Algorithm-ExpectationMaximization

 view release on metacpan or  search on metacpan

lib/Algorithm/ExpectationMaximization.pm  view on Meta::CPAN

#  aborts.
#
#  The visualization code consists of first accessing each of clusters created by the
#  EM() subroutine.  Note that the clusters contain only the symbolic names for the
#  individual records in the source data file.  We therefore next reach into the
#  $self->{_data} hash and get the data coordinates associated with each symbolic
#  label in a cluster.  The numerical data thus generated is then written out to a
#  temp file.  When doing so we must remember to insert TWO BLANK LINES between the
#  data blocks corresponding to the different clusters.  This constraint is imposed
#  on us by Gnuplot when plotting data from the same file since we want to use
#  different point styles for the data points in different cluster files.
#  Subsequently, we call upon the Perl interface provided by the Graphics::GnuplotIF
#  module to plot the data clusters.
sub visualize_clusters {
    my $self = shift;
    my $v_mask;
    my $pause_time;
    if (@_ == 1) {
        $v_mask = shift || die "visualization mask missing";
    } elsif (@_ == 2) {
        $v_mask = shift || die "visualization mask missing";    

lib/Algorithm/ExpectationMaximization.pm  view on Meta::CPAN

            my ($minval,$maxval) = minmax(\@cluster_for_hist);
            push @all_minvals, $minval;
            push @all_maxvals, $maxval;
            push @all_clusters_for_hist, \@cluster_for_hist;
        }
        push @all_minmaxvals, @all_minvals;
        push @all_minmaxvals, @all_maxvals;
        my ($abs_minval,$abs_maxval) = minmax(\@all_minmaxvals);
        my $delta = ($abs_maxval - $abs_minval) / 100.0;
        $plot->gnuplot_cmd("set boxwidth 3");
        $plot->gnuplot_cmd("set style fill solid border -1");
        $plot->gnuplot_cmd("set ytics out nomirror");
        $plot->gnuplot_cmd("set style data histograms");
        $plot->gnuplot_cmd("set style histogram clustered");
        $plot->gnuplot_cmd("set title 'Clusters shown through histograms'");
        $plot->gnuplot_cmd("set xtics rotate by 90 offset 0,-5 out nomirror");
        foreach my $cindex (0..@all_clusters_for_hist-1) {
            my $filename = basename($master_datafile);
            my $temp_file = "__temp1dhist_" . "$cindex" . "_" .  $filename;
            unlink $temp_file if -e $temp_file;
            open OUTPUT, ">$temp_file" or die "Unable to open a temp file in this directory: $!";
            print OUTPUT "Xstep histval\n";
            my @histogram = (0) x 100;
            foreach my $i (0..@{$all_clusters_for_hist[$cindex]}-1) {

lib/Algorithm/ExpectationMaximization.pm  view on Meta::CPAN

            my ($minval,$maxval) = minmax(\@cluster_for_hist);
            push @all_minvals, $minval;
            push @all_maxvals, $maxval;
            push @all_clusters_for_hist, \@cluster_for_hist;
        }
        push @all_minmaxvals, @all_minvals;
        push @all_minmaxvals, @all_maxvals;
        my ($abs_minval,$abs_maxval) = minmax(\@all_minmaxvals);
        my $delta = ($abs_maxval - $abs_minval) / 100.0;
        $plot->gnuplot_cmd("set boxwidth 3");
        $plot->gnuplot_cmd("set style fill solid border -1");
        $plot->gnuplot_cmd("set ytics out nomirror");
        $plot->gnuplot_cmd("set style data histograms");
        $plot->gnuplot_cmd("set style histogram clustered");
        $plot->gnuplot_cmd("set title 'Clusters shown through histograms'");
        $plot->gnuplot_cmd("set xtics rotate by 90 offset 0,-5 out nomirror");
        foreach my $cindex (0..@all_clusters_for_hist-1) {
            my $filename = basename($master_datafile);
            my $temp_file = "__temp1dhist_" . "$cindex" . "_" .  $filename;
            unlink $temp_file if -e $temp_file;
            open OUTPUT, ">$temp_file" or die "Unable to open a temp file in this directory: $!";
            print OUTPUT "Xstep histval\n";
            my @histogram = (0) x 100;
            foreach my $i (0..@{$all_clusters_for_hist[$cindex]}-1) {

lib/Algorithm/ExpectationMaximization.pm  view on Meta::CPAN

            my ($minval,$maxval) = minmax(\@cluster_for_hist);
            push @all_minvals, $minval;
            push @all_maxvals, $maxval;
            push @all_clusters_for_hist, \@cluster_for_hist;
        }
        push @all_minmaxvals, @all_minvals;
        push @all_minmaxvals, @all_maxvals;
        my ($abs_minval,$abs_maxval) = minmax(\@all_minmaxvals);
        my $delta = ($abs_maxval - $abs_minval) / 100.0;
        $plot->gnuplot_cmd("set boxwidth 3");
        $plot->gnuplot_cmd("set style fill solid border -1");
        $plot->gnuplot_cmd("set ytics out nomirror");
        $plot->gnuplot_cmd("set style data histograms");
        $plot->gnuplot_cmd("set style histogram clustered");
        $plot->gnuplot_cmd("set title 'Individual distributions shown through histograms'");
        $plot->gnuplot_cmd("set xtics rotate by 90 offset 0,-5 out nomirror");
        foreach my $cindex (0..@all_clusters_for_hist-1) {
            my $localfilename = basename($filename);
            my $temp_file = "__temp1dhist_" . "$cindex" . "_" .  $localfilename;
            unlink $temp_file if -e $temp_file;
            open OUTPUT, ">$temp_file" or die "Unable to open a temp file in this directory: $!";
            print OUTPUT "Xstep histval\n";

