function [data,class_labels] = load_leukemia(do_preprocessing, do_column_ordering, do_zscore)
% LOAD_LEUKEMIA - Loads the leukemia dataset and applys some preprocessing if desired  
% 
% 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.
% 
%-----

addpath( '../../Code/eda_data' );

load leukemia; data = leukemia.'; 
% n=number of samples=number of patients=72; 
% p=number of features=number of gene expressions=50
%
[n,p] = size(data);

ind_ALL = find(strcmpi(cancertype,'ALL'));
ind_AML = find(strcmpi(cancertype,'AML'));
class_labels = zeros(n,1); 
class_labels(ind_ALL)=1; 
class_labels(ind_AML)=2; 

if( do_preprocessing )
  % this data comes from a natural process ... might be gaussian ... apply the zscore transformation  
  f_mu = mean( data ); 
  f_sd = std( data ); 

  % lets sort the columns in decending order by the magnitude of the variance/standard deviation: 
  if( do_column_ordering ) 
    [f_sd_s,indx] = sort( f_sd ); f_sd_s = fliplr(f_sd_s); indx = fliplr(indx); 
  
    data = data(:,indx); 
    f_mu = f_mu(indx); 
    f_st = f_sd(indx); 
  end
    
  % compute the z-score of this data: 
  if( do_zscore )
    data_t = ( data - repmat( f_mu, [n,1] ) ) ./ repmat( f_sd, [n,1] ); 
    data = data_t; 
  end
  
end