机器学习实战——决策树：matplotlib绘图

书籍：《机器学习实战》中文版
IDE：PyCharm Edu 4.02

环境：Adaconda3  python3.6

第一个例子：

import matplotlib.pyplot as plt#定义文本框和箭头格式decisionNode = dict(boxstyle="sawtooth",fc="0.8")leafNode = dict(boxstyle="round4",fc="0.8")arrow_args = dict(arrowstyle="<-")   #使用反转箭头# 绘制带箭头的注解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)# 主函数def createPlot():    fig = plt.figure(1,facecolor='white')    fig.clf()    createPlot.ax1 = plt.subplot(111,frameon=False)    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()print(createPlot())

结果：

注释：

关于matplotlib中的annotate：http://matplotlib.org/users/annotations_intro.html

第二个例子：

import matplotlib.pyplot as plt# 得到叶子节点数目 以便确定x轴范围def getNumLeafs(mytree):    numLeafs = 0    firstStr = list(mytree.keys())[0]    secondDict = mytree[firstStr]    for key in secondDict.keys():        if type(secondDict[key]).__name__=='dict':            numLeafs += getNumLeafs(secondDict[key])        else: numLeafs += 1    return numLeafs# 得到树的深度 以便确定y轴范围# 即树（字典）中字典类型的数目def getTreeDepth(myTree):    maxDepth = 0    firstStr = list(myTree.keys())[0]    secondDict = myTree[firstStr]    for key in secondDict.keys():        if type(secondDict[key]).__name__=='dict':            thisDepth = 1 + getTreeDepth(secondDict[key])        else: thisDepth = 1        if thisDepth>maxDepth:            maxDepth = thisDepth    return maxDepth# 预先存储树的信息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]#定义文本框和箭头格式decisionNode = dict(boxstyle="sawtooth",fc="0.8")leafNode = dict(boxstyle="round4",fc="0.8")arrow_args = dict(arrowstyle="<-")   #使用反转箭头# 绘制带箭头的注解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)#文本信息的填充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)#树的绘制def plotTree(myTree,parentPt,nodeTxt):    numLeafs = getNumLeafs(myTree)    #depth = getTreeDepth(myTree)   没有用到此变量    firstStr = list(myTree.keys())[0]    cntrPt = (plotTree.xOff + (1.0 + float(numLeafs))/2.0/plotTree.totalW, plotTree.yOff)    plotMidText(cntrPt,parentPt,nodeTxt)    plotNode(firstStr,cntrPt,parentPt,decisionNode) #cntrPt,parentPt坐标相同时，不绘制箭头。    secondDict = myTree[firstStr]    plotTree.yOff = plotTree.yOff - 1.0/plotTree.totalD    for key in secondDict.keys():        if type(secondDict[key]).__name__=='dict':            plotTree(secondDict[key],cntrPt,str(key))        else:            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# 主函数def createPlot(inTree):    fig = plt.figure()    fig.clf()    axprops = dict(xticks=[],yticks=[])   #表示不显示坐标轴    createPlot.ax1 = plt.subplot(111,frameon=False,**axprops)    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()print(createPlot(retrieveTree(0)))

结果：

小结—类型的判断问题：

（1）使用type().__name__  

比如本文中的使用

for key in secondDict.keys():    if type(secondDict[key]).__name__=='dict':        numLeafs += getNumLeafs(secondDict[key])    else: numLeafs += 1

（2）使用isinstance

比如上一篇中决策树分类函数的定义

def classify(inputTree,featLabels,testVec):    firstStr = list(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