# How to compute Cost function for linear regression

390 views (last 30 days)
Muhammad Kundi on 22 Jun 2019
Commented: safwan bin amir on 10 Apr 2022
This question was flagged by Nishant Sitapara
Hi,
I am trying to compute cost function I am using the following code:
function J = computeCost(X, y, theta)
%COMPUTECOST Compute cost for linear regression
% J = COMPUTECOST(X, y, theta) computes the cost of using theta as the
% parameter for linear regression to fit the data points in X and y
% Initialize some useful values
m = length(y); % number of training examples
% You need to return the following variables correctly
J = 0;
% ====================== YOUR CODE HERE ======================
% Instructions: Compute the cost of a particular choice of theta
% You should set J to the cost.
h = X * theta;
sError = (h - y) .^ 2;
J = sum(sError) / (2 * m);
% =========================================================================
end
.But I am getting the following error
Error in computeCost (line 7)
m = length(y); % number of training examples
David Onoja on 4 Feb 2022
Pls how do you submit answers

João Marlon Souto Ferraz on 14 Sep 2020
I believe than this is happen because you are running and trying to compile the function. Just save and to call than function from the other script.

Mahdi Badriyan on 25 May 2020
hi
J = sum(sError) / (2 .* m);
in this way your code will be corrected.

Sanskar Choudhary on 28 Dec 2021
open file submit.m and then run it.(don't run computeCost.m file, this will not work because its just function)
##### 2 CommentsShowHide 1 older comment
David Onoja on 4 Feb 2022
Pls explain better

Ghayyur Abbas on 29 Aug 2019
initialize x y theta with values in the function
##### 2 CommentsShowHide 1 older comment
Tushant Verma on 6 Aug 2020
computeCost(X,y,theta)

Heng Dao on 6 Feb 2021
((h)-y).^2 Try try hope can help u

Prasad Kute on 23 Jul 2021
function J = computeCost(X, y, theta)
%COMPUTECOST Compute cost for linear regression
% J = COMPUTECOST(X, y, theta) computes the cost of using theta as the
% parameter for linear regression to fit the data points in X and y
% Initialize some useful values
m = length(y); % number of training examples
% You need to return the following variables correctly
J = 0;
% ====================== YOUR CODE HERE ======================
% Instructions: Compute the cost of a particular choice of theta
% You should set J to the cost.
J = (1/(2*m))*sum(((X*theta) - y).^2)
Try this, you will get it correct.
##### 2 CommentsShowHide 1 older comment
Image Analyst on 6 Feb 2022
@amenallah berrejeb Why not? Show your code that proves it does not work.

Image Analyst on 4 Feb 2022
You say "sorry...I forgot to mention...I just hit run to execute the program and I get this error message.."
Well that is the whole problem. When you have a function that expects inputs like X, y, theta then you need to supply those inputs. You can't just click the green run triangle and expect somehow that doing that will automagically invent values for X, y, and theta. So you need to do something like
% Declare inputs:
X = rand(1,10);
y = rand(1, 10);
theta = 42;
% Now run the function:
result = computeCost(X, y, theta)
fprintf('Done with the program!\n');
%==========================================================================================
% Define the function:
function J = computeCost(X, y, theta)
%COMPUTECOST Compute cost for linear regression
% J = COMPUTECOST(X, y, theta) computes the cost of using theta as the
% parameter for linear regression to fit the data points in X and y
% Initialize some useful values
m = length(y); % number of training examples
% You need to return the following variables correctly
J = 0;
% ====================== YOUR CODE HERE ======================
% Instructions: Compute the cost of a particular choice of theta
% You should set J to the cost.
h = X * theta;
sError = (h - y) .^ 2;
J = sum(sError) / (2 * m);
end

Image Analyst on 6 Feb 2022
As long as y is defined (like you assigned something to y before you called the function) then that line
m = length(y); % number of training examples
should work. However you didn't give the entire error message. You gave the line the error occurred on but not the actual error description. Why not? You need to include all the red text, not just some of it.
By the way you need to assign something for y, you can't just click the green Run triangle on the toolbar without assigning all the input variables.

Jia He on 6 Feb 2022
If you meet errors in submitting, and your function is correct. Try to delete its .mlx file and submit it again.

MAZEN ALHARBI on 5 Apr 2022
function J = computeCost(X, y, theta)
%COMPUTECOST Compute cost for linear regression
% J = COMPUTECOST(X, y, theta) computes the cost of using theta as the
% parameter for linear regression to fit the data points in X and y
% Initialize some useful values
% number of training examples
% You need to return the following variables correctly
y = data(:, 2);
m = length(y); % number of training examples
X = [ones(m, 1), data(:,1)]; % Add a column of ones to x
theta = zeros(2, 1);
% ====================== YOUR CODE HERE ======================
% Instructions: Compute the cost of a particular choice of theta
% You should set J to the cost.
J = 0;
J = 1/(2*m) * (X * theta - y)' * (X * theta - y); % vectorized form
% =========================================================================
end
safwan bin amir on 10 Apr 2022
@MAZEN ALHARBI you a life saviour. you are doing that ML course of andrew ng?