创建批量推理作业 (AWS SDK)

完成为批量建议准备输入数据后，就可以通过 CreateBatchInferenceJob 操作创建批量推理作业了。

创建批量推理作业

可以使用以下代码创建批量推理作业。指定作业名称、解决方案版本的 Amazon 资源名称 (ARN)，以及您在设置期间为 Amazon Personalize 创建的 IAM 服务角色的 ARN。此角色必须对您的输入和输出 Amazon S3 存储桶具有读写权限。

我们建议使用不同的输出数据位置（文件夹或其他 Amazon S3 存储桶）。对输入和输出位置使用以下语法：s3://<name of your S3 bucket>/<folder name>/<input JSON file name>.json 和 s3://<name of your S3 bucket>/<output folder name>/。

对于 numResults，指定您希望 Amazon Personalize 为每行输入数据预测的物品数量。（可选）提供筛选器 ARN 来筛选建议。如果您的筛选器使用占位符参数，请确保这些参数的值包含在您的输入 JSON 中。有关更多信息，请参阅 筛选批量建议和用户细分（自定义资源）。

SDK for Python (Boto3)

该示例包括可选的 User-Personalization 食谱特定的 itemExplorationConfig 超参数：explorationWeight 和 explorationItemAgeCutOff。（可选）包括 explorationWeight 和 explorationItemAgeCutOff 值以配置浏览。有关更多信息，请参阅User-Personalization 食谱。

import boto3

personalize_rec = boto3.client(service_name='personalize')

personalize_rec.create_batch_inference_job (
    solutionVersionArn = "Solution version ARN",
    jobName = "Batch job name",
    roleArn = "IAM service role ARN",
    filterArn = "Filter ARN",
    batchInferenceJobConfig = {
        # optional USER_PERSONALIZATION recipe hyperparameters
        "itemExplorationConfig": {      
            "explorationWeight": "0.3",
            "explorationItemAgeCutOff": "30"
        }
    },
    jobInput = 
       {"s3DataSource": {"path": "s3://<name of your S3 bucket>/<folder name>/<input JSON file name>.json"}},
    jobOutput = 
       {"s3DataDestination": {"path": "s3://<name of your S3 bucket>/<output folder name>/"}}
)

SDK for Java 2.x

该示例包括可选的 User-Personalization 食谱特定的 itemExplorationConfig 字段：explorationWeight 和 explorationItemAgeCutOff。（可选）包括 explorationWeight 和 explorationItemAgeCutOff 值以配置浏览。有关更多信息，请参阅User-Personalization 食谱。

public static String createPersonalizeBatchInferenceJob(PersonalizeClient personalizeClient,
                                                        String solutionVersionArn,
                                                        String jobName,
                                                        String filterArn,
                                                        String s3InputDataSourcePath,
                                                        String s3DataDestinationPath,
                                                        String roleArn,
                                                        String explorationWeight,
                                                        String explorationItemAgeCutOff) {

  long waitInMilliseconds = 60 * 1000;
  String status;
  String batchInferenceJobArn;

  try {
      // Set up data input and output parameters.
      S3DataConfig inputSource = S3DataConfig.builder()
              .path(s3InputDataSourcePath)
              .build();
      S3DataConfig outputDestination = S3DataConfig.builder()
              .path(s3DataDestinationPath)
              .build();

      BatchInferenceJobInput jobInput = BatchInferenceJobInput.builder()
              .s3DataSource(inputSource)
              .build();
      BatchInferenceJobOutput jobOutputLocation = BatchInferenceJobOutput.builder()
              .s3DataDestination(outputDestination)
              .build();

      // Optional code to build the User-Personalization specific item exploration config.
      HashMap<String, String> explorationConfig = new HashMap<>();

      explorationConfig.put("explorationWeight", explorationWeight);
      explorationConfig.put("explorationItemAgeCutOff", explorationItemAgeCutOff);

      BatchInferenceJobConfig jobConfig = BatchInferenceJobConfig.builder()
              .itemExplorationConfig(explorationConfig)
              .build();
      // End optional User-Personalization recipe specific code.

