Python实现CART决策树

CART决策树

  • 前言
  • 一、CART决策树算法
  • 二、Python代码实现
    • 1.计算结点GINI值
    • 2.分离数据集
    • 3.选择最好的特征
    • 4.生成决策树
    • 5.测试决策树
    • 6.决策树可视化
    • 7.主程序部分
    • CART决策分类树所有代码
  • 三、运行结果
  • 总结


前言

  CART算法的全称是Classification And Regression Tree,采用的是Gini指数(选Gini指数最小的特征s)作为分裂标准,是一种实用的分类算法。


一、CART决策树算法

  主要思路是对一个数据集选择几个属性作为特征,对于每个特征提出一个划分条件,根据这个条件将结点分为两个子节点,对于子节点同样利用下一个特征进行划分,直到某结点的Gini值符合要求,我们认为这个结点的不纯性很小,该节点已成功分类。如此反复执行,最后可以得到由若干个结点组成的决策树,其中的每个叶节点都是分类的结果。

  某结点的Gini值的计算公式如下:
Python实现CART决策树_第1张图片
  如果要对某种划分计算Gini值,可以利用加权平均,即:

在这里插入图片描述
  明确了Gini值的计算以及决策树的基本思路后,就可以继续向下看具体的代码实现了,本文没有使用sklearn库,如果读者只是需要使用该算法,而不想了解算法实际的实现思路的话,可以无需向下看了。

二、Python代码实现

主要分为6个步骤:

  1. 寻找到最佳属性
  2. 创建决策树
  3. 将上一结点分裂,分别计算左、右子节点的Gini值。
  4. 计算Gnin值有一种方法:将数据集对应这个属性的值排序,从头开始选择相邻两个值的平均值作为划分条件,计算该分发下的Gini值,如此遍历一遍,选出最小的一个Gini值对应的划分条件,作为该属性的最佳分裂条件
  5. 对于子节点,Gini值小于阈值,认为其是叶节点,结束这一方向的分裂。若Gini值大于阈值,认为分类还不够纯,需继续分裂,下一次分裂要使用不同的属性值。
  6. 递归调用创建决策树,就可以得到完整的决策树。

使用到的函数主要有5个:

  • calcGini(dataSet)   #计算结点GINI值
  • splitDataSet(dataSet, n, value, type)  #根据条件分离数据集
  • FindBestFeature(dataSet)  #选择最好的特征划分数据集,即返回最佳特征下标及传入数据集各列的Gini指数
  • createTree(dataSet, features, decisionTree)  #生成决策树。输入:训练数据集D,特征集A。输出:决策树T
  • testTree(dataSet)  #获得测试结果,给出混淆矩阵

1.计算结点GINI值

def calcGini(dataSet):

    numTotal = dataSet.shape[0]            # 记录本数据集总条数
    length = len(dataSet[0])               # 计算特征列数
    frequent_0 = 0.0                         # 记录三种样本出现次数
    frequent_1 = 0.0
    frequent_2 = 0.0
    for i in range(0,numTotal):
        if dataSet[i][length-1] == '0.0':
            frequent_0 += 1
        elif dataSet[i][length-1] == '1.0':
            frequent_1 += 1
        elif dataSet[i][length-1] == '2.0':
            frequent_2 += 1
    gini = 1 - (frequent_0/numTotal)**2 - (frequent_1/numTotal)**2 - (frequent_2/numTotal)**2
    return gini

2.分离数据集

def splitDataSet(dataSet, n, value, type):

    subDataSet = []
    numTotal = dataSet.shape[0]            # 记录本数据集总条数
    if type == 1:                          # type==1对应小于等于value的情况
        for i in range(0,numTotal):
            if float(dataSet[i][n]) <= value:
                subDataSet.append(dataSet[i])
    elif type == 2:                        # type==2对应大于value的情况
        for i in range(0,numTotal):
            if float(dataSet[i][n]) > value:
                subDataSet.append(dataSet[i])
    subDataSet = np.array(subDataSet)      # 强制转换为array类型
     
    return subDataSet,len(subDataSet)

