Utilisation de CreateDocumentClassifier avec un kit AWS SDK ou une interface de ligne de commande

Pour créer un classificateur de documents afin de classer les documents

L’exemple create-document-classifier suivant commence le processus d’entraînement pour un modèle de classificateur de documents. Le fichier de données d’entraînement training.csv se trouve au niveau de la balise --input-data-config. Le fichier training.csv est un document à deux colonnes où les étiquettes ou les classifications sont fournies dans la première colonne et les documents dans la deuxième colonne.

aws comprehend create-document-classifier \
    --document-classifier-name example-classifier \
    --data-access-arn arn:aws:comprehend:us-west-2:111122223333:pii-entities-detection-job/123456abcdeb0e11022f22a11EXAMPLE \
    --input-data-config "S3Uri=s3://amzn-s3-demo-bucket/" \
    --language-code en

Sortie :

{
    "DocumentClassifierArn": "arn:aws:comprehend:us-west-2:111122223333:document-classifier/example-classifier"
}

Pour plus d’informations, consultez Classification personnalisée dans le Guide du développeur Amazon Comprehend.

import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.comprehend.ComprehendClient;
import software.amazon.awssdk.services.comprehend.model.ComprehendException;
import software.amazon.awssdk.services.comprehend.model.CreateDocumentClassifierRequest;
import software.amazon.awssdk.services.comprehend.model.CreateDocumentClassifierResponse;
import software.amazon.awssdk.services.comprehend.model.DocumentClassifierInputDataConfig;

/**
 * Before running this code example, you can setup the necessary resources, such
 * as the CSV file and IAM Roles, by following this document:
 * https://aws.amazon.com/blogs/machine-learning/building-a-custom-classifier-using-amazon-comprehend/
 *
 * Also, set up your development environment, including your credentials.
 *
 * For more information, see the following documentation topic:
 *
 * https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
 */
public class DocumentClassifierDemo {
    public static void main(String[] args) {
        final String usage = """

                Usage:    <dataAccessRoleArn> <s3Uri> <documentClassifierName>

                Where:
                  dataAccessRoleArn - The ARN value of the role used for this operation.
                  s3Uri - The Amazon S3 bucket that contains the CSV file.
                  documentClassifierName - The name of the document classifier.
                """;

        if (args.length != 3) {
            System.out.println(usage);
            System.exit(1);
        }

        String dataAccessRoleArn = args[0];
        String s3Uri = args[1];
        String documentClassifierName = args[2];

        Region region = Region.US_EAST_1;
        ComprehendClient comClient = ComprehendClient.builder()
                .region(region)
                .build();

        createDocumentClassifier(comClient, dataAccessRoleArn, s3Uri, documentClassifierName);
        comClient.close();
    }

    public static void createDocumentClassifier(ComprehendClient comClient, String dataAccessRoleArn, String s3Uri,
            String documentClassifierName) {
        try {
            DocumentClassifierInputDataConfig config = DocumentClassifierInputDataConfig.builder()
                    .s3Uri(s3Uri)
                    .build();

            CreateDocumentClassifierRequest createDocumentClassifierRequest = CreateDocumentClassifierRequest.builder()
                    .documentClassifierName(documentClassifierName)
                    .dataAccessRoleArn(dataAccessRoleArn)
                    .languageCode("en")
                    .inputDataConfig(config)
                    .build();

            CreateDocumentClassifierResponse createDocumentClassifierResult = comClient
                    .createDocumentClassifier(createDocumentClassifierRequest);
            String documentClassifierArn = createDocumentClassifierResult.documentClassifierArn();
            System.out.println("Document Classifier ARN: " + documentClassifierArn);

        } catch (ComprehendException e) {
            System.err.println(e.awsErrorDetails().errorMessage());
            System.exit(1);
        }
    }
}

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 create(
        self,
        name,
        language_code,
        training_bucket,
        training_key,
        data_access_role_arn,
        mode,
    ):
        """
        Creates a custom classifier. After the classifier is created, it immediately
        starts training on the data found in the specified Amazon S3 bucket. Training
        can take 30 minutes or longer. The `describe_document_classifier` function
        can be used to get training status and returns a status of TRAINED when the
        classifier is ready to use.

        :param name: The name of the classifier.
        :param language_code: The language the classifier can operate on.
        :param training_bucket: The Amazon S3 bucket that contains the training data.
        :param training_key: The prefix used to find training data in the training
                             bucket. If multiple objects have the same prefix, all
                             of them are used.
        :param data_access_role_arn: The Amazon Resource Name (ARN) of a role that
                                     grants Comprehend permission to read from the
                                     training bucket.
        :return: The ARN of the newly created classifier.
        """
        try:
            response = self.comprehend_client.create_document_classifier(
                DocumentClassifierName=name,
                LanguageCode=language_code,
                InputDataConfig={"S3Uri": f"s3://{training_bucket}/{training_key}"},
                DataAccessRoleArn=data_access_role_arn,
                Mode=mode.value,
            )
            self.classifier_arn = response["DocumentClassifierArn"]
            logger.info("Started classifier creation. Arn is: %s.", self.classifier_arn)
        except ClientError:
            logger.exception("Couldn't create classifier %s.", name)
            raise
        else:
            return self.classifier_arn