view release on metacpan or  search on metacpan

lib/Algorithm/AM/Batch.pm  view on Meta::CPAN

            }

            if($self->end_repeat_hook){
                # pass in self, test item, data, and result
                $self->end_repeat_hook->($self, $test_item,
                    $iteration, $excluded_items, $result);
            }
            push @item_results, $result;
            $iteration++;
        }

        if($self->end_test_hook){
            $self->end_test_hook->($self, $test_item, @item_results);
        }

        push @all_results, @item_results;
    }

    if($log->is_info){
        my ( $sec, $min, $hour ) = localtime();
        $log->info(
            sprintf( "Time: %2s:%02s:%02s", $hour, $min, $sec ) );
    }

    if($self->end_hook){
        $self->end_hook->($self, @all_results);
    }
    $self->_set_test_set(undef);
    return @all_results;
}

# log the summary printouts from the input result object
sub _log_result {
    my ($result) = @_;

    $log->info(${$result->statistical_summary});

    $log->info(${$result->analogical_set_summary()});

    if($log->is_debug){
        $log->debug(${ $result->gang_summary(1) });
    }elsif($log->is_info){
        $log->info(${ $result->gang_summary(0) })
    }
    return;
}

# create the training set for this iteration, calling training_item_hook and
# updating excluded_items along the way
sub _make_training_set {
    my ($self, $test_item, $iteration) = @_;
    my $training_set;

    # $self->_set_excluded_items([]);
    my @excluded_items;
    # Cap the amount of considered data if specified
    my $max = defined $self->max_training_items ?
        int($self->max_training_items) :
        $self->training_set->size;

    # use the original DataSet object if there are no settings
    # that would trim items from it
    if(!$self->training_item_hook &&
            ($self->probability == 1) &&
            $max >= $self->training_set->size){
        $training_set = $self->training_set;
    }else{
        # otherwise, make a new set with just the selected
        # items
        $training_set = Algorithm::AM::DataSet->new(
            cardinality => $self->training_set->cardinality);

        # don't try to add more items than we have!
        my $num_items = ($max > $self->training_set->size) ?
            $self->training_set->size :
            $max;
        for my $data_index ( 0 .. $num_items - 1 ) {
            my $training_item =
                $self->training_set->get_item($data_index);
            # skip this data item if the training_item_hook returns false
            if($self->training_item_hook &&
                    !$self->training_item_hook->($self,
                        $test_item, $iteration, $training_item)
                    ){
                push @excluded_items, $training_item;
                next;
            }
            # skip this data item with probability $self->{probability}
            if($self->probability != 1 &&
                    rand() > $self->probability){
                push @excluded_items, $training_item;
                next;
            }
            $training_set->add_item($training_item);
        }
    }
    # $self->_set_excluded_items(\@excluded_items);
    return ($training_set, \@excluded_items);
}

sub _set_test_set {
    my ($self, $test_set) = @_;
    $self->{test_set} = $test_set;
    return;
}

1;

__END__

=pod

=encoding UTF-8

=head1 NAME

Algorithm::AM::Batch - Classify items in batch mode

=head1 VERSION

version 3.13