机器学习实战第四章--朴素贝叶斯

工作原理

提取所有文档中的词条并进行去重
获取文档的所有类别
计算每个类别中的文档数目
对每篇训练文档: 
    对每个类别: 
        如果词条出现在文档中-->增加该词条的计数值（for循环或者矩阵相加）
        增加所有词条的计数值（此类别下词条总数）
对每个类别: 
    对每个词条: 
        将该词条的数目除以总词条数目得到的条件概率（P(词条|类别)）
返回该文档属于每个类别的条件概率（P(类别|文档的所有词条)）

算法特点

优点: 在数据较少的情况下仍然有效，可以处理多类别问题。
缺点: 对于输入数据的准备方式较为敏感。
适用数据类型: 标称型数据。

开发流程

收集数据: 可以使用任何方法。
准备数据: 需要数值型或者布尔型数据。
分析数据: 有大量特征时，绘制特征作用不大，此时使用直方图效果更好。
训练算法: 计算不同的独立特征的条件概率。
测试算法: 计算错误率。
使用算法: 一个常见的朴素贝叶斯应用是文档分类。可以在任意的分类场景中使用朴素贝叶斯分类器，不一定非要是文本。

项目案例1: 屏蔽社区留言板的侮辱性言论

import numpy as np
# 载入数据
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
# 创建词向量表
def createVocabList(dataSet):
    vocabSet = set([])  #create empty set
    for document in dataSet:
        vocabSet = vocabSet | set(document) #union of the two sets
    return list(vocabSet)
# 将输入转化词向量
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
朴素贝叶斯分类函数（计算每个的词对应的概率）
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 np.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 np.log()
    p0Vect = np.log(p0Num/p0Denom)          #change to np.log()
    return p0Vect, p1Vect, pAbusive
# 朴素贝叶斯分类器
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
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
#便利函数，进行实例测试
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))

项目案例2: 使用朴素贝叶斯过滤垃圾邮件

# 文本切割
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]
# 垃圾邮件测试函数
def spamTest():
    docList = []; classList = []; fullText = []
    for i in range(1, 26):
        wordList = textParse((open('G:/python/machinelearninginaction/Ch04/email/spam/%d.txt' % i,
                 encoding='ISO-8859-1').read()))
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
        wordList = textParse((open('G:/python/machinelearninginaction/Ch04/email/ham/%d.txt' % i,
                 encoding='ISO-8859-1').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(np.random.uniform(0, len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(list(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(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))
    #return vocabList, fullText
# 计算高频词（多是无效辅助词，后续移除）
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]

项目案例3: 使用朴素贝叶斯分类器从个人广告中获取区域倾向

# rss源分类器
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(np.random.uniform(0, len(trainingSet)))
       testSet.append(trainingSet[randIndex])
       del (list(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(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('the error rate is: ', float(errorCount) / len(testSet))
   return vocabList, p0V, p1V
# 最具表征的词汇显示函数
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])

scikit-learn实例

from sklearn.naive_bayes import GaussianNB
clf = GaussianNB()
clf.fit(X_train, y_train)
GaussianNB(priors=None, var_smoothing=1e-09)
clf.score(X_test, y_test)
#1.0
#4.4, 3.2, 1.3, 0.2
clf.predict([[4.4, 3.2, 1.3, 0.2]])
#array([0.])
from sklearn.naive_bayes import BernoulliNB, MultinomialNB