{"id":13487558,"url":"https://github.com/fat-forensics/fat-forensics","last_synced_at":"2025-03-27T22:31:41.120Z","repository":{"id":40685966,"uuid":"146776986","full_name":"fat-forensics/fat-forensics","owner":"fat-forensics","description":"Modular Python Toolbox for Fairness, Accountability and Transparency Forensics","archived":false,"fork":false,"pushed_at":"2023-06-09T22:21:27.000Z","size":2042,"stargazers_count":73,"open_issues_count":7,"forks_count":16,"subscribers_count":6,"default_branch":"master","last_synced_at":"2024-10-02T01:55:54.097Z","etag":null,"topics":["accountability","explainability","explainable-ai","fairness","interpretability","interpretable-ai","machine-learning","transparency"],"latest_commit_sha":null,"homepage":"https://fat-forensics.org","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/fat-forensics.png","metadata":{"files":{"readme":"README.rst","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2018-08-30T16:29:23.000Z","updated_at":"2024-09-11T04:50:50.000Z","dependencies_parsed_at":"2024-01-16T09:01:18.123Z","dependency_job_id":"34e7bc77-150a-430f-b270-442d0baab41c","html_url":"https://github.com/fat-forensics/fat-forensics","commit_stats":null,"previous_names":[],"tags_count":5,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fat-forensics%2Ffat-forensics","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fat-forensics%2Ffat-forensics/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fat-forensics%2Ffat-forensics/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fat-forensics%2Ffat-forensics/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fat-forensics","download_url":"https://codeload.github.com/fat-forensics/fat-forensics/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222322034,"owners_count":16966433,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["accountability","explainability","explainable-ai","fairness","interpretability","interpretable-ai","machine-learning","transparency"],"created_at":"2024-07-31T18:01:00.603Z","updated_at":"2024-10-30T22:31:20.889Z","avatar_url":"https://github.com/fat-forensics.png","language":"Python","funding_links":[],"categories":["Fairness Toolboxes"],"sub_categories":[],"readme":".. -*- mode: rst -*-\n\n=============  ================================================================\nSoftware       |Licence|_ |GitHubRelease|_ |PyPi|_ |Python35|_\nDocs           |Homepage|_\nCI             |GitHubTests|_ |GitHubDocs|_ |Codecov|_\nTry it         |Binder|_\nContact        |MailingList|_ |Gitter|_\nCite           |BibTeX|_ |JOSS|_ |ZENODO|_\n=============  ================================================================\n\n.. |Licence| image:: https://img.shields.io/github/license/fat-forensics/fat-forensics.svg\n.. _Licence: https://github.com/fat-forensics/fat-forensics/blob/master/LICENCE\n\n.. |GitHubRelease| image:: https://img.shields.io/github/release/fat-forensics/fat-forensics.svg\n.. _GitHubRelease: https://github.com/fat-forensics/fat-forensics/releases\n\n.. |PyPi| image:: https://img.shields.io/pypi/v/fat-forensics.svg\n.. _PyPi: https://pypi.org/project/fat-forensics/\n\n.. |Python35| image:: https://img.shields.io/badge/python-3.5-blue.svg\n.. _Python35: https://badge.fury.io/py/fat-forensics\n\n.. .. |ReadTheDocs| image:: https://readthedocs.org/projects/fat-forensics/badge/?version=latest\u0026style=flat\n.. .. _ReadTheDocs: https://fat-forensics.readthedocs.io/en/latest/\n\n.. |Homepage| image:: https://img.shields.io/badge/homepage-read-green.svg\n.. _Homepage: https://fat-forensics.org\n.. What about wiki?\n\n.. |GitHubTests| image:: https://github.com/fat-forensics/fat-forensics/actions/workflows/tests.yml/badge.svg\n.. _GitHubTests: https://github.com/fat-forensics/fat-forensics/actions/workflows/tests.yml\n.. |GitHubDocs| image:: https://github.com/fat-forensics/fat-forensics/actions/workflows/docs.yml/badge.svg\n.. _GitHubDocs: https://github.com/fat-forensics/fat-forensics/actions/workflows/docs.yml\n\n.. .. |CircleCI| image:: https://circleci.com/gh/fat-forensics/fat-forensics/tree/master.svg?style=shield\n.. .. _CircleCI: https://circleci.com/gh/fat-forensics/fat-forensics/tree/master\n\n.. |Codecov| image:: https://codecov.io/gh/fat-forensics/fat-forensics/branch/master/graph/badge.svg\n.. _Codecov: https://codecov.io/gh/fat-forensics/fat-forensics\n\n.. https://codeclimate.com/\n\n.. https://requires.io/\n\n.. |Binder| image:: https://mybinder.org/badge_logo.svg\n.. _Binder: https://mybinder.org/v2/gh/fat-forensics/fat-forensics-doc/master?filepath=notebooks\n\n.. |MailingList| image:: https://img.shields.io/badge/mailing%20list-Google%20Groups-green.svg\n.. _MailingList: https://groups.google.com/forum/#!forum/fat-forensics\n\n.. |Gitter| image:: https://img.shields.io/gitter/room/fat-forensics/FAT-Forensics.svg\n.. _Gitter: https://gitter.im/fat-forensics\n\n.. |BibTeX| image:: https://img.shields.io/badge/cite-BibTeX-blue.svg\n.. _BibTeX: https://fat-forensics.org/getting_started/cite.html\n\n.. |JOSS| image:: https://joss.theoj.org/papers/10.21105/joss.01904/status.svg\n.. _JOSS: https://doi.org/10.21105/joss.01904\n\n.. |ZENODO| image:: https://zenodo.org/badge/DOI/10.5281/zenodo.3833199.svg\n.. _ZENODO: https://doi.org/10.5281/zenodo.3833199\n\n============================================================================\nFAT Forensics: Algorithmic Fairness, Accountability and Transparency Toolbox\n============================================================================\n\nFAT Forensics (``fatf``) is a Python toolbox for evaluating fairness,\naccountability and transparency of predictive systems. It is built on top of\nSciPy_ and NumPy_, and is distributed under the 3-Clause BSD license (new BSD).