Class ForecastingSettings


  • public final class ForecastingSettings
    extends Object
    Forecasting specific parameters.
    • Constructor Detail

      • ForecastingSettings

        public ForecastingSettings()
    • 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.