ModelingAutoTSConfig

class datarobotx.ModelingAutoTSConfig(model_splits=None, allow_partial_history_time_series_predictions=None, external_time_series_baseline_dataset_id=None, external_time_series_baseline_dataset_name=None)

Time series modeling options.

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:

• model_splits (int) – Sets the cap on the number of jobs per model used when building models to control number of jobs in the queue. Higher number of modelSplits will allow for less downsampling leading to the use of more post-processed data.

• allow_partial_history_time_series_predictions (bool) – Specifies whether the time series predictions can use partial historical data.

• external_time_series_baseline_dataset_id (str) – Catalog version id for external prediction data that can be used as a baseline to calculate new metrics.

• external_time_series_baseline_dataset_name (str) – The name of the time series baseline dataset for the project.

See also

DRConfig

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

Attributes:

allow_partial_history_time_series_predictions	Specifies whether the time series predictions can use partial historical data.
external_time_series_baseline_dataset_id	Catalog version id for external prediction data that can be used as a baseline to calculate new metrics.
external_time_series_baseline_dataset_name	The name of the time series baseline dataset for the project.
model_splits	Sets the cap on the number of jobs per model used when building models to control number of jobs in the queue.

Inherited methods:

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

property allow_partial_history_time_series_predictions: bool

Specifies whether the time series predictions can use partial historical data.

Notes

allow_partial_history_time_series_predictions : bool

property external_time_series_baseline_dataset_id: str

Catalog version id for external prediction data that can be used as a baseline to calculate new metrics.

Notes

external_time_series_baseline_dataset_id : str

property external_time_series_baseline_dataset_name: str

The name of the time series baseline dataset for the project.

Notes

external_time_series_baseline_dataset_name : str

property model_splits: int

Sets the cap on the number of jobs per model used when building models to control number of jobs in the queue. Higher number of modelSplits will allow for less downsampling leading to the use of more post- processed data.

Notes

model_splits : int

to_dict()

Return configuration as a dict.

Return type:

Dict[str, Any]