TrainTestSamplesMix

class TrainTestSamplesMix

Detect samples in the test data that appear also in training data.

Parameters

n_samplesint , default: 10_000_000

number of samples to use for this check.

n_to_showint , default: 10

number of samples that appear in test and training data to show.

random_stateint, default: 42

random seed for all check internals.

__init__(n_samples: int = 10000000, n_to_show: int = 10, random_state: int = 42, **kwargs)

__new__(*args, **kwargs)

Methods

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

Examples

Train Test Samples Mix

previous

LabelDrift.to_json

next

TrainTestSamplesMix.add_condition