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];

% Partition the data sets for hold-out tests
index1 = 1:2:instance_n;
index2 = 2:2:instance_n;
data1 = data(index1, :);
data2 = data(index2, :);

k = 3;	% for 3 nearest neighbor
%tic
%label = knnr(data1, data2, k);
%toc

% hold-out test 1
desired_label = data2(:, feature_n+1);
label = zeros(size(desired_label));
tic
for i = 1:size(data2, 1),
	if rem(i, 100)==0,
		fprintf('%g/%g\n', i, size(data2,1));
	end
	label(i) = knnr(data1, data2(i, :), k);
end
toc
right_count = sum(label==desired_label);
recog_rate = right_count/length(desired_label);
fprintf('Recognition rate = %g/%g = %g\n', ...
	right_count, size(data2, 1), recog_rate);

% Swap data sets
temp = data1;
data1 = data2;
data2 = temp;

% hold-out test 2
desired_label = data2(:, feature_n+1);
label = zeros(size(desired_label));
tic
for i = 1:size(data2, 1),
	if rem(i, 100)==0,
		fprintf('%g/%g\n', i, size(data2,1));
	end
	label(i) = knnr(data1, data2(i, :), k);
end
toc
right_count = sum(label==desired_label);
recog_rate = right_count/length(desired_label);
fprintf('Recognition rate = %g/%g = %g\n', ...
	right_count, size(data2, 1), recog_rate);