3.选择最好的特征

def FindBestFeature(dataSet):
    numTotal = dataSet.shape[0]            # 记录本数据集总条数
    numFeatures = len(dataSet[0]) - 2      # 计算特征列数
    bestFeature = -1                       # 初始化参数,记录最优特征列i,下标从0开始
    columnFeaGini={}                       # 初始化参数,记录每一列x的每一种特征的基尼 Gini(D,A)
    for i in range(1, numFeatures+1):      # 遍历所有x特征列,i为特征标号
        featList = list(dataSet[:, i])     # 取这一列x中所有数据,转换为list类型
        featListSort = [float(x) for x in featList]
        featListSort.sort()                # 对该特征值排序
        FeaGinis = []
        FeaGiniv = []
        for j in range(0,len(featListSort)-1):    # j为第几组数据
            value = (featListSort[j]+featListSort[j+1])/2
            feaGini = 0.0
            subDataSet1,sublen1 = splitDataSet(dataSet, i, value, 1)  # 获取切分后的数据
            subDataSet2,sublen2 = splitDataSet(dataSet, i, value, 2)
            feaGini = (sublen1/numTotal) * calcGini(subDataSet1) + (sublen2/numTotal) * calcGini(subDataSet2)  # 计算此分法对应Gini值
            FeaGinis.append(feaGini)       # 记录该特征下各种分法遍历出的Gini值
            FeaGiniv.append(value)         # 记录该特征下的各种分法

        columnFeaGini['%d_%f'%(i,FeaGiniv[FeaGinis.index(min(FeaGinis))])] = min(FeaGinis)    # 将该特征下最小的Gini值
    bestFeature = min(columnFeaGini, key=columnFeaGini.get) # 找到最小的Gini指数对应的数据列
    return bestFeature,columnFeaGini

4.生成决策树

def createTree(dataSet, features, decisionTree):

    if len(features) > 2:           #特征未用完
        bestFeature, columnFeaGini = FindBestFeature(dataSet)
        bestFeatureLable = features[int(bestFeature.split('_')[0])]  # 最佳特征
        NodeName = bestFeatureLable + '\n' +'<=' + bestFeature.split('_')[1]    #结点名称
        decisionTree = {NodeName: {}}   # 构建树,以Gini指数最小的特征bestFeature为子节点
    else:
        return decisionTree

    LeftSet, LeftSet_len = splitDataSet(dataSet, int(bestFeature.split('_')[0]), float(bestFeature.split('_')[1]), 1)
    RightSet, RightSet_len = splitDataSet(dataSet, int(bestFeature.split('_')[0]), float(bestFeature.split('_')[1]), 2)
    del (features[int(bestFeature.split('_')[0])])        # 该特征已为子节点使用,则删除,以便接下来继续构建子树

    if calcGini(LeftSet) <= 0.1 or len(features) == 2:
        L_lables_grp = dict(Counter(LeftSet[:,-1]))
        L_leaf = max(L_lables_grp, key=L_lables_grp.get)  # 获得划分后出现概率最大的分类作为结点的分类
        decisionTree[NodeName]['Y'] = L_leaf              # 设定左枝叶子值
    elif calcGini(LeftSet) > 0.1:
        dataSetNew = np.delete(LeftSet, int(bestFeature.split('_')[0]), axis=1)  # 删除此最优划分x列,使用剩余的x列进行数据划分
        L_subFeatures = features[:]
        decisionTree[NodeName]['Y'] = {'NONE'}
        decisionTree[NodeName]['Y'] = createTree(dataSetNew, L_subFeatures, decisionTree[NodeName]['Y'])   #递归生成左边的树

    if calcGini(RightSet) <= 0.1 or len(features) == 2:
        R_lables_grp = dict(Counter(RightSet[:,-1]))
        R_leaf = max(R_lables_grp, key=R_lables_grp.get)  # 获得划分后出现概率最大的分类作为结点的分类
        decisionTree[NodeName]['N'] = R_leaf              # 设定右枝叶子值
    elif calcGini(RightSet) > 0.1:
        dataSetNew = np.delete(RightSet, int(bestFeature.split('_')[0]), axis=1)  # 删除此最优划分x列,使用剩余的x列进行数据划分
        R_subFeatures = features[:]
        decisionTree[NodeName]['N'] = {'NONE'}
        decisionTree[NodeName]['N'] = createTree(dataSetNew, R_subFeatures, decisionTree[NodeName]['N'])  #递归生成右边的树

