view Code/Classifiers/kmeans_PRAAT_Singing.m @ 2:5fd388fdd6ef

initial commit - this file allows the programmer to select which of the PRAAT generated metrics the user wishes to use for classification, and then applies the k-means classifier.

function [] = kmeans_Singing( varargin )

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

% output results file name
masterFileOutputID = fopen( 'kmeans_Singing_All.txt', 'a' );
% input results file name
inputFileName = 'singingPRAATStats.txt';

% This function allows the user to stipulate which Singing voice LLD's they
% wish to forward to a k-means classifier and produces a file of
% performance characteristics. Input arguments stipulate the LLD's and
% there is a choice of:-
%
% ---- PRAAT JITTER MEASUREMENTS ----
%     '_jitter_ddp'
%     '_jitter_local'
%     '_jitter_ppq5'
%     '_jitter_rap'
% ---- PRAAT SHIMMER MEASUREMENTS ----
%     '_shimmer_local'
%     '_shimmer_dda'
%     '_shimmer_apq3'
%     '_shimmer_apq5'
%     '_shimmer_apq11'
% ---- PRAAT FORMANT MEASUREMENTS ----
%     '_Formant_Burg'
%     '_Formant_all'
%     '_Formant_robust'
%
% A text file entitled kmeans_Singing_LLD1name_LLD2name_ ... LLDNname.txt
% is produced that contains the results of the k-mean classification for
% the LLD's specified and named in the result document title.

