forked from jorgecasas/php-ml
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* Add french stopwords * Add french stopwords test
- Loading branch information
1 parent
4af8449
commit 3dff40e
Showing
2 changed files
with
37 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -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); | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters