机器学习之基于概率论的分类方法 : 朴素贝叶斯

    本文主要记录本人在学习机器学习过程中的相关代码实现，参考《机器学习实战》

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

from numpy import *
import re
import feedparser
#~ loadDataSet() 创建了一些实验样本。该函数返回的第一个变量是进行词条切分后的文档集合 , 
#~ 这些文档来自斑点犬爱好者留言板,第二个变量是一个类别标签的集合
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']]
    classVec = [0,1,0,1,0,1]    #1 is abusive, 0 not
    return postingList,classVec
    
#~创建一个包含在所有文档中出现的不重复词的列表
def createVocabList(dataSet):
    vocabSet=set([])
    for document in dataSet:
        vocabSet=vocabSet|set(document)
    return list(vocabSet)

#~ 获得词汇表后, 便可以使用函数setOfWords2Vec(),该函数的输人参数为词汇表及某个文档 , 输出的
#~ 是文档向量,向量的每一元素为 1 或 0 ,分别表示词汇表中的单词在输人文档中是否出现 。
def setOfWords2Vec(vocabList,inputSet):
    returnVec=[0]*len(vocabList)
    for word in inputSet:
        returnVec[vocabList.index(word)]=1
    else:
        print("the world:%s is not in my Vocabulary!" % word)
    return returnVec

def bagOfWords2VecMN(vocabList,inputSet):
    returnVec=[0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)]+=1
    return returnVec

#~ 代码函数中的输人参数为文档矩阵trainMatrix,以及由每篇文档类别标签所构成的向量
#~ trainCategory
def trainNB0(trainMatrix,trainCategory):
    numTrainDocs=len(trainMatrix)
    numWords=len(trainMatrix[0])
    pAbusive=sum(trainCategory)/float(numTrainDocs)#sum()接受的是一个列表参数
    p0Num=ones(numWords)
    p1Num=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 = log(p1Num/p1Denom)         #change to log()
    p0Vect = log(p0Num/p0Denom)          #change to log()
    return p0Vect,p1Vect,pAbusive

#~ listOposts,listClasses=loadDataSet()
#~ myVocabList=createVocabList(listOposts)
#~ trainMat=[]
#~ for postinDoc in listOposts:
    #~ trainMat.append(setOfWords2Vec(myVocabList,postinDoc))
#~ p0V,plV,pAb = trainNB0(trainMat, listClasses)
#~ print(p0V,plV,pAb)

#~ 要分类的向量vec2Classify以及使用函数匕trainNB0()计算得到的三个概率
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)    #element-wise mult
    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else: 
        return 0

def testingNB():
    listOPosts,listClasses = loadDataSet()
    myVocabList = createVocabList(listOPosts)
    trainMat=[]
    for postinDoc in listOPosts:
        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
    p0V,p1V,pAb = trainNB0(array(trainMat),array(listClasses))
    testEntry = ['love', 'my', 'dalmation']
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    print(testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))
    testEntry = ['stupid', 'garbage']
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    print(testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))

#~ testingNB()

def textParse(bigString):
    listOfTokens=re.split(r'\W*',bigString)
    #~ listOfTokens=bigString.split(r'\W*')
    return [tok.lower() for tok in listOfTokens if len(tok)>2]

def spamTest():
    docList=[];classList=[];fullText=[]
    for i in range(1,26):
        with open('email/spam/%d.txt' % i,encoding='gbk') as fr:
            wordList=textParse(fr.read())
        docList.append(wordList)
        fullText.extend(wordList)
        #extend() 函数用于在列表末尾一次性追加另一个序列中的多个值(用新列表扩展原来的列表)
        classList.append(1)
        with open('email/ham/%d.txt' % i,encoding='gbk') as fr:
            wordList = textParse(fr.read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList=createVocabList(docList)
    trainingSet=list(range(50))
    testSet=[]
    for i in range(10):
        randIndex=int(random.uniform(0,len(trainingSet)))
        #~ numpy.random.uniform(low,high,size)
        #~ 功能：从一个均匀分布[low,high)中随机采样，注意定义域是左闭右开，即包含low，不包含high.
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])
    trainMat=[];trainClasses=[]
    for docIndex in trainingSet:
        trainMat.append(setOfWords2Vec(vocabList,docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V,p1V,pSpam=trainNB0(array(trainMat),array(trainClasses))
    errorCount=0
    for docIndex in testSet:
        wordVector=setOfWords2Vec(vocabList,docList[docIndex])
        if classifyNB(array(wordVector),p0V,p1V,pSpam)!=classList[docIndex]:
            errorCount+=1
    print('the error rate is:',float(errorCount)/len(testSet))

#~ spamTest()
def calcMostFreq(vocabList,fullText):
    import operator
    freqDict = {}
    for token in vocabList:
        freqDict[token]=fullText.count(token)
    sortedFreq = sorted(freqDict.items(), key=operator.itemgetter(1), reverse=True) 
    return sortedFreq[:30] 

def localWords(feed1,feed0):
    import feedparser
    docList=[]; classList = []; fullText =[]
    minLen = min(len(feed1['entries']),len(feed0['entries']))
    for i in range(minLen):
        wordList = textParse(feed1['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1) #NY is class 1
        wordList = textParse(feed0['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = createVocabList(docList)#create vocabulary
    top30Words = calcMostFreq(vocabList,fullText)   #remove top 30 words
    for pairW in top30Words:
        if pairW[0] in vocabList: vocabList.remove(pairW[0])
    trainingSet = list(range(2*minLen)); testSet=[]           #create test set
    for i in range(20):
        randIndex = int(random.uniform(0,len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])  
    trainMat=[]; trainClasses = []
    for docIndex in trainingSet:#train the classifier (get probs) trainNB0
        trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses))
    errorCount = 0
    for docIndex in testSet:        #classify the remaining items
        wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
        if classifyNB(array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
            errorCount += 1
    print('the error rate is: ',float(errorCount)/len(testSet))
    return vocabList,p0V,p1V

def getTopWords(ny,sf):
    import operator
    vocabList,p0V,p1V=localWords(ny,sf)
    topNY=[]; topSF=[]
    for i in range(len(p0V)):
        if p0V[i] > -6.0 : topSF.append((vocabList[i],p0V[i]))
        if p1V[i] > -6.0 : topNY.append((vocabList[i],p1V[i]))
    sortedSF = sorted(topSF, key=lambda pair: pair[1], reverse=True)
    print("SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**")
    for item in sortedSF:
        print(item[0])
    sortedNY = sorted(topNY, key=lambda pair: pair[1], reverse=True)
    print("NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**")
    for item in sortedNY:
        print(item[0])

ny=feedparser.parse('http://newyork.craigslist.org/stp/index.rss')
sf=feedparser.parse('http://sfbay.craigslist.org/stp/index.rss')
vocabList,pSF,pNY=localWords(ny,sf)
vocabList,pSF,pNY=localWords(ny,sf)