本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。

# 批量预测
<a name="timeseries-forecasting-batch"></a>

批量预测，也称为离线推理，可根据一批观察数据生成模型预测。对于大型数据集或者在您不需要立即响应模型预测请求时，批量推理是很好的选择。

与之对比的是，在线推理（实时推理）会实时生成预测。

您可以使用 SageMaker API 来检索 AutoML 作业的最佳候选对象，然后使用该候选任务提交一批输入数据进行推理。

1. 

**读取 AutoML 作业的详细信息。**

   以下 Amazon CLI 命令示例使用 [DescribeAutoMLJobV2](https://docs.amazonaws.cn/sagemaker/latest/APIReference/API_DescribeAutoMLJobV2.html)API 获取 AutoML 作业的详细信息，包括有关最佳候选模型的信息。

   ```
   aws sagemaker describe-auto-ml-job-v2 --auto-ml-job-name {{job-name}} --region {{region}}
   ```

1. 

**从中提取容器定义 [InferenceContainers](https://docs.amazonaws.cn/sagemaker/latest/APIReference/API_AutoMLCandidate.html#sagemaker-Type-AutoMLCandidate-InferenceContainers) 以获得最佳候选模型。**

   容器定义是容器化环境，用于托管经过训练的 SageMaker AI 模型以进行预测。

   ```
   BEST_CANDIDATE=$(aws sagemaker describe-auto-ml-job-v2 \
         --auto-ml-job-name {{job-name}} 
         --region {{region}} \
         --query 'BestCandidate.InferenceContainers[0]' \
         --output json
   ```

   该命令提取最佳候选模型的容器定义，并将其存储在 `BEST_CANDIDATE` 变量中。

1. 

**使用最佳候选容器定义创建 SageMaker AI 模型。**

   使用前面步骤中的容器定义通过 [CreateModel](https://docs.amazonaws.cn/sagemaker/latest/APIReference/API_CreateModel.html)AP SageMaker I 创建 AI 模型。

   ```
   aws sagemaker create-model \
         --model-name '{{model-name}}' \
         --primary-container "$BEST_CANDIDATE"
         --execution-role-arn '{{execution-role-arn>}}' \
         --region '{{region>}}
   ```

   该`--execution-role-arn`参数指定 A SageMaker I 在使用模型进行推理时扮演的 IAM 角色。有关此角色所需权限的详细信息，请参阅 [CreateModel API：执行角色权限](https://docs.amazonaws.cn/)。

1. 

**创建批量转换作业。**

   以下示例使用 [CreateTransformJob](https://docs.amazonaws.cn/cli/latest/reference/sagemaker/create-transform-job.html)API 创建转换作业。

   ```
   aws sagemaker create-transform-job \ 
          --transform-job-name '{{transform-job-name}}' \
          --model-name '{{model-name}}'\
          --transform-input file://transform-input.json \
          --transform-output file://transform-output.json \
          --transform-resources file://transform-resources.json \
          --region '{{region}}'
   ```

   输入、输出和资源详情在不同的 JSON 文件中定义：
   + `transform-input.json`:

     ```
     {
       "DataSource": {
         "S3DataSource": {
           "S3DataType": "S3Prefix",
           "S3Uri": "s3://my-input-data-bucket/path/to/input/data"
         }
       },
       "ContentType": "text/csv",
       "SplitType": "None"
     }
     ```
   + `transform-output.json`:

     ```
     {
       "S3OutputPath": "s3://my-output-bucket/path/to/output",
       "AssembleWith": "Line"
     }
     ```
   + `transform-resources.json`:
**注意**  
我们建议将 [m5.12xlarge](https://www.amazonaws.cn/ec2/instance-types/m5/) 实例用于通用工作负载，将 `m5.24xlarge` 实例用于大数据预测任务。

     ```
     {
       "InstanceType": "instance-type",
       "InstanceCount": 1
     }
     ```

1. 

**使用监控转换作业的进度 [DescribeTransformJob](https://docs.amazonaws.cn/sagemaker/latest/APIReference/API_DescribeTransformJob.html) API。**

   以以下 Amazon CLI 命令为例。

   ```
   aws sagemaker describe-transform-job \
         --transform-job-name '{{transform-job-name}}' \
         --region {{region}}
   ```

1. 

