Re: Efficient Unique Nested Combinations

I don't know anything about Algorithm::Loops, but given your code above, there is no need for the intermediate array @list. Instead, you can work out uniqueness as you go by using the keys of a hash:

#!/usr/bin/perl -w
use strict;
use Algorithm::Loops qw(NestedLoops);


my @symbol = (
   [ 'a', 'b', 'c' ],
   [ 'a', 'b', 'c'  ],
   [ 'a', 'b', 'c'  ],
   [ 'c', 'd', 'e'  ],
);

my $iter = NestedLoops(\@symbol);
my %seen;

while (my @list = $iter->()) {
    my $listString = join ('',sort @list);
    $seen{$listString}++
}

my @sortedUniq = sort (keys %seen);

foreach my $sortedUniq (@sortedUniq) {
    print $sortedUniq,"\n";
}
[download]

Clint

UPDATE - Benchmarks added

I compared the array method to the hash method, both for data that was all the same, and for data that was completely different, the results were:


                 Rate array_diff array_same  hash_diff  hash_same
    array_diff  916/s         --       -10%       -16%       -25%
    array_same 1012/s        11%         --        -7%       -18%
    hash_diff  1092/s        19%         8%         --       -11%
    hash_same  1229/s        34%        21%        13%         --
[download]

Code for benchmarks:


#!/usr/bin/perl -w
use strict;
use Algorithm::Loops qw(NestedLoops);
use Benchmark qw(cmpthese);


my @same = (
   [ 'a', 'a', 'a' ],
   [ 'a', 'a', 'a'  ],
   [ 'a', 'a', 'a'  ],
   [ 'a', 'a', 'a'  ],
);

my @different = (
   [ 'a', 'b', 'c' ],
   [ 'd', 'e', 'f'  ],
   [ 'g', 'h', 'i'  ],
   [ 'j', 'k', 'l'  ],
);



sub array {
    my $symbols = shift;
    my @all;
    my $iter = NestedLoops($symbols);
    my @list;
    while (@list = $iter->()) {
        my @sortedList = sort @list;
        my $listString = join ('',@sortedList);
        push @all, $listString;
        }

    my @uniq = keys %{{ map { $_ => 1 } @all }};
    my @sortedUniq = sort (@uniq);

}

sub hash {
    my $symbols = shift;
    my $iter = NestedLoops($symbols);
    my %seen;

    while (my @list = $iter->()) {
        my $listString = join ('',sort @list);
        $seen{$listString}++
    }

    my @sortedUniq = sort (keys %seen);
}

cmpthese(5000, {
    array_same => sub { array(\@same)},
    array_diff => sub { array(\@different)},
    hash_same  => sub { hash(\@same)},
    hash_diff  => sub { hash(\@different)},
});
[download]

Comment on Re: Efficient Unique Nested Combinations Select or Download Code