朴素贝叶斯分类器 注释

试编程实现拉普拉斯修正的朴素贝叶斯分类器，并以西瓜数据集3.0为训练集，对P.151“测1”进行判别。

代码全是《机器学习》上的，只是将其整合到了一起，能够运行手写体识别。
内容大部分进行了注释，可能有些注释不够精准或者不容理解，见谅！

代码

from numpy import *

def loadDataSet(): #创建实验样本
    postingList=[['青绿','蜷缩','浊响','清晰','凹陷','硬滑',0.697,0.460],
                 ['乌黑','蜷缩','沉闷','清晰','凹陷','硬滑',0.774,0.376],
                 ['乌黑','蜷缩','浊响','清晰','凹陷','硬滑',0.634,0.264],
                 ['青绿','蜷缩','沉闷','清晰','凹陷','硬滑',0.608,0.318],
                 ['浅白','蜷缩','浊响','清晰','凹陷','硬滑',0.556,0.215],
                 ['青绿','稍蜷','浊响','清晰','稍凹','软粘',0.403,0.237],
                 ['乌黑','稍蜷','浊响','稍糊','稍凹','软粘',0.481,0.149],
                 ['乌黑','稍蜷','浊响','清晰','稍凹','硬滑',0.437,0.211],
                 ['乌黑','稍蜷','沉闷','稍糊','稍凹','硬滑',0.666,0.091],
                 ['青绿','硬挺','清脆','清晰','平坦','软粘',0.243,0.267],
                 ['浅白','硬挺','清脆','模糊','平坦','硬滑',0.245,0.057],
                 ['浅白','蜷缩','浊响','模糊','平坦','软粘',0.343,0.099],
                 ['青绿','稍蜷','浊响','稍糊','凹陷','硬滑',0.639,0.161],
                 ['浅白','稍蜷','沉闷','稍糊','凹陷','硬滑',0.657,0.198],
                 ['乌黑','稍蜷','浊响','清晰','稍凹','软粘',0.360,0.370],
                 ['浅白','蜷缩','浊响','模糊','平坦','硬滑',0.593,0.042],
                 ['青绿','蜷缩','沉闷','稍糊','稍凹','硬滑',0.719,0.103]]
    classVec = [1,1,1,1,1,1,1,1,0,0,0,0,0,0,0,0,0]    #1是好瓜，0不是好瓜
    return postingList,classVec

                 
def createVocabList(dataSet): #传入词条切分后的列表
    vocabSet = set([])  #用set（）创建空的集合
    for document in dataSet:
        vocabSet = vocabSet | set(document) #合并两个集合
    return list(vocabSet)

def setOfWords2Vec(vocabList, inputSet): #传入一个集合和被检测列表
    returnVec = [0]*len(vocabList) #初始化列表全为0
    for word in inputSet: #遍历被检测列表
        if word in vocabList: #检测被检测列表中是否有给定样本中的词汇
            returnVec[vocabList.index(word)] = 1 #将该词出现的第一个位置的特征值标记为1
        else: print( "the word: %s is not in my Vocabulary!" % word)
    return returnVec

def trainNB0(trainMatrix,trainCategory): #拉普斯修改后的朴素贝叶斯算法
    numTrainDocs = len(trainMatrix) 
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs) #计算坏瓜所占比例
    p0Num = ones(numWords); p1Num = ones(numWords) 
p0Denom = 2.0; p1Denom = 2.0                        
    for i in range(numTrainDocs):  #遍历每个文本
        if trainCategory[i] == 1:
            p1Num += trainMatrix[i]
            p1Denom += sum(trainMatrix[i])
        else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
    p1Vect = log(p1Num/p1Denom)  #计算每个属性被判为坏瓜属性的概率
    p0Vect = log(p0Num/p0Denom)   #基本同上，避免结果下溢
    return p0Vect,p1Vect,pAbusive

def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)    #属性在出现0/1情况*概率   再求和 + 类别对数概率
    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else: 
        return 0
    
def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1 #每个单词再集合中的出现次数
    return returnVec

def testingNB(canshu):
    listOPosts,listClasses = loadDataSet()  #取样
    myVocabList = createVocabList(listOPosts) #变为无重复集合
    trainMat=[]
    for postinDoc in listOPosts: #标记每个属性是否再大集合中出现
        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
    p0V,p1V,pAb = trainNB0(array(trainMat),array(listClasses))
    testEntry = canshu
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry)) #标记testEntry属性再集合中的出现
    print (testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))

if __name__=='__main__':
  canshu=list(input("请输入:").split()) #将结果输入
  testingNB(canshu)

运行结果