:doc:`NeptuneData <../../neptunedata>` / Client / start_ml_model_transform_job

****************************
start_ml_model_transform_job
****************************



.. py:method:: NeptuneData.Client.start_ml_model_transform_job(**kwargs)

  

  Creates a new model transform job. See `Use a trained model to generate new model artifacts <https://docs.aws.amazon.com/neptune/latest/userguide/machine-learning-model-transform.html>`__.

   

  When invoking this operation in a Neptune cluster that has IAM authentication enabled, the IAM user or role making the request must have a policy attached that allows the `neptune-db\:StartMLModelTransformJob <https://docs.aws.amazon.com/neptune/latest/userguide/iam-dp-actions.html#startmlmodeltransformjob>`__ IAM action in that cluster.

  

  See also: `AWS API Documentation <https://docs.aws.amazon.com/goto/WebAPI/neptunedata-2023-08-01/StartMLModelTransformJob>`_  


  **Request Syntax**
  ::

    response = client.start_ml_model_transform_job(
        id='string',
        dataProcessingJobId='string',
        mlModelTrainingJobId='string',
        trainingJobName='string',
        modelTransformOutputS3Location='string',
        sagemakerIamRoleArn='string',
        neptuneIamRoleArn='string',
        customModelTransformParameters={
            'sourceS3DirectoryPath': 'string',
            'transformEntryPointScript': 'string'
        },
        baseProcessingInstanceType='string',
        baseProcessingInstanceVolumeSizeInGB=123,
        subnets=[
            'string',
        ],
        securityGroupIds=[
            'string',
        ],
        volumeEncryptionKMSKey='string',
        s3OutputEncryptionKMSKey='string'
    )
    
  :type id: string
  :param id: 

    A unique identifier for the new job. The default is an autogenerated UUID.

    

  
  :type dataProcessingJobId: string
  :param dataProcessingJobId: 

    The job ID of a completed data-processing job. You must include either ``dataProcessingJobId`` and a ``mlModelTrainingJobId``, or a ``trainingJobName``.

    

  
  :type mlModelTrainingJobId: string
  :param mlModelTrainingJobId: 

    The job ID of a completed model-training job. You must include either ``dataProcessingJobId`` and a ``mlModelTrainingJobId``, or a ``trainingJobName``.

    

  
  :type trainingJobName: string
  :param trainingJobName: 

    The name of a completed SageMaker training job. You must include either ``dataProcessingJobId`` and a ``mlModelTrainingJobId``, or a ``trainingJobName``.

    

  
  :type modelTransformOutputS3Location: string
  :param modelTransformOutputS3Location: **[REQUIRED]** 

    The location in Amazon S3 where the model artifacts are to be stored.

    

  
  :type sagemakerIamRoleArn: string
  :param sagemakerIamRoleArn: 

    The ARN of an IAM role for SageMaker execution. This must be listed in your DB cluster parameter group or an error will occur.

    

  
  :type neptuneIamRoleArn: string
  :param neptuneIamRoleArn: 

    The ARN of an IAM role that provides Neptune access to SageMaker and Amazon S3 resources. This must be listed in your DB cluster parameter group or an error will occur.

    

  
  :type customModelTransformParameters: dict
  :param customModelTransformParameters: 

    Configuration information for a model transform using a custom model. The ``customModelTransformParameters`` object contains the following fields, which must have values compatible with the saved model parameters from the training job:

    

  
    - **sourceS3DirectoryPath** *(string) --* **[REQUIRED]** 

      The path to the Amazon S3 location where the Python module implementing your model is located. This must point to a valid existing Amazon S3 location that contains, at a minimum, a training script, a transform script, and a ``model-hpo-configuration.json`` file.

      

    
    - **transformEntryPointScript** *(string) --* 

      The name of the entry point in your module of a script that should be run after the best model from the hyperparameter search has been identified, to compute the model artifacts necessary for model deployment. It should be able to run with no command-line arguments. The default is ``transform.py``.

      

    
  
  :type baseProcessingInstanceType: string
  :param baseProcessingInstanceType: 

    The type of ML instance used in preparing and managing training of ML models. This is an ML compute instance chosen based on memory requirements for processing the training data and model.

    

  
  :type baseProcessingInstanceVolumeSizeInGB: integer
  :param baseProcessingInstanceVolumeSizeInGB: 

    The disk volume size of the training instance in gigabytes. The default is 0. Both input data and the output model are stored on disk, so the volume size must be large enough to hold both data sets. If not specified or 0, Neptune ML selects a disk volume size based on the recommendation generated in the data processing step.

    

  
  :type subnets: list
  :param subnets: 

    The IDs of the subnets in the Neptune VPC. The default is None.

    

  
    - *(string) --* 

    

  :type securityGroupIds: list
  :param securityGroupIds: 

    The VPC security group IDs. The default is None.

    

  
    - *(string) --* 

    

  :type volumeEncryptionKMSKey: string
  :param volumeEncryptionKMSKey: 

    The Amazon Key Management Service (KMS) key that SageMaker uses to encrypt data on the storage volume attached to the ML compute instances that run the training job. The default is None.

    

  
  :type s3OutputEncryptionKMSKey: string
  :param s3OutputEncryptionKMSKey: 

    The Amazon Key Management Service (KMS) key that SageMaker uses to encrypt the output of the processing job. The default is none.

    

  
  
  :rtype: dict
  :returns: 
    
    **Response Syntax**

    
    ::

      {
          'id': 'string',
          'arn': 'string',
          'creationTimeInMillis': 123
      }
      
    **Response Structure**

    

    - *(dict) --* 
      

      - **id** *(string) --* 

        The unique ID of the new model transform job.

        
      

      - **arn** *(string) --* 

        The ARN of the model transform job.

        
      

      - **creationTimeInMillis** *(integer) --* 

        The creation time of the model transform job, in milliseconds.

        
  
  **Exceptions**
  
  *   :py:class:`NeptuneData.Client.exceptions.UnsupportedOperationException`

  
  *   :py:class:`NeptuneData.Client.exceptions.BadRequestException`

  
  *   :py:class:`NeptuneData.Client.exceptions.InvalidParameterException`

  
  *   :py:class:`NeptuneData.Client.exceptions.MLResourceNotFoundException`

  
  *   :py:class:`NeptuneData.Client.exceptions.ClientTimeoutException`

  
  *   :py:class:`NeptuneData.Client.exceptions.PreconditionsFailedException`

  
  *   :py:class:`NeptuneData.Client.exceptions.ConstraintViolationException`

  
  *   :py:class:`NeptuneData.Client.exceptions.InvalidArgumentException`

  
  *   :py:class:`NeptuneData.Client.exceptions.MissingParameterException`

  
  *   :py:class:`NeptuneData.Client.exceptions.IllegalArgumentException`

  
  *   :py:class:`NeptuneData.Client.exceptions.TooManyRequestsException`

  