本文数据参照 机器学习-周志华 一书中的决策树一章。可作为此章课后习题3的答案
代码参考了《机器学习实战》一书的内容,并做了不少修改。使其能用于同时包含离散与连续特征的数据集。
本文使用的Python库包括
Idx | 色泽 | 根蒂 | 敲声 | 纹理 | 脐部 | 触感 | 密度 | 含糖率 | label |
1 | 青绿 | 蜷缩 | 浊响 | 清晰 | 凹陷 | 硬滑 | 0.697 | 0.46 | 1 |
2 | 乌黑 | 蜷缩 | 沉闷 | 清晰 | 凹陷 | 硬滑 | 0.774 | 0.376 | 1 |
3 | 乌黑 | 蜷缩 | 浊响 | 清晰 | 凹陷 | 硬滑 | 0.634 | 0.264 | 1 |
4 | 青绿 | 蜷缩 | 沉闷 | 清晰 | 凹陷 | 硬滑 | 0.608 | 0.318 | 1 |
5 | 浅白 | 蜷缩 | 浊响 | 清晰 | 凹陷 | 硬滑 | 0.556 | 0.215 | 1 |
6 | 青绿 | 稍蜷 | 浊响 | 清晰 | 稍凹 | 软粘 | 0.403 | 0.237 | 1 |
7 | 乌黑 | 稍蜷 | 浊响 | 稍糊 | 稍凹 | 软粘 | 0.481 | 0.149 | 1 |
8 | 乌黑 | 稍蜷 | 浊响 | 清晰 | 稍凹 | 硬滑 | 0.437 | 0.211 | 1 |
9 | 乌黑 | 稍蜷 | 沉闷 | 稍糊 | 稍凹 | 硬滑 | 0.666 | 0.091 | 0 |
10 | 青绿 | 硬挺 | 清脆 | 清晰 | 平坦 | 软粘 | 0.243 | 0.267 | 0 |
11 | 浅白 | 硬挺 | 清脆 | 模糊 | 平坦 | 硬滑 | 0.245 | 0.057 | 0 |
12 | 浅白 | 蜷缩 | 浊响 | 模糊 | 平坦 | 软粘 | 0.343 | 0.099 | 0 |
13 | 青绿 | 稍蜷 | 浊响 | 稍糊 | 凹陷 | 硬滑 | 0.639 | 0.161 | 0 |
14 | 浅白 | 稍蜷 | 沉闷 | 稍糊 | 凹陷 | 硬滑 | 0.657 | 0.198 | 0 |
15 | 乌黑 | 稍蜷 | 浊响 | 清晰 | 稍凹 | 软粘 | 0.36 | 0.37 | 0 |
16 | 浅白 | 蜷缩 | 浊响 | 模糊 | 平坦 | 硬滑 | 0.593 | 0.042 | 0 |
17 | 青绿 | 蜷缩 | 沉闷 | 稍糊 | 稍凹 | 硬滑 | 0.719 | 0.103 | 0 |
Idx | color | root | knocks | texture | navel | touch | density | sugar_ratio | label |
1 | dark_green | curl_up | little_heavily | distinct | sinking | hard_smooth | 0.697 | 0.46 | 1 |
2 | black | curl_up | heavily | distinct | sinking | hard_smooth | 0.774 | 0.376 | 1 |
3 | black | curl_up | little_heavily | distinct | sinking | hard_smooth | 0.634 | 0.264 | 1 |
4 | dark_green | curl_up | heavily | distinct | sinking | hard_smooth | 0.608 | 0.318 | 1 |
5 | light_white | curl_up | little_heavily | distinct | sinking | hard_smooth | 0.556 | 0.215 | 1 |
6 | dark_green | little_curl_up | little_heavily | distinct | little_sinking | soft_stick | 0.403 | 0.237 | 1 |
7 | black | little_curl_up | little_heavily | little_blur | little_sinking | soft_stick | 0.481 | 0.149 | 1 |
8 | black | little_curl_up | little_heavily | distinct | little_sinking | hard_smooth | 0.437 | 0.211 | 1 |
9 | black | little_curl_up | heavily | little_blur | little_sinking | hard_smooth | 0.666 | 0.091 | 0 |
10 | dark_green | stiff | clear | distinct | even | soft_stick | 0.243 | 0.267 | 0 |
11 | light_white | stiff | clear | blur | even | hard_smooth | 0.245 | 0.057 | 0 |
12 | light_white | curl_up | little_heavily | blur | even | soft_stick | 0.343 | 0.099 | 0 |
13 | dark_green | little_curl_up | little_heavily | little_blur | sinking | hard_smooth | 0.639 | 0.161 | 0 |
14 | light_white | little_curl_up | heavily | little_blur | sinking | hard_smooth | 0.657 | 0.198 | 0 |
15 | black | little_curl_up | little_heavily | distinct | little_sinking | soft_stick | 0.36 | 0.37 | 0 |
16 | light_white | curl_up | little_heavily | blur | even | hard_smooth | 0.593 | 0.042 | 0 |
17 | dark_green | curl_up | heavily | little_blur | little_sinking | hard_smooth | 0.719 | 0.103 | 0 |
