AI-XGBoost

 view release on metacpan or  search on metacpan

examples/basic.pl  view on Meta::CPAN

use 5.010;
use aliased 'AI::XGBoost::DMatrix';
use AI::XGBoost qw(train);

# We are going to solve a binary classification problem:
#  Mushroom poisonous or not

my $train_data = DMatrix->From(file => 'agaricus.txt.train');
my $test_data = DMatrix->From(file => 'agaricus.txt.test');

# With XGBoost we can solve this problem using 'gbtree' booster
#  and as loss function a logistic regression 'binary:logistic'
#  (Gradient Boosting Regression Tree)
# XGBoost Tree Booster has a lot of parameters that we can tune
# (https://github.com/dmlc/xgboost/blob/master/doc/parameter.md)

my $booster = train(data => $train_data, number_of_rounds => 10, params => {
        objective => 'binary:logistic',
        eta => 1.0,
        max_depth => 2,
        silent => 1
    });

# For binay classification predictions are probability confidence scores in [0, 1]
#  indicating that the label is positive (1 in the first column of agaricus.txt.test)
my $predictions = $booster->predict(data => $test_data);

say join "\n", @$predictions[0 .. 10];

examples/iris.pl  view on Meta::CPAN

# XGBoost uses number for "class" so we are going to codify classes
my %class = (
    setosa => 0,
    versicolor => 1,
    virginica => 2
);

my $iris = Data::Dataset::Classic::Iris::get();

# Split train and test, label and features
my $train_dataset = [map {$iris->{$_}} grep {$_ ne 'species'} keys %$iris];
my $test_dataset = [map {$iris->{$_}} grep {$_ ne 'species'} keys %$iris];

sub transpose {
# Transposing without using PDL, Data::Table, Data::Frame or other modules
# to keep minimal dependencies
    my $array = shift;
    my @aux = ();
    for my $row (@$array) {
        for my $column (0 .. scalar @$row - 1) {
            push @{$aux[$column]}, $row->[$column];
        }
    }
    return \@aux;
}

$train_dataset = transpose($train_dataset);
$test_dataset = transpose($test_dataset);

my $train_label = [map {$class{$_}} @{$iris->{'species'}}];
my $test_label = [map {$class{$_}} @{$iris->{'species'}}];

my $train_data = DMatrix->From(matrix => $train_dataset, label => $train_label);
my $test_data = DMatrix->From(matrix => $test_dataset, label => $test_label);

# Multiclass problems need a diferent objective function and the number
#  of classes, in this case we are using 'multi:softprob' and
#  num_class => 3
my $booster = train(data => $train_data, number_of_rounds => 20, params => {
        max_depth => 3,
        eta => 0.3,
        silent => 1,
        objective => 'multi:softprob',
        num_class => 3
    });

my $predictions = $booster->predict(data => $test_data);

lib/AI/XGBoost.pm  view on Meta::CPAN

use AI::XGBoost::Booster;
use Exporter::Easy ( OK => ['train'] );

our $VERSION = '0.11';    # VERSION

# ABSTRACT: Perl wrapper for XGBoost library L<https://github.com/dmlc/xgboost>

sub train {
    my %args = @_;
    my ( $params, $data, $number_of_rounds ) = @args{qw(params data number_of_rounds)};

    my $booster = AI::XGBoost::Booster->new( cache => [$data] );
    if ( defined $params ) {
        while ( my ( $name, $value ) = each %$params ) {
            $booster->set_param( $name, $value );
        }
    }
    for my $iteration ( 0 .. $number_of_rounds - 1 ) {
        $booster->update( dtrain => $data, iteration => $iteration );
    }
    return $booster;
}

1;

__END__

=pod

misc/using_capi.c  view on Meta::CPAN

#include <stdio.h>
#include <xgboost/c_api.h>

int main() {
    
    DMatrixHandle dtrain;
    DMatrixHandle dtest;
    // Agaricus files can be found in XGBoost demo/data directory
    // Original source: http://archive.ics.uci.edu/ml/datasets/mushroom
    XGDMatrixCreateFromFile("agaricus.txt.test", 0, &dtest);
    XGDMatrixCreateFromFile("agaricus.txt.train", 0, &dtrain);
    DMatrixHandle cache[] = {dtrain};
    BoosterHandle booster;
    XGBoosterCreate(cache, 1, &booster);
    for (int iter = 0; iter < 11; iter++) {
        XGBoosterUpdateOneIter(booster, iter, dtrain);
    }

    bst_ulong out_len;

t/20-dmatrix.t  view on Meta::CPAN

use utf8;

use Test::More tests => 6;

BEGIN {
    use_ok('AI::XGBoost::DMatrix');
}

{
    my $matrix = [ [ 1, 1 ] ];
    my $data = AI::XGBoost::DMatrix->FromMat( matrix => $matrix );
    is( $data->num_row, scalar @$matrix,          'DMatrix constructed has the right number of rows' );
    is( $data->num_col, scalar @{ $matrix->[0] }, 'DMatrix constructed has the right number of cols' );
    is_deeply( [ $data->dims ], [ 1, 2 ], 'DMatrix dim method returns correct dimensions' );
}

{
    my $matrix = [ map { [$_] } 0 .. 9 ];
    my $dmatrix = AI::XGBoost::DMatrix->FromMat( matrix => $matrix );
    my $sliced_matrix = $dmatrix->slice( [ map { $_ % 2 ? $_ : () } 0 .. 9 ] );
    is( $sliced_matrix->num_row, ( scalar @$matrix ) / 2, 'Sliced DMatrix has right number of rows' );
    is( $sliced_matrix->num_col, scalar @{ $matrix->[0] }, 'Sliced DMatrix has right number of cols' );
}

 view all matches for this distribution
 view release on metacpan -  search on metacpan