一、程序及函数

1.引导脚本ex3.m

%% Machine Learning Online Class - Exercise 3 | Part 1: One-vs-all

%  Instructions
%  ------------
%
%  This file contains code that helps you get started on the
%  linear exercise. You will need to complete the following functions
%  in this exericse:
%
%     lrCostFunction.m (logistic regression cost function)
%     oneVsAll.m
%     predictOneVsAll.m
%     predict.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

%% Setup the parameters you will use for this part of the exercise
input_layer_size  = 400;  % 20x20 Input Images of Digits
num_labels = 10;          % 10 labels, from 1 to 10
                          % (note that we have mapped "0" to label 10)

%% =========== Part 1: Loading and Visualizing Data =============
%  We start the exercise by first loading and visualizing the dataset.
%  You will be working with a dataset that contains handwritten digits.

% Load Training Data
fprintf('Loading and Visualizing Data ...\n')

load('ex3data1.mat'); % training data stored in arrays X, y
m = size(X, 1);

% Randomly select 100 data points to display
rand_indices = randperm(m);
sel = X(rand_indices(1:100), :);

displayData(sel);

fprintf('Program paused. Press enter to continue.\n');
pause;

%% ============ Part 2a: Vectorize Logistic Regression ============
%  In this part of the exercise, you will reuse your logistic regression
%  code from the last exercise. You task here is to make sure that your
%  regularized logistic regression implementation is vectorized. After
%  that, you will implement one-vs-all classification for the handwritten
%  digit dataset.

% Test case for lrCostFunction
fprintf('\nTesting lrCostFunction() with regularization');

theta_t = [-2; -1; 1; 2];
X_t = [ones(5,1) reshape(1:15,5,3)/10];
y_t = ([1;0;1;0;1] >= 0.5);
lambda_t = 3;
[J, grad] = lrCostFunction(theta_t, X_t, y_t, lambda_t);

fprintf('\nCost: %f\n', J);
fprintf('Expected cost: 2.534819\n');
fprintf('Gradients:\n');
fprintf(' %f \n', grad);
fprintf('Expected gradients:\n');
fprintf(' 0.146561\n -0.548558\n 0.724722\n 1.398003\n');

fprintf('Program paused. Press enter to continue.\n');
pause;
%% ============ Part 2b: One-vs-All Training ============
fprintf('\nTraining One-vs-All Logistic Regression...\n')

lambda = 0.1;
[all_theta] = oneVsAll(X, y, num_labels, lambda);

fprintf('Program paused. Press enter to continue.\n');
pause;

%% ================ Part 3: Predict for One-Vs-All ================

pred = predictOneVsAll(all_theta, X);

fprintf('\nTraining Set Accuracy: %f %% \n', sum((pred == y) == 1)/m * 100);

2.lrCostFunction.m

function [J, grad] = lrCostFunction(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
n = size(theta); % number of thetas
% You need to return the following variables correctly 

% ====================== 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
% J值的向量化表示
J = 1/m * sum(-1 * y .* log(sigmoid(X * theta)) - (ones(m,1) - y) .* log(ones(m,1) - sigmoid(X * theta))) + lambda / (2 * m) * sum(theta(2:end).^2);
grad = 1/m * (X' * (sigmoid(X * theta) - y));
% =============================================================
end

3.predictOneVsAll.m

function p = predictOneVsAll(all_theta, X)
%PREDICT Predict the label for a trained one-vs-all classifier. The labels 
%are in the range 1..K, where K = size(all_theta, 1). 
%  p = PREDICTONEVSALL(all_theta, X) will return a vector of predictions
%  for each example in the matrix X. Note that X contains the examples in
%  rows. all_theta is a matrix where the i-th row is a trained logistic
%  regression theta vector for the i-th class. You should set p to a vector
%  of values from 1..K (e.g., p = [1; 3; 1; 2] predicts classes 1, 3, 1, 2
%  for 4 examples) 

m = size(X, 1);
num_labels = size(all_theta, 1);

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

% Add ones to the X data matrix
X = [ones(m, 1) X];

% ====================== YOUR CODE HERE ======================
% Instructions: Complete the following code to make predictions using
%               your learned logistic regression parameters (one-vs-all).
%               You should set p to a vector of predictions (from 1 to
%               num_labels).
%
% Hint: This code can be done all vectorized using the max function.
%       In particular, the max function can also return the index of the 
%       max element, for more information see 'help max'. If your examples 
%       are in rows, then, you can use max(A, [], 2) to obtain the max 
%       for each row.
%       
temp_prob = zeros(num_labels,1);
for i = 1 : m
    for j = 1 : num_labels
        % 求出当前样本属于各个类的概率
        temp_prob(j) = sigmoid(all_theta(j,:) * X(i,:)');
        temp_index = find(temp_prob == max(temp_prob));
        if temp_index == 1
            p(i) = 10;
        else
            p(i) = temp_index - 1;
        end
    end
end
% ========================================================================
end

4.sigmoid.m

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

g = 1.0 ./ (1.0 + exp(-z));
end

二、运行结果