holisticai
This is an open-source tool to assess and improve the trustworthiness of AI systems.
File Explorer
Download Latest Version (.zip)- feature-workflow.yml
- publish-pypi-workflow.yml
- publish-slack-workflow.yml
- release-workflow.yml
- dependabot.yml
- custom_style.css
- coffe.svg
- contributor.svg
- datasets.svg
- explainability.svg
- fairness.svg
- gallery.svg
- getting_started.svg
- learn.svg
- reference.svg
- robustness.svg
- security.svg
- start.svg
- class.rst
- function.rst
- layout.html
- index.rst
- index.rst
- measuring_bias_classification.ipynb
- measuring_bias_clustering.ipynb
- measuring_bias_multiclass.ipynb
- measuring_bias_recommender.ipynb
- measuring_bias_regression.ipynb
- inprocessing.ipynb
- postprocessing.ipynb
- preprocessing.ipynb
- example_census_data.ipynb
- inprocessing.ipynb
- postprocessing.ipynb
- preprocessing.ipynb
- example_clustering.ipynb
- inprocessing.ipynb
- postprocessing.ipynb
- preprocessing.ipynb
- example_multiclassification.ipynb
- inprocessing.ipynb
- postprocessing.ipynb
- example_lastfm.ipynb
- inprocessing.ipynb
- postprocessing.ipynb
- preprocessing.ipynb
- example_us_crime.ipynb
- load_datasets.ipynb
- entropy_measures.ipynb
- global_permutation.ipynb
- global_surrogate.ipynb
- local_lime.ipynb
- local_shap.ipynb
- example_clinical_records.ipynb
- measuring_robustness_classification.ipynb
- measuring_robustness_regression.ipynb
- analyzing_privacy_risk_classification.ipynb
- measuring_privacy_risk_classification.ipynb
- measuring_security_classification.ipynb
- measuring_security_multi_classification.ipynb
- measuring_security_regression.ipynb
- anonymization_algorithm.ipynb
- bias.rst
- datasets.rst
- explainability.rst
- robustness.rst
- security.rst
- index.rst
- index.rst
- update_tutorials.sh
- binary_classification.rst
- clustering.rst
- multi_classification.rst
- recommender.rst
- regression.rst
- bc_adversarial_debiasing_adversarial_debiasing.rst
- bc_exp_grad_grid_search_exponentiated_gradient_reduction.rst
- bc_exp_grad_grid_search_grid_search.rst
- bc_meta_fair_classifier_rho_fair.rst
- bc_prejudice_remover_prejudice_remover_regularizer.rst
- c_fair_k_center_fair_k_center.rst
- c_fair_k_median_fair_k_median.rst
- c_fairlet_clustering_fairlet_decomposition.rst
- c_variational_fair_clustering_variational_fair_clustering.rst
- mc_fair_scoring_classifier_fairscoringsystems.rst
- rs_blind_spot_aware_blind_spot_aware_matrix_factorization.rst
- rs_popularity_propensity_matrix_factorization.rst
- rs_popularity_propensity_propensity_scored_recommendations.rst
- rs_two_sided_fairness_fairrec_two_sided_fairness.rst
- bc_calibrated_eq_odds_postprocessing_calibrated_equalized_odds.rst
- bc_eq_odds_post_processing_equality_of_opportunity.rst
- bc_lp_debiaser_linear_program.rst
- bc_ml_debiaser_rto.rst
- bc_reject_option_classification_reject_option_based_classification.rst
- c_mcmf_clustering_mcmf_problem.rst
- mc_lp_debiaser_linear_program.rst
- r_plugin_estimator_and_calibrator_plug_in_estimator_and_recalibration.rst
- r_wasserstein_barycenters_wasserstein_barycenter.rst
- rs_debiasing_exposure_deltr.rst
- rs_disparate_impact_remover_disparate_impact_remover.rst
