FeaturesSAFERConfig

class datarobotx.FeaturesSAFERConfig(relationships_configuration_id=None, feature_engineering_prediction_point=None, autopilot_with_feature_discovery=None, date_removal=None, feature_discovery_supervised_feature_reduction=None)

SAFER 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:

• relationships_configuration_id (str) – Relationships configuration id to be used for Feature Discovery projects.

• feature_engineering_prediction_point (str) – The date column to be used as prediction point for time-based feature engineering.

• autopilot_with_feature_discovery (bool) – If true, autopilot will run on a feature list that includes features found via search for interactions.

• date_removal (bool) – If true, enable creating additional feature lists without dates (does not apply to time-aware projects).

• feature_discovery_supervised_feature_reduction (bool) – Run supervised feature reduction for feature discovery projects.

See also

DRConfig

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

Attributes:

autopilot_with_feature_discovery	If true, autopilot will run on a feature list that includes features found via search for interactions.
date_removal	If true, enable creating additional feature lists without dates (does not apply to time-aware projects).
feature_discovery_supervised_feature_reduction	Run supervised feature reduction for feature discovery projects.
feature_engineering_prediction_point	The date column to be used as prediction point for time-based feature engineering.
relationships_configuration_id	Relationships configuration id to be used for Feature Discovery projects.

Inherited methods:

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

property autopilot_with_feature_discovery: bool

If true, autopilot will run on a feature list that includes features found via search for interactions.

Notes

autopilot_with_feature_discovery : bool

property date_removal: bool

If true, enable creating additional feature lists without dates (does not apply to time-aware projects).

Notes

date_removal : bool

property feature_discovery_supervised_feature_reduction: bool

Run supervised feature reduction for feature discovery projects.

Notes

feature_discovery_supervised_feature_reduction : bool

property feature_engineering_prediction_point: str

The date column to be used as prediction point for time-based feature engineering.

Notes

feature_engineering_prediction_point : str

property relationships_configuration_id: str

Relationships configuration id to be used for Feature Discovery projects.

Notes

relationships_configuration_id : str

to_dict()

Return configuration as a dict.

Return type:

Dict[str, Any]