    return decisionTree

5.测试决策树

def testTree(dataSet):
    numTotal = dataSet.shape[0]  # 记录本数据集总条数
    testmemory = []
    label = dataSet[:,-1]
    TP = 0
    FP = 0
    TN = 0
    FN = 0
    for i in range(0,numTotal):
        if float(dataSet[i][4]) <= 0.001444:                   #标准差
            if float(dataSet[i][1]) <= 0.01022:                #均值
                if float(dataSet[i][6]) <= -0.589019:          #峰度
                    testmemory.append('0.0')
                else:
                    if float(dataSet[i][3]) <= -0.001811:        #四分位差
                        if float(dataSet[i][2]) <= -0.000026:      #中位数
                            testmemory.append('0.0')
                        else:
                            testmemory.append('2.0')
                    else:
                        if float(dataSet[i][2]) <= 0.007687:       #中位数
                            if float(dataSet[i][5]) <= 0.452516:   #偏度
                                testmemory.append('0.0')
                            else:
                                testmemory.append('0.0')
                        else:
                            testmemory.append('2.0')
            else:
                testmemory.append('2.0')
        else:
            if float(dataSet[i][3]) <= -0.013691:                # 四分位差
                testmemory.append('1.0')
            else:
                if float(dataSet[i][5]) <= 1.462280:   #偏度
                    if float(dataSet[i][6]) <= -1.034223:  # 峰度
                        if float(dataSet[i][1]) <= 0.009173:  # 均值
                            if float(dataSet[i][2]) <= -0.004193:  # 中位数
                                testmemory.append('2.0')
                            else:
                                testmemory.append('2.0')
                        else:
                            testmemory.append('0.0')
                    else:
                        testmemory.append('2.0')
                else:
                    if float(dataSet[i][1]) <= -0.023631:  # 均值
                        testmemory.append('2.0')
                    else:
                        testmemory.append('1.0')

    for i in range(0, numTotal):
        if (testmemory[i] == '1.0') and (label[i] == '1.0'):
            TP += 1
        elif (testmemory[i] == '1.0') and (label[i] != '1.0'):
            FP += 1
        elif (testmemory[i] != '1.0') and (label[i] != '1.0'):
            TN += 1
        elif (testmemory[i] != '1.0') and (label[i] == '1.0'):
            FN += 1

    print('TP:%d' % TP)    #真阳性
    print('FP:%d' % FP)    #假阳性
    print('TN:%d' % TN)    #真阴性
    print('FN:%d' % FN)    #假阴性

    cm = confusion_matrix(label, testmemory, labels=["0.0", "1.0", "2.0"])
    plt.rc('figure', figsize=(5, 5))
    plt.matshow(cm, cmap=plt.cm.cool)  # 背景颜色
    plt.colorbar()  # 颜色标签
    # 内部添加图例标签
    for x in range(len(cm)):
        for y in range(len(cm)):
            plt.annotate(cm[x, y], xy=(y, x), horizontalalignment='center', verticalalignment='center')
    plt.ylabel('True Label')
    plt.xlabel('Predicted Label')
    plt.title('decision_tree')
    plt.savefig(r'confusion_matrix')

6.决策树可视化

可视化部分基本摘自《机器学习实战》第三章。

matplotlib.rcParams['font.family']='SimHei'  # 用来正常显示中文
plt.rcParams['axes.unicode_minus']=False  # 用来正常显示负号

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

def getNumLeafs(myTree):
    numLeafs = 0
    firstStr = list(myTree.keys())[0]
    secondDict = myTree[firstStr]
    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
            numLeafs += getNumLeafs(secondDict[key])
        else:
            numLeafs += 1
    return numLeafs

def getTreeDepth(myTree):
    maxDepth = 0
    firstStr = list(myTree.keys())[0]  # myTree.keys()[0]
    secondDict = myTree[firstStr]
    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
            thisDepth = 1 + getTreeDepth(secondDict[key])
        else:
            thisDepth = 1
        if thisDepth > maxDepth: maxDepth = thisDepth
    return maxDepth

