4.5 使用Python进行文本分类

REF：

《机器学习实战》

4.5.1 准备数据 ：从文本中构建词向量

程序清单4-1

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

执行结果：

>>> import bayes
>>> listOPosts, listClasses = bayes.loadDataSet()
>>> myVocabList = bayes.createVocabList(listOPosts)
>>> myVocabList
['cute', 'love', 'help', 'garbage', 'quit', 'I', 'problems', 'is', 'park', 'stop', 'flea', 'dalmation', 'licks', 'food', 'not', 'him', 'buying', 'posting', 'has', 'worthless', 'ate', 'to', 'maybe', 'please', 'dog', 'how', 'stupid', 'so', 'take', 'mr', 'steak', 'my']
>>> bayes.setOfWords2Vec(myVocabList, listOPosts[0])
[0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1]
>>> bayes.setOfWords2Vec(myVocabList, listOPosts[3])
[0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0]
>>>

4.5.2 训练算法：从词向量计算概率

-根据贝叶斯公式：

首先，通过类别 i 中文档数目除以总文档数来计算概率p(ci)。

然后，根据独立性假设把p(w|ci)展开为p(w0|ci)p(w1|ci)……p(wN|ci)

 程序清单4-2 朴素贝叶斯分类器训练函数

def trainNB0(trainMatrix,trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    p0Num = zeros(numWords); p1Num = zeros(numWords)
    p0Denom = 0.0; p1Denom = 0.0
    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 = p1Num/p1Denom
    p0Vect = p0Num/p0Denom
    return p0Vect,p1Vect,pAbusive

执行结果：

>>> from numpy import *
>>> reload(bayes)
<module 'bayes' from 'bayes.py'>
>>> listOPosts, listClasses = bayes.loadDataSet()
>>> myVocabList = bayes.createVocabList(listOPosts)
>>> trainMat = []
>>> for postinDoc in listOPosts:
...     trainMat.append(bayes.setOfWords2Vec( myVocabList, postinDoc  ) )
...
>>> p0V, p1V, pAb = bayes.trainNB0(trainMat,listClasses)
>>> pAb
0.5
>>> p0V
array([ 0.04166667,  0.04166667,  0.04166667,  0.        ,  0.        ,
        0.04166667,  0.04166667,  0.04166667,  0.        ,  0.04166667,
        0.04166667,  0.04166667,  0.04166667,  0.        ,  0.        ,
        0.08333333,  0.        ,  0.        ,  0.04166667,  0.        ,
        0.04166667,  0.04166667,  0.        ,  0.04166667,  0.04166667,
        0.04166667,  0.        ,  0.04166667,  0.        ,  0.04166667,
        0.04166667,  0.125     ])
>>> p1V
array([ 0.        ,  0.        ,  0.        ,  0.05263158,  0.05263158,
        0.        ,  0.        ,  0.        ,  0.05263158,  0.05263158,
        0.        ,  0.        ,  0.        ,  0.05263158,  0.05263158,
        0.05263158,  0.05263158,  0.05263158,  0.        ,  0.10526316,
        0.        ,  0.05263158,  0.05263158,  0.        ,  0.10526316,
        0.        ,  0.15789474,  0.        ,  0.05263158,  0.        ,
        0.        ,  0.        ])
>>>

　　

逐步执行结果：

>>> trainMatrix = trainMat
>>> trainCategory = listClasses
>>> numTrainDocs = len(trainMatrix)
>>> numTrainDocs
6
>>> numWords = len(trainMatrix[0])
>>> numWords
32
>>> trainMatrix
[[0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1], [0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 0, 0, 0], [1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1], [0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1], [0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0]]
>>> trainCategory
[0, 1, 0, 1, 0, 1]
>>> sum(trainCategory)
3
>>> float(numTrainDocs)
6.0
>>> pAbusive = sum(trainCategory)/float(numTrainDocs)
>>> pAbusive
0.5
>>> p0Num = zeros(numWords)
>>> p1Num = zeros(numWords)
>>> p0Denom = 0.0; p1Denom = 0.0
>>> i = 1
>>> p0Num += trainMatrix[i]
>>> p0Num
array([ 0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,
        0.,  1.,  1.,  0.,  0.,  0.,  0.,  0.,  1.,  1.,  0.,  1.,  0.,
        1.,  0.,  1.,  0.,  0.,  0.])
>>> p0Denom += sum(trainMatrix[i])
>>> p0Denom
8.0
>>> p1Vect = p1Num/p1Denom
__main__:1: RuntimeWarning: invalid value encountered in divide
>>> p1Vect
array([ nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,
        nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,
        nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan])
>>> p0Vect = p0Num/p0Denom
>>> p0Vect
array([ 0.   ,  0.   ,  0.   ,  0.   ,  0.   ,  0.   ,  0.   ,  0.   ,
        0.125,  0.   ,  0.   ,  0.   ,  0.   ,  0.   ,  0.125,  0.125,
        0.   ,  0.   ,  0.   ,  0.   ,  0.   ,  0.125,  0.125,  0.   ,
        0.125,  0.   ,  0.125,  0.   ,  0.125,  0.   ,  0.   ,  0.   ])
>>>

　　

4.5.3 测试算法：根据现实情况修改分类器

-

 程序清单4-2 朴素贝叶斯分类器训练函数(修改)

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

程序清单4-3 朴素贝叶斯分类函数

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 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)

执行结果：

>>> reload(bayes)
<module 'bayes' from 'bayes.pyc'>
>>> bayes.testingNB()
['love', 'my', 'dalmation'] classified as:  0
['stupid', 'garbage'] classified as:  1
>>>

逐步执行结果：

>>> from numpy import *
>>> listOPosts,listClasses = bayes.loadDataSet()
>>> myVocabList = bayes.createVocabList(listOPosts)
>>> listOPosts
[['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']]
>>> listClasses
[0, 1, 0, 1, 0, 1]
>>> myVocabList = bayes.createVocabList(listOPosts)
>>> myVocabList
['cute', 'love', 'help', 'garbage', 'quit', 'I', 'problems', 'is', 'park', 'stop', 'flea', 'dalmation', 'licks', 'food', 'not', 'him', 'buying', 'posting', 'has', 'worthless', 'ate', 'to', 'maybe', 'please', 'dog', 'how', 'stupid', 'so', 'take', 'mr', 'steak', 'my']
>>> trainMat=[]
>>> for postinDoc in listOPosts:
...     trainMat.append(bayes.setOfWords2Vec(myVocabList, postinDoc))
...
>>> trainMat
[[0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1], [0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 0, 0, 0], [1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1], [0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1], [0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0]]
>>> p0V,p1V,pAb = bayes.trainNB0(array(trainMat),array(listClasses))
>>> testEntry = ['love', 'my', 'dalmation']
>>> thisDoc = array(bayes.setOfWords2Vec(myVocabList, testEntry))
>>> thisDoc
array([0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 1])
>>> print testEntry,'classified as: ',bayes.classifyNB(thisDoc,p0V,p1V,pAb)
['love', 'my', 'dalmation'] classified as:  0
>>>

4.5.4 准备词袋模型

-如果将每一个词是否出现作为一个特征，叫做词集模型。但是若词在文档中出现不止一次，可以用词袋模型。

程序清单4-4 朴素贝叶斯词袋模型

def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1
    return returnVec