view release on metacpan or  search on metacpan

README  view on Meta::CPAN

 freqs

    Ratings count matrix.

METHODS

 clear

    Reset the instance.

 add($userprefs)

    Update matrices with user preference data, accepts a HashRef or an
    ArrayRef of HashRefs:

        $s->predict({ StarWars => 5, LOTR => 5, StarTrek => 3, Prometheus => 1 });
        $s->predict({ StarWars => 3, StarTrek => 5, Prometheus => 4 });
        $s->predict([
            { IronMan => 4, Avengers => 5, XMen => 3 },
            { XMen => 5, DarkKnight => 5, SpiderMan => 3 },
        ]);

 predict($userprefs)

    Recommend new items given known item ratings.

        $s->predict({ StarWars => 5, LOTR => 5, Prometheus => 1 });

TODO

    Implement Non-Weighted and Bi-Polar Slope One schemes.

REFERENCES

lib/Algorithm/SlopeOne.pm  view on Meta::CPAN

    for (qw(diffs freqs)) {
        delete $self->{$_};
        $self->{$_} = {};
    }

    return $self;
}


sub add {
    my ($self, $userprefs) = @_;

    my $type = ref $userprefs;
    if ($type eq q(HASH)) {
        $userprefs = [ $userprefs ];
    } elsif ($type eq q(ARRAY)) {
    } else {
        confess q(Expects a HashRef or an ArrayRef of HashRefs);
    }

    for my $ratings (@{$userprefs}) {
        for my $item1 (keys %{$ratings}) {
            for my $item2 (keys %{$ratings}) {
                $self->freqs->{$item1}{$item2} ++;
                $self->diffs->{$item1}{$item2} += $ratings->{$item1} - $ratings->{$item2};
            }
        }
    }

    return $self;
}


sub predict {
    my ($self, $userprefs) = @_;

    confess q(Expects a HashRef)
        unless q(HASH) eq ref $userprefs;

    my (%preds, %freqs);
    while (my ($item, $rating) = each %{$userprefs}) {
        while (my ($diffitem, $diffratings) = each %{$self->diffs}) {
            my $freq = $self->freqs->{$diffitem}{$item};
            next unless defined $freq;
            $preds{$diffitem} += $diffratings->{$item} + ($freq * $rating);
            $freqs{$diffitem} += $freq;
        }
    }

    return {
        map { $_ => $preds{$_} / $freqs{$_} }
        grep { not exists $userprefs->{$_} }
        keys %preds
    };
}


1;

__END__

=pod

lib/Algorithm/SlopeOne.pm  view on Meta::CPAN

=head2 freqs

Ratings count matrix.

=head1 METHODS

=head2 clear

Reset the instance.

=head2 add($userprefs)

Update matrices with user preference data, accepts a HashRef or an ArrayRef of HashRefs:

    $s->predict({ StarWars => 5, LOTR => 5, StarTrek => 3, Prometheus => 1 });
    $s->predict({ StarWars => 3, StarTrek => 5, Prometheus => 4 });
    $s->predict([
        { IronMan => 4, Avengers => 5, XMen => 3 },
        { XMen => 5, DarkKnight => 5, SpiderMan => 3 },
    ]);

=head2 predict($userprefs)

Recommend new items given known item ratings.

    $s->predict({ StarWars => 5, LOTR => 5, Prometheus => 1 });

=for Pod::Coverage new

=head1 TODO

Implement I<Non-Weighted> and I<Bi-Polar Slope One> schemes.