      CreateBatchInferenceJobRequest createBatchInferenceJobRequest = CreateBatchInferenceJobRequest.builder()
              .solutionVersionArn(solutionVersionArn)
              .jobInput(jobInput)
              .jobOutput(jobOutputLocation)
              .jobName(jobName)
              .filterArn(filterArn)
              .roleArn(roleArn)
              .batchInferenceJobConfig(jobConfig)   // Optional
              .build();

      batchInferenceJobArn = personalizeClient.createBatchInferenceJob(createBatchInferenceJobRequest)
              .batchInferenceJobArn();
      DescribeBatchInferenceJobRequest describeBatchInferenceJobRequest = DescribeBatchInferenceJobRequest.builder()
              .batchInferenceJobArn(batchInferenceJobArn)
              .build();

      long maxTime = Instant.now().getEpochSecond() + 3 * 60 * 60;

      // wait until the batch inference job is complete.
      while (Instant.now().getEpochSecond() < maxTime) {

          BatchInferenceJob batchInferenceJob = personalizeClient
                  .describeBatchInferenceJob(describeBatchInferenceJobRequest)
                  .batchInferenceJob();

          status = batchInferenceJob.status();
          System.out.println("Batch inference 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 batchInferenceJobArn;

  } catch (PersonalizeException e) {
      System.out.println(e.awsErrorDetails().errorMessage());
  }
  return "";
}

SDK for JavaScript v3

// Get service clients module and commands using ES6 syntax.
import { CreateBatchInferenceJobCommand } from
  "@aws-sdk/client-personalize";
import { personalizeClient } from "./libs/personalizeClients.js";

// Or, create the client here.
// const personalizeClient = new PersonalizeClient({ region: "REGION"});

// Set the batch inference job's parameters.

export const createBatchInferenceJobParam = {
  jobName: 'JOB_NAME',
  jobInput: {         /* required */
    s3DataSource: {   /* required */
      path: 'INPUT_PATH', /* required */
      // kmsKeyArn: 'INPUT_KMS_KEY_ARN' /* optional */'
    }
  },
  jobOutput: {         /* required */
    s3DataDestination: {   /* required */
      path: 'OUTPUT_PATH', /* required */
      // kmsKeyArn: 'OUTPUT_KMS_KEY_ARN' /* optional */'
    }
  },
  roleArn: 'ROLE_ARN', /* required */
  solutionVersionArn: 'SOLUTION_VERSION_ARN', /* required */
  numResults: 20 /* optional integer*/
};

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

处理批处理作业可能需要一段时间才能完成。您可以通过调用 DescribeBatchInferenceJob 和传递 batchRecommendationsJobArn 作为输入参数来检查作业的状态。您也可以通过调ListBatchInferenceJobs用列出您 AWS 环境中的所有 Amazon Personalize 批量推理作业。

创建生成主题的批量推理作业

要为相似的物品生成主题，您必须使用 Similar-Items 配方，并且您的物品数据集必须有一个文本字段和一个物品名称数据列。有关带有主题的建议的更多信息，请参阅内容生成器中带有主题的批量建议。

以下代码创建了一个批量推理作业，该作业可生成带有主题的建议。将 batchInferenceJobMode 保留设置为 "THEME_GENERATION"。将 COLUMNN_NAME 替换为存储物品名称数据的列的名称。

import boto3

personalize_rec = boto3.client(service_name='personalize')

personalize_rec.create_batch_inference_job (
    solutionVersionArn = "Solution version ARN",
    jobName = "Batch job name",
    roleArn = "IAM service role ARN",
    filterArn = "Filter ARN",
    batchInferenceJobMode = "THEME_GENERATION",
    themeGenerationConfig = {
      "fieldsForThemeGeneration": {
          "itemName": "COLUMN_NAME"
      }
    },
    jobInput = 
       {"s3DataSource": {"path": "s3://<name of your S3 bucket>/<folder name>/<input JSON file name>.json"}},
    jobOutput = 
       {"s3DataDestination": {"path": "s3://<name of your S3 bucket>/<output folder name>/"}}
)