com.amazonaws.services.sagemaker.model

Class TimeSeriesForecastingJobConfig

java.lang.Object

com.amazonaws.services.sagemaker.model.TimeSeriesForecastingJobConfig

All Implemented Interfaces:

StructuredPojo, Serializable, Cloneable

@Generated(value="com.amazonaws:aws-java-sdk-code-generator")
public class TimeSeriesForecastingJobConfig
extends Object
implements Serializable, Cloneable, StructuredPojo

The collection of settings used by an AutoML job V2 for the time-series forecasting problem type.

See Also:

AWS API Documentation, Serialized Form

Constructor Summary

Constructors

Constructor and Description
TimeSeriesForecastingJobConfig()

Method Summary

Modifier and Type	Method and Description
TimeSeriesForecastingJobConfig	clone()
boolean	equals(Object obj)
CandidateGenerationConfig	getCandidateGenerationConfig()
AutoMLJobCompletionCriteria	getCompletionCriteria()
String	getFeatureSpecificationS3Uri() A URL to the Amazon S3 data source containing additional selected features that complement the target, itemID, timestamp, and grouped columns set in TimeSeriesConfig.
String	getForecastFrequency() The frequency of predictions in a forecast.
Integer	getForecastHorizon() The number of time-steps that the model predicts.
List<String>	getForecastQuantiles() The quantiles used to train the model for forecasts at a specified quantile.
List<HolidayConfigAttributes>	getHolidayConfig() The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.
TimeSeriesConfig	getTimeSeriesConfig() The collection of components that defines the time-series.
TimeSeriesTransformations	getTransformations() The transformations modifying specific attributes of the time-series, such as filling strategies for missing values.
int	hashCode()
void	marshall(ProtocolMarshaller protocolMarshaller) Marshalls this structured data using the given ProtocolMarshaller.
void	setCandidateGenerationConfig(CandidateGenerationConfig candidateGenerationConfig)
void	setCompletionCriteria(AutoMLJobCompletionCriteria completionCriteria)
void	setFeatureSpecificationS3Uri(String 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.
void	setForecastFrequency(String forecastFrequency) The frequency of predictions in a forecast.
void	setForecastHorizon(Integer forecastHorizon) The number of time-steps that the model predicts.
void	setForecastQuantiles(Collection<String> forecastQuantiles) The quantiles used to train the model for forecasts at a specified quantile.
void	setHolidayConfig(Collection<HolidayConfigAttributes> holidayConfig) The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.
void	setTimeSeriesConfig(TimeSeriesConfig timeSeriesConfig) The collection of components that defines the time-series.
void	setTransformations(TimeSeriesTransformations transformations) The transformations modifying specific attributes of the time-series, such as filling strategies for missing values.
String	toString() Returns a string representation of this object.
TimeSeriesForecastingJobConfig	withCandidateGenerationConfig(CandidateGenerationConfig candidateGenerationConfig)
TimeSeriesForecastingJobConfig	withCompletionCriteria(AutoMLJobCompletionCriteria completionCriteria)
TimeSeriesForecastingJobConfig	withFeatureSpecificationS3Uri(String 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.
TimeSeriesForecastingJobConfig	withForecastFrequency(String forecastFrequency) The frequency of predictions in a forecast.
TimeSeriesForecastingJobConfig	withForecastHorizon(Integer forecastHorizon) The number of time-steps that the model predicts.
TimeSeriesForecastingJobConfig	withForecastQuantiles(Collection<String> forecastQuantiles) The quantiles used to train the model for forecasts at a specified quantile.
TimeSeriesForecastingJobConfig	withForecastQuantiles(String... forecastQuantiles) The quantiles used to train the model for forecasts at a specified quantile.
TimeSeriesForecastingJobConfig	withHolidayConfig(Collection<HolidayConfigAttributes> holidayConfig) The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.
TimeSeriesForecastingJobConfig	withHolidayConfig(HolidayConfigAttributes... holidayConfig) The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.
TimeSeriesForecastingJobConfig	withTimeSeriesConfig(TimeSeriesConfig timeSeriesConfig) The collection of components that defines the time-series.
TimeSeriesForecastingJobConfig	withTransformations(TimeSeriesTransformations transformations) The transformations modifying specific attributes of the time-series, such as filling strategies for missing values.

