决策树模型(matlab)

第一个函数是计算熵的函数

<span style="font-size:18px;">function result=CEntropy(propertyList)

result=0;
totalLength=length(propertyList);
itemList=unique(propertyList);
pNum=length(itemList);
for i=1:pNum
    itemLength=length(find(propertyList==itemList(i)));
    pItem=itemLength/totalLength;
    result=result-pItem*log2(pItem);
end</span>

实现决策树模型的主函数

<span style="font-size:18px;">function decisionTreeModel=decisionTree(data,label,propertyName)

global rootNode;
global Node;

rootNode=struct('NodeName',[]);
Node=struct('fatherNodeName',[],'EdgeProperty',[],'NodeName',[]);

rootIndex=CalcuteNode(data,label);
dataRowIndex=setdiff(1:length(propertyName),rootIndex);
rootNode.NodeName=propertyName(rootIndex);
propertyName(rootIndex)=[];
rootData=data(:,rootIndex);
sonEdge=unique(rootData);

for i=1:length(sonEdge)
    edgeDataIndex=find(rootData==sonEdge(i));
    BuildTree(rootNode.NodeName,sonEdge(i),data(edgeDataIndex,dataRowIndex),label(edgeDataIndex,:),propertyName);
end

model.rootNode=rootNode;
model.Node=Node;
decisionTreeModel=model;</span>

决策树模型主函数需要调用的递归函数，用于构造除了根节点以外的其他节点

<span style="font-size:18px;">function [ output_args ] = BuildTree(fatherNodeName,edge,data,label,propertyName)
%UNTITLED9 Summary of this function goes here
%   Detailed explanation goes here

global rootNode;
global Node;

% rootNode=struct('NodeName',[]);
% Node=struct('fatherNodeName',[],'EdgeProperty',[],'NodeName',[]);

k=length(Node)+1;
Node(k).fatherNodeName=fatherNodeName;
Node(k).EdgeProperty=edge;
if length(unique(label))==1
    Node(k).NodeName=label(1);
    return;
end

sonIndex=CalcuteNode(data,label);
dataRowIndex=setdiff(1:length(propertyName),sonIndex);
Node(k).NodeName=propertyName(sonIndex);
propertyName(sonIndex)=[];
sonData=data(:,sonIndex);
sonEdge=unique(sonData);

for i=1:length(sonEdge)
    edgeDataIndex=find(sonData==sonEdge(i));
    BuildTree(Node(k).NodeName,sonEdge(i),data(edgeDataIndex,dataRowIndex),label(edgeDataIndex,:),propertyName);
end

end
</span>

里面用到的返回下一个特征作为子节点的函数

<span style="font-size:18px;">function [NodeIndex]=CalcuteNode(data,label)

LargeEntropy=CEntropy(label);

[m,n]=size(data);
EntropyGain=LargeEntropy*ones(1,n);

for i=1:n
    pData=data(:,i);
    itemList=unique(pData);
    for j=1:length(itemList)
        itemIndex=find(pData==itemList(j));
        EntropyGain(i)=EntropyGain(i)-length(itemIndex)/m*CEntropy(label(itemIndex));
    end
    % 此处运行则为增益率，注释掉则为增益
%     EntropyGain(i)=EntropyGain(i)/CEntropy(pData);
end
[~,NodeIndex]=max(EntropyGain);
end</span>

接下来，测试用主函数：

<span style="font-size:18px;">clear;clc;

OutlookType=struct('Sunny',1,'Rainy',2,'Overcast',3);
TemperatureType=struct('hot',1,'warm',2,'cool',3);
HumidityType=struct('high',1,'norm',2);
WindyType={'True',1,'False',0};
PlayGolf={'Yes',1,'No',0};
data=struct('Outlook',[],'Temperature',[],'Humidity',[],'Windy',[],'PlayGolf',[]);

Outlook=[1,1,3,2,2,2,3,1,1,2,1,3,3,2]';
Temperature=[1,1,1,2,3,3,3,2,3,3,2,2,1,2]';
Humidity=[1,1,1,1,2,2,2,1,2,2,2,1,2,1]';
Windy=[0,1,0,0,0,1,1,0,0,0,1,1,0,1]';

data=[Outlook Temperature Humidity Windy];
PlayGolf=[0,0,1,1,1,0,1,0,1,1,1,1,1,0]';
propertyName={'Outlook','Temperature','Humidity','Windy'};

decisionTreeModel=decisionTree(data,PlayGolf,propertyName);</span>