TimeSeriesForecastingJobConfig
The collection of settings used by an AutoML job V2 for the timeseries forecasting problem type.
Contents
 ForecastFrequency

The frequency of predictions in a forecast.
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 and15min
indicates every 15 minutes. The value of a frequency must not overlap with the next larger frequency. For example, you must use a frequency of1H
instead of60min
.The valid values for each frequency are the following:

Minute  159

Hour  123

Day  16

Week  14

Month  111

Year  1
Type: String
Length Constraints: Minimum length of 1. Maximum length of 5.
Pattern:
^1YY([19]1[01])MM[14]WW[16]DD([19]1[09]2[03])HH([19][15][09])min$
Required: Yes

 ForecastHorizon

The number of timesteps that the model predicts. The forecast horizon is also called the prediction length. The maximum forecast horizon is the lesser of 500 timesteps or 1/4 of the timesteps in the dataset.
Type: Integer
Valid Range: Minimum value of 1.
Required: Yes
 TimeSeriesConfig

The collection of components that defines the timeseries.
Type: TimeSeriesConfig object
Required: Yes
 CandidateGenerationConfig

Stores the configuration information for how model candidates are generated using an AutoML job V2.
Type: CandidateGenerationConfig object
Required: No
 CompletionCriteria

How long a job is allowed to run, or how many candidates a job is allowed to generate.
Type: AutoMLJobCompletionCriteria object
Required: No
 FeatureSpecificationS3Uri

A URL to the Amazon S3 data source containing additional selected features that complement the target, itemID, timestamp, and grouped columns set in
TimeSeriesConfig
. When not provided, the AutoML job V2 includes all the columns from the original dataset that are not already declared inTimeSeriesConfig
. If provided, the AutoML job V2 only considers these additional columns as a complement to the ones declared inTimeSeriesConfig
.You can input
FeatureAttributeNames
(optional) in JSON format as shown below:{ "FeatureAttributeNames":["col1", "col2", ...] }
.You can also specify the data type of the feature (optional) in the format shown below:
{ "FeatureDataTypes":{"col1":"numeric", "col2":"categorical" ... } }
Autopilot supports the following data types:
numeric
,categorical
,text
, anddatetime
.Note
These column keys must not include any column set in
TimeSeriesConfig
.Type: String
Length Constraints: Maximum length of 1024.
Pattern:
^(httpss3)://([^/]+)/?(.*)$
Required: No
 ForecastQuantiles

The quantiles used to train the model for forecasts at a specified quantile. You can specify quantiles from
0.01
(p1) to0.99
(p99), by increments of 0.01 or higher. Up to five forecast quantiles can be specified. WhenForecastQuantiles
is not provided, the AutoML job uses the quantiles p10, p50, and p90 as default.Type: Array of strings
Array Members: Minimum number of 1 item. Maximum number of 5 items.
Length Constraints: Minimum length of 2. Maximum length of 4.
Pattern:
(^p[19]\d?$)
Required: No
 HolidayConfig

The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.
Type: Array of HolidayConfigAttributes objects
Array Members: Fixed number of 1 item.
Required: No
 Transformations

The transformations modifying specific attributes of the timeseries, such as filling strategies for missing values.
Type: TimeSeriesTransformations object
Required: No
See Also
For more information about using this API in one of the languagespecific Amazon SDKs, see the following: