onevsall.m

function [all_theta] = oneVsAll(X, y, k, lambda)

m = size(X, 1);
n = size(X, 2);
alpha = 0.01;

% this is storing all the theta for all the individual problems
all_theta = zeros(k, n + 1); % 6 x (n+1)

X = [ones(m, 1) X];

for i=1:k
    theta = zeros(n + 1, 1);
    for j = 1:100
        data = [y, X];
        data = data(randperm(size(data,1)),:);
        y = data(:,1);
        y_final = zeros(size(y))
        for p = 1:m
            y_final(y(p)) = 1;
        X = data(:,2:end);
        for p = 1:m
            x = X(p,:); % Select one example
            Y = y_final(p)
            [J, grad] = lrCostFunction(theta, x, Y, lambda);
            theta = theta - alpha * grad;
        end
    end
%    options = optimset('GradObj', 'on', 'MaxIter', 50);
%    [theta] = fmincg (@(t)(lrCostFunction(t, X, (y == i), lambda)),initial_theta, options);
    all_theta(i,:) = theta;
end


end