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 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, va="center", ha="center", rotation=30)

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)
    firstStr = list(myTree.keys())[0]  # myTree.keys()[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

def createPlot(myTree):
    fig = plt.figure(1, facecolor='white')
    fig.clf()
    axprops = dict(xticks=[], yticks=[])
    createPlot.ax1 = plt.subplot(111, frameon=False, **axprops)  # no ticks
    # createPlot.ax1 = plt.subplot(111, frameon=False) #ticks for demo puropses
    plotTree.totalW = float(getNumLeafs(myTree))
    plotTree.totalD = float(getTreeDepth(myTree))
    plotTree.xOff = -0.5 / plotTree.totalW;
    plotTree.yOff = 1.0;
    plotTree(myTree, (0.5, 1.0), '')
    plt.show()

7.主程序部分

trainingData, testingData= read_xslx(r'e:/Table/机器学习/1109/attribute_113.xlsx')
features = list(trainingData[0])          # x的表头,即特征
trainingDataSet = trainingData[1:]        # 训练集

bestFeature, columnFeaGini=FindBestFeature(trainingDataSet)
decisionTree = {}
decisiontree = createTree(trainingDataSet, features, decisionTree)  # 建立决策树,CART分类树
print('CART分类树:\n', decisiontree)
testTree(testingData)
createPlot(decisiontree)

CART决策分类树所有代码

# -*- coding: utf-8 -*-     支持文件中出现中文字符
#########################################################################

"""
Created on Mon Nov 16 21:26:00 2020

@author: ixobgenw

代码功能描述: (1)计算结点GINI值
              (2)分离数据集
              (3)选择最好的特征
              (4)生成决策树
              (5)测试决策树

"""
#####################################################################

import xlrd
import numpy as np
from collections import Counter
import matplotlib.pyplot as plt
import matplotlib


#可视化部分
####################################################################################################################
matplotlib.rcParams['font.family']='SimHei'  # 用来正常显示中文
plt.rcParams['axes.unicode_minus']=False  # 用来正常显示负号

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

def getNumLeafs(myTree):
    numLeafs = 0
    firstStr = list(myTree.keys())[0]
    secondDict = myTree[firstStr]
    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
            numLeafs += getNumLeafs(secondDict[key])
        else:
            numLeafs += 1
    return numLeafs

def getTreeDepth(myTree):
    maxDepth = 0
    firstStr = list(myTree.keys())[0]  # myTree.keys()[0]
    secondDict = myTree[firstStr]
    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
            thisDepth = 1 + getTreeDepth(secondDict[key])
        else:
            thisDepth = 1
        if thisDepth > maxDepth: maxDepth = thisDepth
    return maxDepth

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 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, va="center", ha="center", rotation=30)

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)
    firstStr = list(myTree.keys())[0]  # myTree.keys()[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

def createPlot(myTree):
    fig = plt.figure(1, facecolor='white')
    fig.clf()
    axprops = dict(xticks=[], yticks=[])
    createPlot.ax1 = plt.subplot(111, frameon=False, **axprops)  # no ticks
    # createPlot.ax1 = plt.subplot(111, frameon=False) #ticks for demo puropses
    plotTree.totalW = float(getNumLeafs(myTree))
    plotTree.totalD = float(getTreeDepth(myTree))
    plotTree.xOff = -0.5 / plotTree.totalW;
    plotTree.yOff = 1.0;
    plotTree(myTree, (0.5, 1.0), '')
    plt.show()
####################################################################################################################

#读取excel文件,70%为训练集,30%为测试集
####################################################################################################################
def read_xslx(xslx_path):

    trainingdata = []                      # 先声明一个空list
    testingdata = []
    data = xlrd.open_workbook(xslx_path)   # 读取文件
    table = data.sheet_by_index(0)         # 按索引获取工作表,0就是工作表1

    for i in range(int(0.7*table.nrows)):  # table.nrows表示总行数
        line = table.row_values(i)         # 读取每行数据,保存在line里面,line是list
        trainingdata.append(line)          # 将line加入到trainingdata中,trainingdata是二维list
    trainingdata = np.array(trainingdata)  # 将trainingdata从二维list变成数组

    for i in range(int(0.7*table.nrows),int(table.nrows)):  # table.nrows表示总行数
        line = table.row_values(i)         # 读取每行数据,保存在line里面,line是list
        testingdata.append(line)           # 将line加入到testingdata中,testingdata是二维list
    testingdata = np.array(testingdata)    # 将testingdata从二维list变成数组

    return trainingdata,testingdata
####################################################################################################################