- rs_fair_topk_fair_algorithm.rst
- bc_correlation_remover_correlationremover.rst
- bc_disparate_impact_remover_disparate_impact_remover.rst
- bc_learning_fair_representations_lfr.rst
- bc_reweighing_reweighing.rst
- c_fairlet_clustering_preprocessing_fairlet_decomposition.rst
- inprocessing.rst
- postprocessing.rst
- preprocessing.rst
- bias_metrics.csv
- bias_mitigation.csv
- index.rst
- metrics.rst
- mitigation.rst
- permutation.rst
- similarity.rst
- spread.rst
- stability.rst
- tree.rst
- index.rst
- metrics.rst
- hopskipjump.rst
- linreggdpoisoner.rst
- zoo.rst
- index.rst
- index.rst
- attribute_attack.rst
- data_minimization.rst
- shapr.rst
- anonymize.rst
- index.rst
- metrics.rst
- mitigation.rst
- bias_metrics.csv
- datasets.csv
- datasets.rst
- index.rst
- install.rst
- quickstart.ipynb
- raw_datasets.csv
- technical_risks.rst
- metrics.rst
- mitigation.rst
- plots.rst
- metrics.rst
- plots.rst
- attackers.rst
- metrics.rst
- plots.rst
- metrics.rst
- mitigation.rst
- datasets.rst
- index.rst
- pipeline.rst
- xai_image_plots.py
- conf.py
- hai_logo.svg
- holistic_ai.png
- index.rst
- make.bat
- Makefile
- README
- requirements.txt
- run_tutorials.py
- __init__.py
- _classification.py
- _clustering.py
- _multiclass.py
- _recommender.py
- _regression.py
- __init__.py
- _categorical_feature.py
- _categorical_repairer.py
- _numerical_repairer.py
- _sparse_list.py
- _utils.py
- __init__.py
- _kcenters.py
- _kmedoids.py
- __init__.py
- _base.py
- _scalable.py
- _vanilla.py
- __init__.py
- _base.py
- _scalable.py
- _vanilla.py
- __init__.py
- _utils.py
- __init__.py
- models.py
- transformer.py
- __init__.py
- _constraints.py
- _objectives.py
- __init__.py
- _constraints.py
- _losses.py
- __init__.py
- _conventions.py
- _logger.py
- _moments_utils.py
- __init__.py
- _lagrangian.py
- algorithm.py
- transformer.py
- __init__.py
- algorithms.py
- transformer.py
- __init__.py
- algorithm.py
- transformer.py
- __init__.py
- algorithm.py
- transformer.py
- utils.py
- __init__.py
- algorithm.py
- transformer.py
- __init__.py
- _grid_generator.py
- algorithm.py
- transformer.py
- __init__.py
- propensity_utils.py
- utils.py
- __init__.py
- algorithm.py
- algorithm_utils.py
- transformer.py
- __init__.py
- blind_spot_aware.py
- popularity_propensity.py
- __init__.py
- algorithm.py
- algorithm_utils.py
- constraints.py
- transformer.py
- __init__.py
- algorithm.py
- algorithm_utils.py
- losses.py
- model.py
- transformer.py
- __init__.py
- algorithm.py
- transformer.py
- __init__.py
- _bound_update.py
- _fair_clustering.py
- _logger.py
- _method_utils.py
- _methods.py
- _utils.py
- __init__.py
- algorithm.py
- transformer.py
- __init__.py
- __init__.py
- algorithm.py
- algorithm_utils.py
- transformer.py
- __init__.py
- fail_prob.py
- mtable_generator.py
- valitation_utils.py
- __init__.py
- transformer.py
- __init__.py
- algorithm.py
- algorithm_utils.py
- constraints.py
- transformer.py
- __init__.py
- algorithm.py
- algorithm_utils.py
- constraints.py
- transformer.py
- __init__.py
- algorithm.py
- algorithm_utils.py
- __init__.py
- algorithm.py
- transformer.py
- __init__.py
- algorithm.py
- algorithm_utils.py
- __init__.py
- algorithm.py
