使用資料集匯入任務將大量資料匯入 Amazon Personalize

import boto3

personalize = boto3.client('personalize')

response = personalize.create_dataset_import_job(
    jobName = 'YourImportJob',
    datasetArn = 'dataset_arn',
    dataSource = {'dataLocation':'s3://amzn-s3-demo-bucket/filename.csv'},
    roleArn = 'role_arn',
    importMode = 'FULL'
)

dsij_arn = response['datasetImportJobArn']

print ('Dataset Import Job arn: ' + dsij_arn)

description = personalize.describe_dataset_import_job(
    datasetImportJobArn = dsij_arn)['datasetImportJob']

print('Name: ' + description['jobName'])
print('ARN: ' + description['datasetImportJobArn'])
print('Status: ' + description['status'])

public static String createPersonalizeDatasetImportJob(PersonalizeClient personalizeClient,
                                                      String jobName,
                                                      String datasetArn,
                                                      String s3BucketPath,
                                                      String roleArn,
                                                      ImportMode importMode) {

  long waitInMilliseconds = 60 * 1000;
  String status;
  String datasetImportJobArn;
  
  try {
      DataSource importDataSource = DataSource.builder()
              .dataLocation(s3BucketPath)
              .build();
      
      CreateDatasetImportJobRequest createDatasetImportJobRequest = CreateDatasetImportJobRequest.builder()
              .datasetArn(datasetArn)
              .dataSource(importDataSource)
              .jobName(jobName)
              .roleArn(roleArn)
              .importMode(importMode)
              .build();
  
      datasetImportJobArn = personalizeClient.createDatasetImportJob(createDatasetImportJobRequest)
              .datasetImportJobArn();
      
      DescribeDatasetImportJobRequest describeDatasetImportJobRequest = DescribeDatasetImportJobRequest.builder()
              .datasetImportJobArn(datasetImportJobArn)
              .build();
  
      long maxTime = Instant.now().getEpochSecond() + 3 * 60 * 60;
  
      while (Instant.now().getEpochSecond() < maxTime) {
  
          DatasetImportJob datasetImportJob = personalizeClient
                  .describeDatasetImportJob(describeDatasetImportJobRequest)
                  .datasetImportJob();
  
          status = datasetImportJob.status();
          System.out.println("Dataset import job status: " + status);
  
          if (status.equals("ACTIVE") || status.equals("CREATE FAILED")) {
              break;
          }
          try {
              Thread.sleep(waitInMilliseconds);
          } catch (InterruptedException e) {
              System.out.println(e.getMessage());
          }
      }
      return datasetImportJobArn;
  
  } catch (PersonalizeException e) {
      System.out.println(e.awsErrorDetails().errorMessage());
  }
  return "";
}

// Get service clients and commands using ES6 syntax.
import { CreateDatasetImportJobCommand, PersonalizeClient } from
  "@aws-sdk/client-personalize";

// create personalizeClient
const personalizeClient = new PersonalizeClient({
  region: "REGION"
});

// Set the dataset import job parameters.
export const datasetImportJobParam = {
  datasetArn: 'DATASET_ARN', /* required */
  dataSource: {  
    dataLocation: 's3://amzn-s3-demo-bucket/<folderName>/<CSVfilename>.csv'  /* required */
  },
  jobName: 'NAME',           /* required */
  roleArn: 'ROLE_ARN',       /* required */
  importMode: "FULL"         /* optional, default is FULL */
};

export const run = async () => {
  try {
    const response = await personalizeClient.send(new CreateDatasetImportJobCommand(datasetImportJobParam));
    console.log("Success", response);
    return response; // For unit tests.
  } catch (err) {
    console.log("Error", err);
  }
};
run();