朴素贝叶斯python小样本实例

  1 from numpy import *
  2 
  3 #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，
  4 #该函数返回的第二个变量是一个类别标签的集合
  5 def loadDataSet():
  6     postingList=[[‘my‘, ‘dog‘, ‘has‘, ‘flea‘, ‘problems‘, ‘help‘, ‘please‘],
  7                  [‘maybe‘, ‘not‘, ‘take‘, ‘him‘, ‘to‘, ‘dog‘, ‘park‘, ‘stupid‘],
  8                  [‘my‘, ‘dalmation‘, ‘is‘, ‘so‘, ‘cute‘, ‘I‘, ‘love‘, ‘him‘],
  9                  [‘stop‘, ‘posting‘, ‘stupid‘, ‘worthless‘, ‘garbage‘],
 10                  [‘mr‘, ‘licks‘, ‘ate‘, ‘my‘, ‘steak‘, ‘how‘, ‘to‘, ‘stop‘, ‘him‘],
 11                  [‘quit‘, ‘buying‘, ‘worthless‘, ‘dog‘, ‘food‘, ‘stupid‘]]
 12     classVec = [0,1,0,1,0,1]    #1 is abusive, 0 not
 13     return postingList,classVec
 14 
 15 #创建一个包含所有文档中出现的不重复词的列表
 16 def createVocabList(dataSet):
 17     #创建一个空集
 18     vocabSet = set([])  #create empty set
 19     for document in dataSet:
 20         #创建两个集合的并集
 21         vocabSet = vocabSet | set(document) #union of the two sets
 22     return list(vocabSet)
 23 
 24 #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，
 25 # 分别表示词汇表中的单词在输入文档中是否出现。
 26 #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，
 27 # 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
 28 # 检查某个词是否还在vocabList中，后边可能会用到这一操作
 29 def setOfWords2Vec(vocabList, inputSet):
 30     #创建一个维度都为0的向量
 31     returnVec = [0]*len(vocabList)
 32     for word in inputSet:
 33         if word in vocabList:
 34             returnVec[vocabList.index(word)] = 1
 35         else: print ("the word: %s is not in my Vocabulary!" % word)
 36     return returnVec
 37 ‘‘‘
 38 该函数的伪代码如下：
 39 计算每个类别中的文档数目
 40 对每篇训练文档：
 41     对每个类别：
 42         如果词条出现文档中则增加该词条的计数值
 43         增加所有词条的计数值
 44     对每个类别：
 45         对每个词条：
 46             将该词条的数目除以总词条数目得到条件概率
 47     返回每个类别的条件概率
 48 ‘‘‘
 49 
 50 #
 51 def trainNB0(trainMatrix,trainCategory):
 52     numTrainDocs = len(trainMatrix)
 53     numWords = len(trainMatrix[0])
 54     #初始化概率
 55     pAbusive = sum(trainCategory)/float(numTrainDocs)
 56     p0Num = ones(numWords); p1Num = ones(numWords)      #change to ones()
 57     p0Denom = 2.0; p1Denom = 2.0                        #change to 2.0
 58     for i in range(numTrainDocs):
 59         #向量相加
 60         if trainCategory[i] == 1:
 61             p1Num += trainMatrix[i]
 62             p1Denom += sum(trainMatrix[i])
 63         else:
 64             p0Num += trainMatrix[i]
 65             p0Denom += sum(trainMatrix[i])
 66             #对每个元素做除法
 67     p1Vect = log(p1Num/p1Denom)          #change to log()
 68     p0Vect = log(p0Num/p0Denom)          #change to log()
 69     return p0Vect,p1Vect,pAbusive
 70 
 71 def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
 72     p1 = sum(vec2Classify * p1Vec) + log(pClass1)    #element-wise mult
 73     p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
 74     if p1 > p0:
 75         return 1
 76     else:
 77         return 0
 78 
 79 def bagOfWords2VecMN(vocabList, inputSet):
 80     returnVec = [0]*len(vocabList)
 81     for word in inputSet:
 82         if word in vocabList:
 83             returnVec[vocabList.index(word)] += 1
 84     return returnVec
 85 
 86 def testingNB():
 87     listOPosts,listClasses = loadDataSet()
 88     myVocabList = createVocabList(listOPosts)
 89     trainMat=[]
 90     for postinDoc in listOPosts:
 91         trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
 92     p0V,p1V,pAb = trainNB0(array(trainMat),array(listClasses))
 93     testEntry = [‘love‘, ‘my‘, ‘dalmation‘]
 94     thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
 95     print(testEntry,‘classified as: ‘,classifyNB(thisDoc,p0V,p1V,pAb))
 96     testEntry = [‘stupid‘, ‘garbage‘]
 97     thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
 98     print (testEntry,‘classified as: ‘,classifyNB(thisDoc,p0V,p1V,pAb))
 99 #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，
100 # 这种方法被称为词袋模型。
101 # #
102 
103 mySent=‘This book is the best book on Python or M.L. I have ever laid eyes upon.‘
104 A=mySent.split()
105 print(A)