%%%%%% LOAD DATA %%%%%%%
matrix = (load('podaci_564.mat').data)';
input = matrix(:, 1:2);
output = matrix(:,3);

negative = input(find(output == 0),:);
positive = input(find(output == 1),:);

%a - visualize data classes

figure('Name', 'Data classes');
%0 - red crosses
plot(negative(:,1), negative(:,2),'r+');
hold on;
%1 - blue circles
plot(positive(:,1), positive(:,2),'bo');
%pause;
hold off;

%NOTE - first 450 data samples are class 0 , next 114 are class 1,
%for test randomize data - shuffle
%b  - make test dataset (20% of original size)

shuffled_array = randperm(int32((length(input) * 0.2)));
test_input = input(shuffled_array, :);
test_output = output(shuffled_array, :);


%neural nwtwork creation
first_input_col = input(:,1)';
second_input_col = input(:,2)';
Pr = min_max([first_input_col;second_input_col]);
Ni_1 = [2 3 ];
Ni_2 = [2 3 1];
%output layer is considered as part of hidden layer
%trainlm can produce maximum memory usage problem. Possible solutions:

%1.Slow trainlm training, but reduce memory requirements by setting net.trainParam.mem_reduc to 2 or more. (See help trainlm.)
%2.Use trainbfg, which is slower but more memory-efficient than trainlm.-not available
%3.Use trainrp, which is slower but more memory-efficient than trainbfg. -not available

net = newff(Pr, Ni_2, {"tansig","purelin","logsig"}, "trainlm", "learngdm", "mse");
net.trainParam.mem_reduc = 2;
net.trainParam.Mu = 0.0001;

%Y = sim(net,input');

%plot(input,output);
%,input',Y,'o')
%disp(net.inputs.size);
net.trainParam.epochs = 50;
net = train(net,input',output');
#{Y = sim(net,input);
plot(input,output,input,Y,'o')
#}