**读取批量转换输出。**

   任务完成后，`S3OutputPath` 中会显示预测结果。

   输出文件名称格式如下：`input_data_file_name.out`。例如，如果您的输入文件是 `text_x.csv`，则输出文件名称是 `text_x.csv.out`。

   ```
   aws s3 ls {{s3://my-output-bucket/path/to/output/}}
   ```

以下代码示例说明了如何使用适用于 Python 的 Amazon 软件开发工具包 (boto3) 和 Amazon CLI 用于批量预测的开发工具包。

------
#### [ Amazon SDK for Python (boto3) ]

 以下示例使用 **Amazon SDK for Python (boto3)** 进行批量预测。

```
import sagemaker 
import boto3

session = sagemaker.session.Session()

sm_client = boto3.client('sagemaker', region_name='{{us-west-2}}')
role = '{{arn:aws:iam::1234567890:role/sagemaker-execution-role}}'
output_path = '{{s3://test-auto-ml-job/output}}'
input_data = '{{s3://test-auto-ml-job/test_X.csv}}'

best_candidate = sm_client.describe_auto_ml_job_v2(AutoMLJobName=job_name)['BestCandidate']
best_candidate_containers = best_candidate['InferenceContainers']
best_candidate_name = best_candidate['CandidateName']

# create model
reponse = sm_client.create_model(
    ModelName = best_candidate_name,
    ExecutionRoleArn = role,
    Containers = best_candidate_containers 
)

# Lauch Transform Job
response = sm_client.create_transform_job(
    TransformJobName=f'{best_candidate_name}-transform-job',
    ModelName=model_name,
    TransformInput={
        'DataSource': {
            'S3DataSource': {
                'S3DataType': 'S3Prefix',
                'S3Uri': input_data
            }
        },
        'ContentType': "{{text/csv}}",
        'SplitType': 'None'
    },
    TransformOutput={
        'S3OutputPath': output_path,
        'AssembleWith': 'Line',
    },
    TransformResources={
        'InstanceType': '{{ml.m5.2xlarge}}',
        'InstanceCount': {{1}},
    },
)
```

批量推理作业返回以下格式的响应。

```
{'TransformJobArn': '{{arn:aws:sagemaker:us-west-2:1234567890:transform-job/test-transform-job}}',
 'ResponseMetadata': {'RequestId': '659f97fc-28c4-440b-b957-a49733f7c2f2',
  'HTTPStatusCode': 200,
  'HTTPHeaders': {'x-amzn-requestid': '659f97fc-28c4-440b-b957-a49733f7c2f2',
   'content-type': 'application/x-amz-json-1.1',
   'content-length': '96',
   'date': 'Thu, 11 Aug 2022 22:23:49 GMT'},
  'RetryAttempts': 0}}
```

------
#### [ Amazon Command Line Interface (Amazon CLI) ]

1. **获得最佳候选容器定义**。

   ```
   aws sagemaker describe-auto-ml-job-v2 --auto-ml-job-name '{{test-automl-job}}' --region {{us-west-2}}
   ```

