coursera机器学习课程笔记 第七周 支持向量机 垃圾邮件分类

ex6

github:https://github.com/DLW3D/coursera-machine-learning-ex
练习文件下载地址:https://s3.amazonaws.com/spark-public/ml/exercises/on-demand/machine-learning-ex6.zip

Support Vector Machines 支持向量机

Gaussian Kernel 高斯核函数

gaussianKernel.m

function sim = gaussianKernel(x1, x2, sigma)
	x1 = x1(:); x2 = x2(:);
	sim = exp(-(x1-x2)' * (x1-x2) / 2/(sigma^2));
end

参数估计

dataset3Params.m

function [C, sigma] = dataset3Params(X, y, Xval, yval)
	para = [0.01 0.03 0.1 0.3 1 3 10 30];
	error = 999;
	for C_temp = para
	    for sigma_temp = para
	        model= svmTrain(X, y, C_temp, @(x1, x2) gaussianKernel(x1, x2, sigma_temp));
	        predictions = svmPredict(model, Xval);
	        error_temp = mean(double(predictions ~= yval));
	        if error_temp < error
	            error = error_temp;
	            C = C_temp;
	            sigma = sigma_temp;
	        end
	    end
	end
end

训练SVM

load('ex6data3.mat');

% Choose SVM Parameters
[C, sigma] = dataset3Params(X, y, Xval, yval);%1,0.1

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

svmTrain.m

function [model] = svmTrain(X, Y, C, kernelFunction, ...
                            tol, max_passes)
%SVMTRAIN Trains an SVM classifier using a simplified version of the SMO 
%algorithm. 
%   [model] = SVMTRAIN(X, Y, C, kernelFunction, tol, max_passes) trains an
%   SVM classifier and returns trained model. X is the matrix of training 
%   examples.  Each row is a training example, and the jth column holds the 
%   jth feature.  Y is a column matrix containing 1 for positive examples 
%   and 0 for negative examples.  C is the standard SVM regularization 
%   parameter.  tol is a tolerance value used for determining equality of 
%   floating point numbers. max_passes controls the number of iterations
%   over the dataset (without changes to alpha) before the algorithm quits.
%
% Note: This is a simplified version of the SMO algorithm for training
%       SVMs. In practice, if you want to train an SVM classifier, we
%       recommend using an optimized package such as:  
%
%           LIBSVM   (http://www.csie.ntu.edu.tw/~cjlin/libsvm/)
%           SVMLight (http://svmlight.joachims.org/)
%
%

if ~exist('tol', 'var') || isempty(tol)
    tol = 1e-3;
end

if ~exist('max_passes', 'var') || isempty(max_passes)
    max_passes = 5;
end

% Data parameters
m = size(X, 1);
n = size(X, 2);

% Map 0 to -1
Y(Y==0) = -1;

% Variables
alphas = zeros(m, 1);
b = 0;
E = zeros(m, 1);
passes = 0;
eta = 0;
L = 0;
H = 0;

% Pre-compute the Kernel Matrix since our dataset is small
% (in practice, optimized SVM packages that handle large datasets
%  gracefully will _not_ do this)
% 
% We have implemented optimized vectorized version of the Kernels here so
% that the svm training will run faster.
if strcmp(func2str(kernelFunction), 'linearKernel')
    % Vectorized computation for the Linear Kernel
    % This is equivalent to computing the kernel on every pair of examples
    K = X*X';
elseif strfind(func2str(kernelFunction), 'gaussianKernel')
    % Vectorized RBF Kernel
    % This is equivalent to computing the kernel on every pair of examples
    X2 = sum(X.^2, 2);
    K = bsxfun(@plus, X2, bsxfun(@plus, X2', - 2 * (X * X')));
    K = kernelFunction(1, 0) .^ K;
else
    % Pre-compute the Kernel Matrix
    % The following can be slow due to the lack of vectorization
    K = zeros(m);
    for i = 1:m
        for j = i:m
             K(i,j) = kernelFunction(X(i,:)', X(j,:)');
             K(j,i) = K(i,j); %the matrix is symmetric
        end
    end
end

