create_profile_job ¶

def create_profile_job(
    self,
    dataset_name: "capo_databrew.types.dataset_name.DatasetName",
    name: "capo_databrew.types.job_name.JobName",
    output_location: "capo_databrew.types.s3_location.S3Location",
    role_arn: "capo_databrew.types.arn.Arn",
    *,
    config_overrides: Optional[DataBrewClientConfig] = None,
    encryption_key_arn: Optional[
        "capo_databrew.types.encryption_key_arn.EncryptionKeyArn"
    ] = None,
    encryption_mode: Optional[
        "capo_databrew.types.encryption_mode.EncryptionMode"
    ] = None,
    log_subscription: Optional[
        "capo_databrew.types.log_subscription.LogSubscription"
    ] = None,
    max_capacity: Optional["capo_databrew.types.max_capacity.MaxCapacity"] = None,
    max_retries: Optional["capo_databrew.types.max_retries.MaxRetries"] = None,
    configuration: Optional[
        "capo_databrew.types.profile_configuration.ProfileConfiguration"
    ] = None,
    validation_configurations: Optional[
        "capo_databrew.types.validation_configuration_list.ValidationConfigurationList"
    ] = None,
    tags: Optional["capo_databrew.types.tag_map.TagMap"] = None,
    timeout: Optional["capo_databrew.types.timeout.Timeout"] = None,
    job_sample: Optional["capo_databrew.types.job_sample.JobSample"] = None,
) -> "capo_databrew.types.create_profile_job_response.CreateProfileJobResponse":
    """<p>Creates a new job to analyze a dataset and create its data profile.</p>

    Args:
        dataset_name: <p>The name of the dataset that this job is to act upon.</p>
        encryption_key_arn: <p>The Amazon Resource Name (ARN) of an encryption key that is used to protect the job.</p>
        encryption_mode: <p>The encryption mode for the job, which can be one of the following:</p> <ul> <li> <p> <code>SSE-KMS</code> - <code>SSE-KMS</code> - Server-side encryption with KMS-managed keys.</p> </li> <li> <p> <code>SSE-S3</code> - Server-side encryption with keys managed by Amazon S3.</p> </li> </ul>
        name: <p>The name of the job to be created. Valid characters are alphanumeric (A-Z, a-z, 0-9), hyphen (-), period (.), and space.</p>
        log_subscription: <p>Enables or disables Amazon CloudWatch logging for the job. If logging is enabled, CloudWatch writes one log stream for each job run.</p>
        max_capacity: <p>The maximum number of nodes that DataBrew can use when the job processes data.</p>
        max_retries: <p>The maximum number of times to retry the job after a job run fails.</p>
        configuration: <p>Configuration for profile jobs. Used to select columns, do evaluations, and override default parameters of evaluations. When configuration is null, the profile job will run with default settings.</p>
        validation_configurations: <p>List of validation configurations that are applied to the profile job.</p>
        role_arn: <p>The Amazon Resource Name (ARN) of the Identity and Access Management (IAM) role to be assumed when DataBrew runs the job.</p>
        tags: <p>Metadata tags to apply to this job.</p>
        timeout: <p>The job's timeout in minutes. A job that attempts to run longer than this timeout period ends with a status of <code>TIMEOUT</code>.</p>
        job_sample: <p>Sample configuration for profile jobs only. Determines the number of rows on which the profile job will be executed. If a JobSample value is not provided, the default value will be used. The default value is CUSTOM_ROWS for the mode parameter and 20000 for the size parameter.</p>

    Raises:
        capo_databrew.errors.access_denied_exception.AccessDeniedException: <p>Access to the specified resource was denied.</p>
        capo_databrew.errors.conflict_exception.ConflictException: <p>Updating or deleting a resource can cause an inconsistent state.</p>
        capo_databrew.errors.resource_not_found_exception.ResourceNotFoundException: <p>One or more resources can't be found.</p>
        capo_databrew.errors.service_quota_exceeded_exception.ServiceQuotaExceededException: <p>A service quota is exceeded.</p>
        capo_databrew.errors.validation_exception.ValidationException: <p>The input parameters for this request failed validation.</p>
        capo_databrew.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    def _handler(
        req: "OperationRequest[capo_databrew.types.create_profile_job_request.CreateProfileJobRequest]",
    ) -> OperationResponse[
        "capo_databrew.types.create_profile_job_response.CreateProfileJobResponse"
    ]:
        import capo_databrew._operations.aws_glue_data_brew.create_profile_job

        output, http_response = (
            capo_databrew._operations.aws_glue_data_brew.create_profile_job.create_profile_job(
                req.options, req.input
            )
        )
        return OperationResponse(output=output, response=http_response)

    interceptors_, options_ = self.operation_options(
        config_overrides, OperationLogging("CreateProfileJob")
    )
    input_: capo_databrew.types.create_profile_job_request.CreateProfileJobRequest = {
        "dataset_name": dataset_name,
        "name": name,
        "output_location": output_location,
        "role_arn": role_arn,
    }
    if encryption_key_arn is not None:
        input_["encryption_key_arn"] = encryption_key_arn
    if encryption_mode is not None:
        input_["encryption_mode"] = encryption_mode
    if log_subscription is not None:
        input_["log_subscription"] = log_subscription
    if max_capacity is not None:
        input_["max_capacity"] = max_capacity
    if max_retries is not None:
        input_["max_retries"] = max_retries
    if configuration is not None:
        input_["configuration"] = configuration
    if validation_configurations is not None:
        input_["validation_configurations"] = validation_configurations
    if tags is not None:
        input_["tags"] = tags
    if timeout is not None:
        input_["timeout"] = timeout
    if job_sample is not None:
        input_["job_sample"] = job_sample

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