mlap

function MSE = task1(companyDataInputFileName, sectorDataInputFileName)

% Constant Date Format used in the input files.
DATE_FORMAT = 'dd/mm/yyyy';
% Constant First Value of 2009.
FIRST_DATA = 254;
% Constant number of Folds.
FOLD_COUNT = uint8(5);
% Constant Column References
DATE                 = 1;
COMPANY_STOCK_VOLUME = 2;
COMPANY_STOCK_VALUE  = 3;
SECTOR_STOCK_VOLUME  = 4;
SECTOR_STOCK_VALUE   = 5;
DELTA_COMPANY_VOLUME = 6;
DELTA_COMPANY_VALUE  = 7;
DELTA_SECTOR_VOLUME  = 8;
DELTA_SECTOR_VALUE   = 9;


% Load data from files
companyData = loadCSVData(companyDataInputFileName);
sectorData = loadCSVData(sectorDataInputFileName);

% Combine company and sector data.
combinedData = [companyData(:,:) sectorData(:,2:3)];
% Create data points of vectors.
featureData = chooseFeatures(combinedData);
% Create folds.
folds = createFolds(featureData, FOLD_COUNT);

% Initialise squared errors to a vector of zeros.
squaredErrors = zeros(FOLD_COUNT, 1);
for i = 1:FOLD_COUNT
    [trainingFolds, validationFold] = distributeFolds(folds, i);
    theta = calculateTheta(trainingFolds);
    % Add squared error for this fold to the vector.
    squaredErrors(i) = calculateSquaredError(theta, validationFold);
end
% Return the mean of the squared errors.
MSE = sum(squaredErrors) / length(featureData);

    % Load data from a csv file.
    function data = loadCSVData(filename)
        f = fopen(filename, 'r');
        % Import all data.
        data = textscan(f, repmat('%s',1,3), 'delimiter',',', 'CollectOutput',true);
        % Remove header
        data = data{1}(2:end,:);
        fclose(f);
        clearvars f;
    end

    % Create data with the chosen features.
    function featureData = chooseFeatures(data)
        featureData = zeros(length(data));
        for n = FIRST_DATA:length(data)
            date = datenum(data(n, 1), DATE_FORMAT);
            history = lastDays(date, data, 100);
            inputs = [
                % Constant
                1;

                %---------------%
                % FEATURE SET 1 %
                %---------------%
                %{

                % last 5 days of company's stock prices.
                history(end-5:end-1, COMPANY_STOCK_VALUE);
                % Last 3 days of sector's average stock price.
                history(end-3:end-1, SECTOR_STOCK_VALUE);
                % Day of the week.
                weekday(date);

                %}
                %---------------%
                % FEATURE SET 2 %
                %---------------%
                %{

                % last 3 days of company's stock prices.
                history(end-3:end-1, COMPANY_STOCK_VALUE);
                % Last 5 days of sector's average stock price.
                history(end-5:end-1, SECTOR_STOCK_VALUE);
                % Day of the week.
                weekday(date);

                %}
                %---------------%
                % FEATURE SET 3 %
                %---------------%
                %{

                % last 10 days of company's stock prices.
                history(end-10:end-1, COMPANY_STOCK_VALUE);

                %}
                %---------------%
                % FEATURE SET 4 %
                %---------------%
                %{

                % last 2 days of company's stock prices.
                history(end-2:end-1, COMPANY_STOCK_VALUE);

                %}
                %---------------%
                % FEATURE SET 5 %
                %---------------%
                %%{

                % last 5 days of company's stock prices.
                history(end-5:end-1, COMPANY_STOCK_VALUE);
                % last 3 differences of sector average stock price.
                history(end-3:end-1, DELTA_COMPANY_VALUE);

                %}
                %---------------%
                % FEATURE SET 6 %
                %---------------%
                %%{



                %%}
                %---------------%
                % FEATURE SET 7 %
                %---------------%
                %%{


                %%}
                %---------------%
                % FEATURE SET 8 %
                %---------------%
                %%{


                %%}
                %---------------%
                % FEATURE SET 9 %
                %---------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 10 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 11 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 12 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 13 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 14 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 15 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 16 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 17 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 18 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 19 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 20 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 21 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 22 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 23 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 24 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 25 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 26 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 27 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 28 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 29 %
                %----------------%
                %%{


                %%}
                %----------------%
                % FEATURE SET 30 %
                %----------------%
                %%{


                %%}

            ]';
            % Ouput is company stock price.
            output = history(end, 3);
            % Combine inputs and outputs.
            featureData(n, 1:length(inputs)+1) = [inputs output];
        end
        % Shrink featureData down to what's used.
        featureData = featureData(:, 1:length(inputs)+1);
        % Only take the valid data.
        featureData = featureData(FIRST_DATA:end, :);
        clearvars numOfFeatures date history inputs output;
    end

    % Split the data into K folds, or equally-sized subsamples of the data.
    function folds = createFolds(data, k)
        randomData = data(randperm(length(data)), :);
        foldSize = idivide(length(data), k);
        folds = {
            randomData(1+0*foldSize:1*foldSize, :)
            randomData(1+1*foldSize:2*foldSize, :)
            randomData(1+2*foldSize:3*foldSize, :)
            randomData(1+3*foldSize:4*foldSize, :)
            randomData(1+4*foldSize:end, :)
        };
        clearvars randomData foldSize;
    end

    % Create training and validation folds from some folds.
    function [training, validation] = distributeFolds(folds, i)
        validationFoldVector = folds(i);
        validation = validationFoldVector{1};
        trainingFoldVector = folds([1:i-1 i+1:end]);
        training = vertcat(trainingFoldVector{1:end});
        clearvars validationFoldVector trainingFoldVector;
    end

    % Calculates theta (the regression coefficients)
    function theta = calculateTheta(trainingData)
        % Input matrix
        X = trainingData(:, 1:end-1);
        % Output vector
        Y = trainingData(:, end);
        theta = pinv(X'*X)*X'*Y;
        clearvars X Y;
    end

    % Return the sum of the squared errors.
    function squaredError = calculateSquaredError(theta, validationData)
        % Input matrix
        X = validationData(:, 1:end-1);
        % Target vector
        target = validationData(:, end);
        % Output vector
        output = X * theta;
        % Sum the Squared Error
        squaredError = sum((target - output).^2);
        clearvars X target output;
    end

    % Return the most recent data preceding the date given (if there is
    % data for that day, use it), and also get the last X data points
    % before it, where X = days parameter.
    function subset = lastDays(dateNum, data, days)
        to = find(strcmp(data(:,1), datestr(dateNum, DATE_FORMAT)));
        from = to - days;

        % Remove dates (not used after this point).
        firstcolumn = zeros(to-from+1, 1);
        % Original values from company and sector stock data.
        % Removes date.
        values = str2double(data(from:to,2:end));
        % Changes in the above data (also doesn't include date).
        deltas = str2double(data(from:to,2:end)) - str2double(data(from-1:to-1,2:end));

        % Return the above data.
        subset = [firstcolumn values deltas];
        clearvars from to deltas firstcolumn values deltas;
    end

end