octave2python: ex6

網路上真的大神們一堆阿!!! 娘子～～快跟牛魔王出來看上帝

Gaussian Kernel

• Octave

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;

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

magnitude = sum((x2-x1).^2)
sim = e^(-magnitude/(2 * sigma^2))

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

• python

def gaussianKernel(x1, x2, sigma):
    """
    Computes the radial basis function
    Returns a radial basis function kernel between x1 and x2.
    
    Parameters
    ----------
    x1 :  numpy ndarray
        A vector of size (n, ), representing the first datapoint.
    
    x2 : numpy ndarray
        A vector of size (n, ), representing the second datapoint.
    
    sigma : float
        The bandwidth parameter for the Gaussian kernel.

    Returns
    -------
    sim : float
        The computed RBF between the two provided data points.
    
    Instructions
    ------------
    Fill in this function to return the similarity between `x1` and `x2`
    computed using a Gaussian kernel with bandwidth `sigma`.
    """
    sim = 0
    # ====================== YOUR CODE HERE ======================
    magnitude = np.sum((x1 - x2)**2)
    sim = np.exp(-magnitude/ (2 * (sigma**2)))

    # =============================================================
    return sim

Parameters (C, Sigma) for dataset 3

• Octave

function [C, sigma] = dataset3Params(X, y, Xval, yval)
%DATASET3PARAMS 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] = DATASET3PARAMS(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;
sigma = 0.3;

% ====================== 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))
%

values = [0.01 0.03 0.1 0.3 1 3 10 30];

error_min = inf;


fprintf('chill hommie i am looking for C and sigma, yo values\n');
for C = values
	for sigma = values
		fprintf('.');
		model = svmTrain(X, y, C, @(x1, x2) gaussianKernel(x1, x2, sigma));
	    err = mean(double(svmPredict(model, Xval) ~= yval));
        if (err <= error_min )
          C_final     = C;
          sigma_final = sigma;
          error_min   = err;
          fprintf('new min found C, sigma = %f, %f with error = %f', C_final, sigma_final, error_min)
    end
  end
end
C     = C_final;
sigma = sigma_final;

fprintf('Best value C, sigma = [%f %f] with prediction error = %f\n', C, sigma, error_min);



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

end

• python

Email preprocessing

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.
    %

    for i = 1:length(vocabList)
        if(strcmp(str, vocabList{i}))
            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

• python