close all	% Close all figure windows
clear all	% Clear all variables in memory
fprintf('Loading "abalone.dat"...\n');
load abalone.dat	% Load the data set
feature_n = size(abalone, 2)-1;	% no. of features
instance_n = size(abalone, 1);	% no. of instances 
feature = abalone(:, 1:feature_n);	% feature matrix 
output = abalone(:, feature_n+1);	% output matrix
[a, b] = countele(output);
class_n = length(a);	% No. of classes
fprintf('%g features\n', feature_n);
fprintf('%g instances\n', instance_n);
fprintf('%g classes\n', class_n);
% Plot age distribution
%bar(a, b);
%xlabel('Age');
%ylabel('Counts');
%title('Age Distribution for the Abalone Data Set');
fprintf('Class 1: %g instances are younger than 10 years\n',...
	length(find(output<10)));
fprintf('Class 2: %g instances are equal to or older than 10 years\n',...
	length(find(output>=10)));

% Modify the data set such that instances younger than 10 years fall
% into class 1; all the others into class 2
index1 = find(output<10);
output(index1) = 1*ones(size(index1));
index2 = find(output>=10);
output(index2) = 2*ones(size(index2));

% Data normalization to have zero mean and unity variance r.v.
new_feature = normal(feature);
data = [new_feature output];

misclassify = zeros(10, 1);

tic
for k = 1:10,
	instance_n = size(data, 1);
%	[misclassify(k), index] = louerror(data, k, 1);
	[misclassify(k), index] = louerror(data, k);
	fprintf('Recognition rate = %g\n', 1-misclassify(k)/instance_n);
end
toc

x = 1:10;
y = (1-misclassify/instance_n)*100;
plot(x, y, '-', x, y, 'co');
xlabel('"K" in KNNR');
ylabel('LOU Recognition Rates (%)');
grid on
h = findobj(gcf, 'type', 'line');
set(h, 'linewidth', 2)