Methods inherited from class java.lang.Object

getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

TimeSeriesForecastingJobConfig

public TimeSeriesForecastingJobConfig()

Method Detail

setFeatureSpecificationS3Uri

public void setFeatureSpecificationS3Uri(String 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 in TimeSeriesConfig . If provided, the AutoML job V2 only considers these additional columns as a complement to the ones declared in TimeSeriesConfig.

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, and datetime.

These column keys must not include any column set in TimeSeriesConfig.

Parameters:

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 in TimeSeriesConfig. If provided, the AutoML job V2 only considers these additional columns as a complement to the ones declared in TimeSeriesConfig.

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, and datetime.

These column keys must not include any column set in TimeSeriesConfig.

getFeatureSpecificationS3Uri

public String getFeatureSpecificationS3Uri()

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 in TimeSeriesConfig . If provided, the AutoML job V2 only considers these additional columns as a complement to the ones declared in TimeSeriesConfig.

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, and datetime.

These column keys must not include any column set in TimeSeriesConfig.

Returns:

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 in TimeSeriesConfig. If provided, the AutoML job V2 only considers these additional columns as a complement to the ones declared in TimeSeriesConfig.

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, and datetime.

These column keys must not include any column set in TimeSeriesConfig.

withFeatureSpecificationS3Uri

public TimeSeriesForecastingJobConfig withFeatureSpecificationS3Uri(String 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 in TimeSeriesConfig . If provided, the AutoML job V2 only considers these additional columns as a complement to the ones declared in TimeSeriesConfig.

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, and datetime.

These column keys must not include any column set in TimeSeriesConfig.

Parameters:

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 in TimeSeriesConfig. If provided, the AutoML job V2 only considers these additional columns as a complement to the ones declared in TimeSeriesConfig.

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, and datetime.

These column keys must not include any column set in TimeSeriesConfig.

Returns:

Returns a reference to this object so that method calls can be chained together.

setCompletionCriteria

public void setCompletionCriteria(AutoMLJobCompletionCriteria completionCriteria)

Parameters:

completionCriteria -

getCompletionCriteria

public AutoMLJobCompletionCriteria getCompletionCriteria()

Returns:

withCompletionCriteria

public TimeSeriesForecastingJobConfig withCompletionCriteria(AutoMLJobCompletionCriteria completionCriteria)

Parameters:

completionCriteria -

Returns:

Returns a reference to this object so that method calls can be chained together.

setForecastFrequency

public void setForecastFrequency(String 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 and 15min indicates every 15 minutes. The value of a frequency must not overlap with the next larger frequency. For example, you must use a frequency of 1H instead of 60min.

The valid values for each frequency are the following:

• Minute - 1-59

• Hour - 1-23

• Day - 1-6

• Week - 1-4

• Month - 1-11

• Year - 1

Parameters:

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 and 15min indicates every 15 minutes. The value of a frequency must not overlap with the next larger frequency. For example, you must use a frequency of 1H instead of 60min.

The valid values for each frequency are the following:

• Minute - 1-59

• Hour - 1-23

• Day - 1-6

• Week - 1-4

• Month - 1-11

• Year - 1

getForecastFrequency

public String getForecastFrequency()

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 and 15min indicates every 15 minutes. The value of a frequency must not overlap with the next larger frequency. For example, you must use a frequency of 1H instead of 60min.

The valid values for each frequency are the following:

• Minute - 1-59

• Hour - 1-23

• Day - 1-6

• Week - 1-4

• Month - 1-11

• Year - 1

Returns:

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 and 15min indicates every 15 minutes. The value of a frequency must not overlap with the next larger frequency. For example, you must use a frequency of 1H instead of 60min.

The valid values for each frequency are the following:

• Minute - 1-59

• Hour - 1-23

• Day - 1-6

• Week - 1-4

• Month - 1-11

• Year - 1

withForecastFrequency

public TimeSeriesForecastingJobConfig withForecastFrequency(String 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 and 15min indicates every 15 minutes. The value of a frequency must not overlap with the next larger frequency. For example, you must use a frequency of 1H instead of 60min.

The valid values for each frequency are the following:

• Minute - 1-59

• Hour - 1-23

• Day - 1-6

• Week - 1-4

• Month - 1-11

• Year - 1

Parameters:

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 and 15min indicates every 15 minutes. The value of a frequency must not overlap with the next larger frequency. For example, you must use a frequency of 1H instead of 60min.

