FeatureLabelCorrelation#

class FeatureLabelCorrelation[source]#

Return the PPS (Predictive Power Score) of all features in relation to the label.

The PPS represents the ability of a feature to single-handedly predict another feature or label. A high PPS (close to 1) can mean that this feature’s success in predicting the label is actually due to data leakage - meaning that the feature holds information that is based on the label to begin with.

Uses the ppscore package - for more info, see https://github.com/8080labs/ppscore

Parameters
ppscore_paramsdict , default: None

dictionary of additional parameters for the ppscore.predictors function

n_top_featuresint , default: 5

Number of features to show, sorted by the magnitude of difference in PPS

random_stateint , default: None

Random state for the ppscore.predictors function

__init__(ppscore_params=None, n_top_features: int = 5, random_state: Optional[int] = None, **kwargs)[source]#
__new__(*args, **kwargs)#

Methods

FeatureLabelCorrelation.add_condition(name, ...)

Add new condition function to the check.

FeatureLabelCorrelation.add_condition_feature_pps_not_greater_than([...])

Add condition that will check that pps of the specified feature(s) is not greater than X.

FeatureLabelCorrelation.clean_conditions()

Remove all conditions from this check instance.

FeatureLabelCorrelation.conditions_decision(result)

Run conditions on given result.

FeatureLabelCorrelation.finalize_check_result(...)

Finalize the check result by adding the check instance and processing the conditions.

FeatureLabelCorrelation.metadata([with_doc_link])

Return check metadata.

FeatureLabelCorrelation.name()

Name of class in split camel case.

FeatureLabelCorrelation.params([show_defaults])

Return parameters to show when printing the check.

FeatureLabelCorrelation.remove_condition(index)

Remove given condition by index.

FeatureLabelCorrelation.run(dataset[, model])

Run check.

FeatureLabelCorrelation.run_logic(context[, ...])

Run check.

Examples#