Class ForecastingSettings
- java.lang.Object
-
- com.azure.resourcemanager.machinelearning.models.ForecastingSettings
-
public final class ForecastingSettings extends Object
Forecasting specific parameters.
-
-
Constructor Summary
Constructors Constructor Description ForecastingSettings()
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description String
countryOrRegionForHolidays()
Get the countryOrRegionForHolidays property: Country or region for holidays for forecasting tasks.Integer
cvStepSize()
Get the cvStepSize property: Number of periods between the origin time of one CV fold and the next fold.FeatureLags
featureLags()
Get the featureLags property: Flag for generating lags for the numeric features with 'auto' or null.ForecastHorizon
forecastHorizon()
Get the forecastHorizon property: The desired maximum forecast horizon in units of time-series frequency.String
frequency()
Get the frequency property: When forecasting, this parameter represents the period with which the forecast is desired, for example daily, weekly, yearly, etc.Seasonality
seasonality()
Get the seasonality property: Set time series seasonality as an integer multiple of the series frequency.ShortSeriesHandlingConfiguration
shortSeriesHandlingConfig()
Get the shortSeriesHandlingConfig property: The parameter defining how if AutoML should handle short time series.TargetAggregationFunction
targetAggregateFunction()
Get the targetAggregateFunction property: The function to be used to aggregate the time series target column to conform to a user specified frequency.TargetLags
targetLags()
Get the targetLags property: The number of past periods to lag from the target column.TargetRollingWindowSize
targetRollingWindowSize()
Get the targetRollingWindowSize property: The number of past periods used to create a rolling window average of the target column.String
timeColumnName()
Get the timeColumnName property: The name of the time column.List<String>
timeSeriesIdColumnNames()
Get the timeSeriesIdColumnNames property: The names of columns used to group a timeseries.UseStl
useStl()
Get the useStl property: Configure STL Decomposition of the time-series target column.void
validate()
Validates the instance.ForecastingSettings
withCountryOrRegionForHolidays(String countryOrRegionForHolidays)
Set the countryOrRegionForHolidays property: Country or region for holidays for forecasting tasks.ForecastingSettings
withCvStepSize(Integer cvStepSize)
Set the cvStepSize property: Number of periods between the origin time of one CV fold and the next fold.ForecastingSettings
withFeatureLags(FeatureLags featureLags)
Set the featureLags property: Flag for generating lags for the numeric features with 'auto' or null.ForecastingSettings
withForecastHorizon(ForecastHorizon forecastHorizon)
Set the forecastHorizon property: The desired maximum forecast horizon in units of time-series frequency.ForecastingSettings
withFrequency(String frequency)
Set the frequency property: When forecasting, this parameter represents the period with which the forecast is desired, for example daily, weekly, yearly, etc.ForecastingSettings
withSeasonality(Seasonality seasonality)
Set the seasonality property: Set time series seasonality as an integer multiple of the series frequency.ForecastingSettings
withShortSeriesHandlingConfig(ShortSeriesHandlingConfiguration shortSeriesHandlingConfig)
Set the shortSeriesHandlingConfig property: The parameter defining how if AutoML should handle short time series.ForecastingSettings
withTargetAggregateFunction(TargetAggregationFunction targetAggregateFunction)
Set the targetAggregateFunction property: The function to be used to aggregate the time series target column to conform to a user specified frequency.ForecastingSettings
withTargetLags(TargetLags targetLags)
Set the targetLags property: The number of past periods to lag from the target column.ForecastingSettings
withTargetRollingWindowSize(TargetRollingWindowSize targetRollingWindowSize)
Set the targetRollingWindowSize property: The number of past periods used to create a rolling window average of the target column.ForecastingSettings
withTimeColumnName(String timeColumnName)
Set the timeColumnName property: The name of the time column.ForecastingSettings
withTimeSeriesIdColumnNames(List<String> timeSeriesIdColumnNames)
Set the timeSeriesIdColumnNames property: The names of columns used to group a timeseries.ForecastingSettings
withUseStl(UseStl useStl)
Set the useStl property: Configure STL Decomposition of the time-series target column.
