use strict ;
use warnings ;
use Data::Dumper ;

open my $dataIn1, "<", "Attributes_ID.txt" or die "NO ID FILE: $!" ;
open my $dataIn2, "<", "Attributes.txt" or die "NO ATTR FILE: $!" ;

my $data = () ;
my $attrs = () ;

sub getdata {
    my ( $fileName, $type ) = split /\t/, $_[0] ;
    push @{$data}, $type unless !defined $fileName ;
}

sub getattrs {
    my @attrs = split /\t/, $_[0] ;
    push @{$attrs}, \@attrs unless !defined $attrs[0] ;
}

sub calcPercentages {
	# INPUT: Hash reference
	# Determine the total amount of attributes
	# Walk through each category: Circle, Triangle, ...
	# Take the hit count divided by the total amount of attributes (multiplied by 100?)
	# For each category add something to the hash to store the percentage
	#    e.g. CircleChance, TriangleChance, ....

	# askQuestions could potentially be called here
}

sub askQuestions {
	# INPUT: Hash reference
	# my $h = ...
	# Question 1: Does this attribute occur in Circle more than 50% of the time, and less than 10% of the time in Triangle
	# if ( $h->{ CircleChance } > 50 && $h->{ TriangleChance } < 10 ) {
	#    Do something here.
	#    E.g. Store another result $h
	# }
}

while( <$dataIn1> ) {
    chomp ;
    getdata( $_ ) ;
}

while( <$dataIn2> ) {
    chomp ;
    getattrs( $_ ) ;
}

my @result;
for( my $j = 0 ; $j < @{$attrs} ; ++$j ) {
    my %subres ;
	my $id = $attrs->[$j][0] ;
    @subres{@{$data}} = ( 0 ) x @{$attrs->[0]} ;
    for( my $i = 1 ; $i < @{$attrs->[$j]} ; ++$i ) {
        if ( $attrs->[$j][$i] == 1 ) {
            ++$subres{ $data->[$i-1]}  ; 
        }
    } ;
	# You could potentially start calculating hit count percentages per category here:
	calcPercentages( \%subres ) ;
    push @result, { $id => \%subres } ;
}
print Dumper(\@result) ;