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

% get the column numbers of the results that we want to classify

% COLUMN NUMBER     :   METRIC
%   1   : audio file name
%   2   : jitter ddp
%   3   : jitter local
%   4   : jitter ppq5
%   5   : jitter rap
%   6   : shimmer local
%   7   : shimmer dda
%   8   : shimmer apq3
%   9   : shimmer apq5
%   10  : shimmer apq11
%
% ------------- BURG FORMANTS ---------------
%   11   : Number of BURG formants listed = nBF
%
%   THERE ARE CURRENTLY 24 MEASUREMENTS TAKEN FOR EACH FORMANT
nMetrics = 24;
%
%   12   : mean frequency of the first BURG formant
%   13   : variance of the first BURG formant
%   14   : minimum frequency of the first BURG formant
%   15   : maximum frequency of the first BURG formant
%   16   : mean Frequency Derivative of the first BURG formant
%   17   : varience of the Frequency Derivative of the first BURG formant
%   18   : min of the Frequency Derivative of the first BURG formant
%   19   : max  of the Frequency Derivative of the first BURG formant
%   20   : mean of the Frequency 2nd Derivative of the first BURG formant
%   21   : varience of the Frequency 2nd Derivative of the first BURG formant
%   22   : min of the Frequency 2nd Derivative of the first BURG formant
%   23   :  max of the Frequency 2nd Derivative of the first BURG formant
%   24   : mean of the Bandwidth of the first BURG formant
%   25   :  varience of the Bandwidth of the first BURG formant
%   26   : min of the Bandwidth of the first BURG formant
%   27   : max of the Bandwidth of the first BURG formant
%   28   : mean of the Bandwidth Derivative of the first BURG formant
%   29   : varience of the Bandwidth Derivative of the first BURG formant
%   30   : min of the Bandwidth Derivative of the first BURG formant
%   31   : max of the Bandwidth Derivative of the first BURG formant
%   32   : mean of the Bandwidth 2nd Derivative of the first BURG formant
%   33   : var of the Bandwidth 2nd Derivative of the first BURG formant
%   34   : min of the Bandwidth 2nd Derivative of the first BURG formant
%   35   : max of the Bandwidth 2nd Derivative of the first BURG formant
%
%    ....... there are nMetrics for each formant in nBF formants, so cycle
%    through until the last is reached ......
%
%   36 + ((nBF-1)*nMetrics)       : mean frequency of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 1   : variance of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 2   : minimum frequency of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 3   : maximum frequency of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 4   : mean Frequency Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 5   : varience of the Frequency Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 6   : min of the Frequency Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 7   : max of the Frequency Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 8   : mean of the Frequency 2nd Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 9   : varience of the Frequency 2nd Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 10  : min of the Frequency 2nd Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 11  : max of the Frequency 2nd Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 12  : mean of the Bandwidth of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 13  : varience of the Bandwidth of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 14  : min of the Bandwidth of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 15  : max of the Bandwidth of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 16  : mean of the Bandwidth Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 17  : variece of the Bandwidth Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 18  : min of the Bandwidth Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 19  : max of the Bandwidth Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 20  : mean of the Bandwidth 2nd Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 21  : var of the Bandwidth 2nd Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 22  : min of the Bandwidth 2nd Derivative of the nBF BURG formant
%   36 + ((nBF-1)*nMetrics) + 23  : max of the Bandwidth 2nd Derivative of the nBF BURG formant
%
%   FOR THE MEAN OF ALL BURG FORMANTS
%   36 + (nBF*nMetrics)           : mean of all formants Frequency 
%   36 + (nBF*nMetrics) + 1       : varience of the mean of all formants Frequency 
%   36 + (nBF*nMetrics) + 2       : minimum of the mean of all formants Frequency 
%   36 + (nBF*nMetrics) + 3       : maximum of the mean of all formants Frequency
%   36 + (nBF*nMetrics) + 4       :  mean of all formants mean Frequency Derivative 
%   36 + (nBF*nMetrics) + 5       :  mean of all formants varience Frequency Derivative 
%   36 + (nBF*nMetrics) + 6       :  min of the mean of all formants Frequency Derivative
%   36 + (nBF*nMetrics) + 7       :  max of the mean of all formants Frequency Derivative 
%   36 + (nBF*nMetrics) + 8       :  mean of the mean of all formants Frequency 2nd Derivative 
%   36 + (nBF*nMetrics) + 9       :  varience of the mean of all formants Frequency 2nd Derivative 
%   36 + (nBF*nMetrics) + 10      :  min of the mean of all formants Frequency 2nd Derivative
%   36 + (nBF*nMetrics) + 11      :  max of the mean of all formants Frequency 2nd Derivative
%
% ------------- ALL FORMANTS ---------------
%
%   36 + (nBF*nMetrics) + 12   : Number of ALL formants listed = nAF
%
%   startOfALLMeasurements = 36 + (nBF*nMetrics) + 13;
%
%   startOfALLMeasurements      : mean frequency of the first ALL formant
%   startOfALLMeasurements + 1     : variance of the first ALL formant
%   startOfALLMeasurements + 2     : minimum frequency of the first ALL formant
%   startOfALLMeasurements + 3     : maximum frequency of the first ALL formant
%   startOfALLMeasurements + 4     : mean Frequency Derivative of the first ALL formant
%   startOfALLMeasurements + 5     : varience of the Frequency Derivative of the first ALL formant
%   startOfALLMeasurements + 6     : min of the Frequency Derivative of the first ALL formant
%   startOfALLMeasurements + 7     : max  of the Frequency Derivative of the first ALL formant
%   startOfALLMeasurements + 8     : mean of the Frequency 2nd Derivative of the first ALL formant
%   startOfALLMeasurements + 9     : varience of the Frequency 2nd Derivative of the first ALL formant
%   startOfALLMeasurements + 10    : min of the Frequency 2nd Derivative of the first ALL formant
%   startOfALLMeasurements + 11    :  max of the Frequency 2nd Derivative of the first ALL formant
%   startOfALLMeasurements + 12    : mean of the Bandwidth of the first ALL formant
%   startOfALLMeasurements + 13    :  varience of the Bandwidth of the first ALL formant
%   startOfALLMeasurements + 14    : min of the Bandwidth of the first ALL formant
%   startOfALLMeasurements + 15    : max of the Bandwidth of the first ALL formant
%   startOfALLMeasurements + 16    : mean of the Bandwidth Derivative of the first ALL formant
%   startOfALLMeasurements + 17    : varience of the Bandwidth Derivative of the first ALL formant
%   startOfALLMeasurements + 18    : min of the Bandwidth Derivative of the first ALL formant
%   startOfALLMeasurements + 19    : max of the Bandwidth Derivative of the first ALL formant
%   startOfALLMeasurements + 20    : mean of the Bandwidth 2nd Derivative of the first ALL formant
%   startOfALLMeasurements + 21    : var of the Bandwidth 2nd Derivative of the first ALL formant
%   startOfALLMeasurements + 22    : min of the Bandwidth 2nd Derivative of the first ALL formant
%   startOfALLMeasurements + 23    : max of the Bandwidth 2nd Derivative of the first ALL formant
%
%    ....... there are nMetrics for each formant in nAF formants, so cycle
%    through until the last is reached ......
%
