create_dataset ¶

def create_dataset(
    self,
    dataset_name: "capo_forecast.types.name.Name",
    domain: "capo_forecast.types.domain.Domain",
    dataset_type: "capo_forecast.types.dataset_type.DatasetType",
    schema: "capo_forecast.types.schema.Schema",
    *,
    config_overrides: Optional[forecastClientConfig] = None,
    data_frequency: Optional["capo_forecast.types.frequency.Frequency"] = None,
    encryption_config: Optional[
        "capo_forecast.types.encryption_config.EncryptionConfig"
    ] = None,
    tags: Optional["capo_forecast.types.tags.Tags"] = None,
) -> "capo_forecast.types.create_dataset_response.CreateDatasetResponse":
    """<p>Creates an Amazon Forecast dataset. The information about the dataset that you provide helps Forecast understand how to consume the data for model training. This includes the following:</p> <ul> <li> <p> <i> <code>DataFrequency</code> </i> - How frequently your historical time-series data is collected.</p> </li> <li> <p> <i> <code>Domain</code> </i> and <i> <code>DatasetType</code> </i> - Each dataset has an associated dataset domain and a type within the domain. Amazon Forecast provides a list of predefined domains and types within each domain. For each unique dataset domain and type within the domain, Amazon Forecast requires your data to include a minimum set of predefined fields.</p> </li> <li> <p> <i> <code>Schema</code> </i> - A schema specifies the fields in the dataset, including the field name and data type.</p> </li> </ul> <p>After creating a dataset, you import your training data into it and add the dataset to a dataset group. You use the dataset group to create a predictor. For more information, see <a href="https://docs.aws.amazon.com/forecast/latest/dg/howitworks-datasets-groups.html">Importing datasets</a>.</p> <p>To get a list of all your datasets, use the <a href="https://docs.aws.amazon.com/forecast/latest/dg/API_ListDatasets.html">ListDatasets</a> operation.</p> <p>For example Forecast datasets, see the <a href="https://github.com/aws-samples/amazon-forecast-samples">Amazon Forecast Sample GitHub repository</a>.</p> <note> <p>The <code>Status</code> of a dataset must be <code>ACTIVE</code> before you can import training data. Use the <a href="https://docs.aws.amazon.com/forecast/latest/dg/API_DescribeDataset.html">DescribeDataset</a> operation to get the status.</p> </note>

    Args:
        dataset_name: <p>A name for the dataset.</p>
        domain: <p>The domain associated with the dataset. When you add a dataset to a dataset group, this value and the value specified for the <code>Domain</code> parameter of the <a href="https://docs.aws.amazon.com/forecast/latest/dg/API_CreateDatasetGroup.html">CreateDatasetGroup</a> operation must match.</p> <p>The <code>Domain</code> and <code>DatasetType</code> that you choose determine the fields that must be present in the training data that you import to the dataset. For example, if you choose the <code>RETAIL</code> domain and <code>TARGET_TIME_SERIES</code> as the <code>DatasetType</code>, Amazon Forecast requires <code>item_id</code>, <code>timestamp</code>, and <code>demand</code> fields to be present in your data. For more information, see <a href="https://docs.aws.amazon.com/forecast/latest/dg/howitworks-datasets-groups.html">Importing datasets</a>.</p>
        dataset_type: <p>The dataset type. Valid values depend on the chosen <code>Domain</code>.</p>
        data_frequency: <p>The frequency of data collection. This parameter is required for RELATED_TIME_SERIES datasets.</p> <p>Valid intervals are an integer followed by Y (Year), M (Month), W (Week), D (Day), H (Hour), and min (Minute). For example, "1D" indicates every day and "15min" indicates every 15 minutes. You cannot specify a value that would overlap with the next larger frequency. That means, for example, you cannot specify a frequency of 60 minutes, because that is equivalent to 1 hour. The valid values for each frequency are the following:</p> <ul> <li> <p>Minute - 1-59</p> </li> <li> <p>Hour - 1-23</p> </li> <li> <p>Day - 1-6</p> </li> <li> <p>Week - 1-4</p> </li> <li> <p>Month - 1-11</p> </li> <li> <p>Year - 1</p> </li> </ul> <p>Thus, if you want every other week forecasts, specify "2W". Or, if you want quarterly forecasts, you specify "3M".</p>
        schema: <p>The schema for the dataset. The schema attributes and their order must match the fields in your data. The dataset <code>Domain</code> and <code>DatasetType</code> that you choose determine the minimum required fields in your training data. For information about the required fields for a specific dataset domain and type, see <a href="https://docs.aws.amazon.com/forecast/latest/dg/howitworks-domains-ds-types.html">Dataset Domains and Dataset Types</a>.</p>
        encryption_config: <p>An Key Management Service (KMS) key and the Identity and Access Management (IAM) role that Amazon Forecast can assume to access the key.</p>
        tags: <p>The optional metadata that you apply to the dataset to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define.</p> <p>The following basic restrictions apply to tags:</p> <ul> <li> <p>Maximum number of tags per resource - 50.</p> </li> <li> <p>For each resource, each tag key must be unique, and each tag key can have only one value.</p> </li> <li> <p>Maximum key length - 128 Unicode characters in UTF-8.</p> </li> <li> <p>Maximum value length - 256 Unicode characters in UTF-8.</p> </li> <li> <p>If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @.</p> </li> <li> <p>Tag keys and values are case sensitive.</p> </li> <li> <p>Do not use <code>aws:</code>, <code>AWS:</code>, or any upper or lowercase combination of such as a prefix for keys as it is reserved for Amazon Web Services use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has <code>aws</code> as its prefix but the key does not, then Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of <code>aws</code> do not count against your tags per resource limit.</p> </li> </ul>

    Raises:
        capo_forecast.errors.invalid_input_exception.InvalidInputException: <p>We can't process the request because it includes an invalid value or a value that exceeds the valid range.</p>
        capo_forecast.errors.limit_exceeded_exception.LimitExceededException: <p>The limit on the number of resources per account has been exceeded.</p>
        capo_forecast.errors.resource_already_exists_exception.ResourceAlreadyExistsException: <p>There is already a resource with this name. Try again with a different name.</p>
        capo_forecast.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    def _handler(
        req: "OperationRequest[capo_forecast.types.create_dataset_request.CreateDatasetRequest]",
    ) -> OperationResponse[
        "capo_forecast.types.create_dataset_response.CreateDatasetResponse"
    ]:
        import capo_forecast._operations.amazon_forecast.create_dataset

        output, http_response = (
            capo_forecast._operations.amazon_forecast.create_dataset.create_dataset(
                req.options, req.input
            )
        )
        return OperationResponse(output=output, response=http_response)

    def _redact_input(
        input_: "capo_forecast.types.create_dataset_request.CreateDatasetRequest",
    ) -> dict[str, Any]:
        import capo_forecast.types.create_dataset_request

        return capo_forecast.types.create_dataset_request.redact_sensitive(input_)

    interceptors_, options_ = self.operation_options(
        config_overrides,
        OperationLogging("CreateDataset", redact_input=_redact_input),
    )
    input_: capo_forecast.types.create_dataset_request.CreateDatasetRequest = {
        "dataset_name": dataset_name,
        "domain": domain,
        "dataset_type": dataset_type,
        "schema": schema,
    }
    if data_frequency is not None:
        input_["data_frequency"] = data_frequency
    if encryption_config is not None:
        input_["encryption_config"] = encryption_config
    if tags is not None:
        input_["tags"] = tags

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