Phpml\CrossValidation\RandomSplit

Complexity

Total Complexity

3

Size/Duplication

Total Lines	22
Duplicated Lines	0 %

Coupling/Cohesion

Components	1
Dependencies	2

Importance

Changes	4
Bugs	0	Features	1

1 Method

Rating	Name	Duplication	Size	Complexity
A	splitDataset()	0	15	3

<?php

declare (strict_types = 1);

namespace Phpml\CrossValidation;

use Phpml\Dataset\Dataset;

class RandomSplit extends Split
{
    /**
     * @param Dataset $dataset
     * @param float   $testSize
     */
    protected function splitDataset(Dataset $dataset, float $testSize)
    {
        $samples = $dataset->getSamples();
        $labels = $dataset->getTargets();
        $datasetSize = count($samples);
        $testCount = count($this->testSamples);

        for ($i = $datasetSize; $i > 0; --$i) {
            $key = mt_rand(0, $datasetSize - 1);
            $setName = (count($this->testSamples) - $testCount) / $datasetSize >= $testSize ? 'train' : 'test';

            $this->{$setName.'Samples'}[] = $samples[$key];
            $this->{$setName.'Labels'}[] = $labels[$key];
        }
    }
}