%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Matlab script to perform cross validation on a model generated for 
% numeric data from agriculture
%
% purpose: data mining with SVMs (support vector machines)
% 
% requires:
% - statistics toolbox for cvpartition (from Matlab2008a)
% - readColData script (see link below)
% - SVMTorch (compiled version, of course)
% - data structure used for the results (cv_results)
% -----
% Georg Ru{\ss}
% russ@iws.cs.uni-magdeburg.de
% 2008-09-26
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%% 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) = [];

% only set_3 is actually used here
set_3 = data;
set_3(:,7) = [];

Size_set_3 = size(set_3);

%% modeling stage

% struct to store actual, predicted and error values
cv_results = struct('actual',[], 'prediction', [], 'abserr', [], 'squerr', []);

k=10; % k-fold holdout cross validation
p = 1/k;

% generate data partition
cvdata = cvpartition(Size_set_3(1,1),'Holdout',p)

for i = 1:k;
   
    TrainSet = set_3(cvdata.training,:);
    TestSet = set_3(cvdata.test,:);
    
    dlmwrite('svm-train',size(TrainSet),' ');
    dlmwrite('svm-train',TrainSet,'-append','delimiter',' ');
    
    dlmwrite('svm-test',size(TestSet),' ');
    dlmwrite('svm-test',TestSet,'-append','delimiter',' ');

    
    % run svmtorch as the model
    ! SVMTorch -rm svm-train svm-model
    ! SVMTest -oa svm-results svm-model svm-test
    ! rm svm-model

    % read in model output on test values
    res_read = dlmread('svm-results');
    
    % append values
    cv_results.prediction = vertcat(cv_results.prediction,res_read);
    cv_results.actual = vertcat(cv_results.actual,TestSet(:,8));
    
    i
    
end

%% generate error measures into cv_results

cv_results.abserr = abs(cv_results.actual - cv_results.prediction);
cv_results.squerr = (cv_results.abserr).^2;

mae = mean(cv_results.abserr)
rmse = sqrt(mean(cv_results.squerr))