view release on metacpan or  search on metacpan

t/Algorithm/LibLinear.t  view on Meta::CPAN

use strict;
use warnings;
use File::Temp;
use Test::Exception;
use Test::LeakTrace;
use Test::More;

BEGIN { use_ok 'Algorithm::LibLinear' }

my $input_data_set = do { local $/; <DATA> };

{
    my $learner = new_ok 'Algorithm::LibLinear' => [
        cost => 1,
        epsilon => 0.01,
        solver => 'L2R_L2LOSS_SVC',
        weights => [
            +{ label => 1, weight => 1, },
            +{ label => -1, weight => 1, },
        ],
    ];

    my $data_set =
        Algorithm::LibLinear::DataSet->load(string => $input_data_set);
    isa_ok $data_set, 'Algorithm::LibLinear::DataSet';

    my ($found_cost, $found_loss_sensitivity) = @{
        $learner->find_parameters(
            data_set => $data_set,
            initial_cost => 1,
            num_folds => 5,
        )
    };
    my ($found_cost2) = @{
        $learner->find_cost_parameter(
            data_set => $data_set,
            initial => 1,
            num_folds => 5,
        )
    };
    is $found_cost, $found_cost2;
    is $found_loss_sensitivity, undef;

    throws_ok {
        my $learner = Algorithm::LibLinear->new(
            solver => 'L2R_L2LOSS_SVC_DUAL',
        );
        $learner->find_parameters(data_set => $data_set, num_folds => 5);
    } qr/unsupported/;

    my $classifier = $learner->train(data_set => $data_set);
    isa_ok $classifier, 'Algorithm::LibLinear::Model';

    my @labels = sort { $a <=> $b } @{ $classifier->class_labels };
    is_deeply \@labels, [-1, 1];
    ok(
        +(not $classifier->is_probability_model),
        'L2R_L2LOSS_SVC_DUAL is a model for SVC.',
    );
    is $classifier->num_classes, 2;
    is $classifier->num_features, 13;  # bias factor is not counted in.

    is(
        $classifier->predict(feature => $data_set->as_arrayref->[0]{feature}),
        1
    );

    my $accuracy =
        $learner->cross_validation(data_set => $data_set, num_folds => 5);
    cmp_ok $accuracy, '>', 0.8;

    my $temp_file;
    {
        my $guard = File::Temp->new;
        $temp_file = $guard->filename;
        $classifier->save(filename => $temp_file);
        ok +(-s $temp_file > 0), 'Model object can be written in a file.';

        lives_ok {
            Algorithm::LibLinear::Model->load(filename => $guard->filename);
        } 'Model can be resumed from a file.';
    }

    # $temp_file is no longer exists here.
    throws_ok {
        Algorithm::LibLinear::Model->load(filename => $temp_file);
    } qr/Failed to load a model/i;
}

no_leaks_ok {
    my $learner = Algorithm::LibLinear->new(
        cost => 1,
        epsilon => 0.1,
        solver => 'L2R_L2LOSS_SVC_DUAL',
        weights => [
            +{ label => 1, weight => 1, },
            +{ label => -1, weight => 1, },
        ],
    );
    my $data_set =
        Algorithm::LibLinear::DataSet->load(string => $input_data_set);
    my $classifier = $learner->train(data_set => $data_set);
    my $labels = $classifier->class_labels;
};

done_testing;

