机器学习-朴素贝叶斯

一 开发环境：win7 64 位 + Pycharm5.0 + python3.4.4

二 工具包：numpy + matplotlib （对于microsoft visual c++ 10.0 is required错误，我是通过下载microsoft visual c++ 10.0解决的）

三 参考书籍：机器学习实战

朴素贝叶斯：

优点：在数据较小的情况下仍然有效，可以处理多类别问题

缺点：对于输入数据的准备方式比较敏感

使用数据类型：标称型数据

一般流程：

1）数据收集：可以使用任何方法；

2）准备数据：需要数值型或布尔型数据；

3）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；

4）训练数据：计算不同的独立特征的条件概率；

5）测试算法：计算错误率；

6）使用方法：常见用于文本分类。

四 程序清单：

1.准备数据阶段：

# 生成所有文本中出现的不重复词的列表，dataSet:词表向量def createVocabList(dataSet):   vocabSet = set([])   for document in dataSet:      vocabSet = vocabSet | set(document)   return list(vocabSet)

# 词集模式：将文档转换为文档向量，vocabList：文本单词列表；inputSet：待数字化的词向量def setOfwords2Vec(vocabList, inputSet):   returnVec = [0]*len(vocabList)  # 创建返回的文档向量   for word in vocabList:      if word in inputSet:  # 若word在inputSet中，将文档向量对应位置值设为1         returnVec[vocabList.index(word)] = 1   return returnVec# 词袋模式：将文档转换为文档向量，vocabList：文本单词列表；inputSet：待数字化的词向量def bagOfwords2Vec(vocabList, inputSet):   returnVec = [0]*len(vocabList)  # 创建返回的文档向量   for word in vocabList:      if word in inputSet:  # 若word在inputSet中，将文档向量对应位置值设为1         index = vocabList.index(word)         returnVec[index] += 1   return returnVec

2.训练数据阶段：

# 朴素贝叶斯分类器训练函数，trainMatrix：训练集合；trainCategory：分类列表def trainNB0(trainMatrix, trainCategory):   numTrainDocs = len(trainMatrix)   numWords = len(trainMatrix[0])   pAbusive = sum(trainCategory)/float(numTrainDocs)  # 计算trainCategory=1的概率   # 初始化概率向量   p0Num = ones(numWords)   p1Num = ones(numWords)   p0Denom = 2.0   p1Denom = 2.0   for i in range(numTrainDocs):      if trainCategory[i] == 1:  # trainCategory[i]类别为1，记录此时每个单词出现的次数和总的单词出现次数         p1Num += trainMatrix[i]         p1Denom += sum(trainMatrix[i])      else:         p0Num += trainMatrix[i]         p0Denom += sum(trainMatrix[i])   p1Vect = log(p1Num/p1Denom)  # 计算每个单词在trainCategory[i]类别为1条件下出现的概率   p0Vect = log(p0Num/p0Denom)  # 计算每个单词在trainCategory[i]类别为0条件下出现的概率   return p0Vect, p1Vect, pAbusive

# 朴素贝叶斯分类函数，vec2Classify：数字化后的词向量，p0Vec, p1Vec, pClass1：贝叶斯分类器训练结果def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):   p1 = sum(vec2Classify * p1Vec) + log(pClass1)   p0 = sum(vec2Classify * p0Vec) + log(1 - pClass1)   if p1 > p0:      return 1   else:      return 0

3.算法测试-包括三个测试用例

1）简单输入测试：

def testingNB():   listOposts, listClass = loadDataSet()   myVocabList = createVocabList(listOposts)   trainMat = []   for postinDoc in listOposts:      trainMat.append(setOfwords2Vec(myVocabList, postinDoc))   p0V, p1V, pAb = trainNB0(trainMat, listClass)   testEntry = ['love', 'my', 'dalmation']   thisDoc = setOfwords2Vec(myVocabList, testEntry)   print(testEntry, ' classify as:', classifyNB(thisDoc, p0V, p1V, pAb))   testEntry = ['stupid', 'garbage']   thisDoc = setOfwords2Vec(myVocabList, testEntry)   print(testEntry, ' classify as:', classifyNB(thisDoc, p0V, p1V, pAb))

