《机器学习实战》第三章 3.2 在Python中使用Matplotlib注解绘制树形图
- 自己按照树上的代码敲了一遍(Spyder),调试之后可以使用,向大家分享一下,另外,有好多的注解,希望对大家有帮助。
代码 - 源代码
# -*- coding: utf-8 -*-
"""
Created on Mon Dec 18 10:53:31 2017
@author: XU LI
"""
#使用Matplotlib绘制树形图----注解工具annotations
#博客http://blog.csdn.net/csdn_lzw/article/details/56835176
#使用文本注解绘制树节点
import matplotlib.pyplot as plt
#定义决策树决策结果的属性,用字典来定义
#下面的字典定义也可写作 decisionNode={boxstyle:'sawtooth',fc:'0.8'}
#boxstyle为文本框的类型,sawtooth是锯齿形,fc是边框线粗细
decisionNode = dict(boxstyle="sawtooth", fc="0.8")
leafNode = dict(boxstyle="round4", fc="0.8")
arrow_args = dict(arrowstyle="<-")
def plotNode(nodeTxt, centerPt, parentPt, nodeType):
# annotate是关于一个数据点的文本
# nodeTxt为要显示的文本,centerPt为文本的中心点,箭头所在的点,parentPt为指向文本的点
#createPlot.ax1定义一个绘图区
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')
# 定义一个画布,背景为白色
fig.clf()
# 把画布清空
# createPlot.ax1为全局变量,绘制图像的句柄,subplot为定义了一个绘图,
#111表示figure中的图有1行1列,即1个,最后的1代表第一个图
# frameon表示是否绘制坐标轴矩形
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()
#确定x,y轴的长度来放置所有的树节点
#获取叶节点的数目和树的层数
def getNumLeafs(myTree):
numLeafs = 0
firstStr = myTree.keys()[0]
#字典的第一个键,即树的一个结点
secondDict = myTree[firstStr]
#这个键的值,即该结点的所有子树
for key in secondDict.keys():
if type(secondDict[key]).__name__=='dict':
#使用type()判断子节点是否是字典类型
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':
thisDepth = 1 + getTreeDepth(secondDict[key])
else : thisDepth = 1
if thisDepth > maxDepth: maxDepth = thisDepth
return maxDepth
#输出预先存储的树信息
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'}}}}]
#定义了两个字典
return listOfTrees[i]
#plotTree 函数
def plotMidText(cntrpt,parentPt,txtString):
#计算父节点与子节点的中间位置,在此处添加文本信息
xMid = (parentPt[0] - cntrpt[0])/2.0 + cntrpt[0]
yMid = (parentPt[1] - cntrpt[1])/2.0 + cntrpt[1]
createPlot.ax1.text(xMid,yMid,txtString)
def plotTree(myTree,parentPt,nodeTxt):
#递归函数,计算树的宽和高
numLeafs = getNumLeafs(myTree)
#当前树的叶子数
depth = getTreeDepth(myTree)
#没有用到这个变量
firstStr = myTree.keys()[0]
cntrpt = (plotTree.x0ff + (1.0 + float(numLeafs))/2.0/plotTree.totalW,plotTree.y0ff)
#cntrPt文本中心点 parentPt指向文本中心的点
plotMidText(cntrpt,parentPt,nodeTxt)
#画分支上的键
plotNode(firstStr,cntrpt,parentPt,decisionNode)
secondDict = myTree[firstStr]
plotTree.y0ff = plotTree.y0ff - 1.0/plotTree.totalD
#从上往下画,依次递减y的坐标值
for key in secondDict.keys():
if type(secondDict[key]).__name__=='dict':
#如果是字典则是一个判断(内部)结点
plotTree(secondDict[key],cntrpt,str(key))
else:
plotTree.x0ff = plotTree.x0ff + 1.0/plotTree.totalW
plotNode(secondDict[key],(plotTree.x0ff,plotTree.y0ff),cntrpt,
leafNode)
plotMidText((plotTree.x0ff,plotTree.y0ff),cntrpt,str(key))
plotTree.y0ff = plotTree.y0ff + 1.0/plotTree.totalD
def createPlot(inTree):
#创建绘图区,计算树形图的全局尺寸,并调用递归函数plotTree()
fig = plt.figure(1,facecolor='white')
# 定义一个画布,背景为白色
fig.clf()
# 把画布清空
axprops = dict(xticks=[],yticks=[])
# 定义横纵坐标轴,无内容
createPlot.ax1 = plt.subplot(111,frameon=False,**axprops)
# 绘制图像,无边框,无坐标轴
plotTree.totalW = float(getNumLeafs(inTree))
#树的宽度#全局变量宽度 = 叶子数
plotTree.totalD = float(getTreeDepth(inTree))
#树的深度#全局变量高度 = 深度
plotTree.x0ff = -0.5/plotTree.totalW;#例如绘制3个叶子结点,坐标应为1/3,2/3,3/3
#但这样会使整个图形偏右因此初始的,将x值向左移一点。
plotTree.y0ff = 1.0;
plotTree(inTree, (0.5,1.0), '')
plt.show()
3.结果分析代码
# -*- coding: utf-8 -*-
"""
Created on Sat Oct 28 20:52:14 2017
@author: XU LI
"""
myData,labels = createDataSet()
print myData
print calcShannonEnt(myData)
print'---------------------------------'
print splitDataSet (myData,0,1)
print splitDataSet (myData,0,0)
print splitDataSet (myData,1,1)
print splitDataSet (myData,1,0)
print'---------------------------------'
myData,labels = createDataSet()
print myData
print '第', chooseBestFeatureToSplit(myData),
print '个特征是最好的用于划分数据集的特征'
print'---------------------------------'
myData,labels = createDataSet()
myTree = createTree(myData,labels)
print 'myTree=',myTree
print'---------------------------------'
#treePlotter.createPlot()
print'---------------------------------'
print treePlotter.retrieveTree(1)
myTree = treePlotter.retrieveTree(0)
print myTree
print treePlotter.getNumLeafs(myTree)
print treePlotter.getTreeDepth(myTree)
print'---------------------------------'
myTree = retrieveTree(0)
createPlot(myTree)
4.结果