create_transform_job ¶

def create_transform_job(
    self,
    *,
    config_overrides: Optional[SageMakerClientConfig] = None,
    transform_job_name: Optional[
        "capo_sagemaker.types.transform_job_name.TransformJobName"
    ] = None,
    model_name: Optional["capo_sagemaker.types.model_name.ModelName"] = None,
    max_concurrent_transforms: Optional[
        "capo_sagemaker.types.max_concurrent_transforms.MaxConcurrentTransforms"
    ] = None,
    model_client_config: Optional[
        "capo_sagemaker.types.model_client_config.ModelClientConfig"
    ] = None,
    max_payload_in_mb: Optional[
        "capo_sagemaker.types.max_payload_in_mb.MaxPayloadInMB"
    ] = None,
    batch_strategy: Optional[
        "capo_sagemaker.types.batch_strategy.BatchStrategy"
    ] = None,
    environment: Optional[
        "capo_sagemaker.types.transform_environment_map.TransformEnvironmentMap"
    ] = None,
    transform_input: Optional[
        "capo_sagemaker.types.transform_input.TransformInput"
    ] = None,
    transform_output: Optional[
        "capo_sagemaker.types.transform_output.TransformOutput"
    ] = None,
    data_capture_config: Optional[
        "capo_sagemaker.types.batch_data_capture_config.BatchDataCaptureConfig"
    ] = None,
    transform_resources: Optional[
        "capo_sagemaker.types.transform_resources.TransformResources"
    ] = None,
    data_processing: Optional[
        "capo_sagemaker.types.data_processing.DataProcessing"
    ] = None,
    tags: Optional["capo_sagemaker.types.tag_list.TagList"] = None,
    experiment_config: Optional[
        "capo_sagemaker.types.experiment_config.ExperimentConfig"
    ] = None,
) -> (
    "capo_sagemaker.types.create_transform_job_response.CreateTransformJobResponse"
):
    """<p>Starts a transform job. A transform job uses a trained model to get inferences on a dataset and saves these results to an Amazon S3 location that you specify.</p> <p>To perform batch transformations, you create a transform job and use the data that you have readily available.</p> <p>In the request body, you provide the following:</p> <ul> <li> <p> <code>TransformJobName</code> - Identifies the transform job. The name must be unique within an Amazon Web Services Region in an Amazon Web Services account.</p> </li> <li> <p> <code>ModelName</code> - Identifies the model to use. <code>ModelName</code> must be the name of an existing Amazon SageMaker model in the same Amazon Web Services Region and Amazon Web Services account. For information on creating a model, see <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateModel.html">CreateModel</a>.</p> </li> <li> <p> <code>TransformInput</code> - Describes the dataset to be transformed and the Amazon S3 location where it is stored.</p> </li> <li> <p> <code>TransformOutput</code> - Identifies the Amazon S3 location where you want Amazon SageMaker to save the results from the transform job.</p> </li> <li> <p> <code>TransformResources</code> - Identifies the ML compute instances and AMI image versions for the transform job.</p> </li> </ul> <p>For more information about how batch transformation works, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/batch-transform.html">Batch Transform</a>.</p>