# -*- coding: utf-8 -*-
from numpy import *
import numpy as np
import pandas as pd
from math import log
import operator
#计算数据集的香农熵
def calcShannonEnt(dataSet):
numEntries=len(dataSet)
labelCounts={}
#给所有可能分类创建字典
for featVec in dataSet:
currentLabel=featVec[-1]
if currentLabel not in labelCounts.keys():
labelCounts[currentLabel]=0
labelCounts[currentLabel]+=1
shannonEnt=0.0
#以2为底数计算香农熵
for key in labelCounts:
prob = float(labelCounts[key])/numEntries
shannonEnt-=prob*log(prob,2)
return shannonEnt
#对离散变量划分数据集,取出该特征取值为value的所有样本
def splitDataSet(dataSet,axis,value):
retDataSet=[]
for featVec in dataSet:
if featVec[axis]==value:
reducedFeatVec=featVec[:axis]
reducedFeatVec.extend(featVec[axis+1:])
retDataSet.append(reducedFeatVec)
return retDataSet
#对连续变量划分数据集,direction规定划分的方向,
#决定是划分出小于value的数据样本还是大于value的数据样本集
def splitContinuousDataSet(dataSet,axis,value,direction):
retDataSet=[]
for featVec in dataSet:
if direction==0:
if featVec[axis]>value:
reducedFeatVec=featVec[:axis]
reducedFeatVec.extend(featVec[axis+1:])
retDataSet.append(reducedFeatVec)
else:
if featVec[axis]<=value:
reducedFeatVec=featVec[:axis]
reducedFeatVec.extend(featVec[axis+1:])
retDataSet.append(reducedFeatVec)
return retDataSet
#选择最好的数据集划分方式
def chooseBestFeatureToSplit(dataSet,labels):
numFeatures=len(dataSet[0])-1
baseEntropy=calcShannonEnt(dataSet)
bestInfoGain=0.0
bestFeature=-1
bestSplitDict={}
for i in range(numFeatures):
featList=[example[i] for example in dataSet]
#对连续型特征进行处理
if type(featList[0]).__name__=='float' or type(featList[0]).__name__=='int':
#产生n-1个候选划分点
sortfeatList=sorted(featList)
splitList=[]
for j in range(len(sortfeatList)-1):
splitList.append((sortfeatList[j]+sortfeatList[j+1])/2.0)
bestSplitEntropy=10000
slen=len(splitList)
#求用第j个候选划分点划分时,得到的信息熵,并记录最佳划分点
for j in range(slen):
value=splitList[j]
newEntropy=0.0
subDataSet0=splitContinuousDataSet(dataSet,i,value,0)
subDataSet1=splitContinuousDataSet(dataSet,i,value,1)
prob0=len(subDataSet0)/float(len(dataSet))
newEntropy+=prob0*calcShannonEnt(subDataSet0)
prob1=len(subDataSet1)/float(len(dataSet))
newEntropy+=prob1*calcShannonEnt(subDataSet1)
if newEntropybestInfoGain:
bestInfoGain=infoGain
bestFeature=i
#若当前节点的最佳划分特征为连续特征,则将其以之前记录的划分点为界进行二值化处理
#即是否小于等于bestSplitValue
if type(dataSet[0][bestFeature]).__name__=='float' or type(dataSet[0][bestFeature]).__name__=='int':
bestSplitValue=bestSplitDict[labels[bestFeature]]
labels[bestFeature]=labels[bestFeature]+'<='+str(bestSplitValue)
for i in range(shape(dataSet)[0]):
if dataSet[i][bestFeature]<=bestSplitValue:
dataSet[i][bestFeature]=1
else:
dataSet[i][bestFeature]=0
return bestFeature
#特征若已经划分完,节点下的样本还没有统一取值,则需要进行投票
def majorityCnt(classList):
classCount={}
for vote in classList:
if vote not in classCount.keys():
classCount[vote]=0
classCount[vote]+=1
return max(classCount)
#主程序,递归产生决策树
