% 
% example epage ???104 
% problem epage 129 
% 
% Appy k-means clustering to the ornsay data set   
% 
% 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,midden,beachdune] = load_oronsay(0,0,0,0);
[X,midden,beachdune] = load_oronsay(1,0,1,0);
[X,midden,beachdune] = load_oronsay(1,0,1,1); 
[n,p] = size(X);

truth_labels = midden; truth_type = 'midden'; 

fprintf(['the proptions of ', truth_type ,' labeling in each class\n']); 
tabulate( truth_labels )

y = pdist(X,'euclidean'); 

%link_method = 'complete'; 
link_method = 'average'; % <- gives only one cluster ... 

z = linkage(y,link_method);
figure; dendrogram(z); 
title( ['oronsay dendrogram with ',link_method,' linkage'] ); 

khat=3; 
%fprintf('khat = %10d\n',khat); 
c_agg_inds = cluster(z,'maxclust',khat); 

fprintf('agglomerative clustering proportions:\n'); 
tabulate( c_agg_inds ) 

% A Modified - Example 5.6
% This illustrates the use of the silhouette statistic and plots.  

% Get a k-means clustering using 3 clusters, and 5 replicates. 
% We also ask MATLAB to display the final results for each replicate.
% 
kmus3 = kmeans(X,3,'replicates',5,'display','final');

fprintf('k-means result proportions:\n'); 
tabulate( kmus3 ); 

% Get the silhouette plots for both clusterings and the values.
figure; 
[sil_agg, h_agg] = silhouette(X, c_agg_inds);
m_sil_agg = mean(sil_agg); 
title( ['agglomerative clustering; mean(silhouette) value=',num2str(m_sil_agg)] ); 
saveas( gcf, '../../WriteUp/Graphics/Chapter5/prob_5_14_oronsay_agglomerative_sil_plot', 'epsc' ); 

figure; 
[sil_kmeans, h_kmeans] = silhouette(X, kmus3);
m_sil_kmeans = mean(sil_kmeans);
title( ['k-means clustering; mean(silhouette) value=',num2str(m_sil_kmeans)] ); 
saveas( gcf, '../../WriteUp/Graphics/Chapter5/prob_5_14_oronsay_kmeans_sil_plot', 'epsc' ); 

fprintf('Now computing the Rand index of the derived clusters against truth\n'); 
fprintf('randind(agglomerative,truth) = %20.6f\n',randind(c_agg_inds,truth_labels)); 
fprintf('adjrand(agglomerative,truth) = %20.6f\n',adjrand(c_agg_inds,truth_labels)); 

fprintf('Now computing the Rand index of the derived clusters against truth\n'); 
fprintf('randind(k_means,truth) = %20.6f\n',randind(kmus3,truth_labels)); 
fprintf('adjrand(k_means,truth) = %20.6f\n',adjrand(kmus3,truth_labels));