    Args:
        transform_job_name: <p>The name of the transform job. The name must be unique within an Amazon Web Services Region in an Amazon Web Services account. </p>
        model_name: <p>The name of the model that you want to use for the transform job. <code>ModelName</code> must be the name of an existing Amazon SageMaker model within an Amazon Web Services Region in an Amazon Web Services account.</p>
        max_concurrent_transforms: <p>The maximum number of parallel requests that can be sent to each instance in a transform job. If <code>MaxConcurrentTransforms</code> is set to <code>0</code> or left unset, Amazon SageMaker checks the optional execution-parameters to determine the settings for your chosen algorithm. If the execution-parameters endpoint is not enabled, the default value is <code>1</code>. For more information on execution-parameters, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-batch-code.html#your-algorithms-batch-code-how-containe-serves-requests">How Containers Serve Requests</a>. For built-in algorithms, you don't need to set a value for <code>MaxConcurrentTransforms</code>.</p>
        model_client_config: <p>Configures the timeout and maximum number of retries for processing a transform job invocation.</p>
        max_payload_in_mb: <p>The maximum allowed size of the payload, in MB. A <i>payload</i> is the data portion of a record (without metadata). The value in <code>MaxPayloadInMB</code> must be greater than, or equal to, the size of a single record. To estimate the size of a record in MB, divide the size of your dataset by the number of records. To ensure that the records fit within the maximum payload size, we recommend using a slightly larger value. The default value is <code>6</code> MB. </p> <p>The value of <code>MaxPayloadInMB</code> cannot be greater than 100 MB. If you specify the <code>MaxConcurrentTransforms</code> parameter, the value of <code>(MaxConcurrentTransforms * MaxPayloadInMB)</code> also cannot exceed 100 MB.</p> <p>For cases where the payload might be arbitrarily large and is transmitted using HTTP chunked encoding, set the value to <code>0</code>. This feature works only in supported algorithms. Currently, Amazon SageMaker built-in algorithms do not support HTTP chunked encoding.</p>
        batch_strategy: <p>Specifies the number of records to include in a mini-batch for an HTTP inference request. A <i>record</i> <i/> is a single unit of input data that inference can be made on. For example, a single line in a CSV file is a record. </p> <p>To enable the batch strategy, you must set the <code>SplitType</code> property to <code>Line</code>, <code>RecordIO</code>, or <code>TFRecord</code>.</p> <p>To use only one record when making an HTTP invocation request to a container, set <code>BatchStrategy</code> to <code>SingleRecord</code> and <code>SplitType</code> to <code>Line</code>.</p> <p>To fit as many records in a mini-batch as can fit within the <code>MaxPayloadInMB</code> limit, set <code>BatchStrategy</code> to <code>MultiRecord</code> and <code>SplitType</code> to <code>Line</code>.</p>
        environment: <p>The environment variables to set in the Docker container. Don't include any sensitive data in your environment variables. We support up to 16 key and values entries in the map.</p>
        transform_input: <p>Describes the input source and the way the transform job consumes it.</p>
        transform_output: <p>Describes the results of the transform job.</p>
        data_capture_config: <p>Configuration to control how SageMaker captures inference data.</p>
        transform_resources: <p>Describes the resources, including ML instance types and ML instance count, to use for the transform job.</p>
        data_processing: <p>The data structure used to specify the data to be used for inference in a batch transform job and to associate the data that is relevant to the prediction results in the output. The input filter provided allows you to exclude input data that is not needed for inference in a batch transform job. The output filter provided allows you to include input data relevant to interpreting the predictions in the output from the job. For more information, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/batch-transform-data-processing.html">Associate Prediction Results with their Corresponding Input Records</a>.</p>
        tags: <p>(Optional) An array of key-value pairs. For more information, see <a href="https://docs.aws.amazon.com/awsaccountbilling/latest/aboutv2/cost-alloc-tags.html#allocation-what">Using Cost Allocation Tags</a> in the <i>Amazon Web Services Billing and Cost Management User Guide</i>.</p>

    Raises:
        capo_sagemaker.errors.resource_in_use.ResourceInUse: <p>Resource being accessed is in use.</p>
        capo_sagemaker.errors.resource_limit_exceeded.ResourceLimitExceeded: <p> You have exceeded an SageMaker resource limit. For example, you might have too many training jobs created. </p>
        capo_sagemaker.errors.resource_not_found.ResourceNotFound: <p>Resource being access is not found.</p>
        capo_sagemaker.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    def _handler(
        req: "OperationRequest[capo_sagemaker.types.create_transform_job_request.CreateTransformJobRequest]",
    ) -> OperationResponse[
        "capo_sagemaker.types.create_transform_job_response.CreateTransformJobResponse"
    ]:
        import capo_sagemaker._operations.sage_maker.create_transform_job

        output, http_response = (
            capo_sagemaker._operations.sage_maker.create_transform_job.create_transform_job(
                req.options, req.input
            )
        )
        return OperationResponse(output=output, response=http_response)

    interceptors_, options_ = self.operation_options(
        config_overrides, OperationLogging("CreateTransformJob")
    )
    input_: capo_sagemaker.types.create_transform_job_request.CreateTransformJobRequest = {}
    if transform_job_name is not None:
        input_["transform_job_name"] = transform_job_name
    if model_name is not None:
        input_["model_name"] = model_name
    if max_concurrent_transforms is not None:
        input_["max_concurrent_transforms"] = max_concurrent_transforms
    if model_client_config is not None:
        input_["model_client_config"] = model_client_config
    if max_payload_in_mb is not None:
        input_["max_payload_in_mb"] = max_payload_in_mb
    if batch_strategy is not None:
        input_["batch_strategy"] = batch_strategy
    if environment is not None:
        input_["environment"] = environment
    if transform_input is not None:
        input_["transform_input"] = transform_input
    if transform_output is not None:
        input_["transform_output"] = transform_output
    if data_capture_config is not None:
        input_["data_capture_config"] = data_capture_config
    if transform_resources is not None:
        input_["transform_resources"] = transform_resources
    if data_processing is not None:
        input_["data_processing"] = data_processing
    if tags is not None:
        input_["tags"] = tags
    if experiment_config is not None:
        input_["experiment_config"] = experiment_config

    response = execute_pipeline(
        OperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    response.response.close()
    return response.output