《机器学习实战》决策树

《机器学习实战》K近邻（KNN）分类
上一章写了K近邻分类（见上链接），本章将学习决策树的python实现，虽然K近邻在大多数的时候工作很好，但是没有一个直观的认识，而决策树可以将分类视觉化，使人们对其分类一目了然，当然，对于大型的决策树还是很难进行阅读的。本次的实现决策树只生成树，画出树图，不剪枝。

python实现决策树

##function to calculate the Shannon entropy of a dataset
from math import log
import operator

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
    shannonEnt = 0.0
    for key in labelCounts:
        prob = float(labelCounts[key])/numEntries
        shannonEnt -= prob * log(prob,2)#熵的公式-sum pi*log2(pi) i从1到N
    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

## dataset splitting on a given feature    
def splitDataSet(dataSet,axis, value):#按某一个特征分割数据
    retDataSet = []
    for featVec in dataSet:
        if featVec[axis] == value:
            reducedFeatVec = featVec[:axis]
            reducedFeatVec.extend(featVec[axis+1:])#extend见《python小函数（一）》
            retDataSet.append(reducedFeatVec)
    return retDataSet

## choosing the best feature to split on    
def chooseFeature(dataSet):
    numFeatures = len(dataSet[0]) - 1
    baseEntropy = calcShannonEnt(dataSet)#计算经验熵
    bestInfoGain = 0.0; bestFeature = -1
    for i in range(numFeatures):
        featList = [example[i] for example in dataSet]
        uniqueVals = set(featList)#set见《python小函数（一）》
        newEntropy = 0.0
        for value in uniqueVals:
            subDataSet = splitDataSet(dataSet, i, value)
            prob = len(subDataSet)/float(len(dataSet))
            newEntropy += prob * calcShannonEnt(subDataSet)#计算条件经验熵
        infoGain = baseEntropy - newEntropy#信息增益
        if (infoGain > bestInfoGain):
            bestInfoGain = infoGain
            bestFeature = i #选择最佳分类特征i
    return bestFeature

def majorityCnt(classList):#多数表决原则
    classCount = {}
    for vote in classList:
        if vote not in classCount.keys(): classCount[vote] = 0 #也可以用classCount.get(vote,0)
        classCount[vote] +=1
    sortedClassCount = sorted(classCount.iteritems(), key = operator.itemgetter(1), reverse = True)
    return sortedClassCount[0][0]
 ##trees-building code  
def createTree(dataSet, labels):
    classList = [example[-1] for example in dataSet]#取最后一个，即类
    if classList.count(classList[0]) == len(classList):
        return classList[0]
    if len(dataSet[0]) == 1:
        return majorityCnt(classList)
    bestFeat = chooseFeature(dataSet)
    bestFeatLabel = labels[bestFeat]
    myTree = {bestFeatLabel:{}}#字典里面又包含字典，形成树
    del(labels[bestFeat])#删除最佳特征标签，然后再从剩下的特征选取最佳特征
    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)#递归调用
    return myTree
##Classification function for an existing decision tree
def classify(inputTree,featLabels,testVec):
    firstStr = 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

##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)

##plotting tree nodes with text annotations
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)
    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()
''' 
## identifying the number of leaves in a tree and the depth  
def getNumLeafs(myTree):
    numLeafs = 0
    firstStr = 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

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

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]
## The plotTree function
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)
    getTreeDepth(myTree)
    firstStr = 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()

fr = open(r'c:/Users/ll/Documents/lenses.txt')
lenses = [inst.strip().split('\t') for inst in fr.readlines()]
lensesLabels = ['age','prescript','astigmatic','tearRate']