%
% an extension of Example 8.1
% 
% Written by:
% -- 
% John L. Weatherwax                2005-08-14
% 
% email: wax@alum.mit.edu
% 
% Please send comments and especially bug reports to the
% above email address.
% 
%-----

close all; drawnow; 
rehash; 
clc; 

clear; addpath( '../../Code/eda_data' ); addpath( '../../Code/eda_toolbox' ); addpath( '../Chapter1' ); 

% First load the data.
load leukemia
[n,p] = size(leukemia);
x = zeros(n,p);
% Standardize each row (gene) to be mean
% zero and standard deviation 1.
for i = 1:n
    sig = std(leukemia(i,:));
    mu = mean(leukemia(i,:));
    x(i,:) = (leukemia(i,:) - mu)/sig;
end
% Do hierarchical clustering.
Y = pdist(x);
Z = linkage(Y,'complete');
[H, T] = dendrogram(Z,15,'colorthreshold',0.9 * max( Z(:,3) ) );
title('Leukemia Data: Complete Linkage: 0.9 * max')
saveas( gcf, '../../WriteUp/Graphics/Chapter8/prob_8_1_p_9', 'epsc' ); 

[H, T] = dendrogram(Z,35,'colorthreshold',0.6 * max( Z(:,3) ) );
title('Leukemia Data: Complete Linkage: 0.6 * max')
saveas( gcf, '../../WriteUp/Graphics/Chapter8/prob_8_1_p_6', 'epsc' );