- algorithm_utils.py
- __init__.py
- transformer.py
- __init__.py
- algorithm.py
- algorithm_utils.py
- transformer.py
- __init__.py
- algorithm.py
- transformer.py
- __init__.py
- calibrated_eq_odds_postprocessing.py
- disparate_impact_remover_rs.py
- eq_odds_postprocessing.py
- reject_option_classification.py
- __init__.py
- transformer.py
- __init__.py
- correlation_remover.py
- disparate_impact_remover.py
- learning_fair_representation.py
- reweighing.py
- __init__.py
- __init__.py
- _bias_classification_plots.py
- _bias_exploratory_plots.py
- _bias_exploratory_view.py
- _bias_multiclass_plots.py
- _bias_recommender_plots.py
- _bias_regression_plots.py
- _bias_report_plots.py
- _classification.py
- _multiclass.py
- _recommender.py
- _regression.py
- _report.py
- __init__.py
- __init__.py
- _exploratory.py
- __init__.py
- recruitment.py
- user_feedback.py
- __init__.py
- _dataloaders.py
- _dataset.py
- _load_dataset.py
- _load_dataset.pyi
- _utils.py
- __init__.py
- _classification.py
- _clustering.py
- _multiclass.py
- _regression.py
- __init__.py
- _alpha_score.py
- _fluctuation_ratio.py
- _importance_spread.py
- _position_parity.py
- _rank_alignment.py
- _surrogate.py
- _xai_ease_score.py
- __init__.py
- _importance_stability.py
- _rank_consistency.py
- _stability.py
- __init__.py
- _classification.py
- _clustering.py
- _regression.py
- _stability.py
- __init__.py
- _tree.py
- __init__.py
- _classification.py
- _multiclass.py
- _regression.py
- _tree.py
- __init__.py
- _feature_importance.py
- _miscellaneous.py
- _partial_dependence.py
- _partial_dependencies.py
- _tree.py
- __init__.py
- __init__.py
- _lime.py
- _partial_dependence.py
- _permutation_importance.py
- _shap.py
- _surrogate_importance.py
- _utils.py
- __init__.py
- _estimator.py
- _pipeline_params.py
- _utransformers.py
- __init__.py
- _pipeline.py
- _pipeline_helper.py
- __init__.py
- commons.py
- hop_skip_jump.py
- zeroth_order_optimization.py
- __init__.py
- gb_attackers.py
- gb_base.py
- initializers.py
- utils.py
- __init__.py
- __init__.py
- _binary_classification.py
- __init__.py
- _accuracy_degradation_profile.py
- __init__.py
- __init__.py
- _dataset_shift.py
- _utils.py
- __init__.py
- __init__.py
- _core.py
- _modificators.py
- _selectors.py
- __init__.py
- _black_box_attack.py
- __init__.py
- _anonymization.py
- _attribute_attack.py
- _data_minimization.py
- _privacy_risk_score.py
- _shapr.py
- _utils.py
- __init__.py
- _anonymization.py
- __init__.py
- __init__.py
- _typing.py
- __init__.py
- _tabular.py
- __init__.py
- _kcenters.py
- _kmedoids.py
- _utils.py
- __init__.py
- _classification.py
- __init__.py
- selectors.py
- __init__.py
- non_negative.py
- __init__.py
- _rsbase.py
- __init__.py
- object_repr.css
- object_repr.py
- __init__.py
- _genetic_algorithm.py
- __init__.py
- _plots.py
- _utils.py
- __init__.py
- _base.py
- _trees.py
- __init__.py
- fairea.py
- utils_fairea.py
- __init__.py
- _group_utils.py
- _inprocessing.py
- _postprocessing.py
- _preprocessing.py
- __init__.py
- _transformer_base.py
- __init__.py
- _commons.py
- _definitions.py
- _formatting.py
- _plotting.py
- _recommender_tools.py
- _validation.py
- __about__.py
