朴素贝叶斯算法学习笔记（一）

#coding=utf-8
from numpy import *
'''
准备数据：从文本中构建词向量
'''
#数据集的读取
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
#处理为不重复的列表
def createVocabList(dataSet):
    vocabSet=set([])
    for document in dataSet:
        vocabSet=vocabSet|set(document)#并集
    return list(vocabSet)
#
'''
vocabList:词汇表
inputSet:文档
返回文档向量
'''
def setOfWords2Vec(vocabList,inputSet):
    returnVec=[0]*len(vocabList)
    for word in inputSet:#如果文档中出现了这个单词，则将向量置为1
        if word in vocabList:
            returnVec[vocabList.index(word)]=1
        else:
            print "the word:%s is not in my Vocabulary!"
    return returnVec

listOposts,listClasses=loadDataSet()
print len(listOposts)
myVocabList=createVocabList(listOposts)
print myVocabList

print  setOfWords2Vec(myVocabList,listOposts[3])
'''
训练算法：从词向量计算概率
trainMatrix:文档矩阵
trainCategory:每篇文档构成的标签向量
'''
def trainNB0(trainMatrix,trainCategory):
    numTrainDocs=len(trainMatrix)#计算文档数目
    numWords=len(trainMatrix[0])#计算文档总词条数
    pAbusive=sum(trainCategory)/float(numTrainDocs)#计算侮辱性文档概率
    p0Num=ones(numWords)#初始化正常文章矩阵
    p1Num=ones(numWords)#初始化侮辱性文章矩阵
    p0Denom=2.0#初始化正常词条数
    p1Denom=2.0#初始化非正常词条数
    for i in range(numTrainDocs):
        if trainCategory[i] == 1:#如果是侮辱性文档
            p1Num += trainMatrix[i]#矩阵相加统计侮辱词条
            p1Denom += sum(trainMatrix[i])#统计侮辱词条总数目
        else:#如果是正常文档
            p0Num += trainMatrix[i]#矩阵相加统计正常词条
            p0Denom += sum(trainMatrix[i])#统计正常词条总数目
    p1Vect=p1Num/p1Denom
    p0Vect=p0Num/p0Denom
    return p0Vect,p1Vect,pAbusive
trainMat=[]
for postinDoc in listOposts:
    trainMat.append(setOfWords2Vec(myVocabList,postinDoc))
# print trainMat
# p0V,p1V,pAb=trainNB0(trainMat,listClasses)
# print p0V
# print  p1V
# print pAb
'''
测试算法：根据现实情况修改分类器
'''
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,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)
testingNB()

['cute', 'love', 'help', 'garbage', 'quit', 'I', 'problems', 'is', 'park', 'stop', 'flea', 'dalmation', 'licks', 'food', 'not', 'him', 'buying', 'posting', 'has', 'worthless', 'ate', 'to', 'maybe', 'please', 'dog', 'how', 'stupid', 'so', 'take', 'mr', 'steak', 'my']
[0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0]
['love', 'my', 'dalmation'] classified as: 0
['stupid', 'garbage'] classified as: 1