朴素贝叶斯分类器

# -*- coding: UTF-8 -*- 
from numpy import *

#获取输入词条和分类标签
def loadataset():
    postinglist=[['my', 'dog', 'has', 'flea', 'problems', 'help', 'please'],\
    ['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'],\
    ['my', 'dalmation', 'is', 'so', 'cute', 'I', 'love', 'him'],\
    ['stop', 'posting', 'stupid', 'worthless', 'garbage'],\
    ['mr', 'licks', 'ate', 'my', 'steak', 'how', 'to', 'stop', 'him'],\
    ['quit', 'buying', 'worthless', 'dog', 'food', 'stupid']]
    classvec=[0,1,0,1,0,1]
    return postinglist,classvec

#获取词条的所有单词集合(词汇表)，以列表形式返回
def createvocablist(dataset):
    vocabset=set()
    for i in dataset:
        vocabset=vocabset|set(i)
    return list(vocabset)

#输入待分类词条，测试词条在词汇表中是否出现，记为1
#此处为词集模型，只判断特征值出现与否，对出现频率未加考虑
def setofwords2vec(vocabset,input):
    inputvec=[0]*len(vocabset)
    for word in input:
        if word in vocabset:
            inputvec[vocabset.index(word)]=1
        else:
            print 'the word %s is not in the vocabset' %word
    return inputvec

#词袋模型。对多次出现的特征值累加计数
def bagofwords2vec(vocabset,input):
    inputvec=[0]*len(vocabset)
    for word in input:
        if word in vocabset:
            inputvec[vocabset.index(word)]+=1
        else:
            print 'the word %s is not in the vocabset' %word
    return inputvec

#返回类先验概率和似然函数 
def trainnb(trainmatrix,traincategory):
    numtraindoc=len(trainmatrix)
    numwords=len(trainmatrix[0])
    positive=sum(traincategory)/float(numtraindoc)    #计算垃圾词条的概率，先验概率
    p0num=ones(numwords);p1num=ones(numwords)
    p0sum=0.0;  p1sum=0.0
    for i in range(numtraindoc):
        if traincategory[i]==1:
            p1num+=trainmatrix[i]   #2个list无法相加，故引入numpy进行对应位置的运算
            p1sum+=sum(trainmatrix[i])
        else:
            p0num+=trainmatrix[i]
            p0sum+=sum(trainmatrix[i])
    p0vect=log(p0num/p0sum)
    p1vect=log(p1num/p1sum)
    return p0vect,p1vect,positive

#贝叶斯公式判断不同分类的概率大小
def classifynb(vec2classify,p0vect,p1vect,positive):
    p1=sum(vec2classify*p1vect)+log(positive)
    p0=sum(vec2classify*p0vect)+log(1-positive)
    if p1>p0:
        return 1
    else:
        return 0

#分类未知词条
def testingnb():
    listvec,classvec=loadataset()
    myvocablist=createvocablist(listvec)
    trainmat=[]
    for doc in listvec:
        trainmat.append(bagofwords2vec(myvocablist,doc))  #获取每个词条在词汇表出现与否的列向量
    p0vect,p1vect,positive=trainnb(trainmat,classvec)
    testentry=['love','my','dalmation']
    thisdoc=array(bagofwords2vec(myvocablist,testentry))
    print testentry,'classified as:',classifynb(thisdoc,p0vect,p1vect,positive)
    testentry=['stupid','garbage']
    thisdoc=array(bagofwords2vec(myvocablist,testentry))
    print testentry,'classified as:',classifynb(thisdoc,p0vect,p1vect,positive)

#解析文本文件
def textparse(bigstring):
    import re
    listoftokens=re.split(r'\W*',bigstring)
    return [i.lower() for i in listoftokens if len(i)>2]

#测试算法，使用朴素贝叶斯进行交叉验证
def spamtext():
    dataset=[]
    category=[]    #类别标签
    vocabset=[]    #词汇表
    for i in range(1,26):
        a=open('/Users/enniu/Desktop/jqxx/machinelearninginaction/Ch04/email/ham/%d.txt' %i).read()
        dataset.append(textparse(a))
        category.append(0)
    for i in range(1,26):
        b=open('/Users/enniu/Desktop/jqxx/machinelearninginaction/Ch04/email/spam/%d.txt' %i).read()
        dataset.append(textparse(b))
        category.append(1)
    vocabset=createvocablist(dataset)  #获取输入词条的所有词汇表

