from numpy import *def trainNB0(trainMatrix,trainCatergory):#適用于二分類問題，其中一類的標簽為1#return#p0Vect：標簽為0的樣本中，出現某個特征對應的概率#p1Vect：標簽為1的樣本中，出現某個特征對應的概率#pAbusive：標簽為1的樣本出現的概率numTrainDoc = len(trainMatrix)numWords = len(trainMatrix[0])pAbusive = sum(trainCatergory)/float(numTrainDoc)#防止多個概率的成績當中的一個為0#p0Num: 在訓練樣本標簽為0的數據中，所有特征的對應value值之和，為矩陣#p1Num: 在訓練樣本標簽為1的數據中，所有特征的對應value值之和，為矩陣p0Num = ones(numWords)p1Num = ones(numWords)#p0Denom：在訓練樣本標簽為0的數據中，所有特征的value值之和，為標量#p1Denom：在訓練樣本標簽為1的數據中，所有特征的value值之和，為標量#為什么初始化為2？？p0Denom = 2.0p1Denom = 2.0for i in range(numTrainDoc):if trainCatergory[i] == 1:p1Num +=trainMatrix[i]p1Denom += sum(trainMatrix[i])else:p0Num +=trainMatrix[i]p0Denom += sum(trainMatrix[i])#出于精度的考慮，否則很可能到限歸零，change to log()p1Vect = log(p1Num/p1Denom)p0Vect = log(p0Num/p0Denom)return p0Vect,p1Vect,pAbusivedef classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):#element-wise mult,只算分子的log值，因為只需比較大小，所以正負無關p1 = sum(vec2Classify * p1Vec) + log(pClass1) p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)if p1 > p0:return 1else: return 0 ####################3#from numpy import * #import os #os.chdir(r"/home/luogan/lg/Python728/bayes/classical-machine-learning-algorithm-master/bayesian") #import bayes 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 notreturn postingList,classVecdef createVocabList(dataSet):vocabSet = set([]) #create empty setfor document in dataSet:vocabSet = vocabSet | set(document) #union of the two setsreturn list(vocabSet)def setOfWords2Vec(vocabList, inputSet):returnVec = [0]*len(vocabList)for word in inputSet:if word in vocabList:returnVec[vocabList.index(word)] = 1else: print ("the word: %s is not in my Vocabulary!" % word)return returnVecdef 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))def bagOfWords2VecMN(vocabList, inputSet):returnVec = [0]*len(vocabList)for word in inputSet:if word in vocabList:returnVec[vocabList.index(word)] += 1return returnVecdef textParse(bigString): #input is big string, #output is word listimport relistOfTokens = re.split(r'\W*', bigString)return [tok.lower() for tok in listOfTokens if len(tok) > 2] if __name__ == "__main__":listOPosts,listClasses = loadDataSet()myVocabList = createVocabList(listOPosts)#print (myVocabList)trainMat = []for postinDoc in listOPosts:trainMat.append(setOfWords2Vec(myVocabList, postinDoc))p0V,p1V,pAb = trainNB0(trainMat, listClasses)testingNB()

總結

以上是生活随笔為你收集整理的bayes的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。