56 lines
1.6 KiB
Text
56 lines
1.6 KiB
Text
|
<?php
|
||
|
|
|
||
|
|
declare(strict_types=1);
|
||
|
|
|
||
|
|
namespace Classifier\Lib;
|
||
|
|
|
||
|
|
use Rubix\ML\PersistentModel;
|
||
|
|
use Rubix\ML\Pipeline;
|
||
|
|
use Rubix\ML\Transformers\TextNormalizer;
|
||
|
|
use Rubix\ML\Transformers\WordCountVectorizer;
|
||
|
|
use Rubix\ML\Transformers\TfIdfTransformer;
|
||
|
|
use Rubix\ML\Classifiers\NaiveBayes;
|
||
|
|
use Rubix\ML\Persisters\Filesystem;
|
||
|
|
use Rubix\ML\Datasets\Unlabeled;
|
||
|
|
|
||
|
|
class MessageQualifierShort
|
||
|
|
{
|
||
|
|
private $estimator;
|
||
|
|
private $modelPath;
|
||
|
|
|
||
|
|
public function __construct(string $modelPath = __DIR__ . '/model.rbx')
|
||
|
|
{
|
||
|
|
$this->modelPath = $modelPath;
|
||
|
|
|
||
|
|
if (file_exists($this->modelPath)) {
|
||
|
|
$this->estimator = PersistentModel::load(new Filesystem($this->modelPath));
|
||
|
|
} else {
|
||
|
|
// Pipeline optimisée pour le texte
|
||
|
|
$this->estimator = new PersistentModel(
|
||
|
|
new Pipeline([
|
||
|
|
new TextNormalizer(), // Supprime ponctuation, minuscules
|
||
|
|
new WordCountVectorizer(5000, 1, 2), // Unigrammes et Bigrammes (ex: "alerte" et "alerte incendie")
|
||
|
|
new TfIdfTransformer(), // Donne du poids aux mots rares et importants
|
||
|
|
], new NaiveBayes()),
|
||
|
|
new Filesystem($this->modelPath)
|
||
|
|
);
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
public function predict(string $message): array
|
||
|
|
{
|
||
|
|
$dataset = new Unlabeled([[$message]]);
|
||
|
|
$probabilities = $this->estimator->proba($dataset)[0];
|
||
|
|
|
||
|
|
arsort($probabilities);
|
||
|
|
$label = key($probabilities);
|
||
|
|
$confidence = current($probabilities);
|
||
|
|
|
||
|
|
return [
|
||
|
|
'label' => $label,
|
||
|
|
'confidence' => $confidence,
|
||
|
|
'all_scores' => $probabilities
|
||
|
|
];
|
||
|
|
}
|
||
|
|
}
|