机器学习实战——Ch04朴素贝叶斯分类（修正代码）

最近正在学习《机器学习实战》，发现其中的代码很老，不能在python3上直接运行，而且有错误的地方，翻过了各种坑，在这里分享出来供大家参考。

先写上利用朴素贝叶斯分类进行垃圾邮件分类的代码

import numpy as np

def createVocabList(dataSet):
    #create an empty set
    vocabSet=set([])
    for document in dataSet:
        vocabSet=vocabSet | set(document)
    return list(vocabSet)
    
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

def trainNB0(trainMatrix,trainCategory):
    numTrainDocs=len(trainMatrix)
    numWords=len(trainMatrix[0])
    pAbusive=sum(trainCategory)/float(numTrainDocs)
    #p0Num=zeros(numWords)
    #p1Num=zeros(numWords)
    #为了避免P(w1|c1)*P(w2|c1)...P(wn|c1)=0,要保证任一个分子不为零，将其初始化为1
    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=p1Num/p1Denom
    #为了避免多个很小的数=0，将其对数化
    p1Vect=np.log(p1Num/p1Denom)
    #p0Vect=p0Num/p0Denom
    p0Vect=np.log(p0Num/p0Denom)
    return p0Vect,p1Vect,pAbusive
    
def classify0(vec2Classify,p0Vec,p1Vec,pClass1):
    #元素相乘
    p1=sum(vec2Classify*p1Vec)+np.log(pClass1)
    p0=sum(vec2Classify*p0Vec)+np.log(1-pClass1)
    if p1>p0:
        return 1
    else:
        return 0

def textParse(bigString):
    import re
    listOfTokens=re.split('\W+',bigString,maxsplit=0)
    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.extend(wordList)
        classList.append(1)
        wordList = textParse(open('email/spam/%d.txt' % i,'r').read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList=createVocabList(docList)
    trainingSet=list(range(50));testSet=[]
    #随机构造训练集
    for i in range(10):
        randIndex = int(np.random.uniform(0,len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])
    trainMat=[];trainClass=[]
    for docIndex in trainingSet:
        trainMat.append(setOfWords2Vec(vocabList,docList[docIndex]))
        trainClass.append(classList[docIndex])
        p0V,p1V,pSpam=trainNB0(trainMat,trainClass)
    errorCount=0
    #对测试集进行分类
    for docIndex in testSet:
        wordVector=setOfWords2Vec(vocabList,docList[docIndex])
        if classify0(wordVector,p0V,p1V,pSpam)!=classList[docIndex]:
            errorCount+=1
    print('the error rate is:',float(errorCount)/len(testSet))
   
spamTest()

书中所附的代码，有一处错误是：定义spamTest时，读取文件，原代码是

 wordList = textParse(open('email/spam/%d.txt' % i).read())

应该改为

wordList = textParse(open('email/spam/%d.txt' % i,'r').read())

'r'的意思是“只读”，如果没有加上只读会报错expected string or bytes-like object，同时要注意open(....)只是把这个文件打开，加上.read()才能把文件中的内容显示出来，如下所示

fr=open('email/spam/%d.txt' % 1,'r')
print(fr)
[output]:<_io.TextIOWrapper name='email/spam/1.txt' mode='r' encoding='cp936'>

fr=open('email/spam/%d.txt' % 1,'r').read()
print(fr)
[output]:-- We have 15mg & 30mg pills -- 30/15mg for $203.70 - 60/15mg for $385.80 - 90/15mg for $562.50 -- VISA Only!!! ---