#计算结点GINI值
####################################################################################################################
def calcGini(dataSet):

    numTotal = dataSet.shape[0]            # 记录本数据集总条数
    length = len(dataSet[0])               # 计算特征列数
    frequent_0 = 0.0                         # 记录三种样本出现次数
    frequent_1 = 0.0
    frequent_2 = 0.0
    for i in range(0,numTotal):
        if dataSet[i][length-1] == '0.0':
            frequent_0 += 1
        elif dataSet[i][length-1] == '1.0':
            frequent_1 += 1
        elif dataSet[i][length-1] == '2.0':
            frequent_2 += 1
    gini = 1 - (frequent_0/numTotal)**2 - (frequent_1/numTotal)**2 - (frequent_2/numTotal)**2
    return gini
####################################################################################################################

#根据条件分离数据集
####################################################################################################################
def splitDataSet(dataSet, n, value, type):

    subDataSet = []
    numTotal = dataSet.shape[0]            # 记录本数据集总条数
    if type == 1:                          # type==1对应小于等于value的情况
        for i in range(0,numTotal):
            if float(dataSet[i][n]) <= value:
                subDataSet.append(dataSet[i])
    elif type == 2:                        # type==2对应大于value的情况
        for i in range(0,numTotal):
            if float(dataSet[i][n]) > value:
                subDataSet.append(dataSet[i])
    subDataSet = np.array(subDataSet)      # 强制转换为array类型
     
    return subDataSet,len(subDataSet)
#################################################################################################################### 

#选择最好的特征划分数据集,即返回最佳特征下标及传入数据集各列的Gini指数
####################################################################################################################
def FindBestFeature(dataSet):
    numTotal = dataSet.shape[0]            # 记录本数据集总条数
    numFeatures = len(dataSet[0]) - 2      # 计算特征列数
    bestFeature = -1                       # 初始化参数,记录最优特征列i,下标从0开始
    columnFeaGini={}                       # 初始化参数,记录每一列x的每一种特征的基尼 Gini(D,A)
    for i in range(1, numFeatures+1):      # 遍历所有x特征列,i为特征标号
        featList = list(dataSet[:, i])     # 取这一列x中所有数据,转换为list类型
        featListSort = [float(x) for x in featList]
        featListSort.sort()                # 对该特征值排序
        FeaGinis = []
        FeaGiniv = []
        for j in range(0,len(featListSort)-1):    # j为第几组数据
            value = (featListSort[j]+featListSort[j+1])/2
            feaGini = 0.0
            subDataSet1,sublen1 = splitDataSet(dataSet, i, value, 1)  # 获取切分后的数据
            subDataSet2,sublen2 = splitDataSet(dataSet, i, value, 2)
            feaGini = (sublen1/numTotal) * calcGini(subDataSet1) + (sublen2/numTotal) * calcGini(subDataSet2)  # 计算此分法对应Gini值
            FeaGinis.append(feaGini)       # 记录该特征下各种分法遍历出的Gini值
            FeaGiniv.append(value)         # 记录该特征下的各种分法

        columnFeaGini['%d_%f'%(i,FeaGiniv[FeaGinis.index(min(FeaGinis))])] = min(FeaGinis)    # 将该特征下最小的Gini值
    bestFeature = min(columnFeaGini, key=columnFeaGini.get) # 找到最小的Gini指数对应的数据列
    return bestFeature,columnFeaGini
####################################################################################################################