-
-
-
Method Detail
-
countryOrRegionForHolidays
public String countryOrRegionForHolidays()
Get the countryOrRegionForHolidays property: Country or region for holidays for forecasting tasks. These should be ISO 3166 two-letter country/region codes, for example 'US' or 'GB'.- Returns:
- the countryOrRegionForHolidays value.
-
withCountryOrRegionForHolidays
public ForecastingSettings withCountryOrRegionForHolidays(String countryOrRegionForHolidays)
Set the countryOrRegionForHolidays property: Country or region for holidays for forecasting tasks. These should be ISO 3166 two-letter country/region codes, for example 'US' or 'GB'.- Parameters:
countryOrRegionForHolidays
- the countryOrRegionForHolidays value to set.- Returns:
- the ForecastingSettings object itself.
-
cvStepSize
public Integer cvStepSize()
Get the cvStepSize property: Number of periods between the origin time of one CV fold and the next fold. For example, if `CVStepSize` = 3 for daily data, the origin time for each fold will be three days apart.- Returns:
- the cvStepSize value.
-
withCvStepSize
public ForecastingSettings withCvStepSize(Integer cvStepSize)
Set the cvStepSize property: Number of periods between the origin time of one CV fold and the next fold. For example, if `CVStepSize` = 3 for daily data, the origin time for each fold will be three days apart.- Parameters:
cvStepSize
- the cvStepSize value to set.- Returns:
- the ForecastingSettings object itself.
-
featureLags
public FeatureLags featureLags()
Get the featureLags property: Flag for generating lags for the numeric features with 'auto' or null.- Returns:
- the featureLags value.
-
withFeatureLags
public ForecastingSettings withFeatureLags(FeatureLags featureLags)
Set the featureLags property: Flag for generating lags for the numeric features with 'auto' or null.- Parameters:
featureLags
- the featureLags value to set.- Returns:
- the ForecastingSettings object itself.
-
forecastHorizon
public ForecastHorizon forecastHorizon()
Get the forecastHorizon property: The desired maximum forecast horizon in units of time-series frequency.- Returns:
- the forecastHorizon value.
-
withForecastHorizon
public ForecastingSettings withForecastHorizon(ForecastHorizon forecastHorizon)
Set the forecastHorizon property: The desired maximum forecast horizon in units of time-series frequency.- Parameters:
forecastHorizon
- the forecastHorizon value to set.- Returns:
- the ForecastingSettings object itself.
-
frequency
public String frequency()
Get the frequency property: When forecasting, this parameter represents the period with which the forecast is desired, for example daily, weekly, yearly, etc. The forecast frequency is dataset frequency by default.- Returns:
- the frequency value.
-
withFrequency
public ForecastingSettings withFrequency(String frequency)
Set the frequency property: When forecasting, this parameter represents the period with which the forecast is desired, for example daily, weekly, yearly, etc. The forecast frequency is dataset frequency by default.- Parameters:
frequency
- the frequency value to set.- Returns:
- the ForecastingSettings object itself.
-
seasonality
public Seasonality seasonality()
Get the seasonality property: Set time series seasonality as an integer multiple of the series frequency. If seasonality is set to 'auto', it will be inferred.- Returns:
- the seasonality value.
-
withSeasonality
public ForecastingSettings withSeasonality(Seasonality seasonality)
Set the seasonality property: Set time series seasonality as an integer multiple of the series frequency. If seasonality is set to 'auto', it will be inferred.- Parameters:
seasonality
- the seasonality value to set.- Returns:
- the ForecastingSettings object itself.
-
shortSeriesHandlingConfig
public ShortSeriesHandlingConfiguration shortSeriesHandlingConfig()
Get the shortSeriesHandlingConfig property: The parameter defining how if AutoML should handle short time series.- Returns:
- the shortSeriesHandlingConfig value.
-
withShortSeriesHandlingConfig
public ForecastingSettings withShortSeriesHandlingConfig(ShortSeriesHandlingConfiguration shortSeriesHandlingConfig)
Set the shortSeriesHandlingConfig property: The parameter defining how if AutoML should handle short time series.- Parameters:
shortSeriesHandlingConfig
- the shortSeriesHandlingConfig value to set.- Returns:
- the ForecastingSettings object itself.
