holisticai.bias.mitigation.FairScoreClassifier#

class holisticai.bias.mitigation.FairScoreClassifier(*args, **kargs)[source]#

Fair Score Classifier [1] generates a classification model that integrates fairness constraints for multiclass classification. This algorithm returns a matrix of lambda coefficients that scores a given input vector. The higher the score, the higher the probability of the input vector to be classified as the majority class.

Parameters

objectivesdict

The weighted objectives list to be optimized.

constraintsdict

The constraints list to be used in the optimization. The keys are the constraints names and the values are the bounds.

lambda_boundint

Lower and upper bound for the scoring system cofficients.

time_limitint

The time limit for the optimization algorithm.

verboseint

If >0, will show progress percentage.

Examples

>>> from holisticai.bias.mitigation import FairScoreClassifier
>>> mitigator = FairScoreClassifier(**params)
>>> mitigator.fit(train_data, y, group_a, group_b)
>>> test_data_transformed = mitigator.predict(test_data, group_a, group_b)

References

fit(X, y, group_a, group_b)[source]#

Fit model using Grid Search Algorithm.

Parameters

Xmatrix-like

input matrix

ynumpy array

target vector

protected_groupslist

The sensitive groups.

protected_labelslist

The senstive labels.

sensitive_featuresnumpy array

Matrix where each columns is a sensitive feature e.g. [col_1=group_a, col_2=group_b]

Returns

self

predict(X, group_a, group_b)[source]#

Predict the target vector.

Parameters

Xmatrix-like

input matrix

group_anumpy array

binary mask vector

group_bnumpy array

binary mask vector

Returns

numpy array

set_fit_request(*, group_a: bool | None | str = '$UNCHANGED$', group_b: bool | None | str = '$UNCHANGED$') → FairScoreClassifier#

Request metadata passed to the fit method.

Note that this method is only relevant if enable_metadata_routing=True (see sklearn.set_config()). Please see User Guide on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to fit.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Note

This method is only relevant if this estimator is used as a sub-estimator of a meta-estimator, e.g. used inside a Pipeline. Otherwise it has no effect.

Parameters

group_astr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED

Metadata routing for group_a parameter in fit.

group_bstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED

Metadata routing for group_b parameter in fit.

Returns

selfobject

The updated object.

set_predict_request(*, group_a: bool | None | str = '$UNCHANGED$', group_b: bool | None | str = '$UNCHANGED$') → FairScoreClassifier#

Request metadata passed to the predict method.

Note that this method is only relevant if enable_metadata_routing=True (see sklearn.set_config()). Please see User Guide on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to predict.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Note

This method is only relevant if this estimator is used as a sub-estimator of a meta-estimator, e.g. used inside a Pipeline. Otherwise it has no effect.

Parameters

group_astr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED

Metadata routing for group_a parameter in predict.

group_bstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED

Metadata routing for group_b parameter in predict.

Returns

selfobject

The updated object.

transform_estimator(estimator)[source]#

Transform the estimator.

Parameters

estimatorobject

The estimator object.

Returns

self