TargetAutoTSConfig

class datarobotx.TargetAutoTSConfig(forecast_window_start=None, forecast_window_end=None, multiseries_id_columns=None, windows_basis_unit=None)

Time series target(s) configuration.

Parameters that default to ‘None’ (or are omitted by the user) are overridden to server-side defaults at runtime. Consult the DataRobot REST API and GUI documentation for additional information on each parameter.

Parameters:

• forecast_window_start (int) – For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should start.

• forecast_window_end (int) – For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should end.

• multiseries_id_columns (list of str) – May be used only with time series projects. An array of the column names identifying the series to which each row of the dataset belongs. Currently only one multiseries ID column is supported. See the multiseries section of the time series documentation for more context.

• windows_basis_unit ({'MILLISECOND', 'SECOND', 'MINUTE', 'HOUR', 'DAY', 'WEEK', 'MONTH', 'QUARTER', 'YEAR', 'ROW'}) – For time series projects only. Indicates which unit is basis for feature derivation window and forecast window. Valid options are detected time unit or ROW. If omitted, the default value is detected time unit.

See also

DRConfig

Configuration object for DataRobot project and autopilot settings, also includes detailed examples of usage

Attributes:

forecast_window_end	For time series projects only.
forecast_window_start	For time series projects only.
multiseries_id_columns	May be used only with time series projects.
windows_basis_unit	For time series projects only.

Inherited methods:

keys()	rtype: Collection[str]
to_dict()	Return configuration as a dict.

property forecast_window_end: int

For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should end.

Notes

forecast_window_end : int

property forecast_window_start: int

For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should start.

Notes

forecast_window_start : int

property multiseries_id_columns: List[str]

May be used only with time series projects. An array of the column names identifying the series to which each row of the dataset belongs. Currently only one multiseries ID column is supported. See the multiseries section of the time series documentation for more context.

Notes

multiseries_id_columns : list of str

to_dict()

Return configuration as a dict.

Return type:

Dict[str, Any]

property windows_basis_unit: str

For time series projects only. Indicates which unit is basis for feature derivation window and forecast window. Valid options are detected time unit or ROW. If omitted, the default value is detected time unit.

Notes

windows_basis_unit{‘MILLISECOND’, ‘SECOND’, ‘MINUTE’, ‘HOUR’, ‘DAY’, ‘WEEK’, ‘MONTH’, ‘QUARTER’, ‘YEAR’,

‘ROW’}