Phpml\Clustering\KMeans

Complexity

Total Complexity

8

Size/Duplication

Total Lines	56
Duplicated Lines	0 %

Coupling/Cohesion

Components	1
Dependencies	2

Importance

Changes

0

3 Methods

Rating	Name	Duplication	Size	Complexity
A	__construct()	0	9	2
A	cluster()	0	14	3
A	acluster()	0	14	3

<?php

declare(strict_types=1);

namespace Phpml\Clustering;

use Phpml\Clustering\KMeans\Space;
use Phpml\Exception\InvalidArgumentException;

class KMeans implements Clusterer
{
    public const INIT_RANDOM = 1;

    public const INIT_KMEANS_PLUS_PLUS = 2;

    /**
     * @var int
     */
    private $clustersNumber;

    /**
     * @var int
     */
    private $initialization;

    public function __construct(int $clustersNumber, int $initialization = self::INIT_KMEANS_PLUS_PLUS)
    {
        if ($clustersNumber <= 0) {
            throw new InvalidArgumentException('Invalid clusters number');
        }

        $this->clustersNumber = $clustersNumber;
        $this->initialization = $initialization;
    }

    public function cluster(array $samples): array
    {
        $space = new Space(count($samples[0]));
        foreach ($samples as $sample) {
            $space->addPoint($sample);
        }

        $clusters = [];
        foreach ($space->cluster($this->clustersNumber, $this->initialization) as $cluster) {
            $clusters[] = $cluster->getPoints();
        }

        return $clusters;
    }

    public function acluster(array $samples): array
    {
        $space = new Space(count(reset($samples)));
        foreach ($samples as $key => $sample) {
            $space->addPointWithLabels($sample, $key);
        }

        $clusters = [];
        foreach ($space->cluster($this->clustersNumber, $this->initialization) as $cluster) {
            $clusters[] = $cluster->getPointsWithLabels();
        }

        return $clusters;
    }
}