    #随机选择10个样本作为测试集
    testset=[]         #测试样本序号
    trainset=range(50) #训练样本序号。此步通过索引来操作，不需要更改词集列表
    for i in range(10):
        randindex=int(random.uniform(0,len(trainset)))
        testset.append(trainset[randindex])
        del trainset[randindex]

    #计算剩余40个样本的似然概率.[P(x1|spam),P(x2|spam),P(x3|spam),...]
    trainmat=[]
    trainclass=[]
    for i in trainset:
        trainmat.append(setofwords2vec(vocabset,dataset[i]))
        trainclass.append(category[i])
    p0vect,p1vect,positive=trainnb(trainmat,trainclass)
    #return p0vect,p1vect,positive

    #计算正确与错误的概率
    errorcount=0
    for i in testset:
        wordvect=setofwords2vec(vocabset,dataset[i])
        precategory=classifynb(wordvect,p0vect,p1vect,positive)
        if precategory!=category[i]:
            errorcount+=1
    print 'the error rate is: ',float(errorcount)/len(testset)

if __name__=='__main__':
    i=0
    while i<=10:
        spamtext()
        i=i+1
    

---

# -*- coding: UTF-8 -*- 
from numpy import *

#获取输入词条和分类标签
def loadataset():
    postinglist=[['my', 'dog', 'has', 'flea', 'problems', 'help', 'please'],\
    ['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'],\
    ['my', 'dalmation', 'is', 'so', 'cute', 'I', 'love', 'him'],\
    ['stop', 'posting', 'stupid', 'worthless', 'garbage'],\
    ['mr', 'licks', 'ate', 'my', 'steak', 'how', 'to', 'stop', 'him'],\
    ['quit', 'buying', 'worthless', 'dog', 'food', 'stupid']]
    classvec=[0,1,0,1,0,1]
    return postinglist,classvec

#获取词条的所有单词集合(词汇表)，以列表形式返回
def createvocablist(dataset):
    vocabset=set()
    for i in dataset:
        vocabset=vocabset|set(i)
    return list(vocabset)

#输入待分类词条，测试词条在词汇表中是否出现，记为1
#此处为词集模型，只判断特征值出现与否，对出现频率未加考虑
def setofwords2vec(vocabset,input):
    inputvec=[0]*len(vocabset)
    for word in input:
        if word in vocabset:
            inputvec[vocabset.index(word)]=1
        else:
            print 'the word %s is not in the vocabset' %word
    return inputvec

#词袋模型。对多次出现的特征值累计计数
def bagofwords2vec(vocabset,input):
    inputvec=[0]*len(vocabset)
    for word in input:
        if word in vocabset:
            inputvec[vocabset.index(word)]+=1
        else:
            print 'the word %s is not in the vocabset' %word
    return inputvec

#返回类先验概率和似然函数 
def trainnb(trainmatrix,traincategory):
    numtraindoc=len(trainmatrix)
    numwords=len(trainmatrix[0])
    positive=sum(traincategory)/float(numtraindoc)    #计算垃圾词条的概率，先验概率
    p0num=ones(numwords);p1num=ones(numwords)
    p0sum=0.0;  p1sum=0.0
    for i in range(numtraindoc):
        if traincategory[i]==1:
            p1num+=trainmatrix[i]   #2个list无法相加，故引入numpy进行对应位置的运算
            p1sum+=sum(trainmatrix[i])
        else:
            p0num+=trainmatrix[i]
            p0sum+=sum(trainmatrix[i])
    p0vect=log(p0num/p0sum)
    p1vect=log(p1num/p1sum)
    return p0vect,p1vect,positive

#贝叶斯公式判断不同分类的概率大小
def classifynb(vec2classify,p0vect,p1vect,positive):
    p1=sum(vec2classify*p1vect)+log(positive)
    p0=sum(vec2classify*p0vect)+log(1-positive)
    if p1>p0:
        return 1
    else:
        return 0

#分类未知词条
def testingnb():
    listvec,classvec=loadataset()
    myvocablist=createvocablist(listvec)
    trainmat=[]
    for doc in listvec:
        trainmat.append(bagofwords2vec(myvocablist,doc))  #获取每个词条在词汇表出现与否的列向量
    p0vect,p1vect,positive=trainnb(trainmat,classvec)
    testentry=['love','my','dalmation']
    thisdoc=array(bagofwords2vec(myvocablist,testentry))
    print testentry,'classified as:',classifynb(thisdoc,p0vect,p1vect,positive)
    testentry=['stupid','garbage']
    thisdoc=array(bagofwords2vec(myvocablist,testentry))
    print testentry,'classified as:',classifynb(thisdoc,p0vect,p1vect,positive)

if __name__=='__main__':
    testingnb()