The valid values for each frequency are the following:

• Minute - 1-59

• Hour - 1-23

• Day - 1-6

• Week - 1-4

• Month - 1-11

• Year - 1

Returns:

Returns a reference to this object so that method calls can be chained together.

setForecastHorizon

public void setForecastHorizon(Integer forecastHorizon)

The number of time-steps that the model predicts. The forecast horizon is also called the prediction length. The maximum forecast horizon is the lesser of 500 time-steps or 1/4 of the time-steps in the dataset.

Parameters:

forecastHorizon - The number of time-steps that the model predicts. The forecast horizon is also called the prediction length. The maximum forecast horizon is the lesser of 500 time-steps or 1/4 of the time-steps in the dataset.

getForecastHorizon

public Integer getForecastHorizon()

The number of time-steps that the model predicts. The forecast horizon is also called the prediction length. The maximum forecast horizon is the lesser of 500 time-steps or 1/4 of the time-steps in the dataset.

Returns:

The number of time-steps that the model predicts. The forecast horizon is also called the prediction length. The maximum forecast horizon is the lesser of 500 time-steps or 1/4 of the time-steps in the dataset.

withForecastHorizon

public TimeSeriesForecastingJobConfig withForecastHorizon(Integer forecastHorizon)

The number of time-steps that the model predicts. The forecast horizon is also called the prediction length. The maximum forecast horizon is the lesser of 500 time-steps or 1/4 of the time-steps in the dataset.

Parameters:

forecastHorizon - The number of time-steps that the model predicts. The forecast horizon is also called the prediction length. The maximum forecast horizon is the lesser of 500 time-steps or 1/4 of the time-steps in the dataset.

Returns:

Returns a reference to this object so that method calls can be chained together.

getForecastQuantiles

public List<String> getForecastQuantiles()

The quantiles used to train the model for forecasts at a specified quantile. You can specify quantiles from 0.01 (p1) to 0.99 (p99), by increments of 0.01 or higher. Up to five forecast quantiles can be specified. When ForecastQuantiles is not provided, the AutoML job uses the quantiles p10, p50, and p90 as default.

Returns:

The quantiles used to train the model for forecasts at a specified quantile. You can specify quantiles from 0.01 (p1) to 0.99 (p99), by increments of 0.01 or higher. Up to five forecast quantiles can be specified. When ForecastQuantiles is not provided, the AutoML job uses the quantiles p10, p50, and p90 as default.

setForecastQuantiles

public void setForecastQuantiles(Collection<String> forecastQuantiles)

The quantiles used to train the model for forecasts at a specified quantile. You can specify quantiles from 0.01 (p1) to 0.99 (p99), by increments of 0.01 or higher. Up to five forecast quantiles can be specified. When ForecastQuantiles is not provided, the AutoML job uses the quantiles p10, p50, and p90 as default.

Parameters:

forecastQuantiles - The quantiles used to train the model for forecasts at a specified quantile. You can specify quantiles from 0.01 (p1) to 0.99 (p99), by increments of 0.01 or higher. Up to five forecast quantiles can be specified. When ForecastQuantiles is not provided, the AutoML job uses the quantiles p10, p50, and p90 as default.

withForecastQuantiles

public TimeSeriesForecastingJobConfig withForecastQuantiles(String... forecastQuantiles)

The quantiles used to train the model for forecasts at a specified quantile. You can specify quantiles from 0.01 (p1) to 0.99 (p99), by increments of 0.01 or higher. Up to five forecast quantiles can be specified. When ForecastQuantiles is not provided, the AutoML job uses the quantiles p10, p50, and p90 as default.

NOTE: This method appends the values to the existing list (if any). Use setForecastQuantiles(java.util.Collection) or withForecastQuantiles(java.util.Collection) if you want to override the existing values.

Parameters:

forecastQuantiles - The quantiles used to train the model for forecasts at a specified quantile. You can specify quantiles from 0.01 (p1) to 0.99 (p99), by increments of 0.01 or higher. Up to five forecast quantiles can be specified. When ForecastQuantiles is not provided, the AutoML job uses the quantiles p10, p50, and p90 as default.

Returns:

Returns a reference to this object so that method calls can be chained together.

withForecastQuantiles

public TimeSeriesForecastingJobConfig withForecastQuantiles(Collection<String> forecastQuantiles)

The quantiles used to train the model for forecasts at a specified quantile. You can specify quantiles from 0.01 (p1) to 0.99 (p99), by increments of 0.01 or higher. Up to five forecast quantiles can be specified. When ForecastQuantiles is not provided, the AutoML job uses the quantiles p10, p50, and p90 as default.

