Why won't my linear regression line show?

New to MatLab (and programming in general) and started messing around with my first attempt at linear regression. My code is running but when I run this, the plot has the data points but does not show the linear regression line. Any idea as to why?

format long g

t = [1; 246; 417; 607; 736]; %feature variable, univariate (x axis)
p = [234.31; 431.76; 652.14; 817.26; 2358.96]; %results variable (y axis)

m = length(p); %number of training examples 
theta = zeros(2,1); %initiate parameters  
iterations = 1500; %iterations needed for GD 
alpha = 0.01;  

plot(t,p, "bd", "MarkerSize",8);
title ('Bitcoin price');
xlabel('Days Transpired');
ylabel('Bitcoin Price');


%compute cost function
%add column to t 

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

J = computeprice(t, p, theta);

%running gradient descent 

[theta, J_history] = GradientDescentBTC(t, p, theta, alpha, iterations);
hold on;
plot(t(:, 2),t * theta, '--', "LineWidth", 1); 
legend('Training data', 'Linear regression');
hold off;

[Star Strider]

Unrecognized function or variable 'computeprice'.

[Austin Brune]

%BELOW IS MY CODE FOR 'computeprice' WHICH IS IN ANOTHER SCRIPT 


function J = computeprice(t, p, theta)

m=length(p);

h= t * theta;

J = 1 / (2 * m) * sum((h - p) .^2);

end

Answer 1

[Star Strider]

I believe there is something wrong with ‘computeprice’. It should produce a vector the same length as ‘t’ that is then compared with ’p’ to estimate ‘theta’. Note that it also must have ‘m’ as an argument.

Make necessary changes in ‘computeprice’ in this code (coded as an anonymous function here) to get the desired result:

computeprice = @(t, theta, m) 1 ./ (2 * m) * t.*theta;

t = [1; 246; 417; 607; 736]; %feature variable, univariate (x axis)
p = [234.31; 431.76; 652.14; 817.26; 2358.96]; %results variable (y axis)
m = length(p); %number of training examples 

est_theta = fminsearch(@(theta) norm(computeprice(t, theta, m) - p), rand);

figure
plot(t, p, 'p')
hold on
plot(t, computeprice(t, est_theta, m), '-r', 'LineWidth',2)
hold off
grid

Since it is supposed to be a linear regression, and if I correctly understand what ‘computeprice’ is supposed to do, a much simpler way to calculate this is to use the mldivide,\ function or operator:

est_theta = [1/(2*m)*t] \ p;

figure
plot(t, p, 'p')
hold on
plot(t, est_theta*1/(2*m)*t, '-r', 'LineWidth',2)
hold off
grid

producing the same result as the fminsearch call.

Note that this will demonstrate the linear regression.

.

[Austin Brune]

So, first off, thank you for this! This did end up plotting the line and nice to see that actually show up in figure. I'm very new to this and would find it super helpful if you saw the code I originally had for computeprice as well as my GradientDescent. Where did I go wrong here? Were there any changes I could have made to my original code instead or was I writing nonsense

function J = computeprice(t, p, theta, m)

m=length(p);

h= t * theta;

J = 1 / (2 * m) * sum((h - p) .^2);

end

So that was script for computeprice.m

Here was my script for GradientDescent.m

function [theta, J_history] = GradientDescentBTC(t, p, theta, alpha, iterations)
    
       m= length(p);
       J_history = zeros(iterations, 1);
       
       for i = 1: iterations
           h = t * theta;
           t1 = theta(1) - alpha * (1 / m) * sum(h - p);
           t2 = theta(2) - alpha * (1 / m) * sum((h - p) .* t(:, 2));
           theta(1) = t1;
           theta(2) = t2;
           J_history(i) = computeprice(t, p, theta);
       end
       
end

[Star Strider]

As always, my pleasure!

There are so many problems with your code that I cannot analyse all of them. Most of them have to do with matrix dimensions not matching or not being compatible with the operations they are involved in. However note that ‘t’ is a column vector, so in the ‘t2’ assignment, the ‘t(:,2)’ reference will always throw an error, since it references the second column of a one-column argument.

That said, I cannot follow the logic, so I will stop here.

[Austin Brune]

lol I appreciate it

re: your t(:,2) comment, didn't I create a 2 column vector with t = [ones(m,1),t]?

Other than that, sounds like I just start over as it's ridden with problems

I'm just confused as to why no errors are showing up when I run.

[Star Strider]

As always, my pleasure!

‘re: your t(:,2) comment, didn't I create a 2 column vector with t = [ones(m,1),t]?’

I must have missed copying that when I tried running your code.

Running your code again (and copying everything), ‘J_history’ starts at 3.1176e+012 and quickly overflows. The value for ‘theta’ is a (2x2) NaN vector, so myultiplying it by ‘t’ produces a NaN vector:

CheckResult = t * theta

produces:

CheckResult =
             NaN
             NaN
             NaN
             NaN
             NaN

and NaN (and other non-finite) values do not plot.

I did my best to see in detail what the problems are with your code, however I could not figure out the logic.