#!/usr/perl/perl580/bin/perl 

use Algorithm::Cluster;

open (DATA, "$ARGV[0]");

my $firstline = <DATA>; # Skip the title line

##
while(my $line = <DATA>) {
	chomp $line;
	@field = split /\t/, $line;
	$patient_id[$i] = shift @field;
	$patient_class[$i] = shift @field;
	$j = 0;
	$patient_data[$i] = [ @field ]; #this is the where the data will be stored; the "[]" around
                                        #the array indicates the creationof a matrix to perl.
	print ("Patient $patient_id[$i] is $patient_class[$i]\n");
	$i++;
}

## The code below is useful to check if the matrix in line 23 is correct;
## it's needed only in new datasets to check if the work is right.

#$i = 0;
#for $i (0..$#patient_data) {
#	for $j (0..$#{$patient_data[$i]}) {
#		print ("\t Element $i $j is $patient_data[$i][$j]\n");
#	}
#}


## The hash generated below is the input to the subroutine
## treecluster; for more information about the meaning of
## the paramenters please read http://bonsai.ims.u-tokyo.ac.jp/~mdehoon/software/cluster/cluster.pdf

my %params = (

	transpose =>         0,
	dist      =>       'e',
	data      =>    \@patient_data,
	mask      =>    '',
	weight    =>  '',
	niter     =>       10,
);

my ($clusterid);
my ($i);

$clusterid = Algorithm::Cluster::somcluster(%params);

$i=0;
foreach(@{$clusterid}) {
	printf("Patient %2d assigned to cell (%2d,%2d)\n",$i++,$_->[0],$_->[1]);
}