1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101
| import numpy as np from functools import reduce
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
def 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 returnVec
def trainNB0(trainMatrix,trainCategory): numTrainDocs = len(trainMatrix) numWords = len(trainMatrix[0]) pAbusive = sum(trainCategory)/float(numTrainDocs) p0Num = np.ones(numWords); p1Num = np.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 = np.log(p1Num/p1Denom) p0Vect = np.log(p0Num/p0Denom) return p0Vect,p1Vect,pAbusive
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1): p1 = sum(vec2Classify * p1Vec) + np.log(pClass1) p0 = sum(vec2Classify * p0Vec) + np.log(1.0 - pClass1) if p1 > p0: return 1 else: return 0
def testingNB(): listOPosts,listClasses = loadDataSet() myVocabList = createVocabList(listOPosts) trainMat=[] for postinDoc in listOPosts: trainMat.append(setOfWords2Vec(myVocabList, postinDoc)) p0V,p1V,pAb = trainNB0(np.array(trainMat),np.array(listClasses)) testEntry = ['love', 'my', 'dalmation'] thisDoc = np.array(setOfWords2Vec(myVocabList, testEntry)) if classifyNB(thisDoc,p0V,p1V,pAb): print(testEntry,'属于侮辱类') else: print(testEntry,'属于非侮辱类') testEntry = ['stupid', 'garbage']
thisDoc = np.array(setOfWords2Vec(myVocabList, testEntry)) if classifyNB(thisDoc,p0V,p1V,pAb): print(testEntry,'属于侮辱类') else: print(testEntry,'属于非侮辱类')
if __name__ == '__main__': testingNB()
|