机器学习（六）--------python实现朴素贝叶斯对email分类

贝叶斯分类

4.1 贝叶斯定理

• 计算条件概率
  

4.2 朴素贝叶斯分类

• 朴素：特征条件独立
• 贝叶斯：基于贝叶斯定理

该方法受限于当特征属性有条件独立或基本独立。

4.3 贝叶斯网络

• 贝叶斯网络也成为信念网络，借助有向无环图来刻画属性之间的依赖关系。

贝叶斯网络

• 贝叶斯网络的三种结构
  

一个节点表示一个状态，状态之间的连线表示因果关系，每一个关系有一个描述因果强度的权重，叫做可信度。两个节点相连，说明两个节点之间有因果关系。

4.4 朴素贝叶斯对email分类——python实现

import re
import random
import numpy as np


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


def setOfWords2Vec(vocabList, inputSet):
    returnVec = [0] * len(vocabList)
    for word in inputSet:
        if word in vocabList:
            # 词条存在于词汇表中，则置1
            returnVec[vocabList.index(word)] = 1
        else:
            print("the word: %s is not in my Vocabulary!" % word)
    return returnVec


def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = [0] * len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1
    return returnVec


# 朴素贝叶斯训练函数
def trainNB0(trainMatrix, trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory) / float(numTrainDocs) # 文档属于垃圾邮件类的概率
    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)  # 取对数防止下溢
    return p0Vect, p1Vect, pAbusive


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


def textParse(bigString):
    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, 'r').read())
        docList.append(wordList)
        fullText.append(wordList)
        classList.append(1)
        wordList = textParse(open('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))

    # 训练朴素贝叶斯模型
    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()

其他方法可参考github