from numpy import *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,classVecdef createVocabList(dataSet): vocabSet = set() for document in dataSet: vocabSet = vocabSet | set(document) return list(vocabSet) 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 returnVecdef trainNB0(trainMatrix, trainCategory): numTrainDocs = len(trainMatrix) numWords = len(trainMatrix[0]) pAbusive = sum(trainCategory)/float(numTrainDocs)# p0Num = zeros(numWords)# p1Num = zeros(numWords)# p0Denom = 0.0# p1Denom = 0.0 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)# print sum(p1Num),p1Denom p0Vect = log(p0Num/p0Denom) return p0Vect,p1Vect,pAbusivedef classifyNB(vec2Classify, p0Vec, p1Vec,pClass1): p1 = sum(vec2Classify*p1Vec) + log(pClass1) #after the log operation,the multiply change to add operation p0 = sum(vec2Classify*p0Vec) + log(1-pClass1) return 1 if p1>p0 else 0 def testingNB(): listOPosts,listClasses = loadDataSet() myVocabList = createVocabList(listOPosts) trainMat=[] for postinDoc in listOPosts: trainMat.append(setOfWords2Vec(myVocabList, postinDoc)) p0v,p1v,pab = trainNB0(trainMat, listClasses) testEntity = ['love','my','dalmation'] thisDoc = array(setOfWords2Vec(myVocabList, testEntity)) print testEntity, 'classifiied as:',classifyNB(thisDoc, p0v, p1v, pab) testEntity = ['stupid','garbage'] thisDoc = array(setOfWords2Vec(myVocabList, testEntity)) print testEntity, 'classifiied as:',classifyNB(thisDoc, p0v, p1v, pab) def bagOfWord2VecMN(vocabList, inputSet): returnVec = [0]*len(vocabList) for word in inputSet: if word in vocabList: returnVec[vocabList.index(word)] += 1 return returnVecdef textParse(bigString): import re listOfTokens = 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): wordList = textParse(open('email/spam/%d.txt' % i).read()) 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) vocabList = createVocabList(docList) trainingSet = range(50);testSet = [] 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(trainMat, trainClasses) errorCount = 0 for docIndex in testSet: wordVector = setOfWords2Vec(vocabList, docList[docIndex]) if classifyNB(wordVector, p0v, p1v, pSpam)!=classList[docIndex]: errorCount += 1 print 'the error rate is: ',float(errorCount)/len(testSet) def calcMostFreq(vocabList, fullText): pass if __name__ == '__main__': spamTest() import feedparser ny = feedparser.parse('http://newyork.craigslist.org/stp/index.rss') print len(ny['entries'])
