机器学习实战---朴素贝叶斯

from numpy import *

"""
func: 加载数据

param:
    None

return:
    postingList: 进行词条切分后的文档集合
    classVec: 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

"""
func: 创建一个包含在所有文档中出现的不重复词的列表

param:
    None

return:
    list(vocaSet): 文档中所有不重复词的列表
"""                
def createVocabList(dataSet):
    vocabSet = set([])  #create empty set
    for document in dataSet:
        vocabSet = vocabSet | set(document) #union of the two sets
    return list(vocabSet)

"""
func: 词集模型；
将词汇表转为文档向量，每一个元素为1或0，分别表示词汇表中的单词在输入文档中是否出现。

param:
    vocabList: 词汇表
    inputSet：某个文档

return:
    returnVec：文档向量, 第i个元素表示词汇表中第i个单词是否出现
"""
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 my Vocabulary!" % word)
    return returnVec

"""
func: 朴素贝叶斯词袋模型

param:
    vocabList: 词汇表
    inputSet：某个文档

return:
    returnVec：文档向量, 第i个元素表示词汇表中第i个单词出现的次数
"""
def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1
    return returnVec


"""
func: 朴素贝叶斯分类器训练函数

param:
    trainMatrix: 文档矩阵，每个元素为0或1，表示是否出现在该文档上
    trainCategory: 由每篇文档类别标签所构成的向量

return:
    p0Vect: 向量，p(Wi|C0)，即文档是非侮辱性的条件下，单词Wi出现的概率的对数
    p1Vect: 向量, p(Wi|C1)，即文档是侮辱性的条件下，单词Wi出现的概率的对数
    pAbusive: 文档属于侮辱性文档的概率
"""
def trainNB0(trainMatrix,trainCategory):
    # 训练文档的数量
    numTrainDocs = len(trainMatrix)
    # 词汇表的数量
    numWords = len(trainMatrix[0])
    # 侮辱性文档（class=1）占总训练文档的比，即其概率
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    # 初始化概率，p1Num为向量，第i个元素表示词汇表中第i个单词在侮辱性（class=1）文档中出现的次数；
    # p0Num为向量，第i个元素表示词汇表第i个单词在非侮辱性（class=0）文档中出现的次数；
    p0Num = ones(numWords); p1Num = ones(numWords)      #change to ones() ， 防止某个单词概率为0导致p(c|w)为0
    # p0Denom表示侮辱性（class=0）文档中单词的总数
    # p1Denom表示侮辱性（class=1）文档中单词的总数
    p0Denom = 2.0; p1Denom = 2.0                        #change to 2.0, 防止某个单词概率为0导致p(c|w)为0
    # 对每篇训练文档
    for i in range(numTrainDocs):
        # 对每个类别：           
        if trainCategory[i] == 1:
            # 如果词条出现在文档中-> 增加该词条的计数值
            p1Num += trainMatrix[i]
            # 增加所有词条的计数值
            p1Denom += sum(trainMatrix[i])
        else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
    # 对每个词条，将该词条的数目除以从此条数得到条件概率，即P(W|C)的值,C为类标签，w为某词条
    p1Vect = log(p1Num/p1Denom)          #change to log()， 防止下溢出，即太多很小的数相乘导致最后结果为0
    p0Vect = log(p0Num/p0Denom)          #change to log()
    return p0Vect,p1Vect,pAbusive

"""
func: 朴素贝叶斯分类函数

param:
    vec2Classify: 要分类的向量
    p0Vec: 向量，p(Wi|C0)，即文档是非侮辱性的条件下，单词Wi出现的概率的对数
    p1Vec: 向量, p(Wi|C1)，即文档是侮辱性的条件下，单词Wi出现的概率的对数
    pClass1: 文档属于侮辱性文档的概率

return:
    分类的类别：1或0
    
"""
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    # p(w|c1)p(c1)，因为目标是判断p(c|w)的值的大小，所以可不求p(w),只求p(w|c)p(c)
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)    #element-wise mult
    # p(w|c0)p(c0)
    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else: 
        return 0

"""
func: 对给定的词向量，判断并打印出其类别

param:
    None

return:
    None
"""
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))
    # p0V,p1V,pAb无需重复求解
    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))

"""
func: 切分文本

param:
    bigString: 长字符串

return:
    满足长度大于2的单词的列表，且将大写改为小写
"""
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] 

"""
func: 完整的垃圾邮件测试函数，打印出错误率

param：
    None
return:
    None
""" 
def spamTest():
    docList=[]; classList = []; fullText =[]
    # 导入并解析文本文件
    for i in range(1,26):
        wordList = textParse(open('email/spam/%d.txt' % i).read())
        # 注意append和extend的区别：
        # a = [1,2,3] b=[4,5,6] 
        # a.append(b) [1,2,3,[4,5,6]]
        # a.extend(b) [1,2,3,4,5,6]
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
        wordList = textParse(open('email/ham/%d.txt' % i).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    # 创建词汇表
    vocabList = createVocabList(docList)#create vocabulary
    # 随机构建训练集, trainingSet/testSet存储训练/测试文档集的编号，
    trainingSet = list(range(50)); testSet=[]           #create test set
    for i in range(10):
        # random.uniform：从给定数据范围的均匀分布中抽取样本
        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
    # 对测试集分类
    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

"""
func: 计算单词频数

param:
    vocaList: 词汇表
    fullTest: 所有文档中的所有单词列表，包含重复单词

return:
    频数最好的30个单词
"""
def calcMostFreq(vocabList,fullText):
    import operator
    freqDict = {}
    # 计算出现频率
    for token in vocabList:
        freqDict[token]=fullText.count(token)
    sortedFreq = sorted(freqDict.items(), key=operator.itemgetter(1), reverse=True) 
    return sortedFreq[:30]       

"""
func: RSS源分类器及高频词去除函数

param:
    feed1:RSS源
    feed0:RSS源

return:
    vocabList: 词汇表
    p0V:向量，p(Wi|C0)，即文档是第一个地区的条件下，单词Wi出现的概率的对数
    p1V:向量, p(Wi|C1)，即文档是第二个地区的条件下，单词Wi出现的概率的对数
    
"""
def localWords(feed1,feed0):
    import feedparser
    docList=[]; classList = []; fullText =[]
    minLen = min(len(feed1['entries']),len(feed0['entries']))
    for i in range(minLen):
        # 每次访问一次RSS源
        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)
    # 去除出现次数最高的那些词
    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

"""
func: 最具表征性的词汇显示函数,打印出分类错误率，及大于某个阈值的所有单词

param:
    ny: RSS源
    sy：RSS源

return:
    None
"""
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])