patent #, char1, char2, char3, ... , char480 
 
1234567,1,0,1,0,1,0, ... (480 characteristics) 
      (x 8 million lines)

##</code><code>##

	

#!/usr/bin/perl 
use strict; 
 
my(@patno1,@patno2,@record1,@record2); 
 
my $startat=@ARGV[0]; 
my $endat=@ARGV[1]; 
 
open(OUT, "<patents.csv")|| die("Could not open patents.csv file!\n"); 
my @lines=<OUT>; 
close(OUT); 
 
#clear variance file if it exists 
open(OUT, ">variance.csv")|| die("Could not open file variance.csv!\n"); 
close(OUT); 
 
map(chomp,@lines); 
 
# iterate over all patents 
for(my $i=$startat;$i<=$endat;$i++) 
{ 
	@record1=split(/\,/,$lines[$i]); 
	$patno1=shift(@record1);  
	 
      # iterate through other lines to compare 
	for(my $j=$i+1;$j<$#lines;$j++) 
	{ 
		@record2=split(/\,/,$lines[$j]); 
		$patno2=shift @record2; 
		 
              my $variance=0; 
		 
		# iterate through each characteristic 
		for(my $k=0;$k<$#record1;$k++) 
		{ 
			if($record1[$k]!=$record2[$k]) 
			{ 
				$variance++;					 
			} 
		} 
		 
             open(OUT, ">>variance.csv")|| die("Could not open file variance.csv!\n"); 
		print OUT $patno1.",".$patno2.",".$variance."\n"; 
		close(OUT);		 
			 
		 
	} 
}