Python机器学习与实战笔记之朴素贝叶斯分类

1联合概率分布
p(x,y)=p(y)P(x|y)  或者p(A交B)=p(A)xp(B)  p(A交B)不容易求,假设条件独立拆分成两个事件的乘积
2基本假设条件独立性
3利用贝叶斯定理 p(y|x)=P(x,y)/p(x)=p(y)P(x|y)/sum(y-i)[p(y)P(x|y)]
y=max p(y)P(x|y)
贝叶斯决策理论要求计算两个概率p1(x，y),p2(x, y):
如果p1(x，y) > p2 (x, y) , 那么属于类别1
如果p2(x, y) > pl(x, y) , 那么属于类别2
拉普拉斯估计
每一个似然函数 分子+1对分母加上分子中加上1的总数
在朴素贝叶斯使用数值特征采用数值特征离散化,找见数据分布分割点切分

朴素贝叶斯分类器通常有两种实现方式：一种基于贝努利模型实现， 一种基于多项式模型实现

这里采用前一种实现方式。该实现方式中并不考虑词在文档中出现的次数， 只考虑出不出现，

 因此在这个意义上相当于假设词是等权重的

导入指定目录下的py文件,先导入路径,后引入文件
import sys
sys.path.append("G:/python/pythonwork/ML")

import bayes

Python版实现
http://blog.csdn.net/q383700092/article/details/51773364
R语言版调用函数
http://blog.csdn.net/q383700092/article/details/51774069
MapReduce简化实现版
http://blog.csdn.net/q383700092/article/details/51778765
spark版
后续添加

垃圾邮件分类示例

#coding:utf-8
from numpy import *

#创建了一些实验样本
#postingList,classVec=bayes.loadDataSet()
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]
    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
#wordlist=bayes.createVocabList(postingList)
def createVocabList(dataSet):
    vocabSet = set([])  # 创建一个空集
    for document in dataSet:
        vocabSet = vocabSet | set(document)  # 创建两个集合的并集
    return list(vocabSet)


# 将文档词条转换成词向量
#每个词的出现与否作为一个特征，被描述为词集模型setOfWordsmodel
#wordVec=bayes.setOfWords2Vec(wordlist,postingList[0])
def setOfWords2Vec(vocabList, inputSet):
    returnVec = [0] * len(vocabList)  # 创建一个其中所含元素都为0的向量
    for word in inputSet:
        if word in vocabList:
             returnVec[vocabList.index(word)] = 1     #index函数在字符串里找到字符第一次出现的位置  词集模型
            #returnVec[vocabList.index(word)] += 1  # 文档的词袋模型    每个单词可以出现多次
        else:
            print "the word: %s is not in my Vocabulary!" % word
    return returnVec

#朴素贝叶斯分类器训练函数   从词向量计算概率
#trainMatrix=[]
#for postinDoc in postingList:
#    trainMatrix.append(bayes.setOfWords2Vec(wordlist,postinDoc))
#p0Vect, p1Vect, pAbusive=bayes.trainNB0(trainMatrix,classVec)
def trainNB0(trainMatrix, trainCategory):
    numTrainDocs = len(trainMatrix)  #输入的样本数
    numWords = len(trainMatrix[0])  #每个样本的词的总数
    pAbusive = sum(trainCategory)/float(numTrainDocs)  #侮辱词条所占比例
   # p0Num = zeros(numWords); p1Num = zeros(numWords)
    #p0Denom = 0.0; p1Denom = 0.0
    p0Num = ones(numWords); p1Num = ones(numWords)         #避免一个概率值为0,最后的乘积也为0
    p0Denom = 2.0; p1Denom = 2.0                           #将所有词的出现数初始化为1，并将分母初始化为2
    for i in range(numTrainDocs):
        if trainCategory[i] == 1:     #判读是否是侮辱词
            p1Num += trainMatrix[i]   #每个词出现的个数
            p1Denom += sum(trainMatrix[i])   #词出现的总数
        else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
   # p1Vect = p1Num / p1Denom
    #p0Vect = p0Num / p0Denom
    p1Vect = log(p1Num / p1Denom)
    p0Vect = log(p0Num / p0Denom)      #避免下溢出或者浮点数舍入导致的错误   下溢出是由太多很小的数相乘得到的
    return p0Vect, p1Vect, pAbusive

#朴素贝叶斯分类器
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify*p1Vec) + log(pClass1)
    p0 = sum(vec2Classify*p0Vec) + log(1.0-pClass1)
    if p1 > p0:
        return 1
    else: return 0
#测试朴素贝叶斯分类器
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)

#在词袋中，每个单词可以出现多次
def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1
    return returnVec

#文本切分
def textParse(bigString):  # input is big string, #output is word list
    import re
    listOfTokens = re.split(r'\W*', bigString)
    return [tok.lower() for tok in listOfTokens if len(tok) > 2]
#对贝叶斯垃圾邮件分类器进行自动化处理
#bayes.spamTest()
def spamTest():
    docList = [];
    classList = [];
    fullText = []
    for i in range(1, 26):
        wordList = textParse(open('G:/python/pythonwork/email/spam/%d.txt' % i).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
        wordList = textParse(open('G:/python/pythonwork/email/ham/%d.txt' % i).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = createVocabList(docList)  # create vocabulary
    trainingSet = range(50);
    testSet = []  # create test set
    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:  # 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 "classification error", docList[docIndex]
    print 'the error rate is: ', float(errorCount) / len(testSet)
    # return vocabList,fullText


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

#calcMostFreq该函数遍历词汇表中的每个词并统计它在文本中出现的次数，然
#后根据出现次数从高到低对词典进行排序，最后返回排序最高的100个单词
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 = 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
#返回排名最高的x个不同单词
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]