%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Matlab script to perform cross validation on a model generated for 
% numeric data from agriculture
%
% purpose: data mining with SVMs (support vector machines)
% 
% requires:
% -my splitCV script
% -readColData script
% -SVMTorch (compiled version, of course)
% -----
% Georg Ru{\ss}
% russ@iws.cs.uni-magdeburg.de
% 2008-09-24
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%% Preparation steps, workspace

% clean workspace
clear all;

% set clock
clock_start = clock;
% seed random for reproducible results
rand('seed',1);

%pause;

% change paths to wherever your data is located and readable to matlab
% uses script readColData from
% http://web.cecs.pdx.edu/~gerry/MATLAB/plotting/loadingPlotData.html#colHeadings
[label,id_column,data]=readColData('sorted_all',10,10,1);

%% data specific stuff
% generate three data sets for the nnet to play with
% one: N1, Yield2003, EM38 -- target: Yield2004
% two: N1, Yield2003, EM38, N2, REIP32 -- target: Yield2004
% three: N1, Yield2003, EM38, N2, REIP32, N3, REIP49 -- target: Yield2004
% works by eliminating the respective columns from the 'data' matrix above

set_1 = data;
set_1(:,7) = [];
set_1(:,5) = [];
set_1(:,4) = [];
set_1(:,3) = [];
set_1(:,2) = [];

set_2 = data;
set_2(:,7) = [];
set_2(:,5) = [];
set_2(:,3) = [];

set_3 = data;
set_3(:,7) = [];

%% 
Size_set_3 = size(set_3);

% matrix to store real values vs. values from SVM regression model
%cv_results = zeros(Size_set_3(1,2),2);

cv_results = []

k = 10;

for i = 1:k;
    [TrainSet TestSet] = splitCV(set_3, k, i);
    
    dlmwrite('svm-train',size(TrainSet),' ');
    dlmwrite('svm-train',TrainSet,'-append','delimiter',' ');
    
    
    dlmwrite('svm-test',size(TestSet),' ');
    dlmwrite('svm-test',TestSet,'-append','delimiter',' ');

    
    ! SVMTorch -rm svm-train svm-model
    ! SVMTest -oa svm-results svm-model svm-test
    ! rm svm-model

    
    res_read = dlmread('svm-results');
    
    step_res = horzcat(TestSet(:,8), res_read);
    
    cv_results = vertcat(cv_results,step_res);
    
    i
    
end

%% generate error measures into cv_results

rows = size(cv_results,1)

% absolute error
emptycol = zeros(rows,1)

cv_results = horzcat(cv_results,emptycol)
cv_results = horzcat(cv_results,emptycol)

for i = 1:rows
    cv_results(i,3) = abs(cv_results(i,1)-cv_results(i,2));
    cv_results(i,4) = (cv_results(i,3)).^2;
end

means = mean(cv_results);
mae = means(1,3)
rmse = sqrt(means(1,4))