《机器学习实战》朴素贝叶斯分类器
贝叶斯准则:
p(c|x)=p(x|c)p(c)p(x)(1)
上式中, c 表示某个具体的类别,
- 问题:对于一个分类问题,给定样本的特征向量
x={w1,w2,...,wn}
,预测此样本属于类
c
的概率? 如果
p(c1|x)>p(c2|x) ,则此样本应该归为类 c1 ,反之归为类 c2 。
在公式(1)中,给定一个具体的样本, p(x) 是固定的值,与类别无关。 p(c) 可以很容易得到,关键是条件概率 p(x|c) 的求解?
如何求解条件概率 p(x|c) ?
在朴素贝叶斯中做了如下假设:
p(x|c)=p(w1|c)p(w2|c)...p(wn|c)
上述假设即为 条件独立假设,这个假设正是朴素贝叶斯分类器中 朴素(naive)一词的含义。也可 属性条件独立假设:对已知类别,假设所有属性相互独立。换言之,假设每个属性独立地对分类结果发生影响。
垃圾邮件过滤
from numpy import *
from email import feedparser
def loadDataSet():
"""
@function: 加载训练集
"""
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
def createVocabList(dataSet):
"""
@function: 创建词表
"""
vocabSet = set([]) #create empty set
for document in dataSet:
# 求并集
vocabSet = vocabSet | set(document) #union of the two sets
return list(vocabSet)
def setOfWords2Vec(vocabList, inputSet):
"""
@function: 输出文档向量,词集模型(sef-of-words model)
"""
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
def trainNB0(trainMatrix,trainCategory):
"""
@function: 朴素贝叶斯分类器训练函数
:params:trainMatrix: 文档矩阵
:params:trainCategory: 文档分类
"""
numTrainDocs = len(trainMatrix)
numWords = len(trainMatrix[0])
pAbusive = sum(trainCategory)/float(numTrainDocs) #表示为侮辱性文字的概率
p0Num = ones(numWords); p1Num = ones(numWords) #change to ones()
p0Denom = 2.0; p1Denom = 2.0 #change to 2.0
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(),表示为侮辱性文字的情况下,每个词出现的概率
p0Vect = log(p0Num/p0Denom) #change to log()
return p0Vect,p1Vect,pAbusive
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
"""
@function: 做出最后属于哪一类的判断
:params:vec2Classify: 需要分类的文档向量
:params:p0Vec: 在类 0 中,每个词的条件概率 p(wi|c0)
:params:p1Vec: 在类 1 中,每个词的条件概率 p(wi|c1)
:params:pClass1: 类 1 出现的概率
"""
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):
"""
@function: 文档词袋模型
"""
returnVec = [0]*len(vocabList)
for word in inputSet:
if word in vocabList:
returnVec[vocabList.index(word)] += 1
return returnVec
def testingNB():
"""
@function: 测试朴素贝叶斯算法
"""
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)
def textParse(bigString): #input is big string, #output is word list
"""
@function: 文本预处理函数
"""
import re
listOfTokens = re.split(r'\W*', bigString) #去除非单词字符
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('email/spam/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = textParse(open('email/ham/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = createVocabList(docList) #create vocabulary
trainingSet = range(50); testSet=[] #create test set
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: #train the classifier (get probs) trainNB0
trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses))
errorCount = 0
for docIndex in testSet: #classify the remaining items
#wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
wordVector = setOfWords2Vec(vocabList, docList[docIndex])
#if classifyNB(array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
if classifyNB(array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
errorCount += 1
print "classification error",docList[docIndex]
print 'the error rate is: ',float(errorCount)/len(testSet)