def createTree(dataSet,labels,data_full,labels_full):
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,labels)
bestFeatLabel=labels[bestFeat]
myTree={bestFeatLabel:{}}
featValues=[example[bestFeat] for example in dataSet]
uniqueVals=set(featValues)
if type(dataSet[0][bestFeat]).__name__=='str':
currentlabel=labels_full.index(labels[bestFeat])
featValuesFull=[example[currentlabel] for example in data_full]
uniqueValsFull=set(featValuesFull)
del(labels[bestFeat])
#针对bestFeat的每个取值,划分出一个子树。
for value in uniqueVals:
subLabels=labels[:]
if type(dataSet[0][bestFeat]).__name__=='str':
uniqueValsFull.remove(value)
myTree[bestFeatLabel][value]=createTree(splitDataSet\
(dataSet,bestFeat,value),subLabels,data_full,labels_full)
if type(dataSet[0][bestFeat]).__name__=='str':
for value in uniqueValsFull:
myTree[bestFeatLabel][value]=majorityCnt(classList)
return myTree
df=pd.read_csv('watermelon_4_3.csv')
data=df.values[:,1:].tolist()
data_full=data[:]
labels=df.columns.values[1:-1].tolist()
labels_full=labels[:]
myTree=createTree(data,labels,data_full,labels_full)
import matplotlib.pyplot as plt
decisionNode=dict(boxstyle="sawtooth",fc="0.8")
leafNode=dict(boxstyle="round4",fc="0.8")
arrow_args=dict(arrowstyle="<-")
#计算树的叶子节点数量
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
#计算树的最大深度
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
#画节点
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)
#画箭头上的文字
def plotMidText(cntrPt,parentPt,txtString):
lens=len(txtString)
xMid=(parentPt[0]+cntrPt[0])/2.0-lens*0.002
yMid=(parentPt[1]+cntrPt[1])/2.0
createPlot.ax1.text(xMid,yMid,txtString)
def plotTree(myTree,parentPt,nodeTxt):
numLeafs=getNumLeafs(myTree)
depth=getTreeDepth(myTree)
firstStr=myTree.keys()[0]
cntrPt=(plotTree.x0ff+(1.0+float(numLeafs))/2.0/plotTree.totalW,plotTree.y0ff)
plotMidText(cntrPt,parentPt,nodeTxt)
plotNode(firstStr,cntrPt,parentPt,decisionNode)
secondDict=myTree[firstStr]
plotTree.y0ff=plotTree.y0ff-1.0/plotTree.totalD
for key in secondDict.keys():
if type(secondDict[key]).__name__=='dict':
plotTree(secondDict[key],cntrPt,str(key))
else:
plotTree.x0ff=plotTree.x0ff+1.0/plotTree.totalW
plotNode(secondDict[key],(plotTree.x0ff,plotTree.y0ff),cntrPt,leafNode)
plotMidText((plotTree.x0ff,plotTree.y0ff),cntrPt,str(key))
plotTree.y0ff=plotTree.y0ff+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.x0ff=-0.5/plotTree.totalW
plotTree.y0ff=1.0
plotTree(inTree,(0.5,1.0),'')
plt.show()
createPlot(myTree)
#主程序,递归产生决策树
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,labels)
bestFeatLabel=labels[bestFeat]
myTree={bestFeatLabel:{}}
del(labels[bestFeat])
featValues=[example[bestFeat] for example in dataSet]
uniqueVals=set(featValues)
#针对bestFeat的每个取值,划分出一个子树。
for value in uniqueVals:
subLabels=labels[:]
myTree[bestFeatLabel][value]=createTree(splitDataSet\
(dataSet,bestFeat,value),subLabels)
return myTree