Machine learning practice of ANg(ex7)

for self-use

Code

findClosestCentroids

function idx = findClosestCentroids(X, centroids)
%FINDCLOSESTCENTROIDS computes the centroid memberships for every example
%   idx = FINDCLOSESTCENTROIDS (X, centroids) returns the closest centroids
%   in idx for a dataset X where each row is a single example. idx = m x 1 
%   vector of centroid assignments (i.e. each entry in range [1..K])
%

% Set K
K = size(centroids, 1);

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

% ====================== YOUR CODE HERE ======================
% Instructions: Go over every example, find its closest centroid, and store
%               the index inside idx at the appropriate location.
%               Concretely, idx(i) should contain the index of the centroid
%               closest to example i. Hence, it should be a value in the 
%               range 1..K
%
% Note: You can use a for-loop over the examples to compute this.
%



for i = 1:size(X,1),
  minError = sum((X(i,:)-centroids(1,:)).^2);
  minIdx = 1;
  for j = 2:K,
    error = sum((X(i,:)-centroids(j,:)).^2);
    if(error<minError)
      minError = error;
      minIdx = j;
    endif
  idx(i) = minIdx;%找到每一个X对应的centroid(i)
  endfor
endfor





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

end

computeCentroids

function centroids = computeCentroids(X, idx, K)
%COMPUTECENTROIDS returns the new centroids by computing the means of the 
%data points assigned to each centroid.
%   centroids = COMPUTECENTROIDS(X, idx, K) returns the new centroids by 
%   computing the means of the data points assigned to each centroid. It is
%   given a dataset X where each row is a single data point, a vector
%   idx of centroid assignments (i.e. each entry in range [1..K]) for each
%   example, and K, the number of centroids. You should return a matrix
%   centroids, where each row of centroids is the mean of the data points
%   assigned to it.
%

% Useful variables
[m n] = size(X);

% You need to return the following variables correctly.
centroids = zeros(K, n);


% ====================== YOUR CODE HERE ======================
% Instructions: Go over every centroid and compute mean of all points that
%               belong to it. Concretely, the row vector centroids(i, :)
%               should contain the mean of the data points assigned to
%               centroid i.
%
% Note: You can use a for-loop over the centroids to compute this.
%


%将centroid(i)变更为现cluster(i)中所有X的距离均值点
for i = 1:K,
  C = sum(idx==i);% 是属于centroids i的样本总数
  if(C~=0) %注意分母不能为0
    centroids(i,:) = mean(X(find(idx==i),:));
  end
end





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


end

kMeanInitCentroids

function centroids = kMeansInitCentroids(X, K)
%KMEANSINITCENTROIDS This function initializes K centroids that are to be 
%used in K-Means on the dataset X
%   centroids = KMEANSINITCENTROIDS(X, K) returns K initial centroids to be
%   used with the K-Means on the dataset X
%

% You should return this values correctly
centroids = zeros(K, size(X, 2));

% ====================== YOUR CODE HERE ======================
% Instructions: You should set centroids to randomly chosen examples from
%               the dataset X
%

% Initialize the centroids to be random examples
% Randomly reorder the indices of examples
randidx = randperm(size(X, 1));
% Take the first K examples as centroids
centroids = X(randidx(1:K), :);



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

end

ex7

%% Machine Learning Online Class
%  Exercise 7 | Principle Component Analysis and K-Means Clustering
%
%  Instructions
%  ------------
%
%  This file contains code that helps you get started on the
%  exercise. You will need to complete the following functions:
%
%     pca.m
%     projectData.m
%     recoverData.m
%     computeCentroids.m
%     findClosestCentroids.m
%     kMeansInitCentroids.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

%% ================= Part 1: Find Closest Centroids ====================
%  To help you implement K-Means, we have divided the learning algorithm 
%  into two functions -- findClosestCentroids and computeCentroids. In this
%  part, you should complete the code in the findClosestCentroids function. 
%
fprintf('Finding closest centroids.\n\n');

% Load an example dataset that we will be using
load('ex7data2.mat');

% Select an initial set of centroids
K = 3; % 3 Centroids
initial_centroids = [3 3; 6 2; 8 5];

