for testing and deploying your application
for finding and fixing issues
for empowering human code reviews
<?php
declare (strict_types = 1);
namespace Phpml\FeatureExtraction;
class TfIdfTransformer implements Transformer
{
/**
* @var array
*/
private $idf;
* @param array $samples
*
* @return array
public function transform(array $samples): array
$this->countTokensFrequency($samples);
$count = count($samples);
foreach ($this->idf as &$value) {
$value = log($count / $value, 10);
}
foreach ($samples as &$sample) {
foreach ($sample as $index => &$feature) {
$feature = $feature * $this->idf[$index];
return $samples;
private function countTokensFrequency(array $samples)
$this->idf = array_fill_keys(array_keys($samples[0]), 0);
foreach ($samples as $sample) {
foreach ($sample as $index => $count) {
if ($count > 0) {
++$this->idf[$index];