octoleo/php-ml
1
0
Fork 0
mirror of https://github.com/Llewellynvdm/php-ml.git synced 2024-11-21 20:45:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add french stopwords (#92)

Browse Source 
* Add french stopwords

* Add french stopwords test
This commit is contained in:
Maxime COLIN 2017-05-22 23:18:27 +02:00 committed by Arkadiusz Kondas
parent 4af8449b1c
commit 3dff40ea1d
2 changed files with 37 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
src/Phpml/FeatureExtraction/StopWords/French.php Normal file
View File

@ -0,0 +1,29 @@
<?php
declare(strict_types=1);
namespace Phpml\FeatureExtraction\StopWords;
use Phpml\FeatureExtraction\StopWords;
final class French extends StopWords
{
/**
* @var array
*/
protected $stopWords = [
'alors', 'au', 'aucuns', 'aussi', 'autre', 'avant', 'avec', 'avoir', 'bon', 'car', 'ce', 'cela', 'ces', 'ceux', 'chaque', 'ci',
'comme', 'comment', 'dans', 'des', 'du', 'dedans', 'dehors', 'depuis', 'devrait', 'doit', 'donc', 'dos', 'début', 'elle', 'elles',
'en', 'encore', 'essai', 'est', 'et', 'eu', 'fait', 'faites', 'fois', 'font', 'hors', 'ici', 'il', 'ils', 'je', 'juste', 'la',
'le', 'les', 'leur', 'là', 'ma', 'maintenant', 'mais', 'mes', 'mine', 'moins', 'mon', 'mot', 'même', 'ni', 'nommés', 'notre',
'nous', 'ou', 'où', 'par', 'parce', 'pas', 'peut', 'peu', 'plupart', 'pour', 'pourquoi', 'quand', 'que', 'quel', 'quelle',
'quelles', 'quels', 'qui', 'sa', 'sans', 'ses', 'seulement', 'si', 'sien', 'son', 'sont', 'sous', 'soyez', 'sujet', 'sur', 'ta',
'tandis', 'tellement', 'tels', 'tes', 'ton', 'tous', 'tout', 'trop', 'très', 'tu', 'voient', 'vont', 'votre', 'vous', 'vu',
'ça', 'étaient', 'état', 'étions', 'été', 'être',
];
public function __construct()
{
parent::__construct($this->stopWords);
}
}

8
tests/Phpml/FeatureExtraction/StopWordsTest.php
View File

@ -45,4 +45,12 @@ class StopWordsTest extends TestCase
$this->assertTrue($stopWords->isStopWord('wam'));
$this->assertFalse($stopWords->isStopWord('transhumanizm'));
}
public function testFrenchStopWords()
{
$stopWords = StopWords::factory('French');
$this->assertTrue($stopWords->isStopWord('alors'));
$this->assertFalse($stopWords->isStopWord('carte'));
}
}