#! /local/bin/perl
use strict;
use warnings;

#Declare hash to pull IDs and corresponding degrees into from file
my %degree;
my %newdegree;
my @geneID_1;
my @geneID_2;

my $filename = "edges.txt";   #Set a variable for our file name
open(my $fh, "<", $filename) or die "Can't open file $filename.";  #Open the file edges.txt
while (<$fh>) {
  if ($_ =~ m/(\S+)\t(\S+)/) {           #Match the IDs in the file to $1 and $2
    $degree{$1}++;                       #Count the appearance of each ID, and store this as  
    $degree{$2}++;                       #the value for that key (this will be the degree)
     push (@geneID_1, $1);
     push (@geneID_2, $2);
   }}
close $fh;   #Close the file edges.txt

#Calling the following subroutines
DegreeDistribution();
RandomSequence();
DegreeRan();

#Subroutines can be found below

sub DegreeDistribution{  #Determines the degree distribution (i.e. frequency of each degree)
    my %degree_distribution;
    $degree_distribution{$_}++ for values %degree;  #Creates a hash with the keys as the degrees and the values as the frequencies
    for my $id (keys %degree) {               #This corresponds each below to it's key
    my $d = $degree{$id};                   #This is the degree value corresponding to its gene ID
    my $freq = $degree_distribution{$d};    #This is the frequency value corresponding to its gene ID???
    print "$id has degree:\t$d\t(freq: $freq)\n";
}}

sub RandomSequence{    #Generates a hash of random ID interactions and each IDs degree
	my $length = scalar (@geneID_1);
	for (my $i=0; $i<$length; $i++){
	my $ID = int(rand($length));
	my $new_id1 = $geneID_1[$ID];
	my $new_id2 = $geneID_2[$ID];
	$newdegree{$new_id1}++;
	$newdegree{$new_id2}++;
}}


sub DegreeRan{     #same as sub DegreeDistribution but for the random sequence
    my %degree_distribution;
    $degree_distribution{$_}++ for values %newdegree;  #Creates a hash with the keys as the degrees and the values as the frequencies
    for my $id (keys %degree) {               #This corresponds each below to it's key
    my $d = $degree{$id};                   #This is the degree value corresponding to its gene ID
    my $freq = $degree_distribution{$d};    #This is the frequency value corresponding to its gene ID???
    print "$id has degree:\t$d\t(freq: $freq)\n";
}}

exit;