机器学习入门☞朴素贝叶斯

版权声明：本文为博主原创文章，转载请注明原文地址：http://blog.csdn.net/helloworld_ptt https://blog.csdn.net/helloworld_ptt/article/details/81986482

源代码与资源文件
#本文适用读者:#
了解朴素贝叶斯,并且python version 为 3.x
###朴素贝叶斯的优缺点及其适用性:

优点:在数据较少的情况下仍然有效,可以处理多类别问题
缺点:对于输入数据的准备方式较为敏感
使用数据类型:标称型数据
###朴素贝叶斯的一般过程:
1.收集数据:可以使用任何方法.本章使用RSS源
2.准备数据:需要数值型或者布尔型数据
3.分析数据:有大量特征时,绘制特征作用不大,此时使用直方图效果更好
4.训练算法:计算不同的独立特征的条件概率
5.测试算法:计算错误率
6.使用算法:一个常见的朴素贝叶斯应用是文档分类.可以在任意的分类场景中使用朴素贝叶斯分类器,不一定非要是文本

###词表到向量的转换函数
将以下代码写入到bayes.py文件中

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]

def createVocabList(dataSet): #单词去重
    #0 创建一个空集
    vocabSet = set([])
    for document in dataSet:
    #创建两个集合的并集
        vocabSet = vocabSet | set(document)
    return list(vocabSet)
    return postingList,classVec

def setOfWords2Vec(vocabList, inputSet):#单词查重,转换成01向量
#创建一个其中所含元素都为0的向量
    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

####测试一下:

import bayes
list0posts,listClasses = bayes.loadDataSet()
myVocabList = bayes.createVocabList(list0posts)
myVocabList

结果:

bayes.setOfWords2Vec(myVocabList, list0posts[0])

结果:

###从词向量计算概率:
####朴素贝叶斯分类器训练函数:
将以下代码写入bayes.py文件中

#param
# @trainMatrix 文档向量矩阵
# @trainCategory 每篇文档类别标签所构成的向量
def trainNB0(trainMatrix, trainCategory): 
    numTrainDocs = len(trainMatrix) #文档数量
    numWords = len(trainMatrix[0]) #文档单词数量
    pAbusive = sum(trainCategory)/float(numTrainDocs) #计算侮辱性文档概率
    #(以下两行) 初始化向量所有元素的概率为1
    p0Num = ones(numWords);p1Num = ones(numWords)
    p0Denom = 2.0;p1Denom = 2.0 
    for i in range(numTrainDocs): #对每篇文档向量相加
        if trainCategory[i] == 1:
            p1Num += trainMatrix[i]
            p1Denom += sum(trainMatrix[i])
        else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
 #对向量中的每个元素进行log(元素/侮辱性出现的总次数)运算
    p1Vect = log(p1Num / p1Denom) 
    p0Vect = log(p0Num / p0Denom) 
#取对数是为了防止浮点数向下溢出,保证数据的精确性
    return p0Vect,p1Vect,pAbusive

####测试一下:

list0posts,listClasses = bayes.loadDataSet()
trainMat = []
for postinDoc in list0posts:
    trainMat.append(bayes.setOfWords2Vec(myVocabList, postinDoc))
p0V,p1V,pAb = bayes.trainNB0(trainMat, listClasses)
pAb

结果:

p0V

结果:

p1V

结果:

###朴素贝叶斯分类函数
将以下代码写入bayes.py中

扫描二维码关注公众号，回复： 3900213 查看本文章

#param
# @vec2Classify:文档查重向量
# @p0Vec:非侮辱性向量
# @p1Vec:侮辱性向量
# @pClass1:侮辱性概率
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):#
    #元素相乘
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)
    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else:
        return 0

def testingNB():#测试函数
    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))

####测试一下

import importlib
importlib.reload(bayes)
bayes.testingNB()

结果:

###准备数据:文档词袋模型

#该函数与setOfWords2Vec只有一点不同:将 '= 1'修改为 '+= 1'
def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1
    return returnVec

###准备数据:切分文本

mySent = 'This book is the best book on Python or M.L, I have ever laid eyes upon.'
mySent.split()

结果:

import re 
regEx = re.compile('\\W*')
listOfTokens = regEx.split(mySent)
listOfTokens

结果:

#忽略大小写
[tok for tok in listOfTokens if len(tok) > 0]

结果:

###测试算法:使用朴素贝叶斯进行交叉验证
将以下代码写入文件bayes.py中

#切分文本,并忽略大小写
def textParse(bigString):
    import re
    listOfTokens = re.split(r'\W*', bigString)
    return [tok.lower() for tok in listOfTokens if len(tok) > 2]
    
#测试函数
def spamTest():
    docList = []; classList = []; fullText = []
    for i in range(1,26):#文档数据处理
        #(以下七行) 导入并解析文本文件
        wordList = textParse(open('email/spam/%d.txt' % i,encoding="ISO-8859-1")
.read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)                                                     
        wordList = textParse(open('email/ham/%d.txt' % i,encoding="ISO-8859-1").
read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = createVocabList(docList)
    trainingSet = list(range(50)); testSet = []
    # (以下四行) 随机构建训练集
    for i in range(10):
        randIndex = int(random.uniform(0,len(trainingSet)))
        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
    #(以下四行) 对测试集分类
    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))

####测试一下:

for i in range(10):
    bayes.spamTest()

结果

###使用朴素贝叶斯分类器从个人广告中获取区域倾向
####导入RSS源

import feedparser
ny = feedparser.parse('http://newyork.craigslist.org/stp/index.rss')
sf = feedparser.parse('http://sfbay.craigslist.org/stp/index.rss')
ny['entries']
len(ny['entries'])

结果:
0
很明显,这个网站的数据是空的
所以我们要换一下rss源,故修改上面代码为:

import feedparser
ny = feedparser.parse('http://www.cppblog.com/kevinlynx/category/6337.html/rss')
sf = feedparser.parse('http://blog.163.com/cbn.weekly/rss/')
ny

结果:

###RSS源分类器及高频词去除函数

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=Tr
ue)
    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):
        #每次访问一条RSS源
        wordList = textParse(feed1['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
        wordList = textParse(feed0['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    #(以下四行)去掉出现次数最高的那些词
    vocabList = createVocabList(docList)
    top30Words = calcMostFreq(vocabList, fullText)
    for pairW in top30Words:
        if pairW[0] in vocabList:                                               
            vocabList.remove(pairW[0])
    trainingSet = list(range(2*minLen)); testSet = []
    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:
        trainMat.append(bagOfWords2VecMN(vocabList,docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses))
    errorCount = 0
    for docIndex in testSet:
        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

####测试一下:

for i in range(2):
    vocabList,pSF,pNY = bayes.localWords(ny,sf)

结果:

###分析数据:显示地域相关的用词
将以下代码写入文件bayes.py中

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")
    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")
    for item in sortedNY:
        print (item[0])

####测试一下:

import importlib
importlib.reload(bayes)
bayes.getTopWords(ny,sf)

结果:

###总结:
朴素贝叶斯通过特征之间的条件独立性假设,降低对数据量的需求,尽管条件独立性假设并不正确,但是他仍然是一种有效的分类器