本文共 3040 字，大约阅读时间需要 10 分钟。
**
代码如下：'''使用Python进行文本分类''''''词表到向量的转换函数'''def loadDataSet(): postingList=[['my', 'dog', 'has', 'flea', 'problems', 'help', 'please'], ['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'], ['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'''创建包含所有文档中出现的不重复词的列表'''def createVocabList(dataSet): vocabSet = set([]) for document in dataSet: vocabSet = vocabSet | set(document)'''set of words model（词集模型：仅将每个词的出现与否作为一个特征）'''def setOfWords2Vec(vocabList,inputSet): returnVec = [0]*len(vocabList) for word in inputSet: if word in inputSet: returnVec[vocabList.index(word)] = 1 else: print "the word : %s is not in my Vocabulary!" % word return returnVec'''bag of words model（词袋模型：该模型中每个词可以出现不止一次）'''def bagOfWordsVecMN(vocabList,inputSet): returnVec = [0]*len(vocabList) for word in inputSet: if word in vocabList: returnVec[vocabList.index(word)] += 1 return returnVec'''训练算法：从词向量计算概率''''''trainMatrix:文档矩阵(numTrainDocs行*numWords列)；trainCategory：每篇文档类别标签所构成的向量'''def trainNB0(trainMatrix,trainCategory): numTrainDocs = len(trainMatrix)'''训练文本数''' numWords = len(trainMatrix[0])'''总单词数（词汇表中的总单词数）''' pAbusive = sum(trainCategory)/float(munTrainDocs) '''统计侮辱性（1）在文档中出现的概率''' '''p0Num = zeros(numWords) p1Num = zeros(numWords) p0Denom = 0.0 p1Denom = 0.0变更代码如下：使用拉普拉斯校准避免计算零概率值''' p0Num = ones(numWords) p1Num = ones(numWords) p0Denom = 2.0 p1Denom = 2.0 '''以下分别计算p(wi|c1)和p(wi|c0)的概率''' 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 = p1Num/p1Denom p0Vect = p0Num/p0Denom变更此行代码如下，为避免下溢出（由于太多很小的数相乘造成，在Python环境中由于太多很小的数相乘最后四舍五入会得到0）, 取自然对数，可避免下溢出或者浮点数舍入导致的错误''' p1Vect = log(p1Num/p1Denom) p0Vect = log(p0Num/p0Denom) return p0Vect,p1Vect,pAbusivedef classifyNB(vec2Classify,p0Vec,p1Vec,pClass1): p1 = sum(vec2Classify*p1Vec) + log(pClass1) '''本应该是 p1Vec*pClass1但整体的都去了对数，所以最后变为对数相加的形式''' p0 = sum(vec2Classify*p0Vec) + log(1.0 - pClass1) if p1>p0: return 1 else: return 0def 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)
**
转载地址：http://icaci.baihongyu.com/