【机器学习】Octave 实现逻辑回归 Logistic Regression

function plotData(X, y)
%PLOTDATA Plots the data points X and y into a new figure 
%   PLOTDATA(x,y) plots the data points with + for the positive examples
%   and o for the negative examples. X is assumed to be a Mx2 matrix.

% Create New Figure
figure; hold on;

% ====================== YOUR CODE HERE ======================
% Instructions: Plot the positive and negative examples on a
%               2D plot, using the option ‘k+‘ for the positive
%               examples and ‘ko‘ for the negative examples.


% Find Indices of Positive and Negative Examples
pos = find(y == 1); neg = find(y == 0);
% Plot Examples
plot(X(pos, 1), X(pos, 2), ‘k+‘,‘LineWidth‘, 2, ‘MarkerSize‘, 7);
plot(X(neg, 1), X(neg, 2), ‘ko‘, ‘MarkerFaceColor‘, ‘y‘,‘MarkerSize‘, 7);



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



hold off;

end

clear ; close all; clc

%% Load Data
%  The first two columns contains the exam scores and the third column
%  contains the label.

data = load(‘ex2data1.txt‘);
X = data(:, [1, 2]); y = data(:, 3);   

%% ==================== Part 1: Plotting ====================
%  We start the exercise by first plotting the data to understand the 
%  the problem we are working with.

fprintf([‘Plotting data with + indicating (y = 1) examples and o ‘ ...
         ‘indicating (y = 0) examples.\n‘]);

plotData(X, y);

% Put some labels 
hold on;
% Labels and Legend
xlabel(‘Exam 1 score‘)
ylabel(‘Exam 2 score‘)

% Specified in plot order
legend(‘Admitted‘, ‘Not admitted‘)
hold off;

fprintf(‘\nProgram paused. Press enter to continue.\n‘);
pause;

function g = sigmoid(z)
%SIGMOID Compute sigmoid functoon
%   J = SIGMOID(z) computes the sigmoid of z.

% You need to return the following variables correctly 
g = zeros(size(z));

% ====================== YOUR CODE HERE ======================
% Instructions: Compute the sigmoid of each value of z (z can be a matrix,
%               vector or scalar).
g = 1 ./ ( 1 + exp(-z) ) ;
% =============================================================

end

function [J, grad] = costFunction(theta, X, y)
%COSTFUNCTION Compute cost and gradient for logistic regression
%   J = COSTFUNCTION(theta, X, y) computes the cost of using theta as the
%   parameter for 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
%
% Note: grad should have the same dimensions as theta
%

J= -1 * sum( y .* log( sigmoid(X*theta) ) + (1 - y ) .* log( (1 - sigmoid(X*theta)) ) ) / m ;

grad = ( X‘ * (sigmoid(X*theta) - y ) )/ m ;



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

end

function [J, grad] = costFunctionReg(theta, X, y, lambda)
%COSTFUNCTIONREG Compute cost and gradient for logistic regression with regularization
%   J = COSTFUNCTIONREG(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

theta_1=[0;theta(2:end)];  
J= -1 * sum( y .* log( sigmoid(X*theta) ) + (1 - y ) .* log( (1 - sigmoid(X*theta)) ) ) / m  + lambda/(2*m) * theta_1‘ * theta_1 ;
grad = ( X‘ * (sigmoid(X*theta) - y ) )/ m + lambda/m * theta_1 ;
      




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

end

function p = predict(theta, X)
%PREDICT Predict whether the label is 0 or 1 using learned logistic 
%regression parameters theta
%   p = PREDICT(theta, X) computes the predictions for X using a 
%   threshold at 0.5 (i.e., if sigmoid(theta‘*x) >= 0.5, predict 1)

m = size(X, 1); % Number of training examples

% You need to return the following variables correctly
p = zeros(m, 1);

% ====================== YOUR CODE HERE ======================
% Instructions: Complete the following code to make predictions using
%               your learned logistic regression parameters. 
%               You should set p to a vector of 0‘s and 1‘s
%

k = find(sigmoid( X * theta) >= 0.5 );
p(k)= 1;

% p(sigmoid( X * theta) >= 0.5) = 1;   % it‘s a more compat way.




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


end

%% ============ Part 2: Compute Cost and Gradient ============
%  In this part of the exercise, you will implement the cost and gradient
%  for logistic regression. You neeed to complete the code in 
%  costFunction.m

%  Setup the data matrix appropriately, and add ones for the intercept term
[m, n] = size(X);

% Add intercept term to x and X_test
X = [ones(m, 1) X];

% Initialize fitting parameters
initial_theta = zeros(n + 1, 1);

% Compute and display initial cost and gradient
[cost, grad] = costFunction(initial_theta, X, y);

fprintf(‘Cost at initial theta (zeros): %f\n‘, cost);
fprintf(‘Gradient at initial theta (zeros): \n‘);
fprintf(‘ %f \n‘, grad);

fprintf(‘\nProgram paused. Press enter to continue.\n‘);
pause;

%% ============= Part 3: Optimizing using fminunc  =============
%  In this exercise, you will use a built-in function (fminunc) to find the
%  optimal parameters theta.

