php-ml/tests/Classification/Ensemble/BaggingTest.php

130 lines
4.7 KiB
PHP
Raw Normal View History

2017-02-07 11:37:56 +00:00
<?php
declare(strict_types=1);
namespace Phpml\Tests\Classification\Ensemble;
2017-02-07 11:37:56 +00:00
use Phpml\Classification\DecisionTree;
use Phpml\Classification\Ensemble\Bagging;
2017-02-07 11:37:56 +00:00
use Phpml\Classification\NaiveBayes;
use Phpml\ModelManager;
use PHPUnit\Framework\TestCase;
class BaggingTest extends TestCase
{
private $data = [
['sunny', 85, 85, 'false', 'Dont_play'],
['sunny', 80, 90, 'true', 'Dont_play'],
['overcast', 83, 78, 'false', 'Play'],
['rain', 70, 96, 'false', 'Play'],
['rain', 68, 80, 'false', 'Play'],
['rain', 65, 70, 'true', 'Dont_play'],
['overcast', 64, 65, 'true', 'Play'],
['sunny', 72, 95, 'false', 'Dont_play'],
['sunny', 69, 70, 'false', 'Play'],
['rain', 75, 80, 'false', 'Play'],
['sunny', 75, 70, 'true', 'Play'],
['overcast', 72, 90, 'true', 'Play'],
['overcast', 81, 75, 'false', 'Play'],
['rain', 71, 80, 'true', 'Dont_play'],
2017-02-07 11:37:56 +00:00
];
private $extraData = [
['scorching', 90, 95, 'false', 'Dont_play'],
['scorching', 0, 0, 'false', 'Dont_play'],
2017-02-07 11:37:56 +00:00
];
public function testPredictSingleSample()
{
[$data, $targets] = $this->getData($this->data);
2017-02-07 11:37:56 +00:00
$classifier = $this->getClassifier();
// Testing with default options
$classifier->train($data, $targets);
$this->assertEquals('Dont_play', $classifier->predict(['sunny', 78, 72, 'false']));
$this->assertEquals('Play', $classifier->predict(['overcast', 60, 60, 'false']));
$this->assertEquals('Dont_play', $classifier->predict(['rain', 60, 60, 'true']));
[$data, $targets] = $this->getData($this->extraData);
2017-02-07 11:37:56 +00:00
$classifier->train($data, $targets);
$this->assertEquals('Dont_play', $classifier->predict(['scorching', 95, 90, 'true']));
$this->assertEquals('Play', $classifier->predict(['overcast', 60, 60, 'false']));
return $classifier;
}
public function testSaveAndRestore(): void
2017-02-07 11:37:56 +00:00
{
[$data, $targets] = $this->getData($this->data);
2017-02-07 11:37:56 +00:00
$classifier = $this->getClassifier(5);
$classifier->train($data, $targets);
$testSamples = [['sunny', 78, 72, 'false'], ['overcast', 60, 60, 'false']];
$predicted = $classifier->predict($testSamples);
$filename = 'bagging-test-'.random_int(100, 999).'-'.uniqid();
2017-02-07 11:37:56 +00:00
$filepath = tempnam(sys_get_temp_dir(), $filename);
$modelManager = new ModelManager();
$modelManager->saveToFile($classifier, $filepath);
$restoredClassifier = $modelManager->restoreFromFile($filepath);
$this->assertEquals($classifier, $restoredClassifier);
$this->assertEquals($predicted, $restoredClassifier->predict($testSamples));
}
public function testBaseClassifiers(): void
2017-02-07 11:37:56 +00:00
{
[$data, $targets] = $this->getData($this->data);
2017-02-07 11:37:56 +00:00
$baseClassifiers = $this->getAvailableBaseClassifiers();
foreach ($baseClassifiers as $base => $params) {
$classifier = $this->getClassifier();
$classifier->setClassifer($base, $params);
$classifier->train($data, $targets);
$baseClassifier = new $base(...array_values($params));
$baseClassifier->train($data, $targets);
$testData = [['sunny', 78, 72, 'false'], ['overcast', 60, 60, 'false'], ['rain', 60, 60, 'true']];
foreach ($testData as $test) {
$result = $classifier->predict($test);
$baseResult = $classifier->predict($test);
$this->assertEquals($result, $baseResult);
}
}
}
protected function getClassifier($numBaseClassifiers = 50)
{
$classifier = new Bagging($numBaseClassifiers);
$classifier->setSubsetRatio(1.0);
$classifier->setClassifer(DecisionTree::class, ['depth' => 10]);
2017-02-07 11:37:56 +00:00
return $classifier;
}
protected function getAvailableBaseClassifiers()
{
return [
DecisionTree::class => ['depth' => 5],
NaiveBayes::class => [],
2017-02-07 11:37:56 +00:00
];
}
private function getData($input)
{
// Populating input data to a size large enough
// for base classifiers that they can work with a subset of it
$populated = [];
for ($i = 0; $i < 20; ++$i) {
2017-02-07 11:37:56 +00:00
$populated = array_merge($populated, $input);
}
2017-02-07 11:37:56 +00:00
shuffle($populated);
$targets = array_column($populated, 4);
array_walk($populated, function (&$v): void {
2017-02-07 11:37:56 +00:00
array_splice($v, 4, 1);
});
2017-02-07 11:37:56 +00:00
return [$populated, $targets];
}
}