朴素贝叶斯

# -*- coding: utf-8 -*-

from numpy import *

import random

def loadDataSet():

    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']]

    #1代表侮辱性文字，0为正常

    classVec=[0,1,0,1,0,1]

    return postingList,classVec

#收集新文档中未出现过的不重复的新词

def createVocabList(dataset):

    #不能直接set（dataset），这样会报错，set（）里边只能填入向量

    vocabset=set([])

    for document in dataset:

        #取并集

        vocabset=vocabset | set(document)

    return list(vocabset)

#输出文档向量，表示输入文档中是否有单词是在词汇表中,输入文档必须是向量

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 the Vocabulary!" %word

    return returnVec

#词袋模型

def bagOfWords2Vec(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 the Vocabulary!" %word

    return returnVec

listOfPosts,listClasses=loadDataSet()

myVocabList=createVocabList(listOfPosts)

# print len(myVocabList)

returnVec=setOfWords2Vec(myVocabList, listOfPosts[0])

# print returnVec

# print sum(listClasses)

#朴素贝叶斯分类器训练函数

def trainNBO(trainMatrix,trainCategory):

    #文档中有几个数据

    numTrain=len(trainMatrix)

    #词汇库中有多少词个数

    numWords=len(trainMatrix[0])

    #文档属于侮辱性的概率

    pAbusive=sum(trainCategory)/float(numTrain)

    #非侮辱性的概率

    p0Num=ones(numWords)

    #侮辱性概率

    p1Num=ones(numWords)

    #初始概率为0.5

    p0Denom=2.0

    p1Denom=2.0

    

    for i in range(numTrain):

        if trainCategory[i]==1:

            p1Num += trainMatrix[i]

            p1Denom +=sum(trainMatrix[i])

        else:

            p0Num +=trainMatrix[i]

            p0Denom +=sum(trainMatrix[i])

    

    #防止相乘的数值过小产生下溢出

    p1Vect=log(p1Num/p1Denom)

    p0Vect=log(p0Num/p0Denom)

    

    return p0Vect,p1Vect,pAbusive

trainMatrix=[]

for data in listOfPosts:

    trainMatrix.append(setOfWords2Vec(myVocabList, data))

p0v,p1v,pa=trainNBO(trainMatrix, listClasses)

# print pa,p0v

# print p1v

#朴素贝叶斯分类函数

def classifyNB(vec2Classify,p0Vec,p1Vec,pClass1):

    #贝叶斯概率公式不需要考虑分母，因为只需要比较概率大小

    #由于使用log函数，乘法都变成加法

    p1=sum(vec2Classify * p1Vec) +log(pClass1)

    p0=sum(vec2Classify * p0Vec) ++log(1.0-pClass1)

    if p1>p0:

        return 1

    else:

        return 0

    

#测试算法

# vec2Classify=['love','my','dalmation']

# vec2Classify_2=['stupid','garbage']

# thisDoc=array(setOfWords2Vec(myVocabList, vec2Classify))

# thisDoc_2=array(setOfWords2Vec(myVocabList, vec2Classify_2))

# print classifyNB(thisDoc, p0v, p1v, pa)

# print classifyNB(thisDoc_2, p0v, p1v, pa)

def textParse(bigString):

    import re

    #按照非单词字符断开

    listOfTokens=re.split(r'\W',bigString)

    return [tok.lower() for tok in listOfTokens if len(tok)>2]

def spamTest():

    docList=[]

    classList=[]

    fullText=[]

    #导入文件

    for i in range(1,26):

        fr=open('D:/learn/Ch02/email/spam/%d.txt'%i)

        wordList=textParse(fr.read())

        docList.append(wordList)

        fullText.extend(wordList)

        classList.append(1)

        

        fr==open('D:/learn/Ch02/email/ham/%d.txt'%i)

        wordList=textParse(fr.read())

        docList.append(wordList)

        fullText.extend(wordList)

        classList.append(0)

#     print len(classList)

    vocabList=createVocabList(docList)

    #总共50封邮件，随数据集变化

    trainingSet=range(50)

    testSet=[]

    #随机选取10个作为测试集

    for i in range(10):

        #选取0-50的随机数

        randIndex=int(random.uniform(0,len(trainingSet)))

        testSet.append(trainingSet[randIndex])

        del(trainingSet[randIndex])

        

    trainMat=[]

    trainClasses=[]

    

    for docIndex in trainingSet:

        trainMat.append(bagOfWords2Vec(vocabList, docList[docIndex]))

        trainClasses.append(classList[docIndex])

        

    p0V,p1V,pSpam=trainNBO(array(trainMat), array(trainClasses))

    errorCount=0

    

    for docIndex in testSet:

        wordVector=bagOfWords2Vec(vocabList, docList[docIndex])

        if classifyNB(array(wordVector), p0V, p1V, pSpam)!=classList[docIndex]:

            errorCount+=1

    print 'the error rate is ',float(errorCount)/len(testSet)

# spamTest()