DataConfig#

class datarobotx.DataConfig(smart_downsampled=None, majority_downsampling_rate=None, external_predictions=None, featurelist_id=None)#

Row and column selection 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:

  • smart_downsampled (bool) – Whether to use smart downsampling to throw away excess rows of the majority class. Only applicable to classification and zero-boosted regression projects.

  • majority_downsampling_rate (float) – The percentage between 0 and 100 of the majority rows that should be kept. Must be specified only if using smart downsampling. If not specified, a default will be selected based on the dataset distribution. The chosen rate may not cause the majority class to become smaller than the minority class.

  • external_predictions (list of str) – List of external prediction columns from the dataset.

  • featurelist_id (str) – The ID of a featurelist to use for autopilot.

See also

DRConfig

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

Attributes:

external_predictions

List of external prediction columns from the dataset.

featurelist_id

The ID of a featurelist to use for autopilot.

majority_downsampling_rate

The percentage between 0 and 100 of the majority rows that should be kept.

smart_downsampled

Whether to use smart downsampling to throw away excess rows of the majority class.

Inherited methods:

keys()

rtype:

Collection[str]

to_dict()

Return configuration as a dict.
property external_predictions: List[str]#

List of external prediction columns from the dataset.

Notes

external_predictions : list of str

property featurelist_id: str#

The ID of a featurelist to use for autopilot.

Notes

featurelist_id : str

property majority_downsampling_rate: float#

The percentage between 0 and 100 of the majority rows that should be kept. Must be specified only if using smart downsampling. If not specified, a default will be selected based on the dataset distribution. The chosen rate may not cause the majority class to become smaller than the minority class.

Notes

majority_downsampling_rate : float

property smart_downsampled: bool#

Whether to use smart downsampling to throw away excess rows of the majority class. Only applicable to classification and zero-boosted regression projects.

Notes

smart_downsampled : bool

to_dict()#

Return configuration as a dict.

Return type:

Dict[str, Any]