%  Set options for fminunc
options = optimset(‘GradObj‘, ‘on‘, ‘MaxIter‘, 400);

%  Run fminunc to obtain the optimal theta
%  This function will return theta and the cost 
[theta, cost] = ...
	fminunc(@(t)(costFunction(t, X, y)), initial_theta, options);

% Print theta to screen
fprintf(‘Cost at theta found by fminunc: %f\n‘, cost);
fprintf(‘theta: \n‘);
fprintf(‘ %f \n‘, theta);

% Plot Boundary
plotDecisionBoundary(theta, X, y);

% Put some labels 
hold on;
% Labels and Legend
xlabel(‘Exam 1 score‘)
ylabel(‘Exam 2 score‘)

% Specified in plot order
legend(‘Admitted‘, ‘Not admitted‘)
hold off;

fprintf(‘\nProgram paused. Press enter to continue.\n‘);
pause;

%% ============== Part 4: Predict and Accuracies ==============
%  After learning the parameters, you‘ll like to use it to predict the outcomes
%  on unseen data. In this part, you will use the logistic regression model
%  to predict the probability that a student with score 45 on exam 1 and 
%  score 85 on exam 2 will be admitted.
%
%  Furthermore, you will compute the training and test set accuracies of 
%  our model.
%
%  Your task is to complete the code in predict.m

%  Predict probability for a student with score 45 on exam 1 
%  and score 85 on exam 2 

prob = sigmoid([1 45 85] * theta);
fprintf([‘For a student with scores 45 and 85, we predict an admission ‘ ...
         ‘probability of %f\n\n‘], prob);

% Compute accuracy on our training set
p = predict(theta, X);

fprintf(‘Train Accuracy: %f\n‘, mean(double(p == y)) * 100);

fprintf(‘\nProgram paused. Press enter to continue.\n‘);
pause;

%% Machine Learning Online Class - Exercise 2: Logistic Regression
%
%  Instructions
%  ------------
% 
%  This file contains code that helps you get started on the second part
%  of the exercise which covers regularization with logistic regression.
%
%  You will need to complete the following functions in this exericse:
%
%     sigmoid.m
%     costFunction.m
%     predict.m
%     costFunctionReg.m
%
%  For this exercise, you will not need to change any code in this file,
%  or any other files other than those mentioned above.
%

%% Initialization
clear ; close all; clc

%% Load Data
%  The first two columns contains the X values and the third column
%  contains the label (y).

data = load(‘ex2data2.txt‘);
X = data(:, [1, 2]); y = data(:, 3);

plotData(X, y);

% Put some labels 
hold on;

% Labels and Legend
xlabel(‘Microchip Test 1‘)
ylabel(‘Microchip Test 2‘)

% Specified in plot order
legend(‘y = 1‘, ‘y = 0‘)
hold off;


%% =========== Part 1: Regularized Logistic Regression ============
%  In this part, you are given a dataset with data points that are not
%  linearly separable. However, you would still like to use logistic 
%  regression to classify the data points. 
%
%  To do so, you introduce more features to use -- in particular, you add
%  polynomial features to our data matrix (similar to polynomial
%  regression).
%

% Add Polynomial Features

% Note that mapFeature also adds a column of ones for us, so the intercept
% term is handled
X = mapFeature(X(:,1), X(:,2));

% Initialize fitting parameters
initial_theta = zeros(size(X, 2), 1);

% Set regularization parameter lambda to 1
lambda = 1;

% Compute and display initial cost and gradient for regularized logistic
% regression
[cost, grad] = costFunctionReg(initial_theta, X, y, lambda);

fprintf(‘Cost at initial theta (zeros): %f\n‘, cost);

fprintf(‘\nProgram paused. Press enter to continue.\n‘);
pause;

%% ============= Part 2: Regularization and Accuracies =============
%  Optional Exercise:
%  In this part, you will get to try different values of lambda and 
%  see how regularization affects the decision coundart
%
%  Try the following values of lambda (0, 1, 10, 100).
%
%  How does the decision boundary change when you vary lambda? How does
%  the training set accuracy vary?
%

% Initialize fitting parameters
initial_theta = zeros(size(X, 2), 1);

% Set regularization parameter lambda to 1 (you should vary this)
lambda = 1;

% Set Options
options = optimset(‘GradObj‘, ‘on‘, ‘MaxIter‘, 400);

% Optimize
[theta, J, exit_flag] = ...
	fminunc(@(t)(costFunctionReg(t, X, y, lambda)), initial_theta, options);

% Plot Boundary
plotDecisionBoundary(theta, X, y);
hold on;
title(sprintf(‘lambda = %g‘, lambda))

% Labels and Legend
xlabel(‘Microchip Test 1‘)
ylabel(‘Microchip Test 2‘)

legend(‘y = 1‘, ‘y = 0‘, ‘Decision boundary‘)
hold off;

% Compute accuracy on our training set
p = predict(theta, X);

fprintf(‘Train Accuracy: %f\n‘, mean(double(p == y)) * 100);