3.1 决策树的构造
优点:计算复杂度不高,输出结果易于理解,对中间值的缺失不敏感,可以处理不相关特征数据.
缺点:可能会产生过度匹配问题.
适用数据类型:数值型和标称型.
一般流程:
1.收集数据
2.准备数据
3.分析数据
4.训练算法
5.测试算法
6.使用算法
3.1.1 信息增益
创建数据集
def createDataSet(): dataSet = [[1, 1, 'yes'], [1, 1, 'yes'], [1, 0, 'no'], [0, 1, 'no'], [0, 1, 'no']] labels = ['no surfacing','flippers'] #change to discrete values return dataSet, labels
调用一下
myDat,labels=tree.createDataSet()
计算给定数据集的香农熵
def calcShannonEnt(dataSet): numEntries = len(dataSet) labelCounts = {} for featVec in dataSet: #the the number of unique elements and their occurance currentLabel = featVec[-1] if currentLabel not in labelCounts.keys(): labelCounts[currentLabel] = 0 labelCounts[currentLabel] += 1 shannonEnt = 0.0 for key in labelCounts: prob = float(labelCounts[key])/numEntries shannonEnt -= prob * log(prob,2) #log base 2 return shannonEnt
3.1.2 划分数据集
def splitDataSet(dataSet, axis, value): retDataSet = [] for featVec in dataSet: if featVec[axis] == value: reducedFeatVec = featVec[:axis] #chop out axis used for splitting reducedFeatVec.extend(featVec[axis+1:]) retDataSet.append(reducedFeatVec) return retDataSet
选择最好的数据集划分方式
def chooseBestFeatureToSplit(dataSet): numFeatures = len(dataSet[0]) - 1 #the last column is used for the labels baseEntropy = calcShannonEnt(dataSet) bestInfoGain = 0.0; bestFeature = -1 for i in range(numFeatures): #iterate over all the features featList = [example[i] for example in dataSet]#create a list of all the examples of this feature uniqueVals = set(featList) #get a set of unique values newEntropy = 0.0 for value in uniqueVals: subDataSet = splitDataSet(dataSet, i, value) prob = len(subDataSet)/float(len(dataSet)) newEntropy += prob * calcShannonEnt(subDataSet) infoGain = baseEntropy - newEntropy #calculate the info gain; ie reduction in entropy if (infoGain > bestInfoGain): #compare this to the best gain so far bestInfoGain = infoGain #if better than current best, set to best bestFeature = i return bestFeature #returns an integer
3.1.3 递归构建决策树
工作原理:得到原始数据集,基于最好的属性值划分数据集,由于特征值可能多于两个,因此可能存在大于两个分支的数据集划分.第一次划分后,数据将被向下传递到树分支的下一个节点,在这个节点上,我们可以再次划分数据.因此可以采用递归的原则处理数据集.
递归结束的条件是:程序遍历完所有划分数据集的属性,或者每个分支下的所有实例都具有相同的分类.如果所有实例具有相同的分类,则得到一个叶子节点或者终止块.任何到达叶子节点的数据必然属于叶子节点的分类.
def majorityCnt(classList): classCount={} for vote in classList: if vote not in classCount.keys(): classCount[vote] = 0 classCount[vote] += 1 sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True) return sortedClassCount[0][0]
def createTree(dataSet,labels): classList = [example[-1] for example in dataSet] if classList.count(classList[0]) == len(classList): return classList[0]#stop splitting when all of the classes are equal if len(dataSet[0]) == 1: #stop splitting when there are no more features in dataSet return majorityCnt(classList) bestFeat = chooseBestFeatureToSplit(dataSet) bestFeatLabel = labels[bestFeat] myTree = {bestFeatLabel:{}} del(labels[bestFeat]) featValues = [example[bestFeat] for example in dataSet] uniqueVals = set(featValues) for value in uniqueVals: subLabels = labels[:] #copy all of labels, so trees don't mess up existing labels myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value),subLabels) return myTree
调用一下
myTree=tree.createTree(myDat,labels)
结果如下:
{'no surfacing': {0: 'no', 1: {'flippers': {0: 'no', 1: 'yes'}}}}
3.2 在Python中使用Matplotlib注解缓制树形图
第一个版本
import matplotlib.pyplot as plt decisionNode = dict(boxstyle="sawtooth", fc="0.8") leafNode = dict(boxstyle="round4", fc="0.8") arrow_args = dict(arrowstyle="<-") def plotNode(nodeTxt, centerPt, parentPt, nodeType): createPlot.ax1.annotate(nodeTxt, xy=parentPt, xycoords='axes fraction', xytext=centerPt, textcoords='axes fraction', va="center", ha="center", bbox=nodeType, arrowprops=arrow_args ) def createPlot(): fig = plt.figure(1, facecolor='white') fig.clf() createPlot.ax1 = plt.subplot(111, frameon=False) #ticks for demo puropses plotNode('a decision node', (0.5, 0.1), (0.1, 0.5), decisionNode) plotNode('a leaf node', (0.8, 0.1), (0.3, 0.8), leafNode) plt.show()
