annotate Code/Classifiers/kmeans_Singing.m @ 4:92ca03a8fa99 tip

Update to ICASSP 2013 benchmark

function [] = kmeans_Singing( inputFileName )

cd 'C:\Users\dawn\Dropbox\TestResults'
inputFileName

DEBUG = 1;
% output results file name
outputFileName = ['kmeans_' inputFileName];
masterFileOutputID = fopen( outputFileName, 'a' );

fprintf( masterFileOutputID, '\n RESULTS FILE NAME: %s\n', inputFileName);
inputFileID = fopen( inputFileName );

titleName = '';

fprintf( masterFileOutputID, '\t' );

% -------------------- get the data from the results file ---------------

lineCount = 0;
fileCount = 0;
data = [];
while( ~(feof(inputFileID)) )
    
    outputValues = [];
    thestr = fgetl(inputFileID);
    fileCount = fileCount + 1;

    % determine whether we have a positive or negative sample
    sampleEmotion( fileCount ) = 'U';
    if( ~(isempty(strfind(thestr,'pos'))))
        % sample is positive
        sampleEmotion( fileCount ) = 'P';
    elseif( ~(isempty(strfind(thestr,'neg'))))
        % sample is negative
        sampleEmotion( fileCount ) = 'N';
    else
        disp('EEEK!');
        fileCount = fileCount - 1;
%         pause;
    end

    % determine whether we have a male, female or trans sample
%     gender( fileCount ) = '?';
%     if( ~(isempty(strfind(thestr,'fem'))))
%         % gender is female
%         gender( fileCount ) = 'F';
%     elseif( ~(isempty(strfind(thestr,'male'))))
%         % gender is male
%         gender( fileCount ) = 'M';
%     elseif( ~(isempty(strfind(thestr,'trans'))))
%         % gender is trans
%         gender( fileCount ) = 'T';
%     else
%         disp('EEEK!');
%         pause;
%     end

    if(( ~(isempty(strfind(thestr,'pos')))) || ( ~(isempty(strfind(thestr,'neg')))) )
        %how many values are in the string?
%         spaces = strfind( thestr, ' ' );
        spaces = [ strfind( thestr,  sprintf('\t')) strfind( thestr, ' ' )];
        numberstr = thestr( spaces(1) : end ); % chop off the file name  
        vars = sscanf( numberstr, '%f', inf );
        data( fileCount, : ) = vars;
    end
    lineCount = lineCount + 1;
    
end
fclose(inputFileID);

% ------------  apply the k-means classifier  ------------------------

noOfClusters = 2; % we are only trying to identify positive and negative emotions


[idx ctrs]=kmeans( data, noOfClusters, 'Replicates',100,...
    'start', 'sample', 'Distance', 'cityblock');

%display results grouped by emotion
fprintf( masterFileOutputID, '\n Emotion grouping \n');
fprintf( masterFileOutputID, 'cityblock \n');
[ groupStats, groupNames ] = processKMeansResults( 'cityblock', idx, sampleEmotion, masterFileOutputID, titleName, DEBUG );
[ confusionMatrix ] = getConfusionMatrix( groupStats, groupNames, masterFileOutputID, 'cityblock' );


fprintf( masterFileOutputID, 'sqEuclidean \n');
[idx ctrs]=kmeans( data, noOfClusters, 'Replicates',100,...
    'start', 'sample', 'Distance', 'sqEuclidean');

[ groupStats, groupNames ] = processKMeansResults( 'sqEuclidean', idx, sampleEmotion, masterFileOutputID, titleName, DEBUG );
[ confusionMatrix ] = getConfusionMatrix( groupStats, groupNames, masterFileOutputID, 'sqEuclidean' );


fprintf( masterFileOutputID, 'cosine \n');
[idx ctrs]=kmeans( data, noOfClusters, 'Replicates',100,...
    'start', 'sample', 'Distance', 'cosine');

[ groupStats, groupNames ] = processKMeansResults( 'cosine', idx, sampleEmotion, masterFileOutputID, titleName, DEBUG );
[ confusionMatrix ] = getConfusionMatrix( groupStats, groupNames, masterFileOutputID, 'cosine' );


fprintf( masterFileOutputID, 'correlation \n');
[idx ctrs]=kmeans( data, noOfClusters, 'Replicates',100,...
    'start', 'sample', 'Distance', 'correlation');

[ groupStats, groupNames ] = processKMeansResults( 'correlation', idx, sampleEmotion, masterFileOutputID, titleName, DEBUG );
[ confusionMatrix ] = getConfusionMatrix( groupStats, groupNames, masterFileOutputID, 'correlation' );

% --------------------------------------------------------------------

% display results grouped by gender
% fprintf( masterFileOutputID, '\n Gender grouping \n');
% noOfClusters = 3;
% 
% [idx ctrs]=kmeans( data, noOfClusters, 'Replicates',100,...
%     'start', 'sample', 'Distance', 'cityblock');
% 
% fprintf( masterFileOutputID, 'cityblock \n');
% [ groupStats, groupNames ] = processKMeansResults( 'cityblock', idx, gender, masterFileOutputID, titleName, DEBUG );
% [ confusionMatrix ] = getConfusionMatrix( groupStats, groupNames, masterFileOutputID );
% 
% [idx ctrs]=kmeans( data, noOfClusters, 'Replicates',100,...
%     'start', 'sample', 'Distance', 'sqEuclidean');
% 
% fprintf( masterFileOutputID, 'sqEuclidean \n');
% [ groupStats, groupNames ] = processKMeansResults( 'sqEuclidean', idx, gender, masterFileOutputID, titleName, DEBUG );
% [ confusionMatrix ] = getConfusionMatrix( groupStats, groupNames, masterFileOutputID );

fprintf( masterFileOutputID, '\n' );
fclose( masterFileOutputID );

end