Dawn@4: function [] = kmeans_Singing( inputFileName )
Dawn@4: 
Dawn@4: cd 'C:\Users\dawn\Dropbox\TestResults'
Dawn@4: inputFileName
Dawn@4: 
Dawn@4: DEBUG = 1;
Dawn@4: % output results file name
Dawn@4: outputFileName = ['kmeans_' inputFileName];
Dawn@4: masterFileOutputID = fopen( outputFileName, 'a' );
Dawn@4: 
Dawn@4: fprintf( masterFileOutputID, '\n RESULTS FILE NAME: %s\n', inputFileName);
Dawn@4: inputFileID = fopen( inputFileName );
Dawn@4: 
Dawn@4: titleName = '';
Dawn@4: 
Dawn@4: fprintf( masterFileOutputID, '\t' );
Dawn@4: 
Dawn@4: % -------------------- get the data from the results file ---------------
Dawn@4: 
Dawn@4: lineCount = 0;
Dawn@4: fileCount = 0;
Dawn@4: data = [];
Dawn@4: while( ~(feof(inputFileID)) )
Dawn@4:     
Dawn@4:     outputValues = [];
Dawn@4:     thestr = fgetl(inputFileID);
Dawn@4:     fileCount = fileCount + 1;
Dawn@4: 
Dawn@4:     % determine whether we have a positive or negative sample
Dawn@4:     sampleEmotion( fileCount ) = 'U';
Dawn@4:     if( ~(isempty(strfind(thestr,'pos'))))
Dawn@4:         % sample is positive
Dawn@4:         sampleEmotion( fileCount ) = 'P';
Dawn@4:     elseif( ~(isempty(strfind(thestr,'neg'))))
Dawn@4:         % sample is negative
Dawn@4:         sampleEmotion( fileCount ) = 'N';
Dawn@4:     else
Dawn@4:         disp('EEEK!');
Dawn@4:         fileCount = fileCount - 1;
Dawn@4: %         pause;
Dawn@4:     end
Dawn@4: 
Dawn@4:     % determine whether we have a male, female or trans sample
Dawn@4: %     gender( fileCount ) = '?';
Dawn@4: %     if( ~(isempty(strfind(thestr,'fem'))))
Dawn@4: %         % gender is female
Dawn@4: %         gender( fileCount ) = 'F';
Dawn@4: %     elseif( ~(isempty(strfind(thestr,'male'))))
Dawn@4: %         % gender is male
Dawn@4: %         gender( fileCount ) = 'M';
Dawn@4: %     elseif( ~(isempty(strfind(thestr,'trans'))))
Dawn@4: %         % gender is trans
Dawn@4: %         gender( fileCount ) = 'T';
Dawn@4: %     else
Dawn@4: %         disp('EEEK!');
Dawn@4: %         pause;
Dawn@4: %     end
Dawn@4: 
Dawn@4:     if(( ~(isempty(strfind(thestr,'pos')))) || ( ~(isempty(strfind(thestr,'neg')))) )
Dawn@4:         %how many values are in the string?
Dawn@4: %         spaces = strfind( thestr, ' ' );
Dawn@4:         spaces = [ strfind( thestr,  sprintf('\t')) strfind( thestr, ' ' )];
Dawn@4:         numberstr = thestr( spaces(1) : end ); % chop off the file name  
Dawn@4:         vars = sscanf( numberstr, '%f', inf );
Dawn@4:         data( fileCount, : ) = vars;
Dawn@4:     end
Dawn@4:     lineCount = lineCount + 1;
Dawn@4:     
Dawn@4: end
Dawn@4: fclose(inputFileID);
Dawn@4: 
Dawn@4: % ------------  apply the k-means classifier  ------------------------
Dawn@4: 
Dawn@4: noOfClusters = 2; % we are only trying to identify positive and negative emotions
Dawn@4: 
Dawn@4: 
Dawn@4: [idx ctrs]=kmeans( data, noOfClusters, 'Replicates',100,...
