Download All

Code covered by the BSD License  

Highlights from
Estimating the number of clusters via System Evolution

from Estimating the number of clusters via System Evolution by Kaijun Wang
estimate number of clusters for far clusters, small-larger clusters, slightly overlapping clusters

showClass_up(data, labels, high, S) 
function showClass_up(data, labels, high, S)

if S == 0
  %S = ['k.';'g.';'b.';'c.';'y.';'m.';'k+';'g+';'b+';'c+';'y+';'m+'];
  %S = ['b-';'m-';'g-';'y-';'r-';'k-';'c-';'b.';'m.';'g.';'y.';'r.'];
  S = ['b-';'m-';'g-';'r-';'k-';'c-';'y-';'b-';'m-';'g-';'r-';'k-';'c-';'y-'];
end

[nrow, ncol] = size(data);
R = 1;

for i = 1:nrow
  if length(S) > 2 
    R = labels(i);
    dup = high*R;
    if R > 14
      R = mod(R-1,14)+1;
    end
  else
    dup = high*R;
  end
  drow = data(i,:)+dup;
  plot(1:ncol,drow,S(R,:));
  hold on;
  %text(x,y,['\fontsize{10}' int2str(i)]);
end
title('Every row is displayed along dimensions');
xlim([0 ncol+1]);
%ylim([-3 3]);
%grid on;box on;

Contact us at files@mathworks.com