% Train
fprintf('\nTraining ...');
dots = 12;
while passes < max_passes,
            
    num_changed_alphas = 0;
    for i = 1:m,
        
        % Calculate Ei = f(x(i)) - y(i) using (2). 
        % E(i) = b + sum (X(i, :) * (repmat(alphas.*Y,1,n).*X)') - Y(i);
        E(i) = b + sum (alphas.*Y.*K(:,i)) - Y(i);
        
        if ((Y(i)*E(i) < -tol && alphas(i) < C) || (Y(i)*E(i) > tol && alphas(i) > 0)),
            
            % In practice, there are many heuristics one can use to select
            % the i and j. In this simplified code, we select them randomly.
            j = ceil(m * rand());
            while j == i,  % Make sure i \neq j
                j = ceil(m * rand());
            end

            % Calculate Ej = f(x(j)) - y(j) using (2).
            E(j) = b + sum (alphas.*Y.*K(:,j)) - Y(j);

            % Save old alphas
            alpha_i_old = alphas(i);
            alpha_j_old = alphas(j);
            
            % Compute L and H by (10) or (11). 
            if (Y(i) == Y(j)),
                L = max(0, alphas(j) + alphas(i) - C);
                H = min(C, alphas(j) + alphas(i));
            else
                L = max(0, alphas(j) - alphas(i));
                H = min(C, C + alphas(j) - alphas(i));
            end
           
            if (L == H),
                % continue to next i. 
                continue;
            end

            % Compute eta by (14).
            eta = 2 * K(i,j) - K(i,i) - K(j,j);
            if (eta >= 0),
                % continue to next i. 
                continue;
            end
            
            % Compute and clip new value for alpha j using (12) and (15).
            alphas(j) = alphas(j) - (Y(j) * (E(i) - E(j))) / eta;
            
            % Clip
            alphas(j) = min (H, alphas(j));
            alphas(j) = max (L, alphas(j));
            
            % Check if change in alpha is significant
            if (abs(alphas(j) - alpha_j_old) < tol),
                % continue to next i. 
                % replace anyway
                alphas(j) = alpha_j_old;
                continue;
            end
            
            % Determine value for alpha i using (16). 
            alphas(i) = alphas(i) + Y(i)*Y(j)*(alpha_j_old - alphas(j));
            
            % Compute b1 and b2 using (17) and (18) respectively. 
            b1 = b - E(i) ...
                 - Y(i) * (alphas(i) - alpha_i_old) *  K(i,j)' ...
                 - Y(j) * (alphas(j) - alpha_j_old) *  K(i,j)';
            b2 = b - E(j) ...
                 - Y(i) * (alphas(i) - alpha_i_old) *  K(i,j)' ...
                 - Y(j) * (alphas(j) - alpha_j_old) *  K(j,j)';

            % Compute b by (19). 
            if (0 < alphas(i) && alphas(i) < C),
                b = b1;
            elseif (0 < alphas(j) && alphas(j) < C),
                b = b2;
            else
                b = (b1+b2)/2;
            end

            num_changed_alphas = num_changed_alphas + 1;

        end
        
    end
    
    if (num_changed_alphas == 0),
        passes = passes + 1;
    else
        passes = 0;
    end

    fprintf('.');
    dots = dots + 1;
    if dots > 78
        dots = 0;
        fprintf('\n');
    end
    if exist('OCTAVE_VERSION')
        fflush(stdout);
    end
end
fprintf(' Done! \n\n');

% Save the model
idx = alphas > 0;
model.X= X(idx,:);
model.y= Y(idx);
model.kernelFunction = kernelFunction;
model.b= b;
model.alphas= alphas(idx);
model.w = ((alphas.*Y)'*X)';

end

visualizeBoundary.m

function visualizeBoundary(X, y, model, varargin)
%VISUALIZEBOUNDARY plots a non-linear decision boundary learned by the SVM
%   VISUALIZEBOUNDARYLINEAR(X, y, model) plots a non-linear decision 
%   boundary learned by the SVM and overlays the data on it

% Plot the training data on top of the boundary
plotData(X, y)

% Make classification predictions over a grid of values
x1plot = linspace(min(X(:,1)), max(X(:,1)), 100)';
x2plot = linspace(min(X(:,2)), max(X(:,2)), 100)';
[X1, X2] = meshgrid(x1plot, x2plot);
vals = zeros(size(X1));
for i = 1:size(X1, 2)
   this_X = [X1(:, i), X2(:, i)];
   vals(:, i) = svmPredict(model, this_X);
end

