基于概率论的分类方法：朴素贝叶斯

一、朴素贝叶斯的前提

特征独立且同等重要

二、

import numpy as np
import os
path = os.getcwd()
#%%
'''
准备数据：从文本中构建向量
'''
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]                  # 1 代表侮辱性文字 ，0 代表正常言论 
    return postingList,classVec

def createVocabList(dataSet):
    vocabSet = set([])                        # create empty set
    for document in dataSet:
        vocabSet = vocabSet | set(document)   # union of the two sets
    return list(vocabSet)
 
'''
将每个词的出现与否作为一个特征。             词集模型（set-of-words model)
'''    
def setOfWords2Vec(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] = 1
        else: print ("the word: %s is not in my Vocabulary!" % word)
    return returnVec
 
'''
如果一个词在文档中出现不止一次，这可能意味着包含该词是否出现在文档中所不能表达的
某种信息。                                  词袋模型（bag-of-words model)
'''
def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1
    return returnVec


#%%
'''
训练算法：从词向量计算概率
'''
def trainNB0(trainMatrix,trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    p0Num = np.ones(numWords); p1Num = np.ones(numWords)      #change to ones() 
    p0Denom = 2.0; p1Denom = 2.0                              #change to 2.0
    for i in range(numTrainDocs):
        if trainCategory[i] == 1:
            p1Num += trainMatrix[i]
            p1Denom += sum(trainMatrix[i])
        else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
    p1Vect = np.log(p1Num/p1Denom)          #change to log()
    p0Vect = np.log(p0Num/p0Denom)          #change to log()
    return p0Vect,p1Vect,pAbusive


#%%
'''
预测算法：根据现实情况修改分类器
'''
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + np.log(pClass1)          #element-wise mult
    p0 = sum(vec2Classify * p0Vec) + np.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(np.array(trainMat),np.array(listClasses))
    testEntry = ['love', 'my', 'dalmation']
    thisDoc = np.array(setOfWords2Vec(myVocabList, testEntry))
    print (testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))
    testEntry = ['stupid', 'garbage']
    thisDoc = np.array(setOfWords2Vec(myVocabList, testEntry))
    print (testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))


testingNB()




#%%
'''
实例：使用贝叶斯过滤垃圾邮件
'''

def textParse(bigString):    #input is big string, #output is word list
    import re
    regEX = re.compile(r'\W')
    listOfTokens = regEX.split(bigString)
    return [tok.lower() for tok in listOfTokens if len(tok) > 2] 


def spamTest():
    docList=[]; classList = []; fullText =[]
    for i in range(1,26):
        wordList = textParse(open('email/spam/%d.txt' % i, "rb").read().decode('GBK','ignore') )
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
        wordList = textParse(open('email/ham/%d.txt' % i,  "rb").read().decode('GBK','ignore') )
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
        
    vocabList = createVocabList(docList)                         #创建词汇表
    
    trainingSet = list(range(50)); testSet=[]                    #创建测试集
    for i in range(10):
        randIndex = int(np.random.uniform(0,len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])  
    
    #分类器训练函数    
    trainMat=[]; trainClasses = []
    for docIndex in trainingSet:                
        trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V,p1V,pSpam = trainNB0(np.array(trainMat),np.array(trainClasses))
    
    
    errorCount = 0
    for docIndex in testSet:        #classify the remaining items
        wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
        if classifyNB(np.array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
            errorCount += 1
            print ("classification error",docList[docIndex])
    print ('the error rate is: ',float(errorCount)/len(testSet))

spamTest()