Machine Learning week 7 quiz: programming assignment-Support Vector Machines

一、ex6.m

%% Machine Learning Online Class
%  Exercise 6 | Support Vector Machines
%
%  Instructions
%  ------------
% 
%  This file contains code that helps you get started on the
%  exercise. You will need to complete the following functions:
%
%     gaussianKernel.m
%     dataset3Params.m
%     processEmail.m
%     emailFeatures.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: Loading and Visualizing Data ================
%  We start the exercise by first loading and visualizing the dataset. 
%  The following code will load the dataset into your environment and plot
%  the data.
%

fprintf('Loading and Visualizing Data ...\n')

% Load from ex6data1: 
% You will have X, y in your environment
load('ex6data1.mat');

% Plot training data
plotData(X, y);

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

%% ==================== Part 2: Training Linear SVM ====================
%  The following code will train a linear SVM on the dataset and plot the
%  decision boundary learned.
%

% Load from ex6data1: 
% You will have X, y in your environment
load('ex6data1.mat');

fprintf('\nTraining Linear SVM ...\n')

% You should try to change the C value below and see how the decision
% boundary varies (e.g., try C = 1000)
C = 1;
model = svmTrain(X, y, C, @linearKernel, 1e-3, 20);
visualizeBoundaryLinear(X, y, model);

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

%% =============== Part 3: Implementing Gaussian Kernel ===============
%  You will now implement the Gaussian kernel to use
%  with the SVM. You should complete the code in gaussianKernel.m
%
fprintf('\nEvaluating the Gaussian Kernel ...\n')

x1 = [1 2 1]; x2 = [0 4 -1]; sigma = 2;
sim = gaussianKernel(x1, x2, sigma);

fprintf(['Gaussian Kernel between x1 = [1; 2; 1], x2 = [0; 4; -1], sigma = 0.5 :' ...
         '\n\t%f\n(this value should be about 0.324652)\n'], sim);

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

%% =============== Part 4: Visualizing Dataset 2 ================
%  The following code will load the next dataset into your environment and 
%  plot the data. 
%

fprintf('Loading and Visualizing Data ...\n')

% Load from ex6data2: 
% You will have X, y in your environment
load('ex6data2.mat');

% Plot training data
plotData(X, y);

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

%% ========== Part 5: Training SVM with RBF Kernel (Dataset 2) ==========
%  After you have implemented the kernel, we can now use it to train the 
%  SVM classifier.
% 
fprintf('\nTraining SVM with RBF Kernel (this may take 1 to 2 minutes) ...\n');

% Load from ex6data2: 
% You will have X, y in your environment
load('ex6data2.mat');

% SVM Parameters
C = 1; sigma = 0.1;

% We set the tolerance and max_passes lower here so that the code will run
% faster. However, in practice, you will want to run the training to
% convergence.
model= svmTrain(X, y, C, @(x1, x2) gaussianKernel(x1, x2, sigma)); 
visualizeBoundary(X, y, model);

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

%% =============== Part 6: Visualizing Dataset 3 ================
%  The following code will load the next dataset into your environment and 
%  plot the data. 
%

fprintf('Loading and Visualizing Data ...\n')

% Load from ex6data3: 
% You will have X, y in your environment
load('ex6data3.mat');

% Plot training data
plotData(X, y);

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

%% ========== Part 7: Training SVM with RBF Kernel (Dataset 3) ==========

%  This is a different dataset that you can use to experiment with. Try
%  different values of C and sigma here.
% 

% Load from ex6data3: 
% You will have X, y in your environment
load('ex6data3.mat');

% Try different SVM Parameters here
[C, sigma] = dataset3Params(X, y, Xval, yval);

% Train the SVM
model= svmTrain(X, y, C, @(x1, x2) gaussianKernel(x1, x2, sigma));
visualizeBoundary(X, y, model);

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

二、gaussianKernel.m

function sim = gaussianKernel(x1, x2, sigma)
%RBFKERNEL returns a radial basis function kernel between x1 and x2
%   sim = gaussianKernel(x1, x2) returns a gaussian kernel between x1 and x2
%   and returns the value in sim