#生成决策树。输入:训练数据集D,特征集A。输出:决策树T
####################################################################################################################
def createTree(dataSet, features, decisionTree):

    if len(features) > 2:           #特征未用完
        bestFeature, columnFeaGini = FindBestFeature(dataSet)
        bestFeatureLable = features[int(bestFeature.split('_')[0])]  # 最佳特征
        NodeName = bestFeatureLable + '\n' +'<=' + bestFeature.split('_')[1]    #结点名称
        decisionTree = {NodeName: {}}   # 构建树,以Gini指数最小的特征bestFeature为子节点
    else:
        return decisionTree

    LeftSet, LeftSet_len = splitDataSet(dataSet, int(bestFeature.split('_')[0]), float(bestFeature.split('_')[1]), 1)
    RightSet, RightSet_len = splitDataSet(dataSet, int(bestFeature.split('_')[0]), float(bestFeature.split('_')[1]), 2)
    del (features[int(bestFeature.split('_')[0])])        # 该特征已为子节点使用,则删除,以便接下来继续构建子树

    if calcGini(LeftSet) <= 0.1 or len(features) == 2:
        L_lables_grp = dict(Counter(LeftSet[:,-1]))
        L_leaf = max(L_lables_grp, key=L_lables_grp.get)  # 获得划分后出现概率最大的分类作为结点的分类
        decisionTree[NodeName]['Y'] = L_leaf              # 设定左枝叶子值
    elif calcGini(LeftSet) > 0.1:
        dataSetNew = np.delete(LeftSet, int(bestFeature.split('_')[0]), axis=1)  # 删除此最优划分x列,使用剩余的x列进行数据划分
        L_subFeatures = features[:]
        decisionTree[NodeName]['Y'] = {'NONE'}
        decisionTree[NodeName]['Y'] = createTree(dataSetNew, L_subFeatures, decisionTree[NodeName]['Y'])   #递归生成左边的树

    if calcGini(RightSet) <= 0.1 or len(features) == 2:
        R_lables_grp = dict(Counter(RightSet[:,-1]))
        R_leaf = max(R_lables_grp, key=R_lables_grp.get)  # 获得划分后出现概率最大的分类作为结点的分类
        decisionTree[NodeName]['N'] = R_leaf              # 设定右枝叶子值
    elif calcGini(RightSet) > 0.1:
        dataSetNew = np.delete(RightSet, int(bestFeature.split('_')[0]), axis=1)  # 删除此最优划分x列,使用剩余的x列进行数据划分
        R_subFeatures = features[:]
        decisionTree[NodeName]['N'] = {'NONE'}
        decisionTree[NodeName]['N'] = createTree(dataSetNew, R_subFeatures, decisionTree[NodeName]['N'])  #递归生成右边的树

    return decisionTree
####################################################################################################################

#获得测试结果
####################################################################################################################
def testTree(dataSet):
    numTotal = dataSet.shape[0]  # 记录本数据集总条数
    testmemory = []
    label = dataSet[:,-1]
    TP = 0
    FP = 0
    TN = 0
    FN = 0
    for i in range(0,numTotal):
        if float(dataSet[i][4]) <= 0.001444:                   #标准差
            if float(dataSet[i][1]) <= 0.01022:                #均值
                if float(dataSet[i][6]) <= -0.589019:          #峰度
                    testmemory.append('0.0')
                else:
                    if float(dataSet[i][3]) <= -0.001811:        #四分位差
                        if float(dataSet[i][2]) <= -0.000026:      #中位数
                            testmemory.append('0.0')
                        else:
                            testmemory.append('2.0')
                    else:
                        if float(dataSet[i][2]) <= 0.007687:       #中位数
                            if float(dataSet[i][5]) <= 0.452516:   #偏度
                                testmemory.append('0.0')
                            else:
                                testmemory.append('0.0')
                        else:
                            testmemory.append('2.0')
            else:
                testmemory.append('2.0')
        else:
            if float(dataSet[i][3]) <= -0.013691:                # 四分位差
                testmemory.append('1.0')
            else:
                if float(dataSet[i][5]) <= 1.462280:   #偏度
                    if float(dataSet[i][6]) <= -1.034223:  # 峰度
                        if float(dataSet[i][1]) <= 0.009173:  # 均值
                            if float(dataSet[i][2]) <= -0.004193:  # 中位数
                                testmemory.append('2.0')
                            else:
                                testmemory.append('2.0')
                        else:
                            testmemory.append('0.0')
                    else:
                        testmemory.append('2.0')
                else:
                    if float(dataSet[i][1]) <= -0.023631:  # 均值
                        testmemory.append('2.0')
                    else:
                        testmemory.append('1.0')