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : mean frequency of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : variance of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : minimum frequency of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : maximum frequency of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : mean Frequency Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : varience of the Frequency Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : min of the Frequency Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : max of the Frequency Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : mean of the Frequency 2nd Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : varience of the Frequency 2nd Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : min of the Frequency 2nd Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : max of the Frequency 2nd Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : mean of the Bandwidth of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : varience of the Bandwidth of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : min of the Bandwidth of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : max of the Bandwidth of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : mean of the Bandwidth Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : variece of the Bandwidth Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : min of the Bandwidth Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : max of the Bandwidth Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : mean of the Bandwidth 2nd Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : var of the Bandwidth 2nd Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : min of the Bandwidth 2nd Derivative of the nAF ALL formant
%   startOfALLMeasurements + ((nAF-1)*nMetrics)       : max of the Bandwidth 2nd Derivative of the nAF ALL formant
%
%   FOR THE MEAN OF ALL ALL FORMANTS
%   startOfALLMeasurements + (nAF*nMetrics)           : mean of all formants Frequency 
%   startOfALLMeasurements + (nAF*nMetrics) + 1       : varience of the mean of all formants Frequency 
%   startOfALLMeasurements + (nAF*nMetrics) + 2       : minimum of the mean of all formants Frequency 
%   startOfALLMeasurements + (nAF*nMetrics) + 3       : maximum of the mean of all formants Frequency
%   startOfALLMeasurements + (nAF*nMetrics) + 4       :  mean of all formants mean Frequency Derivative 
%   startOfALLMeasurements + (nAF*nMetrics) + 5       :  mean of all formants varience Frequency Derivative 
%   startOfALLMeasurements + (nAF*nMetrics) + 6       :  min of the mean of all formants Frequency Derivative
%   startOfALLMeasurements + (nAF*nMetrics) + 7       :  max of the mean of all formants Frequency Derivative 
%   startOfALLMeasurements + (nAF*nMetrics) + 8       :  mean of the mean of all formants Frequency 2nd Derivative 
%   startOfALLMeasurements + (nAF*nMetrics) + 9       :  varience of the mean of all formants Frequency 2nd Derivative 
%   startOfALLMeasurements + (nAF*nMetrics) + 10      :  min of the mean of all formants Frequency 2nd Derivative
%   startOfALLMeasurements + (nAF*nMetrics) + 11      :  max of the mean of all formants Frequency 2nd Derivative
%
% ------------- ROBUST FORMANTS ---------------
%
%   startOfALLMeasurements + (nAF*nMetrics) + 12    : Number of ROBUST formants listed = nRF
%
%   startOfROBUSTMeasurements = startOfALLMeasurements + (nAF*nMetrics) + 13;
%
%   startOfROBUSTMeasurements         : mean frequency of the first ROBUST formant
%   startOfROBUSTMeasurements + 1     : variance of the first ROBUST formant
%   startOfROBUSTMeasurements + 2     : minimum frequency of the first ROBUST formant
%   startOfROBUSTMeasurements + 3     : maximum frequency of the first ROBUST formant
%   startOfROBUSTMeasurements + 4     : mean Frequency Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 5     : varience of the Frequency Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 6     : min of the Frequency Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 7     : max  of the Frequency Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 8     : mean of the Frequency 2nd Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 9     : varience of the Frequency 2nd Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 10    : min of the Frequency 2nd Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 11    :  max of the Frequency 2nd Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 12    : mean of the Bandwidth of the first ROBUST formant
%   startOfROBUSTMeasurements + 13    :  varience of the Bandwidth of the first ROBUST formant
%   startOfROBUSTMeasurements + 14    : min of the Bandwidth of the first ROBUST formant
%   startOfROBUSTMeasurements + 15    : max of the Bandwidth of the first ROBUST formant
%   startOfROBUSTMeasurements + 16    : mean of the Bandwidth Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 17    : varience of the Bandwidth Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 18    : min of the Bandwidth Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 19    : max of the Bandwidth Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 20    : mean of the Bandwidth 2nd Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 21    : var of the Bandwidth 2nd Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 22    : min of the Bandwidth 2nd Derivative of the first ROBUST formant
%   startOfROBUSTMeasurements + 23    : max of the Bandwidth 2nd Derivative of the first ROBUST formant
%
%    ....... there are nMetrics for each formant in nRF formants, so cycle
%    through until the last is reached ......
%
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : mean frequency of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : variance of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : minimum frequency of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : maximum frequency of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : mean Frequency Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : varience of the Frequency Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : min of the Frequency Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : max of the Frequency Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : mean of the Frequency 2nd Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : varience of the Frequency 2nd Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : min of the Frequency 2nd Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : max of the Frequency 2nd Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : mean of the Bandwidth of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : varience of the Bandwidth of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : min of the Bandwidth of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : max of the Bandwidth of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : mean of the Bandwidth Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : variece of the Bandwidth Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : min of the Bandwidth Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : max of the Bandwidth Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : mean of the Bandwidth 2nd Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : var of the Bandwidth 2nd Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : min of the Bandwidth 2nd Derivative of the nRF ROBUST formant
%   startOfROBUSTMeasurements + ((nRF-1)*nMetrics)       : max of the Bandwidth 2nd Derivative of the nRF ROBUST formant
%
%   FOR THE MEAN OF ALL ROBUST FORMANTS
%   startOfROBUSTMeasurements + (nRF*nMetrics)           : mean of all formants Frequency 
%   startOfROBUSTMeasurements + (nRF*nMetrics) + 1       : varience of the mean of all formants Frequency 
%   startOfROBUSTMeasurements + (nRF*nMetrics) + 2       : minimum of the mean of all formants Frequency 
%   startOfROBUSTMeasurements + (nRF*nMetrics) + 3       : maximum of the mean of all formants Frequency
%   startOfROBUSTMeasurements + (nRF*nMetrics) + 4       :  mean of all formants mean Frequency Derivative 
%   startOfROBUSTMeasurements + (nRF*nMetrics) + 5       :  mean of all formants varience Frequency Derivative 
%   startOfROBUSTMeasurements + (nRF*nMetrics) + 6       :  min of the mean of all formants Frequency Derivative
%   startOfROBUSTMeasurements + (nRF*nMetrics) + 7       :  max of the mean of all formants Frequency Derivative 
%   startOfROBUSTMeasurements + (nRF*nMetrics) + 8       :  mean of the mean of all formants Frequency 2nd Derivative 
%   startOfROBUSTMeasurements + (nRF*nMetrics) + 9       :  varience of the mean of all formants Frequency 2nd Derivative 
%   startOfROBUSTMeasurements + (nRF*nMetrics) + 10      :  min of the mean of all formants Frequency 2nd Derivative
%   startOfROBUSTMeasurements + (nRF*nMetrics) + 11      :  max of the mean of all formants Frequency 2nd Derivative
%