% Ensure that x1 and x2 are column vectors
x1 = x1(:); x2 = x2(:);

% You need to return the following variables correctly.
sim = 0; % 1*1

% ====================== YOUR CODE HERE ======================
% Instructions: Fill in this function to return the similarity between x1
%               and x2 computed using a Gaussian kernel with bandwidth
%               sigma
%
%

square_diff = sum((x1 - x2) .^ 2);
sim = exp(-square_diff / 2 /(sigma^2));




% =============================================================
    
end

三、dataset3Params.m

function [C, sigma] = dataset3Params(X, y, Xval, yval)
%EX6PARAMS returns your choice of C and sigma for Part 3 of the exercise
%where you select the optimal (C, sigma) learning parameters to use for SVM
%with RBF kernel
%   [C, sigma] = EX6PARAMS(X, y, Xval, yval) returns your choice of C and 
%   sigma. You should complete this function to return the optimal C and 
%   sigma based on a cross-validation set.
%

% You need to return the following variables correctly.
C = 1; % 1*1
sigma = 0.3; % 1*1

% ====================== YOUR CODE HERE ======================
% Instructions: Fill in this function to return the optimal C and sigma
%               learning parameters found using the cross validation set.
%               You can use svmPredict to predict the labels on the cross
%               validation set. For example, 
%                   predictions = svmPredict(model, Xval);
%               will return the predictions on the cross validation set.
%
%  Note: You can compute the prediction error using 
%        mean(double(predictions ~= yval))
%

set_values = [0.01, 0.03, 0.1, 0.3, 1, 3, 10, 30];
results = [];
long = numel(set_values);
for i = 1:long
for j = 1:long

C_temp = set_values(i);
sigma_temp = set_values(j);

model = svmTrain(X, y, C_temp, @(x1, x2) gaussianKernel(x1, x2, sigma_temp));
predictions = svmPredict(model, Xval);

pre_error = mean(double(predictions ~= yval));

results = [results; C_temp, sigma_temp, pre_error];
end
end

[smallest_error, idx] = min(results(:, 3));
C = results(idx, 1);
sigma = results(idx, 2);
% =========================================================================

end

四、processEmail.m

function word_indices = processEmail(email_contents)
%PROCESSEMAIL preprocesses a the body of an email and
%returns a list of word_indices 
%   word_indices = PROCESSEMAIL(email_contents) preprocesses 
%   the body of an email and returns a list of indices of the 
%   words contained in the email. 
%

% Load Vocabulary
vocabList = getVocabList();

% Init return value
word_indices = [];

% ========================== Preprocess Email ===========================

% Find the Headers ( \n\n and remove )
% Uncomment the following lines if you are working with raw emails with the
% full headers

% hdrstart = strfind(email_contents, ([char(10) char(10)]));
% email_contents = email_contents(hdrstart(1):end);

% Lower case
email_contents = lower(email_contents);

% Strip all HTML
% Looks for any expression that starts with < and ends with > and replace
% and does not have any < or > in the tag it with a space
email_contents = regexprep(email_contents, '<[^<>]+>', ' ');

% Handle Numbers
% Look for one or more characters between 0-9
email_contents = regexprep(email_contents, '[0-9]+', 'number');

% Handle URLS
% Look for strings starting with http:// or https://
email_contents = regexprep(email_contents, ...
                           '(http|https)://[^\s]*', 'httpaddr');

% Handle Email Addresses
% Look for strings with @ in the middle
email_contents = regexprep(email_contents, '[^\s]+@[^\s]+', 'emailaddr');

% Handle $ sign
email_contents = regexprep(email_contents, '[$]+', 'dollar');


% ========================== Tokenize Email ===========================

% Output the email to screen as well
fprintf('\n==== Processed Email ====\n\n');

% Process file
l = 0;

while ~isempty(email_contents)

