机器学习实战（2） ——决策树算法（python实现）

 这是学习机器学习算法实战这本书时，写的代码实战。让自己对各个算法有更直观的了解，不能一直不写啊。不管简单还是不简单都亲自一行一行的敲一遍啊。

具体的源码和和数据链接：https://pan.baidu.com/s/1G2S2pb5gfBnxGNNTFgTkEA 密码：fov0

第一个程序是treePlotter.py主要讲述如何使用matplotlib绘制树

# -*- coding: utf-8 -*-
# author: Yufeng Song
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):
     #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.annotate(nodeTxt,xy=parentPt,xycoords="axes fraction",xytext=centerPt,
                            textcoords="axes fraction",va="center",ha="center",bbox=nodeType,
                            arrowprops=arrow_args)

def createPlot():
    # 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
    fig = plt.figure(1,facecolor='white')
    fig.clf()#清空画布
    createPlot.ax1 = plt.subplot(111,frameon=True)
    plotNode('kkk',(0.5,0.1),(0.1,0.5),decisionNode)
    plotNode('jjj',(0.8,0.1),(0.3,0.8),leafNode)#中文节点显示的问题啊
    plt.show()

def getNumLeafs(myTree):
    numLeafs = 0
    #print(id(numLeafs))
    firstStr = list(myTree.keys())[0]
    secondDict = myTree[firstStr]
    for key in secondDict.keys():
        if type(secondDict[key]).__name__ == 'dict':
           #print('hao'+str(id(numLeafs)))
            numLeafs += getNumLeafs(secondDict[key])
        else: numLeafs += 1
    return numLeafs

def getTreeDepth(myTree):
    maxDepth = 0
    firstStr = list(myTree.keys())[0]  # myTree.kyes()[0]python2中的写法
    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

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)


def plotTree(myTree,parentPt,nodeTxt):
    numLeafs = getNumLeafs(myTree)
    depth = getTreeDepth(myTree)
    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)
    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

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()
#


# 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()

if __name__ == '__main__':
    # createPlot()
    myTree = retrieveTree(1)
    print(myTree)
    print(getNumLeafs(myTree))
    print(getTreeDepth(myTree))
    createPlot(myTree)

第二个程序是trees.py 具体讲的是决策树的构成。

# -*- coding: utf-8 -*-
# author: Yufeng Song

from math import log
import treePlotter
import pickle

def calcShannonEnt(dataset):
    numEntries = len(dataset)
    labelCounts = {}
    for featVec in dataset:
        currentLabel = featVec[-1]
        if currentLabel not in labelCounts.keys():
            labelCounts[currentLabel] = 0
        labelCounts[currentLabel] += 1
        #labelCounts[currentLabel] = labelCounts.get(currentLabel,0)+1 #等同上面的三句
    shannonEnt = 0.0
    for key in labelCounts:
        prob = float(labelCounts[key])/numEntries
        shannonEnt -= prob*log(prob,2)
    return shannonEnt

def createDataSet():
    dataSet = [[1,1,'yes'],
               [1,1,'yes'],
               [1,0,'no'],
               # [0,1,'no'],
               [0,1,'no']
               ]
    labels = ['no surfacing','flippers']
    return dataSet,labels



def splitDataSet(dataSet,axis,value):
    retDataSet = []
    for featVec in dataSet:
        if featVec[axis] == value:
            reducedFeatVec = featVec[:axis]
            reducedFeatVec.extend(featVec[axis+1:])#reducedFeatVec.extend(featVec[axis:])记得加一，
                                                 # 把它完全删除掉
            retDataSet.append(reducedFeatVec)
    return retDataSet



def chooseBestFeatureToSplit(dataSet):
    numFeatures = len(dataSet[0])-1
    baseEntroy = calcShannonEnt(dataSet)
    bestInfoGain = 0.0;bestFarture = -1
    for i in range(numFeatures):
        featList = [example[i] for example in dataSet]
        uniqueVals = set(featList)
        newEntroy = 0.0
        for value in uniqueVals:
            subDataSet = splitDataSet(dataSet,i,value)
            prob = len(subDataSet)/float(len(dataSet))#这个类别的概率
            newEntroy += prob*calcShannonEnt(subDataSet)
        infoGain = baseEntroy - newEntroy
        if (infoGain > bestInfoGain):
            bestInfoGain = infoGain
            bestFarture = i
    return bestFarture

def majorityCnt(classList):
    classCount={}
    for vote in classCount:
        if vote not in classCount.keys():classCount[vote] = 0
        classCount[vote] +=1
    sortedClassCount = sorted(classCount.items(),key=lambda item: item[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]
    if len(dataSet[0]) == 1:
        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[:]
        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet,bestFeat,value),subLabels)
    return myTree

def classify(inputTree,featLabels,testVec):
    firstStr = list(inputTree.keys())[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 classLabel

def storeTree(inputTree,filename):
    fw = open(filename,'wb+')#fw = open(filename,'w')二进制的问题
    pickle.dump(inputTree,fw)
    fw.close()

def grabTree(filename):
    fr = open(filename,'rb')
    return pickle.load(fr)







if __name__ == '__main__':
    # myDat,labels = createDataSet()
    # print(calcShannonEnt(myDat))
    # print(splitDataSet(myDat,0,0))
    # print(splitDataSet(myDat,0,1))
    # print(chooseBestFeatureToSplit(myDat))
    # myTree = createTree(myDat,labels)
    # print(myTree)
    # myTree=treePlotter.retrieveTree(0)
    # print(myTree)
    # answer1 = classify(myTree,labels,[1,0])
    # print(answer1)
    # answer2 = classify(myTree,labels,[1,1])
    # print(answer2)
    # storeTree(myTree,'classifierStorage.txt')
    # print(grabTree('classifierStorage.txt'))
    print('*'*50)
    # fr=open('lenses.txt','rb') 不能以二进制数进行读取
    fr=open('lenses.txt')
    fr_readlines = fr.readlines()
    # print(fr.readlines())
    # print(fr_readlines)
    # lenses=[inst.strip().split('\t') for inst in fr.readlines()]
    lenses=[str(inst).strip().split('\t') for inst in fr_readlines]
    print(lenses)
    lensesLabels=['age','prescript','astigmatic','tearRate']
    lensesTree = createTree(lenses,lensesLabels)
    print('#'*50)
    treePlotter.createPlot(lensesTree)