2）垃圾邮件检测

# 文本解析def textParse(bigString):   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 spamtext():   docList = []   classList = []   fullText = []   for i in range(1, 26):  # 生成测试数据      wordList = textParse(open('email/spam/{}.txt'.format(i)).read())      docList.append(wordList)      fullText.extend(wordList)      classList.append(1)      wordList = textParse(open('email/ham/{}.txt'.format(i)).read())      docList.append(wordList)      fullText.extend(wordList)      classList.append(0)   vocabList = createVocabList(docList)  # 生成单词表   trainingSet = list(range(50))  # 创建训练集   testSet = []   for i in range(10):  # 从训练集中随机选取10个作为测试集      randIndex = int(random.uniform(0, len(trainingSet)))      testSet.append(trainingSet[randIndex])  # 添加到测试集中      del(trainingSet[randIndex])  # 从训练集中移除   trainMat = []  # 训练矩阵（仅包含0,1）   trainClasses = []  # 训练矩阵类别列表   for docIndex in trainingSet:  # 训练集数据转换为训练矩阵      trainMat.append(setOfwords2Vec(vocabList, docList[docIndex]))      trainClasses.append(classList[docIndex])   p0V, p1V, pAb = trainNB0(trainMat, trainClasses)   errorCount = 0   for docIndex in testSet:      wordVector = setOfwords2Vec(vocabList, docList[docIndex])      if classifyNB(wordVector, p0V, p1V, pAb) != classList[docIndex]:         errorCount += 1   print('the error rate is:', float(errorCount)/len(testSet))

3）从个人广告中获取区域倾向

# RSS源分类器及高频词去除函数def calcWords(vocabList, fullText):   freqDict = {}   for token in vocabList:      freqDict[token] = fullText.count(token)   sortedFreq = sorted(freqDict.items(), key=operator.itemgetter(1), reverse=True)   return sortedFreq[:60]

文章中去除最高的30个单词，测试中发现错误率高达50%，对于两选一的结果和瞎蒙一样，增加到60后能减少到30%

def localWords(feed1, feed0):   docList = []   classList = []   fullText = []   minLen = min(len(feed1['entries']), len(feed0['entries']))   for i in range(minLen):  # 从RSS源获取数据生成数据集      wordList = textParse(feed1['entries'][i]['summary'])      docList.append(wordList)      fullText.extend(wordList)      classList.append(1)      wordList = textParse(feed0['entries'][i]['summary'])      docList.append(wordList)      fullText.extend(wordList)      classList.append(0)   vocabList = createVocabList(docList)   top60Words = calcWords(vocabList, fullText)  # 获取高频词，一般来说是停词   for pairW in top60Words:  # 去除高频词      if pairW in vocabList:         vocabList.remove(pairW[0])   trainingSet = list(range(2*minLen))   testSet = []   for i in range(20):      randIndex = int(random.uniform(0, len(trainingSet)))      testSet.append(trainingSet[randIndex])      del(trainingSet[randIndex])   trainMat = []   trainClass = []   for docIndex in trainingSet:      trainMat.append(bagOfwords2Vec(vocabList, docList[docIndex]))      trainClass.append(classList[docIndex])   p0V, p1V, pAb = trainNB0(trainMat, trainClass)   errorCount = 0   for docIndex in testSet:      wordVector = bagOfwords2Vec(vocabList, docList[docIndex])      if classifyNB(wordVector, p0V, p1V, pAb) != classList[docIndex]:         errorCount += 1   print('the error rate is:', float(errorCount)/len(testSet))   return vocabList, p0V, p1V

五 数据集和源码：

http://pan.baidu.com/s/1boyIE4J