-
targetAggregateFunction
public TargetAggregationFunction targetAggregateFunction()
Get the targetAggregateFunction property: The function to be used to aggregate the time series target column to conform to a user specified frequency. If the TargetAggregateFunction is set i.e. not 'None', but the freq parameter is not set, the error is raised. The possible target aggregation functions are: "sum", "max", "min" and "mean".- Returns:
- the targetAggregateFunction value.
-
withTargetAggregateFunction
public ForecastingSettings withTargetAggregateFunction(TargetAggregationFunction targetAggregateFunction)
Set the targetAggregateFunction property: The function to be used to aggregate the time series target column to conform to a user specified frequency. If the TargetAggregateFunction is set i.e. not 'None', but the freq parameter is not set, the error is raised. The possible target aggregation functions are: "sum", "max", "min" and "mean".- Parameters:
targetAggregateFunction
- the targetAggregateFunction value to set.- Returns:
- the ForecastingSettings object itself.
-
targetLags
public TargetLags targetLags()
Get the targetLags property: The number of past periods to lag from the target column.- Returns:
- the targetLags value.
-
withTargetLags
public ForecastingSettings withTargetLags(TargetLags targetLags)
Set the targetLags property: The number of past periods to lag from the target column.- Parameters:
targetLags
- the targetLags value to set.- Returns:
- the ForecastingSettings object itself.
-
targetRollingWindowSize
public TargetRollingWindowSize targetRollingWindowSize()
Get the targetRollingWindowSize property: The number of past periods used to create a rolling window average of the target column.- Returns:
- the targetRollingWindowSize value.
-
withTargetRollingWindowSize
public ForecastingSettings withTargetRollingWindowSize(TargetRollingWindowSize targetRollingWindowSize)
Set the targetRollingWindowSize property: The number of past periods used to create a rolling window average of the target column.- Parameters:
targetRollingWindowSize
- the targetRollingWindowSize value to set.- Returns:
- the ForecastingSettings object itself.
-
timeColumnName
public String timeColumnName()
Get the timeColumnName property: The name of the time column. This parameter is required when forecasting to specify the datetime column in the input data used for building the time series and inferring its frequency.- Returns:
- the timeColumnName value.
-
withTimeColumnName
public ForecastingSettings withTimeColumnName(String timeColumnName)
Set the timeColumnName property: The name of the time column. This parameter is required when forecasting to specify the datetime column in the input data used for building the time series and inferring its frequency.- Parameters:
timeColumnName
- the timeColumnName value to set.- Returns:
- the ForecastingSettings object itself.
-
timeSeriesIdColumnNames
public List<String> timeSeriesIdColumnNames()
Get the timeSeriesIdColumnNames property: The names of columns used to group a timeseries. It can be used to create multiple series. If grain is not defined, the data set is assumed to be one time-series. This parameter is used with task type forecasting.- Returns:
- the timeSeriesIdColumnNames value.
-
withTimeSeriesIdColumnNames
public ForecastingSettings withTimeSeriesIdColumnNames(List<String> timeSeriesIdColumnNames)
Set the timeSeriesIdColumnNames property: The names of columns used to group a timeseries. It can be used to create multiple series. If grain is not defined, the data set is assumed to be one time-series. This parameter is used with task type forecasting.- Parameters:
timeSeriesIdColumnNames
- the timeSeriesIdColumnNames value to set.- Returns:
- the ForecastingSettings object itself.
-
useStl
public UseStl useStl()
Get the useStl property: Configure STL Decomposition of the time-series target column.- Returns:
- the useStl value.
-
withUseStl
public ForecastingSettings withUseStl(UseStl useStl)
Set the useStl property: Configure STL Decomposition of the time-series target column.- Parameters:
useStl
- the useStl value to set.- Returns:
- the ForecastingSettings object itself.
-
validate
public void validate()
Validates the instance.- Throws:
IllegalArgumentException
- thrown if the instance is not valid.
-
-