WholeDatasetDrift#

class WholeDatasetDrift[source]#

Calculate drift between the entire train and test datasets using a model trained to distinguish between them.

Deprecated since version 0.9: The WholeDatasetDrift check is deprecated and will be removed in the 0.11 version. Please use the MultivariateDrift check instead.

__init__(n_top_columns: int = 3, min_feature_importance: float = 0.05, max_num_categories_for_display: int = 10, show_categories_by: str = 'largest_difference', n_samples: int = 10000, random_state: int = 42, test_size: float = 0.3, min_meaningful_drift_score: float = 0.05, **kwargs)[source]#
__new__(*args, **kwargs)#

Methods

WholeDatasetDrift.add_condition(name, ...)

Add new condition function to the check.

WholeDatasetDrift.add_condition_overall_drift_value_less_than([...])

Add condition.

WholeDatasetDrift.clean_conditions()

Remove all conditions from this check instance.

WholeDatasetDrift.conditions_decision(result)

Run conditions on given result.

WholeDatasetDrift.config([include_version, ...])

Return check configuration (conditions' configuration not yet supported).

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

Return check object from a CheckConfig object.

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

Deserialize check instance from JSON string.

WholeDatasetDrift.metadata([with_doc_link])

Return check metadata.

WholeDatasetDrift.name()

Name of class in split camel case.

WholeDatasetDrift.params([show_defaults])

Return parameters to show when printing the check.

WholeDatasetDrift.remove_condition(index)

Remove given condition by index.

WholeDatasetDrift.run(train_dataset, ...[, ...])

Run check.

WholeDatasetDrift.run_logic(context)

Run check.

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

Serialize check instance to JSON string.