利用Python实现朴素贝叶斯文本分类

Python是一种面向对象、解释型计算机程序设计语，作者是Guido van Rossum（吉多·范罗苏姆），1991年公开正式发行。粗糙进行归纳：

（1）Python是纯粹自由软件，源代码和解释器CPython遵循 GPL协议

（2）Python语法简洁清晰

（3）Python具有丰富和强大的库（^_^胶水语言^_^）         

        NumPy系统是Python的一种开源的数值计算扩展，一个用python实现的科学计算包。这种工具可用来存储和处理大型矩阵。

（1）下载对应Python版本的NumPy（请用Ctrl+F查找numpy）

http://www.lfd.uci.edu/~gohlke/pythonlibs/#numpy        

（2）将.whl改为.rar

   

（3）将.rar中的内容全部Copy到Python安装目录下的.\Lib\site-packages之下。例如：

               D:\Program Files\python\Lib\site-packages

Until to here, we can use it. Ok, Let's see an example about Naive Bayesian Network and itsAlgorithm.

1）Naive Bayesian Network

2）Naive Bayesian Algorithm

 

3）I will give some net-source to you

        http://scikit-learn.org/stable/modules/naive_bayes.html

         http://www.saedsayad.com/naive_bayesian.htm

            http://www.saedsayad.com/naive_bayesian_exercise.htm

            http://www.saedsayad.com/flash/Bayesian.html

   Step  to here, we already have prepared Programming Language, Tool of NumPy, Naive Bayesian Network and Algorithm. So, let's implement Naive Baysian Classifier by this Language & Tool &Theory.Fellow is Code-Programming, ^_^let's see it now.

1）Some Code of Python-Self-Methods about Naive Bayesian and save it as bayes.py.

'''

Created on Oct 19, 2010

@author: Peter

'''

#导入numpy（一种开源的数值计算扩展，可用来存储和处理大型矩阵）

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

        else: print (("the word: %s is not in my Vocabulary!" % word))

    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)

    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).read())

        docList.append(wordList)

        fullText.extend(wordList)

        classList.append(1)

        wordList = textParse(open('email/ham/%d.txt' % i).read())

        docList.append(wordList)

        fullText.extend(wordList)

        classList.append(0)

    vocabList = createVocabList(docList)#create vocabulary

    trainingSet = 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.iteritems(), 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 = textParse(feed1[ 'entries' ][ i ][ 'summary' ])

        docList.append(wordList)

        fullText.extend(wordList)

        classList.append(1) #NY is class 1

        wordList = textParse(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 = 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 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 ( '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 ])

2）In order to instruction how to use methods Up, I gives an example which used to check words-list and Detail as fellowing.

     import bayes

        ListOPosts, ListClasses = bayes.loadDataSet()

        myVocabList = bayes.createVocabList(ListOPosts)

        #Ok, Let's see the fianlly-result.^_^

        myVocabList

RUNNING RESULT AS FOLLOWING