Utilizzare DescribeDocumentClassifier con un SDK AWS o una CLI

Come descrivere un classificatore di documenti

L’esempio describe-document-classifier seguente ottiene le proprietà di un modello di classificatore di documenti personalizzato.

aws comprehend describe-document-classifier \
    --document-classifier-arn arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier-1

Output:

{
    "DocumentClassifierProperties": {
        "DocumentClassifierArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier-1",
        "LanguageCode": "en",
        "Status": "TRAINED",
        "SubmitTime": "2023-06-13T19:04:15.735000+00:00",
        "EndTime": "2023-06-13T19:42:31.752000+00:00",
        "TrainingStartTime": "2023-06-13T19:08:20.114000+00:00",
        "TrainingEndTime": "2023-06-13T19:41:35.080000+00:00",
        "InputDataConfig": {
            "DataFormat": "COMPREHEND_CSV",
            "S3Uri": "s3://amzn-s3-demo-bucket/trainingdata"
        },
        "OutputDataConfig": {},
        "ClassifierMetadata": {
            "NumberOfLabels": 3,
            "NumberOfTrainedDocuments": 5016,
            "NumberOfTestDocuments": 557,
            "EvaluationMetrics": {
                "Accuracy": 0.9856,
                "Precision": 0.9919,
                "Recall": 0.9459,
                "F1Score": 0.9673,
                "MicroPrecision": 0.9856,
                "MicroRecall": 0.9856,
                "MicroF1Score": 0.9856,
                "HammingLoss": 0.0144
            }
        },
        "DataAccessRoleArn": "arn:aws:iam::111122223333:role/service-role/AmazonComprehendServiceRole-example-role",
        "Mode": "MULTI_CLASS"
    }
}

Per ulteriori informazioni, consulta Creazione e gestione di modelli personalizzati nella Guida per gli sviluppatori di Amazon Comprehend.

class ComprehendClassifier:
    """Encapsulates an Amazon Comprehend custom classifier."""

    def __init__(self, comprehend_client):
        """
        :param comprehend_client: A Boto3 Comprehend client.
        """
        self.comprehend_client = comprehend_client
        self.classifier_arn = None


    def describe(self, classifier_arn=None):
        """
        Gets metadata about a custom classifier, including its current status.

        :param classifier_arn: The ARN of the classifier to look up.
        :return: Metadata about the classifier.
        """
        if classifier_arn is not None:
            self.classifier_arn = classifier_arn
        try:
            response = self.comprehend_client.describe_document_classifier(
                DocumentClassifierArn=self.classifier_arn
            )
            classifier = response["DocumentClassifierProperties"]
            logger.info("Got classifier %s.", self.classifier_arn)
        except ClientError:
            logger.exception("Couldn't get classifier %s.", self.classifier_arn)
            raise
        else:
            return classifier