# This input data is copied from heart_scale file in LIBLINEAR distribution.
__DATA__
+1 1:0.708333 2:1 3:1 4:-0.320755 5:-0.105023 6:-1 7:1 8:-0.419847 9:-1 10:-0.225806 12:1 13:-1 
-1 1:0.583333 2:-1 3:0.333333 4:-0.603774 5:1 6:-1 7:1 8:0.358779 9:-1 10:-0.483871 12:-1 13:1 
+1 1:0.166667 2:1 3:-0.333333 4:-0.433962 5:-0.383562 6:-1 7:-1 8:0.0687023 9:-1 10:-0.903226 11:-1 12:-1 13:1 
-1 1:0.458333 2:1 3:1 4:-0.358491 5:-0.374429 6:-1 7:-1 8:-0.480916 9:1 10:-0.935484 12:-0.333333 13:1 
-1 1:0.875 2:-1 3:-0.333333 4:-0.509434 5:-0.347032 6:-1 7:1 8:-0.236641 9:1 10:-0.935484 11:-1 12:-0.333333 13:-1 
-1 1:0.5 2:1 3:1 4:-0.509434 5:-0.767123 6:-1 7:-1 8:0.0534351 9:-1 10:-0.870968 11:-1 12:-1 13:1 
+1 1:0.125 2:1 3:0.333333 4:-0.320755 5:-0.406393 6:1 7:1 8:0.0839695 9:1 10:-0.806452 12:-0.333333 13:0.5 
+1 1:0.25 2:1 3:1 4:-0.698113 5:-0.484018 6:-1 7:1 8:0.0839695 9:1 10:-0.612903 12:-0.333333 13:1 
+1 1:0.291667 2:1 3:1 4:-0.132075 5:-0.237443 6:-1 7:1 8:0.51145 9:-1 10:-0.612903 12:0.333333 13:1 
+1 1:0.416667 2:-1 3:1 4:0.0566038 5:0.283105 6:-1 7:1 8:0.267176 9:-1 10:0.290323 12:1 13:1 
-1 1:0.25 2:1 3:1 4:-0.226415 5:-0.506849 6:-1 7:-1 8:0.374046 9:-1 10:-0.83871 12:-1 13:1 
-1 2:1 3:1 4:-0.0943396 5:-0.543379 6:-1 7:1 8:-0.389313 9:1 10:-1 11:-1 12:-1 13:1 
-1 1:-0.375 2:1 3:0.333333 4:-0.132075 5:-0.502283 6:-1 7:1 8:0.664122 9:-1 10:-1 11:-1 12:-1 13:-1 
+1 1:0.333333 2:1 3:-1 4:-0.245283 5:-0.506849 6:-1 7:-1 8:0.129771 9:-1 10:-0.16129 12:0.333333 13:-1 
-1 1:0.166667 2:-1 3:1 4:-0.358491 5:-0.191781 6:-1 7:1 8:0.343511 9:-1 10:-1 11:-1 12:-0.333333 13:-1 
-1 1:0.75 2:-1 3:1 4:-0.660377 5:-0.894977 6:-1 7:-1 8:-0.175573 9:-1 10:-0.483871 12:-1 13:-1 
+1 1:-0.291667 2:1 3:1 4:-0.132075 5:-0.155251 6:-1 7:-1 8:-0.251908 9:1 10:-0.419355 12:0.333333 13:1 
+1 2:1 3:1 4:-0.132075 5:-0.648402 6:1 7:1 8:0.282443 9:1 11:1 12:-1 13:1 
-1 1:0.458333 2:1 3:-1 4:-0.698113 5:-0.611872 6:-1 7:1 8:0.114504 9:1 10:-0.419355 12:-1 13:-1 
-1 1:-0.541667 2:1 3:-1 4:-0.132075 5:-0.666667 6:-1 7:-1 8:0.633588 9:1 10:-0.548387 11:-1 12:-1 13:1 
+1 1:0.583333 2:1 3:1 4:-0.509434 5:-0.52968 6:-1 7:1 8:-0.114504 9:1 10:-0.16129 12:0.333333 13:1 
-1 1:-0.208333 2:1 3:-0.333333 4:-0.320755 5:-0.456621 6:-1 7:1 8:0.664122 9:-1 10:-0.935484 12:-1 13:-1 
-1 1:-0.416667 2:1 3:1 4:-0.603774 5:-0.191781 6:-1 7:-1 8:0.679389 9:-1 10:-0.612903 12:-1 13:-1 
-1 1:-0.25 2:1 3:1 4:-0.660377 5:-0.643836 6:-1 7:-1 8:0.0992366 9:-1 10:-0.967742 11:-1 12:-1 13:-1 
-1 1:0.0416667 2:-1 3:-0.333333 4:-0.283019 5:-0.260274 6:1 7:1 8:0.343511 9:1 10:-1 11:-1 12:-0.333333 13:-1 
-1 1:-0.208333 2:-1 3:0.333333 4:-0.320755 5:-0.319635 6:-1 7:-1 8:0.0381679 9:-1 10:-0.935484 11:-1 12:-1 13:-1 
-1 1:-0.291667 2:-1 3:1 4:-0.169811 5:-0.465753 6:-1 7:1 8:0.236641 9:1 10:-1 12:-1 13:-1 
-1 1:-0.0833333 2:-1 3:0.333333 4:-0.509434 5:-0.228311 6:-1 7:1 8:0.312977 9:-1 10:-0.806452 11:-1 12:-1 13:-1 
+1 1:0.208333 2:1 3:0.333333 4:-0.660377 5:-0.525114 6:-1 7:1 8:0.435115 9:-1 10:-0.193548 12:-0.333333 13:1 
-1 1:0.75 2:-1 3:0.333333 4:-0.698113 5:-0.365297 6:1 7:1 8:-0.0992366 9:-1 10:-1 11:-1 12:-0.333333 13:-1 
+1 1:0.166667 2:1 3:0.333333 4:-0.358491 5:-0.52968 6:-1 7:1 8:0.206107 9:-1 10:-0.870968 12:-0.333333 13:1 
-1 1:0.541667 2:1 3:1 4:0.245283 5:-0.534247 6:-1 7:1 8:0.0229008 9:-1 10:-0.258065 11:-1 12:-1 13:0.5 
-1 1:-0.666667 2:-1 3:0.333333 4:-0.509434 5:-0.593607 6:-1 7:-1 8:0.51145 9:-1 10:-1 11:-1 12:-1 13:-1 
+1 1:0.25 2:1 3:1 4:0.433962 5:-0.086758 6:-1 7:1 8:0.0534351 9:1 10:0.0967742 11:1 12:-1 13:1 
+1 1:-0.125 2:1 3:1 4:-0.0566038 5:-0.6621 6:-1 7:1 8:-0.160305 9:1 10:-0.709677 12:-1 13:1 
+1 1:-0.208333 2:1 3:1 4:-0.320755 5:-0.406393 6:1 7:1 8:0.206107 9:1 10:-1 11:-1 12:0.333333 13:1