% The farthest point clustering scheme tends to grab points that are evenly
% spaced over the support of the dataset. When there are lots of "outliers"
% there may be very few points where most of the data are.

K = 30;  % Grab K points
D = 2;   % in D dimensions, out of
N = 1e3; % a dataset of size N

alpha = 0.8;
xx = [randn(D, ceil(N*alpha)),...
      bsxfun(@plus, [4;4], 3*exp(randn(D, N-ceil(N*alpha))))];
idx = ceil(N*rand(1,K));
idx2 = grabk(xx, K);

clf;
subplot(1,2,1); hold on;
plot(xx(1,:), xx(2,:), '+');
plot(xx(1,idx), xx(2,idx), 'rx', 'MarkerSize', 10, 'LineWidth', 2);
axis equal

subplot(1,2,2); hold on;
plot(xx(1,:), xx(2,:), '+');
plot(xx(1,idx2), xx(2,idx2), 'rx', 'MarkerSize', 10, 'LineWidth', 2);
axis equal