朴素贝叶斯分类器-垃圾邮件过滤

# -*- coding:utf-8 -*-
import re
import numpy as np
import random


def textParse(bigString):
    ‘‘‘
    接收一个文档中内容，转换成由字母、数字组成的字符串列表
    :param bigString:接收内容
    :return:字符串列表
    ‘‘‘
    reg = re.findall(‘\w{3,}‘,bigString)
    return [i.lower() for i in reg]

def createVocabList(dataSet):
    vocabSet = set()
    for document in dataSet:
        vocabSet = vocabSet | set(document)
    return list(vocabSet)

def setOfWords2Vec(vocalList,inputSet):
    ‘‘‘
    根据vocalList词汇表，将输入的inputSet对应转换成向量，字符串出现在vocalList中为1，否则为0
    :param vocalList:词汇表
    :param inputSet:输入字符串列表
    :return: returnVec:文档向量
    ‘‘‘
    returnVec = [0] * len(vocalList)
    for word in inputSet:
        if word in vocalList:
            returnVec[vocalList.index(word)] = 1
        else:
            print("the word:%s is not in my Vocabulary!"%word)
    return returnVec

def trainNB0(trainMatrix,trainCategory):
    ‘‘‘
    计算条件概率
    p1Vec:[p(w0|1) p(w1|1) p(w3|1) ... p(wn|1)]
    p0Vec:[p(w0|0) p(w1|0) p(w3|0) ... p(wn|0)]
    :param trainMatrix:训练矩阵
    :param trainCategory:训练矩阵对应的标签
    :return:
    p1Vec-侮辱类的条件概率数组
    p0Vec-非侮辱类的条件概率数组
    pAbusive-文档属于侮辱类的概率
    ‘‘‘
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    p1Vec = np.ones(numWords)
    p0Vec = np.ones(numWords)
    p1Demon = 2.0
    p0Demon = 2.0
    for i in range(numTrainDocs):
        if trainCategory[i] == 1:
            p1Vec += trainCategory[i]
            p1Demon += sum(trainMatrix[i])
        else:
            p0Vec += trainCategory[i]
            p0Demon += sum(trainMatrix[i])
    p1Vec = p1Vec / p1Demon
    p0Vec = p0Vec / p0Demon
    return p0Vec,p1Vec,pAbusive

def classifyNB(vec2Classify,p0Vec,p1Vec,pClass1):
    ‘‘‘
    计算并比较文档是侮辱性和非侮辱性概率大小
    :param vec2Classify: 待分类的文档向量
    :param p0Vec:非侮辱类的条件概率数组
    :param p1Vec:侮辱类的条件概率数组
    :param pClass1:训练文档中，属于侮辱类的概率
    :return:1-属于侮辱类，0-属于非侮辱类
    ‘‘‘
    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 spamTest():
    ‘‘‘
    随机选择40个文档作为训练数据，10个作为测试数据，测试朴素贝叶斯分类器效果
    :return:无，打印错误率
    ‘‘‘
    docList = []
    classList = []
    fullText = []
    for i in range(1,26):
        wordList = textParse(open(‘email/spam/%d.txt‘%i,‘r‘,encoding=‘ISO-8859-1‘).read())
        docList.append(wordList)
        classList.append(1)
        wordList = textParse(open(‘email/ham/%d.txt‘%i,‘r‘,encoding=‘ISO-8859-1‘).read())
        docList.append(wordList)
        classList.append(0)
    vocalList = 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 = []
    trainingClasses = []
    for docIndex in trainingSet:
        trainMat.append(setOfWords2Vec(vocalList,docList[docIndex]))
        trainingClasses.append(classList[docIndex])
    p0V,p1V,pSpam = trainNB0(np.array(trainMat),np.array(trainingClasses))
    errorCount = 0
    for docIndex in testSet:
        wordVector = setOfWords2Vec(vocalList,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()