% Find the closest centroids for the examples using the
% initial_centroids
idx = findClosestCentroids(X, initial_centroids);

fprintf('Closest centroids for the first 3 examples: \n')
fprintf(' %d', idx(1:3));
fprintf('\n(the closest centroids should be 1, 3, 2 respectively)\n');

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

%% ===================== Part 2: Compute Means =========================
%  After implementing the closest centroids function, you should now
%  complete the computeCentroids function.
%
fprintf('\nComputing centroids means.\n\n');

%  Compute means based on the closest centroids found in the previous part.
centroids = computeCentroids(X, idx, K);

fprintf('Centroids computed after initial finding of closest centroids: \n')
fprintf(' %f %f \n' , centroids');
fprintf('\n(the centroids should be\n');
fprintf('   [ 2.428301 3.157924 ]\n');
fprintf('   [ 5.813503 2.633656 ]\n');
fprintf('   [ 7.119387 3.616684 ]\n\n');

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


%% =================== Part 3: K-Means Clustering ======================
%  After you have completed the two functions computeCentroids and
%  findClosestCentroids, you have all the necessary pieces to run the
%  kMeans algorithm. In this part, you will run the K-Means algorithm on
%  the example dataset we have provided. 
%
fprintf('\nRunning K-Means clustering on example dataset.\n\n');

% Load an example dataset
load('ex7data2.mat');

% Settings for running K-Means
K = 3;
max_iters = 10;

% For consistency, here we set centroids to specific values
% but in practice you want to generate them automatically, such as by
% settings them to be random examples (as can be seen in
% kMeansInitCentroids).
initial_centroids = [3 3; 6 2; 8 5];

% Run K-Means algorithm. The 'true' at the end tells our function to plot
% the progress of K-Means
[centroids, idx] = runkMeans(X, initial_centroids, max_iters, true);
fprintf('\nK-Means Done.\n\n');

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

%% ============= Part 4: K-Means Clustering on Pixels ===============
%  In this exercise, you will use K-Means to compress an image. To do this,
%  you will first run K-Means on the colors of the pixels in the image and
%  then you will map each pixel onto its closest centroid.
%  
%  You should now complete the code in kMeansInitCentroids.m
%

fprintf('\nRunning K-Means clustering on pixels from an image.\n\n');

%  Load an image of a bird
A = double(imread('bird_small.png'));

% If imread does not work for you, you can try instead
%   load ('bird_small.mat');

A = A / 255; % Divide by 255 so that all values are in the range 0 - 1

% Size of the image
img_size = size(A);

% Reshape the image into an Nx3 matrix where N = number of pixels.
% Each row will contain the Red, Green and Blue pixel values
% This gives us our dataset matrix X that we will use K-Means on.
X = reshape(A, img_size(1) * img_size(2), 3);

% Run your K-Means algorithm on this data
% You should try different values of K and max_iters here
K = 16; 
max_iters = 10;

% When using K-Means, it is important the initialize the centroids
% randomly. 
% You should complete the code in kMeansInitCentroids.m before proceeding
initial_centroids = kMeansInitCentroids(X, K);

% Run K-Means
[centroids, idx] = runkMeans(X, initial_centroids, max_iters);

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


%% ================= Part 5: Image Compression ======================
%  In this part of the exercise, you will use the clusters of K-Means to
%  compress an image. To do this, we first find the closest clusters for
%  each example. After that, we 

fprintf('\nApplying K-Means to compress an image.\n\n');

% Find closest cluster members
idx = findClosestCentroids(X, centroids);

% Essentially, now we have represented the image X as in terms of the
% indices in idx. 

% We can now recover the image from the indices (idx) by mapping each pixel
% (specified by its index in idx) to the centroid value
X_recovered = centroids(idx,:);

% Reshape the recovered image into proper dimensions
X_recovered = reshape(X_recovered, img_size(1), img_size(2), 3);

% Display the original image 
subplot(1, 2, 1);
imagesc(A); 
title('Original');

% Display compressed image side by side
subplot(1, 2, 2);
imagesc(X_recovered)
title(sprintf('Compressed, with %d colors.', K));


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

Result