noOfArguments = length(varargin);
columnIndices = [];

getBURGFormants = 0;
getAllForamnts=0;
getRobustFormants=0;

for i=1 : noOfArguments
    if( strcmp( varargin{i}, 'jitter_ddp' ))
        columnIndices = [columnIndices 1];
    elseif( strcmp( varargin{i}, 'jitter_local' ))
        columnIndices = [columnIndices 2];
    elseif( strcmp( varargin{i}, 'jitter_ppq5' ))
        columnIndices = [columnIndices 3];
    elseif( strcmp( varargin{i}, 'jitter_rap' ))
        columnIndices = [columnIndices 4];
    elseif( strcmp( varargin{i}, 'shimmer_local' ))
        columnIndices = [columnIndices 5];
    elseif( strcmp( varargin{i}, 'shimmer_dda' ))
        columnIndices = [columnIndices 6];
    elseif( strcmp( varargin{i}, 'shimmer_apq3' ))
        columnIndices = [columnIndices 7];
    elseif( strcmp( varargin{i}, 'shimmer_apq5' ))
        columnIndices = [columnIndices 8];
    elseif( strcmp( varargin{i}, 'shimmer_apq11' ))
        columnIndices = [columnIndices 9];
    elseif( strcmp( varargin{i}, 'formant_Burg' ))
        getBURGFormants = 1;
    elseif( strcmp( varargin{i}, 'formant_all' ))
        getAllForamnts=1;
    elseif( strcmp( varargin{i}, 'formant_robust' ))
        getRobustFormants=1;
    end
end


