#!/usr/bin/perl

  use strict;
  use warnings;

#exit if there's more or less than two arguments
  if(scalar(@ARGV)!= 2) { print "\nUsage script.pl <file name> <number of columns>\n";
                      exit();
                       }

##you will print results but first remove any previous files
      my $remove_random = "random.txt";
        if (unlink($remove_random) == 1) {
                        print "Existing \"random.txt\" file was removed\n";
                          }
 ## proceed by opening  the file
 
my $ro = $ARGV[0];
    open(DATA3, $ro);
  
        while ($ro = <DATA3>)
            {
                      
            #now make a file for the output
        my $output_r = "random.txt"; 
           if (! open(POS, ">>$output_r") ) {
            print "Cannot open file \"$output_r\" to write to!!\n\n";
        exit;
        }  
   
# now randomly generate the columns to count z's
# but first declare variables

 my $randomize = $ARGV[1];      # the number of columns entered at command-line
  
  my $range = $randomize;       # the maximum number of columns
  my $minimum = 1;            # the minimum number of columns
  my $y;                    # the increasing number of columns
  my $x;                  # the random genome selected
  my $count;             # count the number of randomisations done
  my @uniform = ();
  my @data = ();
  my $n = 0;
  
#loop through the selection process

  for($y = 1; $y < $range +1; $y++){    # make selection from 2 columns to 96 columns
           
                      print "\n";       # separate each random selection by a space
                      
           for($x = 1; $x < $y; $x++){           # do the random column selection

           #randomly select columns
           my $random_number = int(rand($range)) + $minimum;
  
           #print the columns selected at random
           print $random_number . "\n";
           $count++;
                      
                     
## random columns for selection have been created
## now compare the elements of each of the groups selected and count only the number of z's common to all columns for each group!
## i.e. count only those times that have z's in all of them (i.e. the group)
           
  ##this bit of the script is not working ###

 #        @uniform = $random_number;
                                
#                    my @temp =   map { [ $_[1], $_[0], $_ ] } # step 1
   #                          map { $_->[2] } # step 2
   #                           @uniform;

#Count array elements that match a pattern
#In a scalar context, grep returns a count of the selected elements.
#foreach my $num_genes(@temp){
#print POS "@temp\n";
#}
              }
       }
  
#evaluate the number of random columns/columns selections used for this analysis

          print POS "\n". $count*30 ." random columns selections were used!!\n";
          print  "\n". $count*30 ." random columns selections were used!!\n"; 
  }
            # the end #
            
              my $count2;
                  open (FILE, "random.txt") or die"can't count clusters\n";
                    $count2++ while <FILE>;
                  print "\n$count2 round(s) done\n";