def loadDataSet(): 
 postingList =[['my','dog','has',' flea','problems','help','please'], 
     ['mybe','not','take','him','to','dog','park','stupid'], 
     ['my','dalmation','is','so','cute','i','love','hime'], 
     ['stop','posting','stupid','worthless','garbage'], 
     ['mr','licks','ate','my','steak','how','to','stop','hime'], 
     ['quit','buying','worthless','dog','food','stupid','quit']] 
 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 bagOfWords2VecMN(vocabList,inputSet): 
 returnVec =[0]*len(vocabList) 
 for word in inputSet: 
  returnVec[vocabList.index(word)] +=1 
 return returnVec 

def trainNBO(trainMatrix,trainCategory): 
  numTrainDocs = len(trainMatrix) 
  numWords =len(trainMatrix[0]) 
  #计算p(垃圾)的概率 
  pAbusive = sum(trainCategory)/float(numTrainDocs) 
  #为了防止一个概率为0，假设都有一个 
  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 = np.log((p1Num/p1Denom)) 
  p0Vect = np.log(p0Num/p0Denom) 
  return p0Vect,p1Vect,pAbusive 

def classifyNB(vec2Classify,p0Vec,p1Vec,pClass1): 
  p1 =sum(vec2Classify * p1Vec) +math.log(pClass1) 
  p0 = sum(vec2Classify * p0Vec)+math.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(bagOfWords2VecMN(myVocabList,postinDoc)) 
  p0V,p1V,pAb =trainNBO(trainMat,ListClasses) 
  testEntry =['stupid','my','dalmation'] 
  thisDoc = array(bagOfWords2VecMN(myVocabList,testEntry)) 
  print testEntry,'classified as',classifyNB(thisDoc,p0V,p1V,pAb)