outputFileName = 'individualResults/kmeans_Results_';
resultsFileName = 'kmeans_Results_';
titleName = '';
for i=1 : noOfArguments
%     outputFileName = [ outputFileName varargin{i} '_'];
%     resultsFileName = [ resultsFileName varargin{i} '_'];
    titleName = [ titleName varargin{i} '_'];
    fprintf( masterFileOutputID, '%s_', varargin{i} );
end

% titleName = outputFileName;
outputFileName = [ outputFileName titleName ];
resultsFileName = [ resultsFileName titleName ];

fprintf( masterFileOutputID, '\t' );

outputFileName = [ outputFileName '.txt'];
resultsFileName = [ resultsFileName '.txt'];

fileOutputID = fopen( outputFileName, 'w' );
fileKMeansOutputID = fopen( resultsFileName, 'w' );

% -------------------- get the data from the results file ---------------
lineCount = 0;
fileCount = 0;
data = [];
while( ~(feof(inputFileID)) )
    
    outputValues = [];
%     sampleEmotion = [];
%     gender = [];
    
    thestr = fgetl(inputFileID);
    if( lineCount > 10 )    % skip the file header
        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!');
            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

        %how many values are in the string?
        spaces = strfind( thestr, ' ' );
        numberstr = thestr( spaces(1) : end ); % chop off the file name
        frmtpos = strfind( numberstr, 'maxNoOfFormants'); % find the position of the label for number of formants
        
        str1 = numberstr( 1 : frmtpos(1)-1 ); % string contains jitter and shimmer values
        str2 = numberstr( frmtpos(1) : frmtpos(2)-1 ); % string contains all BURG formant information
        str3 = numberstr( frmtpos(2) : frmtpos(3)-1 ); % string contains all ALL formant information
        str4 = numberstr( frmtpos(3) : end ); % string contains all ROBUST formant information
        
        vars = sscanf( str1, '%f', inf );
        % extract the shimmer and jitter values
        outputValues = [ outputValues vars( columnIndices )'];
        
        if( getBURGFormants )
            spaces = strfind( str2, ' ' ); % remove the string 'maxNoOfFormants'
            vars = sscanf( str2( spaces(1) : end ), '%f', inf );
            outputValues = stripOutFormantValues( vars, outputValues );
        end
        
        if( getAllForamnts )
            spaces = strfind( str3, ' ' ); % remove the string 'maxNoOfFormants'
            vars = sscanf( str3( spaces(1) : end ), '%f', inf );
            outputValues = stripOutFormantValues( vars, outputValues );
        end
        
        if( getRobustFormants )
            spaces = strfind( str4, ' ' ); % remove the string 'maxNoOfFormants'
            vars = sscanf( str4( spaces(1) : end ), '%f', inf );
            outputValues = stripOutFormantValues( vars, outputValues );
        end
        
        [m n] = size( data );
        % sometimes the 'all' formants command gives us fewer formants than
        % usual. If this is the case,then we will have to pad with zeros
        % for now.
        if( n > length( outputValues ) )
            lenDiff = n - length( outputValues );
            outputValues = [ outputValues zeros( 1, lenDiff ) ];
        end
        
        data( fileCount, : ) = outputValues;
        
    end
    lineCount = lineCount + 1;
    
end
fclose(inputFileID);

%individual examination of the metrics does confirm that there is little
%difference in emotional content. However, singer identification is OK. 

