File Manager - BorneoXploit

Editing: KDNeighborsRegressor.php

<?php

namespace Rubix\ML\Regressors;

use Rubix\ML\Learner;
use Rubix\ML\Estimator;
use Rubix\ML\Persistable;
use Rubix\ML\EstimatorType;
use Rubix\ML\Helpers\Stats;
use Rubix\ML\Helpers\Params;
use Rubix\ML\Datasets\Dataset;
use Rubix\ML\Graph\Trees\KDTree;
use Rubix\ML\Graph\Trees\Spatial;
use Rubix\ML\Traits\AutotrackRevisions;
use Rubix\ML\Specifications\DatasetIsLabeled;
use Rubix\ML\Specifications\DatasetIsNotEmpty;
use Rubix\ML\Specifications\SpecificationChain;
use Rubix\ML\Specifications\DatasetHasDimensionality;
use Rubix\ML\Specifications\LabelsAreCompatibleWithLearner;
use Rubix\ML\Specifications\SamplesAreCompatibleWithEstimator;
use Rubix\ML\Exceptions\InvalidArgumentException;
use Rubix\ML\Exceptions\RuntimeException;

/**
 * K-d Neighbors Regressor
 *
 * A fast implementation of KNN Regressor using a spatially-aware binary tree for nearest
 * neighbors search. K-d Neighbors Regressor works by locating the neighborhood of a sample
 * via binary search and then does a brute force search only on the samples close to or
 * within the neighborhood of the unknown sample. The main advantage of K-d Neighbors over
 * brute force KNN is inference speed, however you no longer have the ability to partially
 * train.
 *
 * @category    Machine Learning
 * @package     Rubix/ML
 * @author      Andrew DalPino
 */
class KDNeighborsRegressor implements Estimator, Learner, Persistable
{
    use AutotrackRevisions;

/**
     * The number of neighbors to consider when making a prediction.
     *
     * @var int
     */
    protected int $k;

/**
     * Should we consider the distances of our nearest neighbors when making predictions?
     *
     * @var bool
     */
    protected bool $weighted;

/**
     * The spatial tree used to run nearest neighbor searches.
     *
     * @var Spatial
     */
    protected Spatial $tree;

/**
     * The dimensionality of the training set.
     *
     * @var int|null
     */
    protected ?int $featureCount = null;

/**
     * @param int $k
     * @param bool $weighted
     * @param Spatial|null $tree
     * @throws InvalidArgumentException
     */
    public function __construct(int $k = 5, bool $weighted = false, ?Spatial $tree = null)
    {
        if ($k < 1) {
            throw new InvalidArgumentException('At least 1 neighbor is required'
                . " to make a prediction, $k given.");
        }

$this->k = $k;
        $this->weighted = $weighted;
        $this->tree = $tree ?? new KDTree();
    }

/**
     * Return the estimator type.
     *
     * @internal
     *
     * @return EstimatorType
     */
    public function type() : EstimatorType
    {
        return EstimatorType::regressor();
    }

/**
     * Return the data types that the estimator is compatible with.
     *
     * @internal
     *
     * @return list<\Rubix\ML\DataType>
     */
    public function compatibility() : array
    {
        return $this->tree->kernel()->compatibility();
    }

/**
     * Return the settings of the hyper-parameters in an associative array.
     *
     * @internal
     *
     * @return mixed[]
     */
    public function params() : array
    {
        return [
            'k' => $this->k,
            'weighted' => $this->weighted,
            'tree' => $this->tree,
        ];
    }

/**
     * Has the learner been trained?
     *
     * @return bool
     */
    public function trained() : bool
    {
        return !$this->tree->bare();
    }

/**
     * Return the base k-d tree instance.
     *
     * @return Spatial
     */
    public function tree() : Spatial
    {
        return $this->tree;
    }

/**
     * @param \Rubix\ML\Datasets\Labeled $dataset
     */
    public function train(Dataset $dataset) : void
    {
        SpecificationChain::with([
            new DatasetIsLabeled($dataset),
            new DatasetIsNotEmpty($dataset),
            new SamplesAreCompatibleWithEstimator($dataset, $this),
            new LabelsAreCompatibleWithLearner($dataset, $this),
        ])->check();

$this->featureCount = $dataset->numFeatures();

$this->tree->grow($dataset);
    }

/**
     * Make a prediction based on the nearest neighbors.
     *
     * @param Dataset $dataset
     * @throws RuntimeException
     * @return list<int|float>
     */
    public function predict(Dataset $dataset) : array
    {
        if ($this->tree->bare() or !$this->featureCount) {
            throw new RuntimeException('Estimator has not been trained.');
        }

DatasetHasDimensionality::with($dataset, $this->featureCount)->check();

return array_map([$this, 'predictSample'], $dataset->samples());
    }

/**
     * Predict a single sample and return the result.
     *
     * @internal
     *
     * @param list<string|int|float> $sample
     * @return int|float
     */
    public function predictSample(array $sample)
    {
        [$samples, $labels, $distances] = $this->tree->nearest($sample, $this->k);

if ($this->weighted) {
            $weights = [];

foreach ($distances as $distance) {
                $weights[] = 1.0 / (1.0 + $distance);
            }

return Stats::weightedMean($labels, $weights);
        }

return Stats::mean($labels);
    }

/**
     * Return the string representation of the object.
     *
     * @internal
     *
     * @return string
     */
    public function __toString() : string
    {
        return 'K-d Neighbors Regressor (' . Params::stringify($this->params()) . ')';
    }
}

Cancel