朴素贝叶斯分类
#coding=utf-8
'''
Created on 2016年1月9日
@author: admin
'''
from numpy import *
# 加载数据集函数
def loadDataSet():
# 定义邮件列表
postingList = [['my','dog','has','flea',\
'problem','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']]
# 定义标签向量,1——abusive,0——not abusive
classVec = [0,1,0,1,0,1]
return postingList,classVec
# 创建词汇列表
def createVocabList(dataSet):
# 定义词汇集
vocabSet = set([])
# 遍历文档
for document in dataSet:
# 将每个document合并到vocabSet,|用来联合两个集合
vocabSet = vocabSet | set(document)
# 返回词汇集
return list(vocabSet)
# 把单词转换成向量
def setOfWords2Vec(vocabList,inputSet):
# 定义要返回的向量
returnVec = [0] * len(vocabList)
# 遍历输出集中的单词
for word in inputSet:
# 单词在词汇集中
if word in vocabList:
# 对应的位置设为1
returnVec[vocabList.index(word)] = 1
else:
print "the word: %s is not in my Vocabulary!" % word
# 返回向量
return returnVec
# 把单词转换成向量,用词袋模型,计算词出现的次数
def bagOfWords2VecMN(vocabList,inputSet):
# 定义要返回的向量
returnVec = [0] * len(vocabList)
# 遍历输出集中的单词
for word in inputSet:
# 单词在词汇集中
if word in vocabList:
# 对应的词出现次数 加1
returnVec[vocabList.index(word)] += 1
# 返回向量
return returnVec
# 条件概率的计算
def trainNB0(trainMatrix,trainCategory):
# 计算文档的数目
numTrainDocs = len(trainMatrix)
# 计算单词的数目
numWords = len(trainMatrix[0])
# 计算类别的概率,abusive为1,not abusive为0
pAbusive =sum(trainCategory) / float(numTrainDocs)
# 初始化计数器,1行numWords列,p0是not abusive
# p0Num =zeros(numWords)
p0Num = ones(numWords)
# 初始化计数器,p1是abusive
p1Num = ones(numWords)
# 初始化分母
p0Denom = 2.0
p1Denom = 2.0
# 遍历文档
for i in range(numTrainDocs):
# 计算abusive对应的词汇的数目,trainMatrix为0-1值形成的向量
if trainCategory[i] == 1:
# p1Num存储的是每个词出现的次数
p1Num += trainMatrix[i]
# p1Denom存储的是词的总数目
p1Denom += sum(trainMatrix[i])
# 计算not abusive词汇的数目
else:
# 每个词在not abusive下出现的次数
p0Num += trainMatrix[i]
# not abusive下的总词数
p0Denom += sum(trainMatrix[i])
# 计算abusive下每个词出现的概率
# p1Vect = p1Num / p1Denom
p1Vect = log(p1Num / p1Denom)
# 计算not abusive下每个词出现的概率
# p0Vect = p0Num / p0Denom
p0Vect = log(p0Num / p0Denom)
# 返回词出现的概率和文档为abusive的概率,not abusive的概率为1-pAbusive
return p0Vect,p1Vect,pAbusive
def classifyNB(vec2Classify,p0Vec,p1Vec,pClass1):
# 计算abusive的概率
p1 = sum(vec2Classify * p1Vec) + log(pClass1)
# 计算not abusive的概率
p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
# 根据概率大小判断属于哪个类
if p1 > p0:
return 1
else:
return 0
# 测试
def testingNB():
# 加载数据集
listOPosts,listClass = loadDataSet()
# 创建词汇列表
myVocabList = createVocabList(listOPosts)
trainMat = []
for postinDoc in listOPosts:
trainMat.append(setOfWords2Vec(myVocabList,postinDoc))
p0V,p1V,pAb = trainNB0(array(trainMat),array(listClass))
# print p0V,p1V,pAb
# print trainMat
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)
# 文本解析
# 输入是字符串,输出是单词列表
def textParse(bigString):
# 导入正则表达式的包
import re
# 用正则表达式分割字符串
listOfTokens = re.split(r'\W*', bigString)
# 返回小写单词列表
return [tok.lower() for tok in listOfTokens if len(tok) > 2]
# 垃圾邮件测试
def spamTest():
# 定义docList文档列表,classList类别列表,fullText所有文档词汇
docList=[]; classList = []; fullText =[]
# 遍历email/spam和email/ham下的txt文件
for i in range(1,26):
# 定义并读取垃圾邮件文件的词汇分割列表
wordList = textParse(open('email/spam/%d.txt' % i).read())
# 将词汇列表加到文档列表中
docList.append(wordList)
# 将所有词汇列表汇总到fullText中
fullText.extend(wordList)
# 文档类别为1,spam
classList.append(1)
# 读取非垃圾邮件的文档
wordList = textParse(open('email/ham/%d.txt' % i).read())
# 添加到文档列表中
docList.append(wordList)
# 添加到所有词汇列表中
fullText.extend(wordList)
# 类别为0,非垃圾邮件
classList.append(0)
# 创建词汇列表
vocabList = createVocabList(docList)
# 定义训练集的索引和测试集
trainingSet = range(50); testSet=[]
# 随机的选择10个作为测试集
for i in range(10):
# 随机索引
randIndex = int(random.uniform(0,len(trainingSet)))
# 将随机选择的文档加入到测试集中
testSet.append(trainingSet[randIndex])
# 从训练集中删除随机选择的文档
del(trainingSet[randIndex])
# 定义训练集的矩阵和类别
trainMat=[]; trainClasses = []
# 遍历训练集,求得先验概率和条件概率
for docIndex in trainingSet:
# 将词汇列表变为向量放到trainMat中
trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
# 训练集的类别标签
trainClasses.append(classList[docIndex])
# 计算先验概率,条件概率
p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses))
# 定义错误计数
errorCount = 0
# 对测试集进行分类
for docIndex in testSet:
# 将测试集词汇向量化
wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
# 对测试数据进行分类
if classifyNB(array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
# 分类不正确,错误计数加1
errorCount += 1
print "classification error",docList[docIndex]
# 输出错误率
print 'the error rate is: ',float(errorCount)/len(testSet)