机器学习实战：朴素贝叶斯-邮件分类

email.py

import numpy as np
import random
import re

"""
函数说明：接收一个大字符串并将其解析为字符串列表
Parameters:
    bigString - 接收的字符串
Returns:
    
"""
def textParse(bigString):
    listOfTokens = re.split(r'\W+',bigString)
    return [tok.lower() for tok in listOfTokens if len(tok)>2]


"""
函数说明：将切分的实验样本词条整理成词汇表
Parameters:
    dataSet - 整理的样本数据集
Returns:
    vocabSet - 返回词汇表
"""
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
Parameters:
    vocabList - 词汇表
    inputSet - 切分的词条向量
Returns:
    returnVec - 文档向量
"""
def setOfWords2Vec(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：根据vocabList词汇表，构建词袋模型
Parameters:
    vocabList - 词汇表
    inputSet - 切分的词条列表
Returns:
    returnVec - 文档向量，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
Parameters:
    trainMatrix - 训练文档矩阵，即setOfWords2Vec返回的returnVec构成的矩阵
    trainCategory - 训练类别标签向量
Returns:
    p0Vect - 非侮辱类的条件概率数组
    p1Vect - 侮辱类的条件概率数组
    pAbusive - 文档属于侮辱类的概率
"""
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/p1Denom)
    return p0Vect,p1Vect,pAbusive


"""
函数说明：朴素贝叶斯分类器分类函数
Parameters:
    vec2Classify - 待分类的词条数组
    p0Vec - 非侮辱类的条件概率数组
    p1Vec -侮辱类的条件概率数组
    pClass1 - 文档属于侮辱类的概率
Returns:
    0 - 属于非侮辱类
    1 - 属于侮辱类
"""
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:测试朴素贝叶斯分类器

Parameters:
    无
Returns:
    无
"""
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)
    trainMat = list(range(50)); testMat = []
    for i in range(10):
        docIndex = int(random.uniform(0,len(trainMat)))
        testMat.append(trainMat[docIndex])
        del(trainMat[docIndex])
    trainMatrix = [];trainClasses = []
    for randIndex in trainMat:
        trainMatrix.append(setOfWords2Vec(vocabList,docList[randIndex]))
        trainClasses.append(classList[randIndex])
    p0V,p1V,pSpam = trainNB0(np.array(trainMatrix),np.array(trainClasses))
    errorCount = 0.0
    for randIndex in testMat:
        vector = setOfWords2Vec(vocabList,docList[randIndex])
        if classifyNB(vector,p0V,p1V,pSpam) != classList[randIndex]:
            errorCount += 1.0
            print('错误向量',docList[randIndex])
    print("错误率：%.2f%%"%(float(errorCount)/len(testMat)*100))

main.py

from email import *
if __name__ == '__main__':
    spamTest()