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

X = load_sparrow(1,0,1,0);
[n,p] = size(X);

% specify a number of cluster (and their threshold) to visualize ... 
% ... these are based on the dendrogram plot and would need to be changed for each new data set
khat     = 4;
k_thresh = 3.;

y = pdist(X,'euclidean'); 
z = linkage(y,'average'); 
figure; [h,T]=dendrogram(z,'colorthreshold',k_thresh);
title( 'sparrow dendrogram with average linkage' ); 
%saveas( gcf, '../../WriteUp/Graphics/Chapter8/prob_8_5_sparrow_den', 'epsc' ); 


%
% A treemap:
% 
% Example 8.2 This shows the treemap implementation in Matlab.  Let's continue with the same
% leukemia data set as in the previous example.  The matrix Z was calculated in Example 8.1.
%
treemap(z,khat);
title( 'a treemap of the sparrow dataset' ); 
%saveas( gcf, '../../WriteUp/Graphics/Chapter8/prob_8_5_sparrow_tm', 'epsc' ); 

%
% A rectangle plot: 
%
% Example 8.3 Use same leukemia data set and matrix Z from Example 8.1.  The second argument is the
% number of clusters. The third argument is a string specifying what information the second argument
% provides.
%

rectplot(z,khat,'nclus',zeros(1,n))
%rectplot(Z,13.0,'dis');
title( 'a rectangle plot of the sparrow dataset' ); 
saveas( gcf, '../../WriteUp/Graphics/Chapter8/prob_8_5_sparrow_rp', 'epsc' ); 

%
% The ReClus plot
% 
reclus(T);
title( 'ReClus plot of the sparrow dataset' );
%saveas( gcf, '../../WriteUp/Graphics/Chapter8/prob_8_5_sparrow_rc', 'epsc' ); 

%
% A data image:
%
% Example 8.6 This shows how to do the data image.
%
T = cluster(z,'maxclust',khat);
% Sort these, so points in the same cluster are adjacent.
[Ts,inds] = sort(T);
% Sort the distance matrix using this and replot.
Ys = squareform(y); 
figure
imagesc(Ys(inds,inds))
title('Interpoint Distance Matrix - Cluster Order')
colormap(gray(256))
axis off
saveas( gcf, '../../WriteUp/Graphics/Chapter8/prob_8_5_sparrow_di', 'epsc' );