机器学习
朴素贝叶斯过滤垃圾邮件
#!/usr/bin/python
# -*- coding: utf-8 -*-
from numpy import *
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] # 标签
return postingList, classVec
def createVocabList(dataSet): # 返回词汇列表
vocabSet = set([]) # 创建空集
for document in dataSet:
vocabSet = vocabSet|set(document)
return list(vocabSet)
def setOfWords2Vec(vocabList, inputSet): # 输入:词汇表 输入文档
returnVec = [0]*len(vocabList) # *重复符(运算符)
for word in inputSet:
if word in vocabList:
returnVec[vocabList.index(word)] = 1 # index()函数
else:
print"the word %s is not in my Vocabulary!" %word
return returnVec
# 词袋模型
def bagOfWords2VecMN(vocabList, inputSet): # 输入:词汇表 输入文档
returnVec = [0]*len(vocabList)
for word in inputSet:
if word in vocabList:
returnVec[vocabList.index(word)] += 1
return returnVec
#训练函数:
def trainNB0(trainMatrix, trainCategory): # naive bayes 输入:训练文档矩阵 训练文档类别
numTrainDocs = len(trainMatrix)
numWords = len(trainMatrix[0])
pAbusive = sum(trainCategory)/float(numTrainDocs) # 计算p(Ci) pabusive:侮辱文档概率, 1-pabusive :正常文档概率
p0Num = ones(numWords); p1Num = ones(numWords) # 分别统计各类别单词出现的次数 change to ones()
p0Denom = 2.0; p1Denom = 2.0
for i in range(numTrainDocs):
if trainCategory[i] == 1:
p1Num += trainMatrix[i] # numpy.array的数组运算
p1Denom += sum(trainMatrix[i])
else:
p0Num += trainMatrix[i]
p0Denom += sum(trainMatrix[i])
p1Vect = log(p1Num/p1Denom) # 计算p(Wj | Ci) ; change to log(): 防止下溢出
p0Vect = log(p0Num/p0Denom)
return p0Vect,p1Vect,pAbusive
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1): # 输入:需分类的向量;P(Wj | C0)向量;P(Wj | C1)向量;P(C1)
p1 = sum(vec2Classify* p1Vec)+log(pClass1) # SUM(log(P(Wj|Ci))) + log(P(Ci))
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,pAb = trainNB0(array(trainMat),array(listClasses)) # 训练
testEntry = ['love', 'my', 'dalmation']
thisDoc = array(setOfWords2Vec(myVocabList, testEntry)) # 测试
print testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb)
testEntry = ['stupid', 'garbage']
thisDoc = array(setOfWords2Vec(myVocabList, testEntry)) # 测试
print testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb)
def textParse(bigString): # 输入字符串、返回所有单词列表
import re
listOfTokens = re.split(r'\W*', bigString) # 切割字符串
return [tok.lower() for tok in listOfTokens if len(tok) > 2] # 列表推导式:小写转化、过小单词滤除
def spamTest(): # 垃圾邮件交叉验证
docList = []; # 所有文档矩阵
classList = [] # 所有文档类别
#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) # 创建词汇表
trainingSet = range(50);
testSet = [] # 划分训练集与测试集
for i in range(10):
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat = []; # 训练文档矩阵
trainClasses = [] # 训练文档类别
for docIndex in trainingSet:
trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = trainNB0(array(trainMat), array(trainClasses)) # 训练
errorCount = 0
for docIndex in testSet: # 测试每个测试样本,记录错误判断
wordVector = bagOfWords2VecMN(vocabList, docList[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)
spamTest()
#testingNB()
#listOPosts,listClasses = loadDataSet()
#myVocabList = createVocabList(listOPosts)
#trainMat = []
#for postinDoc in listOPosts:
# trainMat.append(setOfWords2Vec(myVocabList,postinDoc))
#p0V,p1V,pAb = trainNB0(trainMat,listClasses)
pass