1. **创建模型**。

   ```
   aws sagemaker create-model --model-name '{{test-sagemaker-model}}'
   --containers '[{
       "Image": "348316444620.dkr.ecr.us-west-2.amazonaws.com/sagemaker-sklearn-automl:2.5-1-cpu-py3",
       "ModelDataUrl": "{{s3://amzn-s3-demo-bucket/out/test-job1/data-processor-models/test-job1-dpp0-1-e569ff7ad77f4e55a7e549a/output/model.tar.gz}}",
       "Environment": {
           "AUTOML_SPARSE_ENCODE_RECORDIO_PROTOBUF": "1",
           "AUTOML_TRANSFORM_MODE": "feature-transform",
           "SAGEMAKER_DEFAULT_INVOCATIONS_ACCEPT": "application/x-recordio-protobuf",
           "SAGEMAKER_PROGRAM": "sagemaker_serve",
           "SAGEMAKER_SUBMIT_DIRECTORY": "/opt/ml/model/code"
       }
   }, {
       "Image": "348316444620.dkr.ecr.us-west-2.amazonaws.com/sagemaker-xgboost:1.3-1-cpu-py3",
       "ModelDataUrl": "{{s3://amzn-s3-demo-bucket/out/test-job1/tuning/flicdf10v2-dpp0-xgb/test-job1E9-244-7490a1c0/output/model.tar.gz}}",
       "Environment": {
           "MAX_CONTENT_LENGTH": "20971520",
           "SAGEMAKER_DEFAULT_INVOCATIONS_ACCEPT": "text/csv",
           "SAGEMAKER_INFERENCE_OUTPUT": "predicted_label", 
           "SAGEMAKER_INFERENCE_SUPPORTED": "predicted_label,probability,probabilities" 
       }
   }, {
       "Image": "348316444620.dkr.ecr.us-west-2.amazonaws.com/sagemaker-sklearn-automl:2.5-1-cpu-py3", 
       "ModelDataUrl": "{{s3://amzn-s3-demo-bucket/out/test-job1/data-processor-models/test-job1-dpp0-1-e569ff7ad77f4e55a7e549a/output/model.tar.gz}}", 
       "Environment": { 
           "AUTOML_TRANSFORM_MODE": "inverse-label-transform", 
           "SAGEMAKER_DEFAULT_INVOCATIONS_ACCEPT": "text/csv", 
           "SAGEMAKER_INFERENCE_INPUT": "predicted_label", 
           "SAGEMAKER_INFERENCE_OUTPUT": "predicted_label", 
           "SAGEMAKER_INFERENCE_SUPPORTED": "predicted_label,probability,labels,probabilities", 
           "SAGEMAKER_PROGRAM": "sagemaker_serve", 
           "SAGEMAKER_SUBMIT_DIRECTORY": "/opt/ml/model/code" 
       } 
   }]' \
   --execution-role-arn '{{arn:aws:iam::1234567890:role/sagemaker-execution-role}}' \
   --region '{{us-west-2}}'
   ```

1. **创建转换作业**。

   ```
   aws sagemaker create-transform-job --transform-job-name '{{test-tranform-job}}'\
    --model-name '{{test-sagemaker-model}}'\
    --transform-input '{
           "DataSource": {
               "S3DataSource": {
                   "S3DataType": "S3Prefix",
                   "S3Uri": "{{s3://amzn-s3-demo-bucket/data.csv}}"
               }
           },
           "ContentType": "{{text/csv}}",
           "SplitType": "None"
       }'\
   --transform-output '{
           "S3OutputPath": "{{s3://amzn-s3-demo-bucket/output/}}",
           "AssembleWith": "Line"
       }'\
   --transform-resources '{
           "InstanceType": "{{ml.m5.2xlarge}}",
           "InstanceCount": {{1}}
       }'\
   --region '{{us-west-2}}'
   ```

1. **检查转换作业的进度**。

   ```
   aws sagemaker describe-transform-job --transform-job-name  '{{test-tranform-job}}' --region {{us-west-2}}
   ```

   以下是来自转换作业的响应。

   ```
   {
       "TransformJobName": "{{test-tranform-job}}",
       "TransformJobArn": "{{arn:aws:sagemaker:us-west-2:1234567890:transform-job/test-tranform-job}}",
       "TransformJobStatus": "InProgress",
       "ModelName": "{{test-model}}",
       "TransformInput": {
           "DataSource": {
               "S3DataSource": {
                   "S3DataType": "S3Prefix",
                   "S3Uri": "{{s3://amzn-s3-demo-bucket/data.csv}}"
               }
           },
           "ContentType": "{{text/csv}}",
           "CompressionType": "None",
           "SplitType": "None"
       },
       "TransformOutput": {
           "S3OutputPath": "{{s3://amzn-s3-demo-bucket/output/}}",
           "AssembleWith": "Line",
           "KmsKeyId": ""
       },
       "TransformResources": {
           "InstanceType": "{{ml.m5.2xlarge}}",
           "InstanceCount": {{1}}
       },
       "CreationTime": 1662495635.679,
       "TransformStartTime": 1662495847.496,
       "DataProcessing": {
           "InputFilter": "$",
           "OutputFilter": "$",
           "JoinSource": "None"
       }
   }
   ```

   将 `TransformJobStatus` 更改为 `Completed` 后，您可以在中 `S3OutputPath` 查看推理结果。

------