    for i in range(0, numTotal):
        if (testmemory[i] == '1.0') and (label[i] == '1.0'):
            TP += 1
        elif (testmemory[i] == '1.0') and (label[i] != '1.0'):
            FP += 1
        elif (testmemory[i] != '1.0') and (label[i] != '1.0'):
            TN += 1
        elif (testmemory[i] != '1.0') and (label[i] == '1.0'):
            FN += 1

    print('TP:%d' % TP)    #真阳性
    print('FP:%d' % FP)    #假阳性
    print('TN:%d' % TN)    #真阴性
    print('FN:%d' % FN)    #假阴性

    cm = confusion_matrix(label, testmemory, labels=["0.0", "1.0", "2.0"])
    plt.rc('figure', figsize=(5, 5))
    plt.matshow(cm, cmap=plt.cm.cool)  # 背景颜色
    plt.colorbar()  # 颜色标签
    # 内部添加图例标签
    for x in range(len(cm)):
        for y in range(len(cm)):
            plt.annotate(cm[x, y], xy=(y, x), horizontalalignment='center', verticalalignment='center')
    plt.ylabel('True Label')
    plt.xlabel('Predicted Label')
    plt.title('decision_tree')
    plt.savefig(r'confusion_matrix')
####################################################################################################################

trainingData, testingData= read_xslx(r'e:/Table/机器学习/1109/attribute_113.xlsx')
features = list(trainingData[0])          # x的表头,即特征
trainingDataSet = trainingData[1:]        # 训练集

bestFeature, columnFeaGini=FindBestFeature(trainingDataSet)
decisionTree = {}
decisiontree = createTree(trainingDataSet, features, decisionTree)  # 建立决策树,CART分类树
print('CART分类树:\n', decisiontree)
testTree(testingData)
createPlot(decisiontree)

三、运行结果

CART分类树:
{‘标准差\n<=0.001444’: {‘Y’: {‘均值\n<=0.010220’: {‘Y’: {‘峰度\n<=-0.589019’: {‘Y’: ‘0.0’, ‘N’: {‘四分位差\n<=-0.001811’: {‘Y’: {‘中位数\n<=-0.000026’: {‘Y’: ‘0.0’, ‘N’: ‘2.0’}}, ‘N’: {‘中位数\n<=0.007687’: {‘Y’: {‘偏度\n<=0.452516’: {‘Y’: ‘0.0’, ‘N’: ‘0.0’}}, ‘N’: ‘2.0’}}}}}}, ‘N’: ‘2.0’}}, ‘N’: {‘四分位差\n<=-0.013691’: {‘Y’: ‘1.0’, ‘N’: {‘偏度\n<=1.462280’: {‘Y’: {‘峰度\n<=-1.034223’: {‘Y’: {‘均值\n<=0.009173’: {‘Y’: {‘中位数\n<=-0.004193’: {‘Y’: ‘2.0’, ‘N’: ‘2.0’}}, ‘N’: ‘0.0’}}, ‘N’: ‘2.0’}}, ‘N’: {‘均值\n<=-0.023631’: {‘Y’: ‘2.0’, ‘N’: ‘1.0’}}}}}}}}

Python实现CART决策树_第2张图片混淆矩阵:
如果将“1”看做一类,“0”和“2”看做一类,结果为:
TP:13
FP:0
TN:74
FN:3

如果每种标签都看做一类,则混淆矩阵为:
Python实现CART决策树_第3张图片

总结

  用轮子前最好还是先造个轮子感受一下。以上就是CART决策分类树的全部内容。内容基本上为笔者在BIT的机器学习课程所学,部分思路来自博客https://blog.csdn.net/weixin_43383558/article/details/84303339。本文内容为笔者初学之作,如有错误,欢迎评论指点。如有可改进之处,也欢迎讨论。

你可能感兴趣的:(决策树,python,机器学习,算法)