IndexTrainTestLeakage

class IndexTrainTestLeakage

Check if test indexes are present in train data.

Parameters

n_to_showint , default: 5

Number of samples with same indices in train and test to show.

n_samplesint , default: 10_000_000

number of samples to use for this check.

random_stateint, default: 42

random seed for all check internals.

__init__(n_to_show: int = 5, n_samples: int = 10000000, random_state: int = 42, **kwargs)

__new__(*args, **kwargs)

Methods

IndexTrainTestLeakage.add_condition(name, ...)	Add new condition function to the check.
IndexTrainTestLeakage.add_condition_ratio_less_or_equal([...])	Add condition - require index leakage ratio to be less or equal to threshold.
IndexTrainTestLeakage.clean_conditions()	Remove all conditions from this check instance.
IndexTrainTestLeakage.conditions_decision(result)	Run conditions on given result.
IndexTrainTestLeakage.config([...])	Return check configuration (conditions' configuration not yet supported).
IndexTrainTestLeakage.from_config(conf[, ...])	Return check object from a CheckConfig object.
IndexTrainTestLeakage.from_json(conf[, ...])	Deserialize check instance from JSON string.
IndexTrainTestLeakage.metadata([with_doc_link])	Return check metadata.
IndexTrainTestLeakage.name()	Name of class in split camel case.
IndexTrainTestLeakage.params([show_defaults])	Return parameters to show when printing the check.
IndexTrainTestLeakage.remove_condition(index)	Remove given condition by index.
IndexTrainTestLeakage.run(train_dataset, ...)	Run check.
IndexTrainTestLeakage.run_logic(context)	Run check.
IndexTrainTestLeakage.to_json([indent, ...])	Serialize check instance to JSON string.

previous

IdentifierLabelCorrelation.to_json

next

IndexTrainTestLeakage.add_condition