TrainTestLabelDrift#

class TrainTestLabelDrift[source]#

The TrainTestLabelDrift check is deprecated and will be removed in the 0.14 version.

Please use the LabelDrift check instead.

__init__(*args, **kwargs)[source]#
__new__(*args, **kwargs)#

Methods

TrainTestLabelDrift.add_condition(name, ...)

Add new condition function to the check.

TrainTestLabelDrift.add_condition_drift_score_less_than([...])

Add condition - require label properties drift score to be less than a certain threshold.

TrainTestLabelDrift.clean_conditions()

Remove all conditions from this check instance.

TrainTestLabelDrift.compute(context)

Calculate drift on label properties samples that were collected during update() calls.

TrainTestLabelDrift.conditions_decision(result)

Run conditions on given result.

TrainTestLabelDrift.config([...])

Return check configuration.

TrainTestLabelDrift.from_config(conf[, ...])

Return check object from a CheckConfig object.

TrainTestLabelDrift.from_json(conf[, ...])

Deserialize check instance from JSON string.

TrainTestLabelDrift.greater_is_better()

Return True if the check reduce_output is better when it is greater.

TrainTestLabelDrift.initialize_run(context)

Initialize run.

TrainTestLabelDrift.metadata([with_doc_link])

Return check metadata.

TrainTestLabelDrift.name()

Name of class in split camel case.

TrainTestLabelDrift.params([show_defaults])

Return parameters to show when printing the check.

TrainTestLabelDrift.property_reduce(...)

Return an aggregated drift score based on aggregation method defined.

TrainTestLabelDrift.reduce_output(check_result)

Return label drift score per label property.

TrainTestLabelDrift.remove_condition(index)

Remove given condition by index.

TrainTestLabelDrift.run(train_dataset, ...)

Run check.

TrainTestLabelDrift.to_json([indent, ...])

Serialize check instance to JSON string.

TrainTestLabelDrift.update(context, batch, ...)

Perform update on batch for train or test properties.