function [J, grad] = lrCostFunction(theta, X, y, lambda)
%LRCOSTFUNCTION Compute cost and gradient for logistic regression with 
%regularization
%   J = LRCOSTFUNCTION(theta, X, y, lambda) computes the cost of using
%   theta as the parameter for regularized logistic regression and the
%   gradient of the cost w.r.t. to the parameters. 

% Initialize some useful values
m = length(y); % number of training examples

% You need to return the following variables correctly 
J = 0;
grad = zeros(size(theta));

% ====================== YOUR CODE HERE ======================
% Instructions: Compute the cost of a particular choice of theta.
%               You should set J to the cost.
%               Compute the partial derivatives and set grad to the partial
%               derivatives of the cost w.r.t. each parameter in theta
%
% Hint: The computation of the cost function and gradients can be
%       efficiently vectorized. For example, consider the computation
%
%           sigmoid(X * theta)
%
%       Each row of the resulting matrix will contain the value of the
%       prediction for that example. You can make use of this to vectorize
%       the cost function and gradient computations. 
%
% Hint: When computing the gradient of the regularized cost function, 
%       there're many possible vectorized solutions, but one solution
%       looks like:
%           grad = (unregularized gradient for logistic regression)
%           temp = theta; 
%           temp(1) = 0;   % because we don't add anything for j = 0  
%           grad = grad + YOUR_CODE_HERE (using the temp variable)
%

% Calculating J
theta_t_x = X*theta;
h_theta = sigmoid(theta_t_x);

part_1 = -y'*log(h_theta);
part_2 = (1 - y)' * log(1 - h_theta);
part_3 =  sum(theta(2:length(theta)).^2);
%part_3 = sum(theta(2:length(theta)).*theta(2:length(theta)));

J = ((1 / m) * sum(part_1 - part_2)) + ((lambda/(2*m)) * part_3);

% Calculating g
temp_1 = sigmoid(X*theta) - y;
temp_2 = repmat(temp_1, 1, size(X, 2));

theta_vector = (lambda/m) * theta;
theta_vector(1) = 0;
grad = (1/m * sum(X .* temp_2))' + theta_vector;

% =============================================================

grad = grad(:);

end