python源码,朴素贝叶斯实现多分类

发布时间:2020-07-16 12:18:03 作者:nineteens
来源:网络 阅读:722

  机器学习实战中,朴素贝叶斯那一章节只实现了二分类,网上大多数博客也只是照搬书上的源码,没有弄懂实现的根本。在此梳理了一遍朴素贝叶斯的原理,实现了5分类的例子,也是自己的一点心得,交流一下。

  from numpy import *

  '''

  贝叶斯公式 p(ci|w) = p(w|ci)*p(ci) / p(w)

  即比较两类别分子大小,把结果归为分子大的一类

  p(w|ci)条件概率,即在类别1或0下,w(词频)出现的概率(词频/此类别总词数即n/N)

  '''

  # 取得DataSet中不重复的word

  def createVocabList(dataSet):

  vocabSet = set([])#使用set创建不重复词表库

  for document in dataSet:

  vocabSet = vocabSet | set(document) #创建两个集合的并集

  return list(vocabSet)

  '''

  我们将每个词的出现与否作为一个特征,这可以被描述为词集模型(set-of-words model)。

  在词集中,每个词只能出现一次。

  '''

  def setOfWords2Vec(vocabList, inputSet):

  returnVec = [0]*len(vocabList)#创建一个所包含元素都为0的向量

  #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的对应值设为1

  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

  '''

  如果一个词在文档中出现不止一次,这可能意味着包含该词是否出现在文档中所不能表达的某种信息,

  这种方法被称为词袋模型(bag-of-words model)。

  在词袋中,每个单词可以出现多次。

  为适应词袋模型,需要对函数setOfWords2Vec稍加修改,修改后的函数称为bagOfWords2VecMN

  '''

  def bagOfWords2Vec(vocabList, inputSet):

  returnVec = [0]*len(vocabList)

  for word in inputSet:

  if word in vocabList:

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

  return returnVec

  def countX(aList,el):

  count = 0

  for item in aList:

  if item == el:

  count += 1

  return count

  def trainNB0(trainMatrix,trainCategory):

  '''

  trainMatrix:文档矩阵

  trainCategory:每篇文档类别标签

  '''

  numTrainDocs = len(trainMatrix)

  numWords = len(trainMatrix[0])

  pAbusive0 = countX(trainCategory,0) / float(numTrainDocs)

  pAbusive1 = countX(trainCategory,1) / float(numTrainDocs)

  pAbusive2 = countX(trainCategory,2) / float(numTrainDocs)

  pAbusive3 = countX(trainCategory,3) / float(numTrainDocs)

  pAbusive4 = countX(trainCategory,4) / float(numTrainDocs)

  #初始化所有词出现数为1,并将分母初始化为2,避免某一个概率值为0

  p0Num = ones(numWords); p1Num = ones(numWords)

  p2Num = ones(numWords)

  p3Num = ones(numWords)

  p4Num = ones(numWords)

  p0Denom = 2.0; p1Denom = 2.0 ;p2Denom = 2.0

  p3Denom = 2.0; p4Denom = 2.0

  for i in range(numTrainDocs):

  # 1类的矩阵相加

  if trainCategory[i] == 1:

  p1Num += trainMatrix[i]

  p1Denom += sum(trainMatrix[i])

  if trainCategory[i] == 2:

  p2Num += trainMatrix[i]

  p2Denom += sum(trainMatrix[i])

  if trainCategory[i] == 3:

  p3Num += trainMatrix[i]

  p3Denom += sum(trainMatrix[i])

  if trainCategory[i] == 4:

  p4Num += trainMatrix[i]

  p4Denom += sum(trainMatrix[i])

  if trainCategory[i] == 0:

  p0Num += trainMatrix[i]

  p0Denom += sum(trainMatrix[i])

  #将结果取自然对数,避免下溢出,即太多很小的数相乘造成的影响

  p4Vect = log(p4Num/p4Denom)

  p3Vect = log(p3Num/p3Denom)

  p2Vect = log(p2Num/p2Denom)

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

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

  return p0Vect,p1Vect,p2Vect,p3Vect,p4Vect,pAbusive0,pAbusive1,pAbusive2,pAbusive3,pAbusive4

  def classifyNB(vec2Classify,p0Vec,p1Vec,p2Vec,p3Vec,p4Vec,pClass0,pClass1,pClass2,pClass3,pClass4):

  p1 = sum(vec2Classify * p1Vec) + log(pClass1)

  p2 = sum(vec2Classify * p2Vec) + log(pClass2)

  p3 = sum(vec2Classify * p3Vec) + log(pClass3)

  p4 = sum(vec2Classify * p4Vec) + log(pClass4)

  p0 = sum(vec2Classify * p0Vec) + log(pClass0)

  ## print(p0,p1,p2,p3,p4)无锡人流医院 http://www.bhnkyy39.com/

  return [p0,p1,p2,p3,p4].index(max([p0,p1,p2,p3,p4]))

  if __name__ == "__main__":

  dataset = [['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'],

  ['i','love','you'],

  ['you','kiss','me'],

  ['hate','heng','no'],

  ['can','i','hug','you'],

  ['refuse','me','ache'],

  ['1','4','3'],

  ['5','2','3'],

  ['1','2','3']]

  # 0,1,2,3,4分别表示不同类别

  classVec = [0,1,0,1,0,1,2,2,4,2,4,3,3,3]

  print("正在创建词频列表")

  myVocabList = createVocabList(dataset)

  print("正在建词向量")

  trainMat = []

  for postinDoc in dataset:

  trainMat.append(setOfWords2Vec(myVocabList,postinDoc))

  print("开始训练")

  p0V,p1V,p2V,p3V,p4V,pAb0,pAb1,pAb2,pAb3,pAb4 = trainNB0(array(trainMat),array(classVec))

  # 输入的测试案例

  tmp = ['love','you','kiss','you']

  thisDoc = array(setOfWords2Vec(myVocabList,tmp))

  flag = classifyNB(thisDoc,p0V,p1V,p2V,p3V,p4V,pAb0,pAb1,pAb2,pAb3,pAb4)

  print('flag is',flag)


推荐阅读:
  1. 学习日志---朴素贝叶斯算法
  2. 对Python源码加密及反编译前后对比

免责声明:本站发布的内容(图片、视频和文字)以原创、转载和分享为主,文章观点不代表本网站立场,如果涉及侵权请联系站长邮箱:is@yisu.com进行举报,并提供相关证据,一经查实,将立刻删除涉嫌侵权内容。

朴素贝叶斯 多分类

上一篇:Ubuntu16.04 ab安装以及使用教程

下一篇:RPC框架与分布式服务框架的区别

相关阅读

您好,登录后才能下订单哦!

密码登录
登录注册
其他方式登录
点击 登录注册 即表示同意《亿速云用户服务条款》