Parameters:

forecastQuantiles - The quantiles used to train the model for forecasts at a specified quantile. You can specify quantiles from 0.01 (p1) to 0.99 (p99), by increments of 0.01 or higher. Up to five forecast quantiles can be specified. When ForecastQuantiles is not provided, the AutoML job uses the quantiles p10, p50, and p90 as default.

Returns:

Returns a reference to this object so that method calls can be chained together.

setTransformations

public void setTransformations(TimeSeriesTransformations transformations)

The transformations modifying specific attributes of the time-series, such as filling strategies for missing values.

Parameters:

transformations - The transformations modifying specific attributes of the time-series, such as filling strategies for missing values.

getTransformations

public TimeSeriesTransformations getTransformations()

The transformations modifying specific attributes of the time-series, such as filling strategies for missing values.

Returns:

The transformations modifying specific attributes of the time-series, such as filling strategies for missing values.

withTransformations

public TimeSeriesForecastingJobConfig withTransformations(TimeSeriesTransformations transformations)

The transformations modifying specific attributes of the time-series, such as filling strategies for missing values.

Parameters:

transformations - The transformations modifying specific attributes of the time-series, such as filling strategies for missing values.

Returns:

Returns a reference to this object so that method calls can be chained together.

setTimeSeriesConfig

public void setTimeSeriesConfig(TimeSeriesConfig timeSeriesConfig)

The collection of components that defines the time-series.

Parameters:

timeSeriesConfig - The collection of components that defines the time-series.

getTimeSeriesConfig

public TimeSeriesConfig getTimeSeriesConfig()

The collection of components that defines the time-series.

Returns:

The collection of components that defines the time-series.

withTimeSeriesConfig

public TimeSeriesForecastingJobConfig withTimeSeriesConfig(TimeSeriesConfig timeSeriesConfig)

The collection of components that defines the time-series.

Parameters:

timeSeriesConfig - The collection of components that defines the time-series.

Returns:

Returns a reference to this object so that method calls can be chained together.

getHolidayConfig

public List<HolidayConfigAttributes> getHolidayConfig()

The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.

Returns:

The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.

setHolidayConfig

public void setHolidayConfig(Collection<HolidayConfigAttributes> holidayConfig)

The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.

Parameters:

holidayConfig - The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.

withHolidayConfig

public TimeSeriesForecastingJobConfig withHolidayConfig(HolidayConfigAttributes... holidayConfig)

The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.

NOTE: This method appends the values to the existing list (if any). Use setHolidayConfig(java.util.Collection) or withHolidayConfig(java.util.Collection) if you want to override the existing values.

Parameters:

holidayConfig - The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.

Returns:

Returns a reference to this object so that method calls can be chained together.

withHolidayConfig

public TimeSeriesForecastingJobConfig withHolidayConfig(Collection<HolidayConfigAttributes> holidayConfig)

The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.

Parameters:

holidayConfig - The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.

Returns:

Returns a reference to this object so that method calls can be chained together.

setCandidateGenerationConfig

public void setCandidateGenerationConfig(CandidateGenerationConfig candidateGenerationConfig)

Parameters:

candidateGenerationConfig -

getCandidateGenerationConfig

public CandidateGenerationConfig getCandidateGenerationConfig()

Returns:

withCandidateGenerationConfig

public TimeSeriesForecastingJobConfig withCandidateGenerationConfig(CandidateGenerationConfig candidateGenerationConfig)

Parameters:

candidateGenerationConfig -

Returns:

Returns a reference to this object so that method calls can be chained together.

toString

public String toString()

Returns a string representation of this object. This is useful for testing and debugging. Sensitive data will be redacted from this string using a placeholder value.

Overrides:

toString in class Object

Returns:

A string representation of this object.

See Also:

Object.toString()

equals

public boolean equals(Object obj)

Overrides:

equals in class Object

hashCode

public int hashCode()

Overrides:

hashCode in class Object

clone

public TimeSeriesForecastingJobConfig clone()

Overrides:

clone in class Object

marshall

public void marshall(ProtocolMarshaller protocolMarshaller)

Description copied from interface: StructuredPojo

Marshalls this structured data using the given ProtocolMarshaller.

Specified by:

marshall in interface StructuredPojo

Parameters:

protocolMarshaller - Implementation of ProtocolMarshaller used to marshall this object's data.