from numpy import *

 #创建一些实验样本。该函数返回的第一个变量是进行词条切分后的文档集合，

 #该函数返回的第二个变量是一个类别标签的集合

 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 not

     return postingList,classVec

 #创建一个包含所有文档中出现的不重复词的列表

 def createVocabList(dataSet):

     #创建一个空集

     vocabSet = set([])  #create empty set

     for document in dataSet:

         #创建两个集合的并集

         vocabSet = vocabSet | set(document) #union of the two sets

     return list(vocabSet)

 #该函数的输入参数为词汇表及其某个文档，输出的是文档向量，向量的每一元素为1或0，

 # 分别表示词汇表中的单词在输入文档中是否出现。

 #函数首先创建一个和词汇表等长的向量，并将其元素都设置为0.接着，遍历文档中的所有单词，

 # 如果出现了词汇表中的单词，则将输出的文档向量中对应值设为1.一切顺利的话，就不需要

 # 检查某个词是否还在vocabList中，后边可能会用到这一操作

 def setOfWords2Vec(vocabList, inputSet):

     #创建一个维度都为0的向量

     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

 '''

 该函数的伪代码如下：

 计算每个类别中的文档数目

 对每篇训练文档：

     对每个类别：

         如果词条出现文档中则增加该词条的计数值

         增加所有词条的计数值

     对每个类别：

         对每个词条：

             将该词条的数目除以总词条数目得到条件概率

     返回每个类别的条件概率

 '''

 #

 def trainNB0(trainMatrix,trainCategory):

     numTrainDocs = len(trainMatrix)

     numWords = len(trainMatrix[0])

     #初始化概率

     pAbusive = sum(trainCategory)/float(numTrainDocs)

     p0Num = ones(numWords); p1Num = ones(numWords)      #change to ones()

     p0Denom = 2.0; p1Denom = 2.0                        #change to 2.0

     for i in range(numTrainDocs):

         #向量相加

         if trainCategory[i] == 1:

             p1Num += trainMatrix[i]

             p1Denom += sum(trainMatrix[i])

         else:

             p0Num += trainMatrix[i]

             p0Denom += sum(trainMatrix[i])

             #对每个元素做除法

     p1Vect = log(p1Num/p1Denom)          #change to log()

     p0Vect = log(p0Num/p0Denom)          #change to log()

     return p0Vect,p1Vect,pAbusive

 def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):

     p1 = sum(vec2Classify * p1Vec) + log(pClass1)    #element-wise mult

     p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)

     if p1 > p0:

         return 1

     else:

         return 0

 def bagOfWords2VecMN(vocabList, inputSet):

     returnVec = [0]*len(vocabList)

     for word in inputSet:

         if word in vocabList:

             returnVec[vocabList.index(word)] += 1

     return returnVec

 def 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))

 #如果一个词在文档中出现不止依次，这可能意味着包含该词是否出现的文档所不能表达的某种信息，

 # 这种方法被称为词袋模型。

 # #

 mySent='This book is the best book on Python or M.L. I have ever laid eyes upon.'

 A=mySent.split()

 print(A)