是这样的图
重新来一个版本
def getNumLeafs(myTree): numLeafs = 0 firstStr = myTree.keys()[0] secondDict = myTree[firstStr] for key in secondDict.keys(): if type(secondDict[key]).__name__=='dict':#test to see if the nodes are dictonaires, if not they are leaf nodes numLeafs += getNumLeafs(secondDict[key]) else: numLeafs +=1 return numLeafs def getTreeDepth(myTree): maxDepth = 0 firstStr = myTree.keys()[0] secondDict = myTree[firstStr] for key in secondDict.keys(): if type(secondDict[key]).__name__=='dict':#test to see if the nodes are dictonaires, if not they are leaf nodes thisDepth = 1 + getTreeDepth(secondDict[key]) else: thisDepth = 1 if thisDepth > maxDepth: maxDepth = thisDepth return maxDepth
def retrieveTree(i): listOfTrees =[{'no surfacing': {0: 'no', 1: {'flippers': {0: 'no', 1: 'yes'}}}}, {'no surfacing': {0: 'no', 1: {'flippers': {0: {'head': {0: 'no', 1: 'yes'}}, 1: 'no'}}}} ] return listOfTrees[i]
def plotMidText(cntrPt, parentPt, txtString): xMid = (parentPt[0]-cntrPt[0])/2.0 + cntrPt[0] yMid = (parentPt[1]-cntrPt[1])/2.0 + cntrPt[1] createPlot.ax1.text(xMid, yMid, txtString, va="center", ha="center", rotation=30) def plotTree(myTree, parentPt, nodeTxt):#if the first key tells you what feat was split on numLeafs = getNumLeafs(myTree) #this determines the x width of this tree depth = getTreeDepth(myTree) firstStr = myTree.keys()[0] #the text label for this node should be this cntrPt = (plotTree.xOff + (1.0 + float(numLeafs))/2.0/plotTree.totalW, plotTree.yOff) plotMidText(cntrPt, parentPt, nodeTxt) plotNode(firstStr, cntrPt, parentPt, decisionNode) secondDict = myTree[firstStr] plotTree.yOff = plotTree.yOff - 1.0/plotTree.totalD for key in secondDict.keys(): if type(secondDict[key]).__name__=='dict':#test to see if the nodes are dictonaires, if not they are leaf nodes plotTree(secondDict[key],cntrPt,str(key)) #recursion else: #it's a leaf node print the leaf node plotTree.xOff = plotTree.xOff + 1.0/plotTree.totalW plotNode(secondDict[key], (plotTree.xOff, plotTree.yOff), cntrPt, leafNode) plotMidText((plotTree.xOff, plotTree.yOff), cntrPt, str(key)) plotTree.yOff = plotTree.yOff + 1.0/plotTree.totalD #if you do get a dictonary you know it's a tree, and the first element will be another dict
新版本
def createPlot(inTree): fig = plt.figure(1, facecolor='white') fig.clf() axprops = dict(xticks=[], yticks=[]) createPlot.ax1 = plt.subplot(111, frameon=False, **axprops) #no ticks #createPlot.ax1 = plt.subplot(111, frameon=False) #ticks for demo puropses plotTree.totalW = float(getNumLeafs(inTree)) plotTree.totalD = float(getTreeDepth(inTree)) plotTree.xOff = -0.5/plotTree.totalW; plotTree.yOff = 1.0; plotTree(inTree, (0.5,1.0), '') plt.show()
把树改一下
myTree['no surfacing'][3]='maybe'
重新画,变成这样
3.3 测试和存储分类器
3.3.1 测试算法:使用决策树执行分类
def classify(inputTree,featLabels,testVec): firstStr = inputTree.keys()[0] secondDict = inputTree[firstStr] featIndex = featLabels.index(firstStr) key = testVec[featIndex] valueOfFeat = secondDict[key] if isinstance(valueOfFeat, dict): classLabel = classify(valueOfFeat, featLabels, testVec) else: classLabel = valueOfFeat return classLabel
3.3.2 使用算法:决策树的存储
def storeTree(inputTree,filename): import pickle fw = open(filename,'w') pickle.dump(inputTree,fw) fw.close() def grabTree(filename): import pickle fr = open(filename) return pickle.load(fr)
3.4 使用决策树预测隐形眼镜类型
fr=open('G:学习机器学习实战MLiA_SourceCodemachinelearninginactionCh03lenses.txt') lenses=[inst.strip().split(' ') for inst in fr.readlines()] lensesLabels=['age','prescript','astigmatic','tearRate'] lensesTree=tree.createTree(lenses,lensesLabels) treeplot.createPlot(lensesTree)
