create_data_source_from_redshift async ¶

async def create_data_source_from_redshift(
    self,
    data_source_id: "capo_machine_learning.types.entity_id.EntityId",
    data_spec: "capo_machine_learning.types.redshift_data_spec.RedshiftDataSpec",
    role_arn: "capo_machine_learning.types.role_arn.RoleARN",
    *,
    config_overrides: Optional[AsyncMachineLearningClientConfig] = None,
    data_source_name: Optional[
        "capo_machine_learning.types.entity_name.EntityName"
    ] = None,
    compute_statistics: Optional[
        "capo_machine_learning.types.compute_statistics.ComputeStatistics"
    ] = None,
) -> "capo_machine_learning.types.create_data_source_from_redshift_output.CreateDataSourceFromRedshiftOutput":
    r"""<p>Creates a <code>DataSource</code> from a database hosted on an Amazon Redshift cluster. A <code>DataSource</code> references data that can be used to perform either <code>CreateMLModel</code>, <code>CreateEvaluation</code>, or <code>CreateBatchPrediction</code> operations.</p> <p> <code>CreateDataSourceFromRedshift</code> is an asynchronous operation. In response to <code>CreateDataSourceFromRedshift</code>, Amazon Machine Learning (Amazon ML) immediately returns and sets the <code>DataSource</code> status to <code>PENDING</code>. After the <code>DataSource</code> is created and ready for use, Amazon ML sets the <code>Status</code> parameter to <code>COMPLETED</code>. <code>DataSource</code> in <code>COMPLETED</code> or <code>PENDING</code> states can be used to perform only <code>CreateMLModel</code>, <code>CreateEvaluation</code>, or <code>CreateBatchPrediction</code> operations. </p> <p> If Amazon ML can't accept the input source, it sets the <code>Status</code> parameter to <code>FAILED</code> and includes an error message in the <code>Message</code> attribute of the <code>GetDataSource</code> operation response. </p> <p>The observations should be contained in the database hosted on an Amazon Redshift cluster and should be specified by a <code>SelectSqlQuery</code> query. Amazon ML executes an <code>Unload</code> command in Amazon Redshift to transfer the result set of the <code>SelectSqlQuery</code> query to <code>S3StagingLocation</code>.</p> <p>After the <code>DataSource</code> has been created, it's ready for use in evaluations and batch predictions. If you plan to use the <code>DataSource</code> to train an <code>MLModel</code>, the <code>DataSource</code> also requires a recipe. A recipe describes how each input variable will be used in training an <code>MLModel</code>. Will the variable be included or excluded from training? Will the variable be manipulated; for example, will it be combined with another variable or will it be split apart into word combinations? The recipe provides answers to these questions.</p> <p>You can't change an existing datasource, but you can copy and modify the settings from an existing Amazon Redshift datasource to create a new datasource. To do so, call <code>GetDataSource</code> for an existing datasource and copy the values to a <code>CreateDataSource</code> call. Change the settings that you want to change and make sure that all required fields have the appropriate values.</p>

    Args:
        data_source_id: <p>A user-supplied ID that uniquely identifies the <code>DataSource</code>.</p>
        data_source_name: <p>A user-supplied name or description of the <code>DataSource</code>. </p>
        data_spec: <p>The data specification of an Amazon Redshift <code>DataSource</code>:</p> <ul> <li> <p>DatabaseInformation -</p> <ul> <li> <p> <code>DatabaseName</code> - The name of the Amazon Redshift database.</p> </li> <li> <p> <code> ClusterIdentifier</code> - The unique ID for the Amazon Redshift cluster.</p> </li> </ul> </li> <li> <p>DatabaseCredentials - The AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon Redshift database.</p> </li> <li> <p>SelectSqlQuery - The query that is used to retrieve the observation data for the <code>Datasource</code>.</p> </li> <li> <p>S3StagingLocation - The Amazon Simple Storage Service (Amazon S3) location for staging Amazon Redshift data. The data retrieved from Amazon Redshift using the <code>SelectSqlQuery</code> query is stored in this location.</p> </li> <li> <p>DataSchemaUri - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>DataSource</code>.</p> <p> Sample - <code> "{\"splitting\":{\"percentBegin\":10,\"percentEnd\":60}}"</code> </p> </li> </ul>
        role_arn: <p>A fully specified role Amazon Resource Name (ARN). Amazon ML assumes the role on behalf of the user to create the following:</p> <ul> <li> <p>A security group to allow Amazon ML to execute the <code>SelectSqlQuery</code> query on an Amazon Redshift cluster</p> </li> <li> <p>An Amazon S3 bucket policy to grant Amazon ML read/write permissions on the <code>S3StagingLocation</code> </p> </li> </ul>
        compute_statistics: <p>The compute statistics for a <code>DataSource</code>. The statistics are generated from the observation data referenced by a <code>DataSource</code>. Amazon ML uses the statistics internally during <code>MLModel</code> training. This parameter must be set to <code>true</code> if the <code>DataSource</code> needs to be used for <code>MLModel</code> training.</p>

    Raises:
        capo_machine_learning.errors.idempotent_parameter_mismatch_exception.IdempotentParameterMismatchException: <p>A second request to use or change an object was not allowed. This can result from retrying a request using a parameter that was not present in the original request.</p>
        capo_machine_learning.errors.internal_server_exception.InternalServerException: <p>An error on the server occurred when trying to process a request.</p>
        capo_machine_learning.errors.invalid_input_exception.InvalidInputException: <p>An error on the client occurred. Typically, the cause is an invalid input value.</p>
        capo_machine_learning.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    async def _handler(
        req: "AsyncOperationRequest[capo_machine_learning.types.create_data_source_from_redshift_input.CreateDataSourceFromRedshiftInput]",
    ) -> AsyncOperationResponse[
        "capo_machine_learning.types.create_data_source_from_redshift_output.CreateDataSourceFromRedshiftOutput"
    ]:
        import capo_machine_learning._operations.amazon_ml_20141212.create_data_source_from_redshift

        (
            output,
            http_response,
        ) = await capo_machine_learning._operations.amazon_ml_20141212.create_data_source_from_redshift.async_create_data_source_from_redshift(
            req.options, req.input
        )
        return AsyncOperationResponse(output=output, response=http_response)

    def _redact_input(
        input_: "capo_machine_learning.types.create_data_source_from_redshift_input.CreateDataSourceFromRedshiftInput",
    ) -> dict[str, Any]:
        import capo_machine_learning.types.create_data_source_from_redshift_input

        return capo_machine_learning.types.create_data_source_from_redshift_input.redact_sensitive(
            input_
        )

    interceptors_, options_ = self.operation_options(
        config_overrides,
        OperationLogging(
            "CreateDataSourceFromRedshift", redact_input=_redact_input
        ),
    )
    input_: capo_machine_learning.types.create_data_source_from_redshift_input.CreateDataSourceFromRedshiftInput = {
        "data_source_id": data_source_id,
        "data_spec": data_spec,
        "role_arn": role_arn,
    }
    if data_source_name is not None:
        input_["data_source_name"] = data_source_name
    if compute_statistics is not None:
        input_["compute_statistics"] = compute_statistics

    response = await aexecute_pipeline(
        AsyncOperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    await response.response.aclose()
    return response.output