Python实现的朴素贝叶斯算法经典示例【测试可用】

本文实例讲述了Python实现的朴素贝叶斯算法。分享给大家供大家参考，具体如下：

代码主要参考机器学习实战那本书，发现最近老外的书确实比中国人写的好，由浅入深，代码通俗易懂，不多说上代码：

#encoding:utf-8'''''Created on 2015年9月6日@author: ZHOUMEIXU204朴素贝叶斯实现过程'''#在该算法中类标签为1和0，如果是多标签稍微改动代码既可import numpy as nppath=u"D://Users//zhoumeixu204/Desktop//python语言机器学习//机器学习实战代码  python//机器学习实战代码//machinelearninginaction//Ch04//"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,classVecdef createVocabList(dataset):  vocabSet=set([])  for document in dataset:    vocabSet=vocabSet|set(document)  return list(vocabSet)def setOfWordseVec(vocabList,inputSet):  returnVec=[0]*len(vocabList)  for word in inputSet:    if word in vocabList:      returnVec[vocabList.index(word)]=1  #vocabList.index() 函数获取vocabList列表某个元素的位置，这段代码得到一个只包含0和1的列表    else:      print("the word :%s is not in my Vocabulary!"%word)  return returnVeclistOPosts,listClasses=loadDataSet()myVocabList=createVocabList(listOPosts)print(len(myVocabList))print(myVocabList)print(setOfWordseVec(myVocabList, listOPosts[0]))print(setOfWordseVec(myVocabList, listOPosts[3]))#上述代码是将文本转化为向量的形式，如果出现则在向量中为1，若不出现 ，则为0def trainNB0(trainMatrix,trainCategory):  #创建朴素贝叶斯分类器函数  numTrainDocs=len(trainMatrix)  numWords=len(trainMatrix[0])  pAbusive=sum(trainCategory)/float(numTrainDocs)  p0Num=np.ones(numWords);p1Num=np.ones(numWords)  p0Deom=2.0;p1Deom=2.0  for i in range(numTrainDocs):    if trainCategory[i]==1:      p1Num+=trainMatrix[i]      p1Deom+=sum(trainMatrix[i])    else:      p0Num+=trainMatrix[i]      p0Deom+=sum(trainMatrix[i])  p1vect=np.log(p1Num/p1Deom)  #change to log  p0vect=np.log(p0Num/p0Deom)  #change to log  return p0vect,p1vect,pAbusivelistOPosts,listClasses=loadDataSet()myVocabList=createVocabList(listOPosts)trainMat=[]for postinDoc in listOPosts:  trainMat.append(setOfWordseVec(myVocabList, postinDoc))p0V,p1V,pAb=trainNB0(trainMat, listClasses)if __name__!='__main__':  print("p0的概况")  print (p0V)  print("p1的概率")  print (p1V)  print("pAb的概率")  print (pAb)

运行结果：

32
['him', 'garbage', 'problems', 'take', 'steak', 'quit', 'so', 'is', 'cute', 'posting', 'dog', 'to', 'love', 'licks', 'dalmation', 'flea', 'I', 'please', 'maybe', 'buying', 'my', 'stupid', 'park', 'food', 'stop', 'has', 'ate', 'help', 'how', 'mr', 'worthless', 'not']