<?php

namespace Rubix\ML\Tests;

use Rubix\ML\Online;
use Rubix\ML\Pipeline;
use Rubix\ML\DataType;
use Rubix\ML\Estimator;
use Rubix\ML\Persistable;
use Rubix\ML\Probabilistic;
use Rubix\ML\EstimatorType;
use Rubix\ML\Datasets\Unlabeled;
use Rubix\ML\AnomalyDetectors\Scoring;
use Rubix\ML\Datasets\Generators\Blob;
use Rubix\ML\Classifiers\SoftmaxClassifier;
use Rubix\ML\Transformers\PolynomialExpander;
use Rubix\ML\Transformers\ZScaleStandardizer;
use Rubix\ML\Datasets\Generators\Agglomerate;
use Rubix\ML\CrossValidation\Metrics\Accuracy;
use Rubix\ML\Exceptions\RuntimeException;
use PHPUnit\Framework\TestCase;

/**
 * @group MetaEstimators
 * @covers \Rubix\ML\Pipeline
 */
class PipelineTest extends TestCase
{
    protected const TRAIN_SIZE = 512;

    protected const TEST_SIZE = 256;

    protected const MIN_SCORE = 0.8;

    protected const RANDOM_SEED = 0;

    /**
     * @var Agglomerate
     */
    protected $generator;

    /**
     * @var Pipeline
     */
    protected $estimator;

    /**
     * @var Accuracy
     */
    protected $metric;

    /**
     * @before
     */
    protected function setUp() : void
    {
        $this->generator = new Agglomerate([
            'red' => new Blob([255, 32, 0], 50.0),
            'green' => new Blob([0, 128, 0], 10.0),
            'blue' => new Blob([0, 32, 255], 30.0),
        ], [0.5, 0.2, 0.3]);

        $this->estimator = new Pipeline([
            new PolynomialExpander(2),
            new ZScaleStandardizer(),
        ], new SoftmaxClassifier(), true);

        $this->metric = new Accuracy();

        srand(self::RANDOM_SEED);
    }

    protected function assertPreConditions() : void
    {
        $this->assertFalse($this->estimator->trained());
    }

    /**
     * @test
     */
    public function build() : void
    {
        $this->assertInstanceOf(Pipeline::class, $this->estimator);
        $this->assertInstanceOf(Online::class, $this->estimator);
        $this->assertInstanceOf(Probabilistic::class, $this->estimator);
        $this->assertInstanceOf(Scoring::class, $this->estimator);
        $this->assertInstanceOf(Persistable::class, $this->estimator);
        $this->assertInstanceOf(Estimator::class, $this->estimator);
    }

    /**
     * @test
     */
    public function type() : void
    {
        $this->assertEquals(EstimatorType::classifier(), $this->estimator->type());
    }

    /**
     * @test
     */
    public function compatibility() : void
    {
        $expected = [
            DataType::continuous(),
        ];

        $this->assertEquals($expected, $this->estimator->compatibility());
    }

    /**
     * @test
     */
    public function params() : void
    {
        $expected = [
            'transformers' => [
                new PolynomialExpander(2),
                new ZScaleStandardizer(),
            ],
            'estimator' => new SoftmaxClassifier(),
            'elastic' => true,
        ];

        $this->assertEquals($expected, $this->estimator->params());
    }

    /**
     * @test
     */
    public function trainPartialPredict() : void
    {
        $training = $this->generator->generate(self::TRAIN_SIZE);
        $testing = $this->generator->generate(self::TEST_SIZE);

        $folds = $training->stratifiedFold(3);

        $this->estimator->train($folds[0]);
        $this->estimator->partial($folds[1]);
        $this->estimator->partial($folds[2]);

        $this->assertTrue($this->estimator->trained());

        $predictions = $this->estimator->predict($testing);

        $score = $this->metric->score($predictions, $testing->labels());

        $this->assertGreaterThanOrEqual(self::MIN_SCORE, $score);
    }

    /**
     * @test
     */
    public function predictUntrained() : void
    {
        $this->expectException(RuntimeException::class);

        $this->estimator->predict(Unlabeled::quick());
    }
}