Last active
December 25, 2018 17:07
-
-
Save charusat09/597c2eea6c5f0d753c60f1cd6bbe65bc to your computer and use it in GitHub Desktop.
Predict House Price based on Area in feet, Locality, No of Bed Rooms. I have created this demo project while completing my ML course
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
850,3,3,4500000 | |
1000,4,4,3500000 | |
585,3,3,3100000 | |
801,4,4,5500000 | |
729,4,3,4200000 | |
776,4,3,4500000 | |
700,2,3,7100000 | |
800,4,3,4400000 | |
1500,3,5,10000000 | |
1800,3,4,7500000 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
% This program runs with Octave 3.8+ software | |
clear ; close all; clc | |
data = load('ex1TrainingSet.txt'); | |
X = data(:, 1:3); | |
y = data(:, 4); | |
m = length(y); | |
dd = [810 3 3] | |
ddd = [1 dd] | |
[X mu sigma] = featureNormalize(X); | |
X = [ones(m, 1) X]; | |
alpha = 0.01; | |
num_iters = 400; | |
theta = zeros(4, 1); | |
[theta, J_history] = gradientDescentMulti(X, y, theta, alpha, num_iters); | |
figure; | |
plot(1:numel(J_history), J_history, '-b', 'LineWidth', 2); | |
xlabel('Number of iterations'); | |
ylabel('Cost J'); | |
d = dd; | |
d = (d - mu) ./ sigma; | |
d = [ones(1, 1) d]; | |
price = d * theta; | |
fprintf(['Predicted price of a %d sq-ft, %d locality and %d bed room house ' ... | |
'(using gradient descent):\n $%f\n'], d(1), d(2), d(3), price); | |
data = csvread('ex1TrainingSet.txt'); | |
X = data(:, 1:3); | |
y = data(:, 4); | |
m = length(y); | |
X = [ones(m, 1) X]; | |
theta = normalEqn(X, y); | |
d = ddd; | |
price = d * theta; % You should change this | |
fprintf(['Predicted price of a %d sq-ft, %d locality and %d bed room house ' ... | |
'(using gradient descent):\n $%f\n'], d(2), d(3), d(4), price); | |
function [X_norm, mu, sigma] = featureNormalize(X) | |
X_norm = X; | |
mu = zeros(1, size(X, 2)); | |
sigma = zeros(1, size(X, 2)); | |
mu = mean(X_norm); | |
sigma = std(X_norm); | |
tf_mu = X_norm - repmat(mu,length(X_norm),1); | |
tf_std = repmat(sigma,length(X_norm),1); | |
X_norm = tf_mu ./ tf_std; | |
end | |
function [theta, J_history] = gradientDescentMulti(X, y, theta, alpha, num_iters) | |
m = length(y); | |
J_history = zeros(num_iters, 1); | |
for iter = 1:num_iters | |
delta = (1/m)*sum(X.*repmat((X*theta - y), 1, size(X,2))); | |
theta = (theta' - (alpha * delta))'; | |
J_history(iter) = computeCostMulti(X, y, theta); | |
end | |
end | |
function [theta] = normalEqn(X, y) | |
theta = zeros(size(X, 2), 1); | |
theta = pinv(X'*X)*X'*y; | |
end | |
function J = computeCostMulti(X, y, theta) | |
m = length(y); % number of training examples | |
J = 0; | |
J = (1/(2*m))*sum(power((X*theta - y),2)); | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment