Gunakan CreateDocumentClassifier dengan AWS SDK atau CLI

Contoh kode berikut menunjukkan cara menggunakanCreateDocumentClassifier.

Contoh tindakan adalah kutipan kode dari program yang lebih besar dan harus dijalankan dalam konteks. Anda dapat melihat tindakan ini dalam konteks dalam contoh kode berikut:

• Latih pengklasifikasi khusus dan klasifikasikan dokumen

CLI

AWS CLI

Untuk membuat pengklasifikasi dokumen untuk mengkategorikan dokumen

create-document-classifierContoh berikut memulai proses pelatihan untuk model pengklasifikasi dokumen. File data pelatihantraining.csv,, terletak di --input-data-config tag. training.csvadalah dokumen dua kolom di mana label, atau, klasifikasi disediakan di kolom pertama dan dokumen disediakan di kolom kedua.

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://DOC-EXAMPLE-BUCKET/" \
    --language-code en

Output:

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

Untuk informasi selengkapnya, lihat Klasifikasi Kustom di Panduan Pengembang Amazon Comprehend.

• Untuk detail API, lihat CreateDocumentClassifierdi Referensi AWS CLI Perintah.

Java

SDK untuk Java 2.x

catatan

Ada lebih banyak tentang GitHub. Temukan contoh lengkapnya dan pelajari cara mengatur dan menjalankannya di AWS Repositori Contoh Kode.

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);
        }
    }
}

• Untuk detail API, lihat CreateDocumentClassifierdi Referensi AWS SDK for Java 2.x API.

Python

SDK untuk Python (Boto3)

catatan

Ada lebih banyak tentang GitHub. Temukan contoh lengkapnya dan pelajari cara mengatur dan menjalankannya di AWS Repositori Contoh Kode.

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

• Untuk detail API, lihat CreateDocumentClassifierdi AWS SDK for Python (Boto3) Referensi API.

Untuk daftar lengkap panduan pengembang AWS SDK dan contoh kode, lihatMenggunakan Amazon Comprehend dengan SDK AWS. Topik ini juga mencakup informasi tentang memulai dan detail tentang versi SDK sebelumnya.