域数据集组入门 (SDK for Java 2.x)

将以下依赖项添加到 pom.xml 文件中。最新版本号可能与示例代码不同。

<dependency>
	<groupId>software.amazon.awssdk</groupId>
	<artifactId>personalize</artifactId>
	<version>2.16.83</version>
</dependency>
<dependency>
	<groupId>software.amazon.awssdk</groupId>
	<artifactId>personalizeruntime</artifactId>
	<version>2.16.83</version>
</dependency>
<dependency>
	<groupId>software.amazon.awssdk</groupId>
	<artifactId>personalizeevents</artifactId>
	<version>2.16.83</version>
</dependency>

将以下导入语句添加至您的项目。

// import client packages
import software.amazon.awssdk.services.personalize.PersonalizeClient;
import software.amazon.awssdk.services.personalizeruntime.PersonalizeRuntimeClient;
// Amazon Personalize exception package
import software.amazon.awssdk.services.personalize.model.PersonalizeException;
// schema packages
import software.amazon.awssdk.services.personalize.model.CreateSchemaRequest;
// dataset group packages
import software.amazon.awssdk.services.personalize.model.CreateDatasetGroupRequest;
import software.amazon.awssdk.services.personalize.model.DescribeDatasetGroupRequest;
// dataset packages
import software.amazon.awssdk.services.personalize.model.CreateDatasetRequest;
// dataset import job packages
import software.amazon.awssdk.services.personalize.model.CreateDatasetImportJobRequest;
import software.amazon.awssdk.services.personalize.model.DataSource;
import software.amazon.awssdk.services.personalize.model.DatasetImportJob;
import software.amazon.awssdk.services.personalize.model.DescribeDatasetImportJobRequest;
// recommender packages
import software.amazon.awssdk.services.personalize.model.CreateRecommenderRequest;
import software.amazon.awssdk.services.personalize.model.CreateRecommenderResponse;
import software.amazon.awssdk.services.personalize.model.DescribeRecommenderRequest;
// get recommendations packages
import software.amazon.awssdk.services.personalizeruntime.model.GetRecommendationsRequest;
import software.amazon.awssdk.services.personalizeruntime.model.GetRecommendationsResponse;
import software.amazon.awssdk.services.personalizeruntime.model.PredictedItem;
// Java time utility package
import java.time.Instant; 

将以下 Avro 架构作为 JSON 文件保存到您的工作目录中。此架构与您在完成创建训练数据（域数据集组）时创建的 CSV 文件中的列相匹配。

{
  "type": "record",
  "name": "Interactions",
  "namespace": "com.amazonaws.personalize.schema",
  "fields": [
      {
          "name": "USER_ID",
          "type": "string"
      },
      {
          "name": "ITEM_ID",
          "type": "string"
      },
      {
          "name": "EVENT_TYPE",
          "type": "string"
      },
      {
          "name": "TIMESTAMP",
          "type": "long"
      }
  ],
  "version": "1.0"
}

使用以下 createDomainSchema 方法创建 Amazon Personalize 域架构。将以下内容作为参数传递：Amazon Personalize 服务客户端、架构名称、域的 VIDEO_ON_DEMAND，以及您在上一步中创建的架构 JSON 文件的文件路径。该方法将返回新架构的 Amazon 资源名称 (ARN)。请将其存储以便将来使用。

    public static String createDomainSchema(PersonalizeClient personalizeClient, String schemaName, String domain,
            String filePath) {

        String schema = null;
        try {
            schema = new String(Files.readAllBytes(Paths.get(filePath)));
        } catch (IOException e) {
            System.out.println(e.getMessage());
        }

        try {
            CreateSchemaRequest createSchemaRequest = CreateSchemaRequest.builder()
                    .name(schemaName)
                    .domain(domain)
                    .schema(schema)
                    .build();

            String schemaArn = personalizeClient.createSchema(createSchemaRequest).schemaArn();

            System.out.println("Schema arn: " + schemaArn);

            return schemaArn;

        } catch (PersonalizeException e) {
            System.err.println(e.awsErrorDetails().errorMessage());
            System.exit(1);
        }
        return "";
    }

创建数据集组。使用以下 createDomainDatasetGroup 方法创建域数据集组。将以下内容作为参数传递：Amazon Personalize 服务客户端、数据集组的名称以及域的传递 VIDEO_ON_DEMAND。该方法将返回新数据集组的 ARN。请将其存储以便将来使用。

    public static String createDomainDatasetGroup(PersonalizeClient personalizeClient,
            String datasetGroupName,
            String domain) {

        try {
            CreateDatasetGroupRequest createDatasetGroupRequest = CreateDatasetGroupRequest.builder()
                    .name(datasetGroupName)
                    .domain(domain)
                    .build();
            return personalizeClient.createDatasetGroup(createDatasetGroupRequest).datasetGroupArn();
        } catch (PersonalizeException e) {
            System.out.println(e.awsErrorDetails().errorMessage());
        }
        return "";
    }

创建物品交互数据集。使用以下 createDataset 方法创建物品交互数据集。将以下内容作为参数传递：Amazon Personalize 服务客户端、数据集名称、架构的 ARN、数据集组的 ARN 以及数据集类型的 Interactions。该方法将返回新数据集的 ARN。请将其存储以便将来使用。

    public static String createDataset(PersonalizeClient personalizeClient,
            String datasetName,
            String datasetGroupArn,
            String datasetType,
            String schemaArn) {
        try {
            CreateDatasetRequest request = CreateDatasetRequest.builder()
                    .name(datasetName)
                    .datasetGroupArn(datasetGroupArn)
                    .datasetType(datasetType)
                    .schemaArn(schemaArn)
                    .build();

            String datasetArn = personalizeClient.createDataset(request)
                    .datasetArn();
            System.out.println("Dataset " + datasetName + " created.");
            return datasetArn;

        } catch (PersonalizeException e) {
            System.err.println(e.awsErrorDetails().errorMessage());
            System.exit(1);
        }
        return "";
    }

使用数据集导入作业导入数据。使用以下 createPersonalizeDatasetImportJob 方法创建数据集导入作业。

将以下内容作为参数传递：Amazon Personalize 服务客户端、作业名称和交互数据集的 ARN。传递存储训练数据的 Amazon S3 存储桶路径 (s3://bucket name/folder name/ratings.csv) 以及服务角色的 ARN。您在入门先决条件期间创建了此角色。该方法将返回数据集导入作业的 ARN。（可选）将其存储起来以备后用。

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

        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)
                    .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 "";
    }