机器学习实战—朴素贝叶斯—代码修改（亲测可用）

问题背景

最近在学习机器学习实战这本书，这本书的讲解生动切合实际，我认为是一本非常不错的书。但年头毕竟长了，部分代码无法运行也是可以理解的，所以我通过调试将其修改为能跑出结果的代码

具体问题

1. RSS源地址无法访问
2. 部分语法为python2语法
3. 代码逻辑有bug
4. 只有对于英文的内容解析而没有中文的（我调用了jieba库来解决这个问题）
5. 其它暂不列举

代码

bayes.py

'''
Created on Oct 19, 2010

@author: Peter
'''
from numpy import *

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 is abusive, 0 not
    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)

def setOfWords2Vec(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] = 1
    return returnVec

def trainNB0(trainMatrix,trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    p0Num = ones(numWords); p1Num = 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 = log(p1Num/p1Denom)          #change to log()
    p0Vect = log(p0Num/p0Denom)          #change to log()
    return p0Vect,p1Vect,pAbusive

def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)    #element-wise mult
    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
    return returnVec

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))

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

def textParse1(bigString):    #input is big string, #output is word list
    import jieba
    listOfTokens = jieba.lcut(bigString)
    list = [tok for tok in listOfTokens if u'一' <= tok[0] <= u'龥']
    return list

def spamTest():
    docList=[]; classList = []; fullText =[]
    for i in range(1,26):
        str1 = open('email/spam/%d.txt' % i,encoding='Shift_JIS').read()
        wordList = textParse(str1)
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
        str2 = open('email/ham/%d.txt' % i,encoding='Shift_JIS').read()
        wordList = textParse(str2)
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = createVocabList(docList)#create vocabulary
    trainingSet = list(range(50)); testSet=[]           #create test set
    for i in range(10):
        randIndex = int(random.uniform(0,len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])  
    trainMat=[]; trainClasses = []
    for docIndex in trainingSet:#train the classifier (get probs) trainNB0
        trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses))
    errorCount = 0
    for docIndex in testSet:        #classify the remaining items
        wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
        if classifyNB(array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
            errorCount += 1
            print ("classification error",docList[docIndex])
    print ('the error rate is: ',float(errorCount)/len(testSet))
    #return vocabList,fullText

def calcMostFreq(vocabList,fullText):
    import operator
    freqDict = {}
    for token in vocabList:
        freqDict[token]=fullText.count(token)
    sortedFreq = sorted(freqDict.items(), key=operator.itemgetter(1), reverse=True)
    return sortedFreq[:30]       

def localWords(feed1,feed0):
    import feedparser
    docList=[]; classList = []; fullText =[]
    minLen = min(len(feed1['entries']),len(feed0['entries']))
    for i in range(minLen):
        wordList = textParse1(feed1['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1) #NY is class 1
        wordList = textParse1(feed0['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = createVocabList(docList)#create vocabulary
    top30Words = calcMostFreq(vocabList,fullText)   #remove top 30 words
    for pairW in top30Words:
        if pairW[0] in vocabList: vocabList.remove(pairW[0])
    trainingSet = list(range(2*minLen)); testSet=[]           #create test set
    for i in range(20):
        randIndex = int(random.uniform(0,len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])  
    trainMat=[]; trainClasses = []
    for docIndex in testSet:#train the classifier (get probs) trainNB0
        trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses))
    errorCount = 0
    for docIndex in testSet:        #classify the remaining items
        wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
        if classifyNB(array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
            errorCount += 1
    print ('the error rate is: ',float(errorCount)/len(testSet))
    return vocabList,p0V,p1V

def getTopWords(ny,sf):
    import operator
    vocabList,p0V,p1V=localWords(ny,sf)
    topNY=[]; topSF=[]
    for i in range(len(p0V)):
        if p0V[i] > -6.0 : topSF.append((vocabList[i],p0V[i]))
        if p1V[i] > -6.0 : topNY.append((vocabList[i],p1V[i]))
    sortedSF = sorted(topSF, key=lambda pair: pair[1], reverse=True)
    print ("SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**")
    for item in sortedSF:
        print (item[0])
    sortedNY = sorted(topNY, key=lambda pair: pair[1], reverse=True)
    print ("NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**")
    for item in sortedNY:
        print (item[0])

test.py(个人测试代码)

# Author : hang
# @TIme  : 2021-11-20 19:51
# @File  : test.py

import machinelearninginaction.Ch04.bayes as bayes
# listOPosts,listClasses=bayes.loadDataSet()
# myVocabList = bayes.createVocabList(listOPosts)
# # bayes.setOfWords2Vec(myVocabList,listOPosts[0])
# trainMat = []
# for postinDoc in listOPosts:
#     trainMat.append((bayes.setOfWords2Vec(myVocabList,postinDoc)))
# p0V,p1V,pAb = bayes.trainNB0(trainMat,listClasses)
# print(p0V,p1V,pAb)
# bayes.testingNB()
# bayes.spamTest()
import feedparser
ny=feedparser.parse('http://blog.sina.com.cn/rss/cng.xml')
sf=feedparser.parse('http://rss.yule.sohu.com/rss/yuletoutiao.xml')
# bayes.getTopWords(ny,nf)
a,b,c = bayes.localWords(ny,sf)