/**
* @param Dataset $dataset
*
* @return Dataset[]|array
*/
private function splitByTarget(Dataset $dataset) : array
{
$targets = $dataset->getTargets();
$samples = $dataset->getSamples();
$uniqueTargets = array_unique($targets);
$split = array_combine($uniqueTargets, array_fill(0, count($uniqueTargets), []));
foreach ($samples as $key => $sample) {
$split[$targets[$key]][] = $sample;
}
$datasets = $this->createDatasets($uniqueTargets, $split);
return $datasets;
}
/**
* @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];
}
}
