usec45.m

c4.5 关于决策树decision tree的matlab实现程序

%UseC45.m
%Shiliang Sun ([e-mail]), Apr. 9, 2007
%Show how to use the C4.5 algorithm to train a decision tree and classify
%test samples.
%This code is based on the C4_5.m file from "Classification Toolbox for Matlab"
%(http://www.yom-tov.info/cgi-bin/list_uploaded_files.pl). Several bugs have been fixed.

clear;
load DataForC45;

train_patterns=Traindata'; 
train_patterns=train_patterns(1:4,:);  train_targets=Traindata(:,end)';

test_patterns=[
    7 1 1 1 2
    7 1 2 2 1
    7 3 1 2 2];

test_patterns=test_patterns(:,1:4)';

%================================================C4.5 decision tree
% Inputs:
% 	training_patterns   - Train patterns, (the number of features) * (the number of samples)
%	training_targets	- Train targets, 1*(the number of samples)
%   test_patterns       - Test  patterns, (the number of features) * (the number of samples)
%	Fra_inc_node        - Fraction of incorrectly assigned samples at a
%	                     node.  To avoid overfitting. 
% Outputs
%	test_targets        - Predicted targets, 1*(the number of samples)

Fra_inc_node=0;

%NOTE: In this implementation it is assumed that a pattern vector with fewer than 10 unique values (the parameter Nu)
%is discrete, and will be treated as such. Other vectors will be treated as continuous
[Ni, M]		= size(train_patterns);
inc_node    = Fra_inc_node*M; %Stop building a subtree if the total samples are less than inc_node.
Nu          = 10;

%Find which of the input patterns are discrete, and discretisize the corresponding
%dimension on the test patterns
discrete_dim = zeros(1,Ni);
for i = 1:Ni,
    Ub = unique(train_patterns(i,:));
    Nb = length(Ub);
    if (Nb <= Nu),
        %This is a discrete pattern
        discrete_dim(i)	= Nb;
        dist            = abs(ones(Nb ,1)*test_patterns(i,:) - Ub'*ones(1, size(test_patterns,2)));
        [m, in]         = min(dist);
        test_patterns(i,:)  = Ub(in);
    end
end

%=======================Build the tree recursively
disp('Building a tree...')
tree            = C4_5TrainFun(train_patterns, train_targets, inc_node, discrete_dim)

%======================Classify test samples
disp('Classify test samples using the tree...')
test_targets    =  C4_5TestFun(test_patterns, tree, discrete_dim)