workshops_recommender_systems/Datasets/ml-100k/allbut.pl

35 lines
716 B
Perl
Raw Normal View History

2020-05-21 13:42:50 +02:00
#!/usr/local/bin/perl
# get args
if (@ARGV < 3) {
print STDERR "Usage: $0 base_name start stop max_test [ratings ...]\n";
exit 1;
}
$basename = shift;
$start = shift;
$stop = shift;
$maxtest = shift;
# open files
open( TESTFILE, ">$basename.test" ) or die "Cannot open $basename.test for writing\n";
open( BASEFILE, ">$basename.base" ) or die "Cannot open $basename.base for writing\n";
# init variables
$testcnt = 0;
while (<>) {
($user) = split;
if (! defined $ratingcnt{$user}) {
$ratingcnt{$user} = 0;
}
++$ratingcnt{$user};
if (($testcnt < $maxtest || $maxtest <= 0)
&& $ratingcnt{$user} >= $start && $ratingcnt{$user} <= $stop) {
++$testcnt;
print TESTFILE;
}
else {
print BASEFILE;
}
}