- __init__.py
- test_bias_multiclass_auxiliar_test_g1.py
- test_bias_multiclass_auxiliar_test_g2.py
- test_bias_multiclass_auxiliar_test_g3.py
- utils.py
- test_bias_classification.py
- test_bias_clustering.py
- test_bias_multiclass.py
- test_bias_recommender.py
- test_bias_regression.py
- test_inprocessing.py
- test_postprocessor.py
- test_preprocessor.py
- utils.py
- __init__.py
- utils.py
- test_feature_importance.py
- test_feature_importance_strategies.py
- test_local_feature_importance.py
- test_partial_dependence.py
- test_xai_ease_score.py
- test_load_datasets.py
- test_global_importance.py
- test_local_importance.py
- test_surrogate_metrics.py
- test_xai_classification.py
- test_xai_multiclassification.py
- test_xai_regression.py
- test_xai_tree.py
- test_classification_attackers.py
- test_regression_attackers.py
- test_dataset_shift_metrics.py
- test_plots.py
- test_classification_metrics.py
- test_attribute_attack.py
- test_data_minimization.py
- test_feature_selectors.py
- test_privacy_risk_score.py
- test_shapr.py
- utils.py
- __init__.py
- measuring_bias_classification.ipynb
- measuring_bias_clustering.ipynb
- measuring_bias_multiclass.ipynb
- measuring_bias_recommender.ipynb
- measuring_bias_regression.ipynb
- inprocessing.ipynb
- postprocessing.ipynb
- preprocessing.ipynb
- example_census_data.ipynb
- inprocessing.ipynb
- postprocessing.ipynb
- preprocessing.ipynb
- example_clustering.ipynb
- inprocessing.ipynb
- postprocessing.ipynb
- preprocessing.ipynb
- example_multiclassification.ipynb
- inprocessing.ipynb
- postprocessing.ipynb
- example_lastfm.ipynb
- inprocessing.ipynb
- postprocessing.ipynb
- preprocessing.ipynb
- example_us_crime.ipynb
- load_datasets.ipynb
- measuring_efficacy_classification.ipynb
- measuring_efficacy_clustering.ipynb
- measuring_efficacy_multiclass.ipynb
- measuring_efficacy_regression.ipynb
- tree_based_metrics.ipynb
- xai_metrics_global_feature_importance.ipynb
- xai_metrics_local_feature_importance.ipynb
- xai_metrics_surrogate.ipynb
- tree_based_metrics.ipynb
- xai_metrics_global_feature_importance.ipynb
- xai_metrics_local_feature_importance.ipynb
- xai_metrics_surrogate.ipynb
- entropy_measures.ipynb
- global_permutation.ipynb
- global_surrogate.ipynb
- local_lime.ipynb
- local_shap.ipynb
- xai_metrics_global_feature_importance.ipynb
- xai_metrics_local_feature_importance.ipynb
- xai_metrics_surrogate.ipynb
- example_clinical_records.ipynb
- measuring_explainability_us_crime.ipynb
- meauring_explainability_adult.ipynb
- app.py
- hai-mlflow-tutorial.ipynb
- measuring_accuracy_degradation_classification.ipynb
- measuring_robustness_classification.ipynb
- measuring_robustness_regression.ipynb
- analyzing_privacy_risk_classification.ipynb
- measuring_privacy_risk_classification.ipynb
- measuring_security_classification.ipynb
- measuring_security_multi_classification.ipynb
- measuring_security_regression.ipynb
- anonymization_algorithm.ipynb
- fairea_tutorial.ipynb
- datasets.py
- .gitignore
- .readthedocs.yaml
- CHANGELOG.md
- CODEOWNERS
- CONTRIBUTING.md
- LICENSE
- pyproject.toml
- README.md
- ruff_default.toml
// repository documentation
Was this content helpful?
(0 ratings)