决策树算法python实现

from math import log
import operator
#决策树算法

def createDataSet():
    dataSet = [[1,1,0,0,1,'男'],
               [1,1,1,0,0,'男'],
               [1,1,0,0,0,'男'],
               [1,1,0,0,0,'男'],
               [1,1,0,1,0,'女'],
               [1,1,1,1,0,'女'],
               [1,0,1,1,0,'女'],
               [0,1,1,1,0,'女'],
               [0,0,1,1,0,'女'],
               [0,1,0,1,0,'女'],
               [0,0,1,0,1,'女'],
               [1,0,1,0,1,'女'],
               [0,1,0,0,1,'男'],
               [0,1,0,1,1,'男']]
    labels = ['身高','胡子','胸','头发','体毛']
    return dataSet,labels

def calcShannonEnt(dataSet):
    '''计算给定数据集的香农熵'''
    numEntries = len(dataSet)
    labelCounts = {}
    for featVec in dataSet:
        currentLabel = featVec[-1]
        if currentLabel not in labelCounts.keys():
            labelCounts[currentLabel] = 1
        else:
            labelCounts[currentLabel] += 1
    shannonEnt = 0.0
    for key in labelCounts:
        prob = float(labelCounts[key])/numEntries
        shannonEnt -= prob * log(prob,2)
    return shannonEnt

def splitDataSet(dataSet,axis,value):
    '''按照给定特征划分数据集'''
    retDataSet = []
    for featVec in dataSet:
        if  featVec[axis] == value:
            reducedFeatVec = featVec[:axis]
            reducedFeatVec.extend(featVec[axis+1:])
            retDataSet.append(reducedFeatVec)
    return retDataSet

def chooseBestFeatureToSplit(dataSet):
    '''选择最好的数据集划分方式'''
    numFeatures = len(dataSet[0])-1
    baseEntropy = calcShannonEnt(dataSet)
    bestInfoGain = 0.0; bestFeature = -1
    for i in range(numFeatures):
        featList = [example[i] for example in dataSet]
        uniqueVals = set(featList)
        newEntropy = 0.0
        for value in uniqueVals:
            subDataSet = splitDataSet(dataSet,i,value)
            prob = len(subDataSet)/float(len(dataSet))
            newEntropy += prob * calcShannonEnt(subDataSet)
        infoGain = baseEntropy - newEntropy
        if(infoGain > bestInfoGain):
            bestInfoGain = infoGain
            bestFeature = i
    return bestFeature

def majorityCnt(classList):
    '''
    该函数与KNN中的classify0部分的投票表决代码非常类似，该函数使用分类名称的列表，然后创建键值为classList中唯一
    值的数据字典，字典对象存储了classList中每个类标签出现的频率，最后利用operator操作键值排序字典，并返回出现次数
    最多的分类名称
    :param classList:
    :return:
    '''
    classCount = {}
    for vote in classList:
        if  vote not in classCount.keys():
            classCount[vote] = 0
        classCount[vote] += 1
    sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)
    return sortedClassCount[0][0]

def createTree(dataSet,labels):
    '''创建树的函数代码'''
    classList = [example[-1] for example in dataSet]
    #类别完全相同则停止继续划分
    if  classList.count(classList[0])==len(classList):
        return classList[0]
    #遍历完所有特征时返回出现次数最多的类别
    if len(dataSet[0])==1:
        return majorityCnt(classList)
    bestFeat = chooseBestFeatureToSplit(dataSet)
    bestFeatLabel = labels[bestFeat]
    myTree = {bestFeatLabel:{}}
    #这里会逐渐删除特征所以运行玩次函数 labels会发生变化所以我们才做一个副本切记切记
    labels2 = labels.copy()
    del(labels2[bestFeat])
    #得到列表包含的所有属性值
    featValues = [example[bestFeat] for example in dataSet]
    uniqueVals = set(featValues)
    for value in uniqueVals:
        subLabels = labels2[:]
        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet,bestFeat,value),subLabels)
    return myTree

def classify(inputTree,featLabels,testVec):
    '''使用决策树的分类函数'''
    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

##使用pickle 模块存储决策树
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)

import matplotlib.pyplot as plt

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

#使用文本注解绘制树节点
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)


def getNumLeafs(myTree):
    '''获取叶子节点的数目'''
    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

def getTreeDepth(myTree):
    '''获取树的层数（深度）'''
    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

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,nodeText):
    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, nodeText)
    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='w')
    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()