Python 朴素贝叶斯分类器

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']]
    # 给出6个文本list
    classVec = [0,1,0,1,0,1] # 人为给出标签  1 有侮辱性文字 0 正常
    return postingList, classVec

def creatVocabList(dataSet):
    VocabSet = set([]) # 创建一个空list，并使用set的数据类型，保证字典中无重复
    for word in dataSet:
        VocabSet = VocabSet | set(word) # 操作符‘|’表示两个集合的并集
    return list(VocabSet)  # 返回list的数据类型

def setOfWords2Vec(vocabList, inputSet):   #词集模型
        # input为输入要对比的样本 比如postingList[0]
    returnVec = [0]*len(vocabList) # 创建所有为0的向量
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] = 1  #vocabList.index(word) 为word在vocabList中的索引值 如果在vocabList中有这个单词，相应位置设为1
        else:
            print("the word %s is not in VocabList" % word)
    return returnVec
# 输出文档向量，向量的元素为0或者1，分别表示字典中的单词在输入文档中是否没出现还是出现。

# 训练算法：计算概率
from numpy import *
def trainNB(trainMatrix, trainLabel): # 输入训练数据矩阵 和 训练标签
    numTrainDocs = len(trainMatrix) # 训练样本个数
    numWords = len(trainMatrix[0]) # 字典的长度 相当于属性个数
    pAbusive = sum(trainLabel)/float(numTrainDocs ) # P(Vj) V={1,0} 含有侮辱性文档的概率，由于是二分类，另外一个 可以用1减去即可。
    p0Num = ones(numWords) # 第0类文档中每个词条出现的总数量
    p1Num = ones(numWords) 
    p0Denom = 2.0    # 第0类文档所有词条的数量
    p1Denom = 2.0
    for i in range(numTrainDocs):  # 遍历所有的文档 对每篇训练文档：
        if (trainLabel[i] == 1):  # 对每个类别
            p1Num += trainMatrix[i]   # 增加该词条的计算值
            p1Denom += sum(trainMatrix[i])  # 增加所有词条的计数值
        else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
    p1Vect = log(p1Num/p1Denom) # 对每个类别，对每个词条，计算条件概率
    p0Vect = log(p0Num/p0Denom)  # 对每个元素除以该类别中的总词数，（用一个数组除以浮点数即可实现）
    return p0Vect,p1Vect,pAbusive # 返回两个向量 一个概率

'''
data, label = loadDataSet()
vocab = creatVocabList(data)
#print(vocab)
trainMat = []
for i in data:
    trainMat.append(setOfWords2Vec(vocab, i))
p0v, p1v, pAb = trainNB(trainMat, label)
#print(p0v)
#print(p1v)
#print(pAb)
'''

#测试算法 : 朴素贝叶斯分类器
# p(v_j)*(多个P(ai|vj)相乘)
def classifyNB(Vect2classify, p0Vec, p1Vec, pAb):  #  朴素贝叶斯分类器
    # 输入Vect2classify 为要分类的文档,已经变为向量形式
    p1 = sum(Vect2classify*p1Vec) + log(pAb) # log(ab)=log(a)+log(b)
    p0 = sum(Vect2classify*p0Vec) + log(1-pAb)  # 计算V_NB 括号里面的想成为对应元素相乘
    if p1>p0:  # 分类
        return 1
    else:
        return 0
def testingNB():    
    data, label = loadDataSet()
    Vocab = creatVocabList(data)
    trainMat = []
    for i in data:
        trainMat.append(setOfWords2Vec(Vocab, i))
    p0Vec, p1Vec, pAb = trainNB(trainMat, label)
    test1 = ['love','my','dalmation']
    test2 = ['stupid','garbage','love','dog']
    testDoc1 = array(setOfWords2Vec(Vocab, test1)) # 为什么要用array数组？？ 注（a）
    testDoc2 = array(setOfWords2Vec(Vocab, test2))
    print(test1,'classified as: ', classifyNB(testDoc1, p0Vec, p1Vec, pAb))
    print(test2,'classified as: ', classifyNB(testDoc2, p0Vec, p1Vec, pAb))

testingNB()

 

 

from numpy import *
def creatVocabList(dataSet):

def bagOfWords2Vec(vocabList, inputSet): 

def trainNB(): # 上面已经解读

def classifyNB():

def textSeg(emailText):

def spamTest():    # 垃圾邮件测试
    DocList = []   # 
    labelList = []  # 标签list
    FullList = []   # 
    for i in range(1, 26): # 每个文件夹下25个txt文件
        emailText = open('email/spam/%d.txt' % i).read()
        wordList = textSeg(emailText)
        DocList.append(wordList) # append extend 区别，决策树里面有详细讲解
        FullList.extend(wordList)
        labelList.append(1)  # 人为标记
        emailText = open('email/ham/%d.txt' % i).read()
        wordList = textSeg(emailText)
        DocList.append(wordList) # append extend 区别，决策树里面有详细讲解
        FullList.extend(wordList)
        labelList.append(0)  # 人为标记
    Vocab = creatVocabList(DocList) # 创建字典
    # 随机抽取训练测试样本，总共50个样本 选取10个测试
    traingSetIndex = list(range(50)) 
    testSetIndex = [] 
    for i in range(10):
        index = int(random.uniform(0,50)) # 随机生成0-50的数
        testSetIndex.append(traingSetIndex[index]) # 选出来的放入 testSetIndex
        del(traingSetIndex[index]) # 还要删除traingSetIndex相应的位置索引
    trainMat = []
    trainLabel = []
    for i in traingSetIndex:
        trainMat.append(bagOfWords2Vec(Vocab, DocList[i]))
        trainLabel.append(labelList[i])
    p0Vec, p1Vec, pAb = trainNB(trainMat, trainLabel)
    errorcount = 0
    for i in testSetIndex: # 测试
        test = bagOfWords2Vec(Vocab, DocList(i))
        if classifyNB(test, p0Vec, p1Vec, pAb) != labelList[i]:
            errorcount += 1
    print('the error is: ', float(errorcount)/len(testSetIndex))       

From：贝叶斯学习 -- matlab、python代码分析（4）