.split(r'\W*', bigString)  
    return [tok.lower() for tok in listOfTokens if len(tok) > 2]

"""
函数说明:测试朴素贝叶斯分类器，使用朴素贝叶斯进行交叉验证
"""def spamTest():
    docList = []
    classList = []
    fullText = []
    for i in range(1, 26):  
        wordList = textParse(open('D:/贝叶斯算法实战数据集/Naive_Bayes-master/email/spam/%d.txt' % i, 'r').read())  
        docList.append(wordList)
        fullText.append(wordList)
        classList.append(1)  
        wordList = textParse(open('D:/贝叶斯算法实战数据集/Naive_Bayes-master/email/ham/%d.txt' % i, 'r').read()) 
        docList.append(wordList)
        fullText.append(wordList)
        classList.append(0) 
vocabList = createVocabList(docList)  
    trainingSet = list(range(50))  
    testSet = []  
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:  
        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("分类错误的测试集：", docList[docIndex])
    print('错误率：%.2f%%' % (float(errorCount) / len(testSet) * 100))

if __name__ == '__main__':
    spamTest()

作者：JerryLoveCoding