1. 《机器学习实战》K近邻(KNN)分类
2. 《机器学习实战》决策树
对于朴素贝叶斯理论分析可看朴素贝叶斯法及其R实现 ,对于这篇的R实现,只是在这种特殊情况,对于一般的情况并没有实现,所以,本篇文章使用python实现朴素贝叶斯分类的一般方法,并对垃圾邮件进行分类。
##word list vector function
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]
return postingList, classVec
def createVocabList(dataSet):
vocabSet = set([])
for document in dataSet:
vocabSet = vocabSet | set(document)#创建集合的并集
return list(vocabSet)
def setOfWords2Vec(vocabList,inputSet):
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
##change setOfWords2Vec() to bagOfWords2VecMN() (bag of words model)
def bagOfWords2VecMN(vocabList,inputSet):
returnVec = [0]*len(vocabList)
for word in inputSet:
if word in vocabList:
returnVec[vocabList.index(word)] += 1
return returnVec
##naive bayes classifier training function
from numpy import *
def trainNB0(trainMatrix,trainCategory):
numTrainDocs = len(trainMatrix)
numWords = len(trainMatrix[0])
pAbusive = sum(trainCategory)/float(numTrainDocs)
p0Num = ones(numWords); p1Num = ones(numWords)#每个单词至少有一个,即使用拉普拉斯方法
p0Denom = 2.0; p1Denom = 2.0 #对每一个单词有2个类,所以加总为2
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 = log(p1Num/p1Denom) #change to log(),防止数值过小
p0Vect = log(p0Num/p0Denom) #change to log(),同上
return p0Vect, p1Vect, pAbusive
##Naive Bayes classify function
def classifyNB(vec2Classify,p0Vec,p1Vec,pClass1):
p1 = sum(vec2Classify * p1Vec) + log(pClass1)
p0 = sum(vec2Classify *p0Vec) + 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(setOfWords2Vec(myVocabList,postinDoc))
p0V,p1V,pb = 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)
##file parsing and full spam test functions
def textParse(bigString):
import re
listOfTokens = re.split(r'\W*',bigString)
return [tok.lower() for tok in listOfTokens if len(tok)>2]
def spamTest():
docList = []; classList = []; fullText = []
for i in range(1,26):
wordList = textParse(open(r'c:/Users/ll/Documents/spam/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = textParse(open(r'c:/Users/ll/Documents/ham/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = createVocabList(docList)
trainingSet = range(50); testSet = []
for i in range(10):
randIndex = int(random.uniform(0,len(trainingSet)))
testSet.append(trainingSet[randIndex])
del(trainingSet[randIndex])
trainMat = []; trainClasses = []
for docIndex in trainingSet:
trainMat.append(setOfWords2Vec(vocabList,docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses))
errorCount = 0
for docIndex in testSet:
wordVector = setOfWords2Vec(vocabList,docList[docIndex])
if classifyNB(array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
errorCount += 1
print docList[docIndex]
print 'the error rate is: ', float(errorCount)/len(testSet)