%% Kimia_simple
% Introductory PR experiment on blob images.
% It loads the images, computes features, creates scatterplot
% and estimates the nearest neighbor classification error.
%
% <http://37steps.com/software/prtools/ PRTools> and
% <http://37steps.com/software/prdatafiles/ PRDataFiles> should be in the path
%
% <http://37steps.com/exam/kimia_simple/kimia_simple.m Download the m-file from
% here>.
% See http://37steps.com/prtools for more. 

%% Section 1 Check availablity of toolboxes
% <http://37steps.com/software/prtools/ PRTools> and <http://37steps.com/software/prdatafiles/ PRDataFiles> should be in the path
if exist('ldc',         'file') ~= 2, error('PRTools not in path'); end
if exist('kimia_images','file') ~= 2, error('PRDataFiles not in path'); end
delfigs; % delete all figures to avoid clutter

%% Section 2 load datafile
% Show all images, class sizes and class names
A = kimia_images; % accept downloading again, neglect warnings,
figure; show(A,12);
classnames(A)

%% Section 3 Select two classes
% 
B = selclass(A,char('camel','elephant'));
figure; show(B,6);

%% Section 4 Compute features
% Compute for every object its 
% - area (sum of pixels inside) 
% - perimeter (sum of pixels on the contour)
feat1 = im_stat([],'sum');
feat2 = filtim('bwperim')*im_stat([],'sum');
C = B*[feat1 feat2]*datasetm;
C = setfeatlab(C,{'Size','Perimenter'});
disp(+C);

%% Section 5 Scatterplots
% Show the original scatterplot,
% after normalization on variance,
% and with a classifier
figure; scatterd(C,'legend'); axis equal; fontsize(14);
% Some tricky statements to get non-matching NN labels
[~,nn] = min(distm(C)+1e100*eye(size(C,1)));
hold on; scatterd(C(labcmp(getlab(C),getlab(C(nn,:))),:),'ko');
fontsize(14);

D = C*mapex(scalem,'variance');
figure; scatterd(D,'legend'); axis equal; fontsize(14);
% Some tricky statements to get non-matching NN labels
[~,nn] = min(distm(D)+1e100*eye(size(D,1)));
hold on; scatterd(D(labcmp(getlab(D),getlab(D(nn,:))),:),'ko');
fontsize(14);

figure; scatterd(D,'legend'); axis equal; fontsize(14);
plotc(knnc(D,1),'col');
fontsize(14);

%% Section 6 First classification
% Compute the nearest neighbor errors for the two scatterplots
fprintf('LOO NN error of original features %4.2f\n',testk(C,1));
fprintf('LOO NN error of rescaled features %4.2f\n',testk(D,1));