            my @histogram = (0) x 100;

lib/Algorithm/ExpectationMaximization.pm  view on Meta::CPAN

            my ($minval,$maxval) = minmax(\@cluster_for_hist);
            push @all_minvals, $minval;
            push @all_maxvals, $maxval;
            push @all_clusters_for_hist, \@cluster_for_hist;
        }
        push @all_minmaxvals, @all_minvals;
        push @all_minmaxvals, @all_maxvals;
        my ($abs_minval,$abs_maxval) = minmax(\@all_minmaxvals);
        my $delta = ($abs_maxval - $abs_minval) / 100.0;
        $plot->gnuplot_cmd("set boxwidth 3");
        $plot->gnuplot_cmd("set style fill solid border -1");
        $plot->gnuplot_cmd("set ytics out nomirror");
        $plot->gnuplot_cmd("set style data histograms");
        $plot->gnuplot_cmd("set style histogram clustered");
        $plot->gnuplot_cmd("set title 'Individual distributions shown through histograms'");
        $plot->gnuplot_cmd("set xtics rotate by 90 offset 0,-5 out nomirror");
        foreach my $cindex (0..@all_clusters_for_hist-1) {
            my $localfilename = basename($filename);
            my $temp_file = "__temp1dhist_" . "$cindex" . "_" .  $localfilename;
            unlink $temp_file if -e $temp_file;
            open OUTPUT, ">$temp_file" or die "Unable to open a temp file in this directory: $!";
            print OUTPUT "Xstep histval\n";

            my @histogram = (0) x 100;

lib/Algorithm/ExpectationMaximization.pm  view on Meta::CPAN

        $arg_string = "\"$temp_file\" using 1:2 title $plot_title with points lt -1 pt 1";
    } elsif ($visualization_data_field_width == 1 ) {
        open INPUT, "$temp_file" or die "Unable to open a temp file in this directory: $!";
        my @all_data = <INPUT>;
        close INPUT;
        @all_data = map {chomp $_; $_} @all_data;
        @all_data = grep $_, @all_data;
        my ($minval,$maxval) = minmax(\@all_data);
        my $delta = ($maxval - $minval) / 100.0;
        $plot->gnuplot_cmd("set boxwidth 3");
        $plot->gnuplot_cmd("set style fill solid border -1");
        $plot->gnuplot_cmd("set ytics out nomirror");
        $plot->gnuplot_cmd("set style data histograms");
        $plot->gnuplot_cmd("set style histogram clustered");
        $plot->gnuplot_cmd("set title 'Overall distribution of 1D data'");
        $plot->gnuplot_cmd("set xtics rotate by 90 offset 0,-5 out nomirror");
        my $localfilename = basename($filename);
        my $temp_file = "__temp1dhist_" .  $localfilename;
        unlink $temp_file if -e $temp_file;
        open OUTPUT, ">$temp_file" or die "Unable to open a temp file in this directory: $!";
        print OUTPUT "Xstep histval\n";
        my @histogram = (0) x 100;
        foreach my $i (0..@all_data-1) {
            $histogram[int( ($all_data[$i] - $minval) / $delta )]++;

lib/Algorithm/ExpectationMaximization.pm  view on Meta::CPAN

        $arg_string = "\"$temp_file\" using 1:2 title $plot_title with points lt -1 pt 1";
    } elsif ($visualization_data_field_width == 1 ) {
        open INPUT, "$temp_file" or die "Unable to open a temp file in this directory: $!";
        my @all_data = <INPUT>;
        close INPUT;
        @all_data = map {chomp $_; $_} @all_data;
        @all_data = grep $_, @all_data;
        my ($minval,$maxval) = minmax(\@all_data);
        my $delta = ($maxval - $minval) / 100.0;
        $plot->gnuplot_cmd("set boxwidth 3");
        $plot->gnuplot_cmd("set style fill solid border -1");
        $plot->gnuplot_cmd("set ytics out nomirror");
        $plot->gnuplot_cmd("set style data histograms");
        $plot->gnuplot_cmd("set style histogram clustered");
        $plot->gnuplot_cmd("set title 'Overall distribution of 1D data'");
        $plot->gnuplot_cmd("set xtics rotate by 90 offset 0,-5 out nomirror");
        my $localfilename = basename($filename);
        my $temp_file = "__temp1dhist_" .  $localfilename;
        unlink $temp_file if -e $temp_file;
        open OUTPUT, ">$temp_file" or die "Unable to open a temp file in this directory: $!";
        print OUTPUT "Xstep histval\n";
        my @histogram = (0) x 100;
        foreach my $i (0..@all_data-1) {
            $histogram[int( ($all_data[$i] - $minval) / $delta )]++;