    % Tokenize and also get rid of any punctuation
    [str, email_contents] = ...
       strtok(email_contents, ...
              [' @$/#.-:&*+=[]?!(){},''">_<;%' char(10) char(13)]);
   
    % Remove any non alphanumeric characters
    str = regexprep(str, '[^a-zA-Z0-9]', '');

    % Stem the word 
    % (the porterStemmer sometimes has issues, so we use a try catch block)
    try str = porterStemmer(strtrim(str)); 
    catch str = ''; continue;
    end;

    % Skip the word if it is too short
    if length(str) < 1
       continue;
    end

    % Look up the word in the dictionary and add to word_indices if
    % found
    % ====================== YOUR CODE HERE ======================
    % Instructions: Fill in this function to add the index of str to
    %               word_indices if it is in the vocabulary. At this point
    %               of the code, you have a stemmed word from the email in
    %               the variable str. You should look up str in the
    %               vocabulary list (vocabList). If a match exists, you
    %               should add the index of the word to the word_indices
    %               vector. Concretely, if str = 'action', then you should
    %               look up the vocabulary list to find where in vocabList
    %               'action' appears. For example, if vocabList{18} =
    %               'action', then, you should add 18 to the word_indices 
    %               vector (e.g., word_indices = [word_indices ; 18]; ).
    % 
    % Note: vocabList{idx} returns a the word with index idx in the
    %       vocabulary list.
    % 
    % Note: You can use strcmp(str1, str2) to compare two strings (str1 and
    %       str2). It will return 1 only if the two strings are equivalent.
    %

%%%%%%%%%%%%%%%%%%%%% NOT CORRECT %%%%%%%%%%%%%%%%%%%%%
%str2 = str(:);
%long_dic = numel(vocabList2);
%long_email = numel(str2);

%for i = 1:long_email
%for j = 1:long_dic
%if 1 == strcmp(str2(i), vocabList2(j))
%word_indices = [word_indices ; j];
%break;
%end % if-end
%end
%end
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%CORRECT
word_indices = [word_indices, find(ismember(vocabList, str))];





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


    % Print to screen, ensuring that the output lines are not too long
    if (l + length(str) + 1) > 78
        fprintf('\n');
        l = 0;
    end
    fprintf('%s ', str);
    l = l + length(str) + 1;

end

% Print footer
fprintf('\n\n=========================\n');

end

五、emailFeatures.m

function x = emailFeatures(word_indices)
%EMAILFEATURES takes in a word_indices vector and produces a feature vector
%from the word indices
%   x = EMAILFEATURES(word_indices) takes in a word_indices vector and 
%   produces a feature vector from the word indices. 

% Total number of words in the dictionary
n = 1899;

% You need to return the following variables correctly.
x = zeros(n, 1); % n*1

% ====================== YOUR CODE HERE ======================
% Instructions: Fill in this function to return a feature vector for the
%               given email (word_indices). To help make it easier to 
%               process the emails, we have have already pre-processed each
%               email and converted each word in the email into an index in
%               a fixed dictionary (of 1899 words). The variable
%               word_indices contains the list of indices of the words
%               which occur in one email.
% 
%               Concretely, if an email has the text:
%
%                  The quick brown fox jumped over the lazy dog.
%
%               Then, the word_indices vector for this text might look 
%               like:
%               
%                   60  100   33   44   10     53  60  58   5
%
%               where, we have mapped each word onto a number, for example:
%
%                   the   -- 60
%                   quick -- 100
%                   ...
%
%              (note: the above numbers are just an example and are not the
%               actual mappings).
%
%              Your task is take one such word_indices vector and construct
%              a binary feature vector that indicates whether a particular
%              word occurs in the email. That is, x(i) = 1 when word i
%              is present in the email. Concretely, if the word 'the' (say,
%              index 60) appears in the email, then x(60) = 1. The feature
%              vector should look like:
%
%              x = [ 0 0 0 0 1 0 0 0 ... 0 0 0 0 1 ... 0 0 0 1 0 ..];
%
%


x([word_indices]) = 1;





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

end

六、submit results