% Plot the SVM boundary
hold on
contour(X1, X2, vals, [0.5 0.5], 'b');
hold off;

end

Spam Classification with SVMs 基于SVM的垃圾邮件分类

Process Email 邮件预处理

In processEmail.m, we have implemented the following email prepro-
cessing and normalization steps:
• Lower-casing: The entire email is converted into lower case, so
that captialization is ignored (e.g., IndIcaTE is treated the same as
Indicate).
• Stripping HTML: All HTML tags are removed from the emails.
Many emails often come with HTML formatting; we remove all the
HTML tags, so that only the content remains.
• Normalizing URLs: All URLs are replaced with the text “httpaddr”.
• Normalizing Email Addresses: All email addresses are replaced
with the text “emailaddr”.
• Normalizing Numbers: All numbers are replaced with the text
“number”.
• Normalizing Dollars: All dollar signs ($) are replaced with the text
“dollar”.
• Word Stemming: Words are reduced to their stemmed form. For ex-
ample, “discount”, “discounts”, “discounted” and “discounting” are all
replaced with “discount”. Sometimes, the Stemmer actually strips off
additional characters from the end, so “include”, “includes”, “included”,
and “including” are all replaced with “includ”.
• Removal of non-words: Non-words and punctuation have been re-
moved. All white spaces (tabs, newlines, spaces) have all been trimmed
to a single space character.

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
	for i = 1:length(vocabList)
	    if strcmp(vocabList(i),str)
	        word_indices= [word_indices; i];
	    end
	end

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


    % 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

处理邮件特征

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;

x = zeros(n, 1);
for i = word_indices
    x(i) = x(i) + 1;
end
end

SVM Predict 通过SVM预测

svmPredict.m

function pred = svmPredict(model, X)
%SVMPREDICT returns a vector of predictions using a trained SVM model
%(svmTrain). 
%   pred = SVMPREDICT(model, X) returns a vector of predictions using a 
%   trained SVM model (svmTrain). X is a mxn matrix where there each 
%   example is a row. model is a svm model returned from svmTrain.
%   predictions pred is a m x 1 column of predictions of {0, 1} values.
%

% Check if we are getting a column vector, if so, then assume that we only
% need to do prediction for a single example
if (size(X, 2) == 1)
    % Examples should be in rows
    X = X';
end

% Dataset 
m = size(X, 1);
p = zeros(m, 1);
pred = zeros(m, 1);

if strcmp(func2str(model.kernelFunction), 'linearKernel')
    % We can use the weights and bias directly if working with the 
    % linear kernel
    p = X * model.w + model.b;
elseif strfind(func2str(model.kernelFunction), 'gaussianKernel')
    % Vectorized RBF Kernel
    % This is equivalent to computing the kernel on every pair of examples
    X1 = sum(X.^2, 2);
    X2 = sum(model.X.^2, 2)';
    K = bsxfun(@plus, X1, bsxfun(@plus, X2, - 2 * X * model.X'));
    K = model.kernelFunction(1, 0) .^ K;
    K = bsxfun(@times, model.y', K);
    K = bsxfun(@times, model.alphas', K);
    p = sum(K, 2);
else
    % Other Non-linear kernel
    for i = 1:m
        prediction = 0;
        for j = 1:size(model.X, 1)
            prediction = prediction + ...
                model.alphas(j) * model.y(j) * ...
                model.kernelFunction(X(i,:)', model.X(j,:)');
        end
        p(i) = prediction + model.b;
    end
end

% Convert predictions into 0 / 1
pred(p >= 0) =  1;
pred(p <  0) =  0;

end

运行预测

%% 训练
load('spamTrain.mat');

fprintf('\nTraining Linear SVM (Spam Classification)\n')
fprintf('(this may take 1 to 2 minutes) ...\n')

C = 0.1;
model = svmTrain(X, y, C, @linearKernel);

p = svmPredict(model, X);

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

%% 测试
load('spamTest.mat');

fprintf('\nEvaluating the trained Linear SVM on a test set ...\n')

p = svmPredict(model, Xtest);

fprintf('Test Accuracy: %f\n', mean(double(p == ytest)) * 100);

%% 预测
filename = 'spamSample1.txt';

% Read and predict
file_contents = readFile(filename);
word_indices  = processEmail(file_contents);
x = emailFeatures(word_indices);
p = svmPredict(model, x);

fprintf('\nProcessed %s\n\nSpam Classification: %d\n', filename, p);
fprintf('(1 indicates spam, 0 indicates not spam)\n\n');