# -*- coding: cp936 -*-from numpy import * #过滤网站的恶意留言 # 创建一个实验样本 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 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 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!" % wordreturn returnVec#朴素贝叶斯分类器训练函数 从词向量计算概率 def trainNB0(trainMatrix, trainCategory):numTrainDocs = len(trainMatrix) #文本数量numWords = len(trainMatrix[0]) #文本中词汇数量也是词库的大小pAbusive = sum(trainCategory)/float(numTrainDocs) #P(wi) # p0Num = zeros(numWords); p1Num = zeros(numWords)#p0Denom = 0.0; p1Denom = 0.0p0Num = ones(numWords); p1Num = ones(numWords)#避免一个概率值为0,最后的乘积也为0p0Denom = 2.0; p1Denom = 2.0for i in range(numTrainDocs):if trainCategory[i] == 1:p1Num += trainMatrix[i] #按行进行相加，，每个词汇自己计算总数p1Denom += sum(trainMatrix[i]) #所有词汇一共出现的次数else:p0Num += trainMatrix[i]p0Denom += sum(trainMatrix[i])#p1Vect = p1Num / p1Denom#p0Vect = p0Num / p0Denom #计算获得p(wi|c1),p(wi|c0)#print (p1Num)#print (p1Denom)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): #vec2Classify表示需要分类的向量p1 = sum(vec2Classify*p1Vec) + log(pClass1)p0 = sum(vec2Classify*p0Vec) + log(1.0-pClass1)if p1 > p0:return 1else: return 0def test():listPosts,listClasses = loadDataSet()myVocablist = createVocabList(listPosts)set1 = setOfWords2Vec(myVocablist,listPosts[0])#print(set1)set2 = setOfWords2Vec(myVocablist,listPosts[1])#print(set2)trainMat = []for postinDoc in listPosts:trainMat.append(setOfWords2Vec(myVocablist,postinDoc))#print(trainMat)#print(listClasses)p0V,p1V,pAb = trainNB0(trainMat,listClasses)print(pAb)print(p1V)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)#垃圾邮件过滤的例子：def textParse(bigString):#正则表达式进行文本分割import relistOfTokens = re.split(r'\W*',bigString)return [tok.lower() for tok in listOfTokens if len(tok) > 2]def spamTest():docList = []; classList = []; fullText = []for i in range(1,26):#导入并解析文本文件wordList = textParse(open('E:/python project/Bayes/email/spam/%d.txt' % i).read())docList.append(wordList)fullText.extend(wordList)classList.append(1)wordList = textParse(open('E:/python project/Bayes/email/ham/%d.txt' % i).read())docList.append(wordList)fullText.extend(wordList)classList.append(0)vocabList = createVocabList(docList)trainingSet = range(50);testSet = []for i in range(10):#随机构建10个测试集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 = 0for docIndex in testSet:#对测试集进行分类wordVector = setOfWords2Vec(vocabList, docList[docIndex])if classifyNB(array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:errorCount += 1print 'the error rate is: ', float(errorCount)/len(testSet)
只有不断找寻机会的人才会及时把握机会。
