InverseDocumentFrequency extension for php-nlp-tools

InverseDocumentFrequency.php

<?php

namespace App\Utilities;

use NlpTools\FeatureFactories\DataAsFeatures;
use NlpTools\Documents\TrainingSet;

class InverseDocumentFrequency
{

    const FREQUENCY_MODE = 1;
    const SMOOTH_MODE = 2;
    const PROBABILISTIC_MODE = 3;
  
    public function __construct(TrainingSet $tset, $mode=self::FREQUENCY_MODE)
    {
        $this->mode = $mode;

        $ff = new DataAsFeatures();
        $tset->setAsKey(TrainingSet::CLASS_AS_KEY);
        foreach ($tset as $class=>$doc) {
            $tokens = $ff->getFeatureArray($class,$doc);
            $tokens = array_fill_keys($tokens,1);
            foreach ($tokens as $token=>$v) {
                if (isset($this->idf[$token]))
                    $this->idf[$token]++;
                else
                    $this->idf[$token] = 1;
            }
        }

        $D = count($tset);

        if($this->mode === self::SMOOTH_MODE){
            foreach ($this->idf as $key => &$value) {
                $value = log(1 + ($D/$value));
            }
        }
        elseif($this->mode === self::FREQUENCY_MODE){
            foreach ($this->idf as $key => &$value) {
                $value = log($D/$value);
            }
        }
        elseif($this->mode === self::PROBABILISTIC_MODE){
            foreach ($this->idf as $key => &$value) {
                $value = log(($D-$value)/$value);
            }
        }


        $this->logD = log($D);

    }


    public function getIdf($term)
    {
        if (isset($this->idf[$term])) {
            return $this->idf[$term];
        } else {
            return $this->logD;
        }

    }


}