% figure(2); subplot(211); hold off;
% 
% for( i = 1 : length(data) )
%     if( sampleEmotion(i) == 'N')
%         plot( i, data(i), 'b.' );
%     else
%         plot( i, data(i), 'r.' );
%     end
%     hold on;
% end
% 
% subplot(212); hold off;
% 
% for( i = 1 : length(data) )
%     if( gender(i) == 'M')
%         plot( i, data(i), 'b.' );
%     elseif( gender(i) == 'F')
%         plot( i, data(i), 'r.' );
%     else
%         plot( i, data(i), 'g.' );
%     end
%     hold on;
% end

% ------------  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
processKMeansResults( 'cityblock', idx, sampleEmotion, fileOutputID, fileKMeansOutputID, masterFileOutputID, titleName );

disp('press space');
pause;

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

processKMeansResults( 'sqEuclidean', idx, sampleEmotion, fileOutputID, fileKMeansOutputID, masterFileOutputID, titleName );

disp('press space');
pause;


%display results grouped by gender

noOfClusters = 3;

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

processKMeansResults( 'cityblock', idx, gender, fileOutputID, fileKMeansOutputID, masterFileOutputID, titleName );

disp('press space');
pause;

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

processKMeansResults( 'sqEuclidean', idx, gender, fileOutputID, fileKMeansOutputID, masterFileOutputID, titleName );

disp('press space');
pause;


% [idx ctrs]=kmeans( data, noOfClusters, 'Replicates',100,...
%     'start', 'sample', 'Distance', 'cosine');
% 
% processKMeansResults( 'cosine', idx, sampleEmotion, fileOutputID, fileKMeansOutputID, masterFileOutputID, titleName);
% 
% disp('press space');
% pause;

% [idx ctrs]=kmeans( data, noOfClusters, 'Replicates',100,...
%     'start', 'sample', 'Distance', 'correlation');
% 
% processKMeansResults( 'correlation', idx, sampleEmotion, fileOutputID, fileKMeansOutputID, masterFileOutputID, titleName );
% 
% disp('press space');
% pause;

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

end

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

function [ outputValues ] = stripOutFormantValues( vars, outputValues )
    
    noOfFormantValues = length( vars ) - 1; % gives the number of formant arguments only
    noOfFormants = vars(1);
    % there are 12 measurements for the mean of all formants (so the number
    % of formants is not important) for each formant measurement.
    if( noOfFormants ~= (noOfFormantValues-12)/24 )
        disp('EEK!');
        pause;
    else
        outputValues = [ outputValues vars( 2:end )' ];
    end

end

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

function [] = processKMeansResults( ID, idx, groupingCriteria, fileOutputID, fileKMeansOutputID, masterFileOutputID, titleName )

    fprintf( fileKMeansOutputID, '%s\t', ID );
    fprintf( masterFileOutputID, '%s\t', ID );
    
    if( length( idx ) ~= length( groupingCriteria ) )
        disp('EEEK!');
        pause;
    end

    groupIDs = '';
    groupStr = '';
    for( i = 1 : length( idx ))
        fprintf( fileOutputID, '%s \t %d \n', groupingCriteria(i), idx(i) );
        gID = [ groupingCriteria(i) num2str( idx(i) )];
        groupIDs = [ groupIDs ; gID ];
        groupStr = [ groupStr gID ];
    end

    % ------------- work out the confusion matrix -------------------------

    groups = unique( groupIDs, 'rows' );
    noOfGroups = length( groups );
    orderedGroups = sort(cellstr(groups));
    groupStats = [];
    for( i = 1 : noOfGroups )
        groupStats(i) = ((length( strfind( groupStr, char(orderedGroups(i)))))/length( idx ) ) * 100;
        fprintf( fileKMeansOutputID, '%s \t %f \t', char(orderedGroups(i)), groupStats(i) );
        fprintf( masterFileOutputID, '%s \t %f \t', char(orderedGroups(i)), groupStats(i) );
    end
    
    figure(1);
    bar( groupStats );
    set( gca, 'XTickLabel', orderedGroups );
    title([ titleName ' ' ID]);
    
end