Dawn@4:     'start', 'sample', 'Distance', 'cityblock');
Dawn@4: 
Dawn@4: %display results grouped by emotion
Dawn@4: fprintf( masterFileOutputID, '\n Emotion grouping \n');
Dawn@4: fprintf( masterFileOutputID, 'cityblock \n');
Dawn@4: [ groupStats, groupNames ] = processKMeansResults( 'cityblock', idx, sampleEmotion, masterFileOutputID, titleName, DEBUG );
Dawn@4: [ confusionMatrix ] = getConfusionMatrix( groupStats, groupNames, masterFileOutputID, 'cityblock' );
Dawn@4: 
Dawn@4: 
Dawn@4: fprintf( masterFileOutputID, 'sqEuclidean \n');
Dawn@4: [idx ctrs]=kmeans( data, noOfClusters, 'Replicates',100,...
Dawn@4:     'start', 'sample', 'Distance', 'sqEuclidean');
Dawn@4: 
Dawn@4: [ groupStats, groupNames ] = processKMeansResults( 'sqEuclidean', idx, sampleEmotion, masterFileOutputID, titleName, DEBUG );
Dawn@4: [ confusionMatrix ] = getConfusionMatrix( groupStats, groupNames, masterFileOutputID, 'sqEuclidean' );
Dawn@4: 
Dawn@4: 
Dawn@4: fprintf( masterFileOutputID, 'cosine \n');
Dawn@4: [idx ctrs]=kmeans( data, noOfClusters, 'Replicates',100,...
Dawn@4:     'start', 'sample', 'Distance', 'cosine');
Dawn@4: 
Dawn@4: [ groupStats, groupNames ] = processKMeansResults( 'cosine', idx, sampleEmotion, masterFileOutputID, titleName, DEBUG );
Dawn@4: [ confusionMatrix ] = getConfusionMatrix( groupStats, groupNames, masterFileOutputID, 'cosine' );
Dawn@4: 
Dawn@4: 
Dawn@4: fprintf( masterFileOutputID, 'correlation \n');
Dawn@4: [idx ctrs]=kmeans( data, noOfClusters, 'Replicates',100,...
Dawn@4:     'start', 'sample', 'Distance', 'correlation');
Dawn@4: 
Dawn@4: [ groupStats, groupNames ] = processKMeansResults( 'correlation', idx, sampleEmotion, masterFileOutputID, titleName, DEBUG );
Dawn@4: [ confusionMatrix ] = getConfusionMatrix( groupStats, groupNames, masterFileOutputID, 'correlation' );
Dawn@4: 
Dawn@4: % --------------------------------------------------------------------
Dawn@4: 
Dawn@4: % display results grouped by gender
Dawn@4: % fprintf( masterFileOutputID, '\n Gender grouping \n');
Dawn@4: % noOfClusters = 3;
Dawn@4: % 
Dawn@4: % [idx ctrs]=kmeans( data, noOfClusters, 'Replicates',100,...
Dawn@4: %     'start', 'sample', 'Distance', 'cityblock');
Dawn@4: % 
Dawn@4: % fprintf( masterFileOutputID, 'cityblock \n');
Dawn@4: % [ groupStats, groupNames ] = processKMeansResults( 'cityblock', idx, gender, masterFileOutputID, titleName, DEBUG );
Dawn@4: % [ confusionMatrix ] = getConfusionMatrix( groupStats, groupNames, masterFileOutputID );
Dawn@4: % 
Dawn@4: % [idx ctrs]=kmeans( data, noOfClusters, 'Replicates',100,...
Dawn@4: %     'start', 'sample', 'Distance', 'sqEuclidean');
Dawn@4: % 
Dawn@4: % fprintf( masterFileOutputID, 'sqEuclidean \n');
Dawn@4: % [ groupStats, groupNames ] = processKMeansResults( 'sqEuclidean', idx, gender, masterFileOutputID, titleName, DEBUG );
Dawn@4: % [ confusionMatrix ] = getConfusionMatrix( groupStats, groupNames, masterFileOutputID );
Dawn@4: 
Dawn@4: fprintf( masterFileOutputID, '\n' );
Dawn@4: fclose( masterFileOutputID );
Dawn@4: 
Dawn@4: end
Dawn@4: 
Dawn@4: