Matplotlib绘图库的使用 (更新中)

Matplotlib　的用法介绍

Matplotlib 绘图库的使用

matplotlib的定义：

matplotlib 是一个Python下的2D绘图库，能够在跨平台的交互环境中产生各种硬拷贝格式的印刷级的图形

1.在jupyter上输出matplotlib 矢量图．

矢量图的好处是，放大后不会出现模糊，可以使用在论文中代替orange画图．

#添加一段代码就行
import matplotlib 
import matplotlib.pyplot as plt 
%matplotlib inline
%config InlineBackend.figure_format='svg'

上面这段输出矢量图的代码，基于Python3 输出是错误的．语法不对，再寻找解决方案

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt 
with tf.Session() as sess:
    fig,ax=plt.subplots()
    ax.plot=(tf.random_normal([100]).eval(),tf.random_normal([100]).eval(),'o')
    ax.set_title('Sample random plot for tersotflow')
    plt.show()
    plt.savefig('result.svg')
    # plt.savefig() 只要指定文件名的后缀是.pdf或是　.eps就能够输出　相应的文件

<matplotlib.figure.Figure at 0x7f7a502ac9e8>

2.利用 Matplotlib 绘制决策树图

Unfortunately,Python does’t include a good tool for plotting trees. so we’ll make our own.

这才是真正的工程师精神

Matplotlib has a great tool ,called annotations.that can add text near data in a plot.

2.1Plotting trees nodes with text annotations

利用文字注释功能来画树结点

import matplotlib.pyplot as plt

# define nodeType 叶结点，判别结点，箭头类型的定义

decisionNode=dict(boxstyle="sawtooth",fc="0.8")
leafNode=dict(boxstyle="round4",fc="0.8")
arrow_args=dict(arrowstyle="<-")

# 定义结点函数

def plotNode(nodeText,centerPt,parentPt,nodeType):
    createPlot.ax1.annotate(nodeText,xy=parentPt,xycoords='axes fraction',xytext=centerPt,textcoords='axes fraction',
                           va='center',ha='center',bbox=nodeType,arrowprops=arrow_args)
    # 这个参数多的有点恐怖．没有看懂

# 创造一个绘制图

def createPlot():
    fig=plt.figure(1,facecolor='white')
    fig.clf()                 #create a new figure and clear it  将新建的画板进行清理　
    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()

# 调用函数，将绘制的图在屏幕上显示

createPlot()

2.2 A strategy for plotting tree

Identifying the number of leaves in a tree and the depth

Need to know how many leafnodes and how many levels to decide the properly size the X,Y direction.

# Numleafs function
def getNumLeafs(myTree):
    numLeafs=0
    firstList=list(myTree.keys())
    firstStr=firstList[0]
    secondDict=myTree[firstStr]# 读取键值的value
    for key in secondDict.keys():# 监测是否有还有字典集合
        if type(secondDict[key]).__name__=='dict':
            numLeafs+=getNumLeafs(secondDict[key])
        else: numLeafs+=1
    return numLeafs

# depths function
def getTreeDepth(myTree):
    maxDepth=0
    firstList=list(myTree.keys())
    firstStr=firstList[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

需要注意的是这里有　Python版本的问题
Python 2 中　firstStr=myTree.keys()[0]
Python 3　中　firstList=list(firstStr)
             firstStr=firstList[0]
       　　　　这个函数的目的是将字典的第一个键值进行读取，

# make a tree data
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]

retrieveTree(0)

{'no surfacing': {0: 'no', 1: {'flippers': {0: 'no', 1: 'yes'}}}}

#运行函数查看
getNumLeafs(retrieveTree(1))

# Plots text between child and parent
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)

# define the main functions, plotTree
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)
    firstList = list(myTree.keys())
    firstStr=firstList[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

# 进行图形显示
def createPlot(inTree):
    fig=plt.figure(1,facecolor='white')
    fig.clf()
    axprops=dict(xticks=[],yticks=[])
    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()

# 调用函数进行来完成树的绘制
createPlot(retrieveTree(0))

createPlot(retrieveTree(1))

2.3 Put our decision tree code to use on some real data

# classification function for an existing decision tree

def classify(inputTree,featLabels,testVec):
    firstList=list(inputTree.keys())
    firstStr=firstList[0]
    secondDict=inputTree[firstStr]
    featIndex=featLabels.index(firstStr)
    for key in secondDict.keys():
        if testVec[featIndex]==key:
            if type(secondDict[key]).__name__=='dict':
                classLabel=classify(secondDict[key],featLabels,testVec)
            else:
                classLabel=secondDict[key]
    return classLabels

利用pickle　来进行序列化　serialize objects allow us to store them for later use

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)

2.4persisting the decision tree

# methods for persisting the decision tree with pickle
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)

Summary

matplotlib 的用法多种多样，实时更新中