Creates a forecast for each item in the TARGET_TIME_SERIES dataset that was used to train the predictor. This is known as inference. To retrieve the forecast for a single item at low latency, use the operation. To export the complete forecast into your Amazon Simple Storage Service (Amazon S3) bucket, use the CreateForecastExportJob operation.
The range of the forecast is determined by the ForecastHorizon value, which you specify in the CreatePredictor request. When you query a forecast, you can request a specific date range within the forecast.
To get a list of all your forecasts, use the ListForecasts operation.
The forecasts generated by Amazon Forecast are in the same time zone as the dataset that was used to create the predictor.
For more information, see howitworks-forecast.
The Status of the forecast must be ACTIVE before you can query or export the forecast. Use the DescribeForecast operation to get the status.
By default, a forecast includes predictions for every item (item_id) in the dataset group that was used to train the predictor. However, you can use the TimeSeriesSelector object to generate a forecast on a subset of time series. Forecast creation is skipped for any time series that you specify that are not in the input dataset. The forecast export file will not contain these time series or their forecasted values.
Parameters:
-
forecast_name
(Name)
–
-
predictor_arn
(Arn)
–
The Amazon Resource Name (ARN) of the predictor to use to generate the forecast.
-
forecast_types
(Optional[ForecastTypes], default:
None
)
–
The quantiles at which probabilistic forecasts are generated. You can currently specify up to 5 quantiles per forecast. Accepted values include 0.01 to 0.99 (increments of .01 only) and mean. The mean forecast is different from the median (0.50) when the distribution is not symmetric (for example, Beta and Negative Binomial).
The default quantiles are the quantiles you specified during predictor creation. If you didn't specify quantiles, the default values are ["0.1", "0.5", "0.9"].
-
tags
(Optional[Tags], default:
None
)
–
The optional metadata that you apply to the forecast to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define.
The following basic restrictions apply to tags:
-
Maximum number of tags per resource - 50.
-
For each resource, each tag key must be unique, and each tag key can have only one value.
-
Maximum key length - 128 Unicode characters in UTF-8.
-
Maximum value length - 256 Unicode characters in UTF-8.
-
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: + - = . _ : / @.
-
Tag keys and values are case sensitive.
-
Do not use aws:, AWS:, 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 aws 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 aws do not count against your tags per resource limit.
-
time_series_selector
(Optional[TimeSeriesSelector], default:
None
)
–
Defines the set of time series that are used to create the forecasts in a TimeSeriesIdentifiers object.
The TimeSeriesIdentifiers object needs the following information:
Raises:
Source code in docs_src/capo_forecast/_services/forecast.py
| def create_forecast(
self,
forecast_name: "capo_forecast.types.name.Name",
predictor_arn: "capo_forecast.types.arn.Arn",
*,
config_overrides: Optional[forecastClientConfig] = None,
forecast_types: Optional[
"capo_forecast.types.forecast_types.ForecastTypes"
] = None,
tags: Optional["capo_forecast.types.tags.Tags"] = None,
time_series_selector: Optional[
"capo_forecast.types.time_series_selector.TimeSeriesSelector"
] = None,
) -> "capo_forecast.types.create_forecast_response.CreateForecastResponse":
"""<p>Creates a forecast for each item in the <code>TARGET_TIME_SERIES</code> dataset that was used to train the predictor. This is known as inference. To retrieve the forecast for a single item at low latency, use the operation. To export the complete forecast into your Amazon Simple Storage Service (Amazon S3) bucket, use the <a>CreateForecastExportJob</a> operation.</p> <p>The range of the forecast is determined by the <code>ForecastHorizon</code> value, which you specify in the <a>CreatePredictor</a> request. When you query a forecast, you can request a specific date range within the forecast.</p> <p>To get a list of all your forecasts, use the <a>ListForecasts</a> operation.</p> <note> <p>The forecasts generated by Amazon Forecast are in the same time zone as the dataset that was used to create the predictor.</p> </note> <p>For more information, see <a>howitworks-forecast</a>.</p> <note> <p>The <code>Status</code> of the forecast must be <code>ACTIVE</code> before you can query or export the forecast. Use the <a>DescribeForecast</a> operation to get the status.</p> </note> <p>By default, a forecast includes predictions for every item (<code>item_id</code>) in the dataset group that was used to train the predictor. However, you can use the <code>TimeSeriesSelector</code> object to generate a forecast on a subset of time series. Forecast creation is skipped for any time series that you specify that are not in the input dataset. The forecast export file will not contain these time series or their forecasted values.</p>
Args:
forecast_name: <p>A name for the forecast.</p>
predictor_arn: <p>The Amazon Resource Name (ARN) of the predictor to use to generate the forecast.</p>
forecast_types: <p>The quantiles at which probabilistic forecasts are generated. <b>You can currently specify up to 5 quantiles per forecast</b>. Accepted values include <code>0.01 to 0.99</code> (increments of .01 only) and <code>mean</code>. The mean forecast is different from the median (0.50) when the distribution is not symmetric (for example, Beta and Negative Binomial). </p> <p>The default quantiles are the quantiles you specified during predictor creation. If you didn't specify quantiles, the default values are <code>["0.1", "0.5", "0.9"]</code>. </p>
tags: <p>The optional metadata that you apply to the forecast 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>
time_series_selector: <p>Defines the set of time series that are used to create the forecasts in a <code>TimeSeriesIdentifiers</code> object.</p> <p>The <code>TimeSeriesIdentifiers</code> object needs the following information:</p> <ul> <li> <p> <code>DataSource</code> </p> </li> <li> <p> <code>Format</code> </p> </li> <li> <p> <code>Schema</code> </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.resource_in_use_exception.ResourceInUseException: <p>The specified resource is in use.</p>
capo_forecast.errors.resource_not_found_exception.ResourceNotFoundException: <p>We can't find a resource with that Amazon Resource Name (ARN). Check the ARN and try again.</p>
capo_forecast.errors.UnknownServiceError: The service returned an error code this client does not model.
"""
def _handler(
req: "OperationRequest[capo_forecast.types.create_forecast_request.CreateForecastRequest]",
) -> OperationResponse[
"capo_forecast.types.create_forecast_response.CreateForecastResponse"
]:
import capo_forecast._operations.amazon_forecast.create_forecast
output, http_response = (
capo_forecast._operations.amazon_forecast.create_forecast.create_forecast(
req.options, req.input
)
)
return OperationResponse(output=output, response=http_response)
def _redact_input(
input_: "capo_forecast.types.create_forecast_request.CreateForecastRequest",
) -> dict[str, Any]:
import capo_forecast.types.create_forecast_request
return capo_forecast.types.create_forecast_request.redact_sensitive(input_)
interceptors_, options_ = self.operation_options(
config_overrides,
OperationLogging("CreateForecast", redact_input=_redact_input),
)
input_: capo_forecast.types.create_forecast_request.CreateForecastRequest = {
"forecast_name": forecast_name,
"predictor_arn": predictor_arn,
}
if forecast_types is not None:
input_["forecast_types"] = forecast_types
if tags is not None:
input_["tags"] = tags
if time_series_selector is not None:
input_["time_series_selector"] = time_series_selector
response = execute_pipeline(
OperationRequest(input=input_, options=options_),
handler=_handler,
interceptors=list(interceptors_),
)
response.response.close()
return response.output
|