\n\nFAT Forensics implements the state of the art *fairness*, *accountability* and\n*transparency* (FAT) algorithms for the three main components of any data\nmodelling pipeline: *data* (raw data and features), predictive *models* and\nmodel *predictions*. We envisage two main use cases for the package, each\nsupported by distinct features implemented to support it: an interactive\n*research mode* aimed at researchers who may want to use it for an exploratory\nanalysis and a *deployment mode* aimed at practitioners who may want to use it\nfor monitoring FAT aspects of a predictive system.\n\nPlease visit the project's web site `https://fat-forensics.org`_ for more\ndetails.\n\nInstallation\n============\n\nDependencies\n------------\n\nFAT Forensics requires **Python 3.5** or higher and the following dependencies:\n\n+------------+------------+\n| Package    | Version    |\n+============+============+\n| NumPy_     | \u003e=1.10.0   |\n+------------+------------+\n| SciPy_     | \u003e=0.13.3   |\n+------------+------------+\n\nIn addition, some of the modules require *optional* dependencies:\n\n+--------------------------------------------------------------+------------------+------------+\n| ``fatf`` module                                              | Package          | Version    |\n+==============================================================+==================+============+\n| ``fatf.transparency.predictions.surrogate_explainers``       |                  |            |\n+--------------------------------------------------------------+                  |            |\n| ``fatf.transparency.predictions.surrogate_image_explainers`` |                  |            |\n+--------------------------------------------------------------+                  |            |\n| ``fatf.transparency.sklearn``                                | `scikit-learn`_  | \u003e=0.19.2   |\n+--------------------------------------------------------------+                  |            |\n| ``fatf.utils.data.feature_selection.sklearn``                |                  |            |\n+--------------------------------------------------------------+------------------+------------+\n| ``fatf.transparency.predictions.surrogate_image_explainers`` |                  |            |\n+--------------------------------------------------------------+                  |            |\n| ``fatf.utils.data.occlusion``                                | `scikit-image`_  | \u003e=0.17.0   |\n+--------------------------------------------------------------+                  |            |\n| ``fatf.utils.data.segmentation``                             |                  |            |\n+--------------------------------------------------------------+------------------+------------+\n| ``fatf.transparency.predictions.surrogate_image_explainers`` |                  |            |\n+--------------------------------------------------------------+                  |            |\n| ``fatf.utils.data.occlusion``                                | `Pillow`_        | \u003e=8.4.0    |\n+--------------------------------------------------------------+                  |            |\n| ``fatf.utils.data.segmentation``                             |                  |            |\n+--------------------------------------------------------------+------------------+------------+\n| ``fatf.vis``                                                 | matplotlib_      | \u003e=3.0.0    |\n+--------------------------------------------------------------+------------------+------------+\n\nUser Installation\n-----------------\n\nThe easies way to install FAT Forensics is via ``pip``::\n\n   pip install fat-forensics\n\nwhich will only installed the required dependencies. If you want to install the\npackage together with all the auxiliary dependencies please consider using the\n``[all]`` option::\n\n   pip install fat-forensics[all]\n\nThe documentation provides more detailed `installation instructions \u003cinst_\u003e`_.\n\nChangelog\n=========\n\nSee the changelog_ for a development history and project milestones.\n\nDevelopment\n===========\n\nWe welcome new contributors of all experience levels. The\n`Development Guide \u003cdev_guide_\u003e`_ has detailed information about contributing\ncode, documentation, tests and more. Some basic development instructions are\nincluded below.\n\nImportant Links\n---------------\n\n* Project's web site and documentation: `https://fat-forensics.org`_.\n* Official source code repository:\n  `https://github.com/fat-forensics/fat-forensics`_.\n* FAT Forensics releases: `https://pypi.org/project/fat-forensics`_.\n* Issue tracker: `https://github.com/fat-forensics/fat-forensics/issues`_.\n\nSource Code\n-----------\n\nYou can check out the latest FAT Forensics source code via git with the\ncommand::\n\n   git clone https://github.com/fat-forensics/fat-forensics.git\n\nContributing\n------------\n\nTo learn more about contributing to FAT Forensics, please see our\n`Contributing Guide \u003ccontrib_guide_\u003e`_.\n\nTesting\n-------\n\nYou can launch the test suite from the root directory of this repository with::\n\n   make test-with-code-coverage\n\nTo run the tests you will need to have version 3.9.1 of ``pytest`` installed.\nThis package, together with other development dependencies, can be also\ninstalled with::\n\n   pip install -r requirements-dev.txt\n\nor with::\n\n   pip install fat-forensics[dev]\n\nSee the *Testing* section of the `Development Guide \u003cdev_testing_\u003e`_ page for\nmore information.\n\n    Please note that the ``make test-with-code-coverage`` command will test the\n    version of the package in the local ``fatf`` directory and not the one\n    installed since the pytest command is preceded by ``PYTHONPATH=./``. If\n    you want to test the installed version, consider using the command from the\n    ``Makefile`` without the ``PYTHONPATH`` variable.\n\n    To control the randomness during the tests the ``Makefile`` sets the random\n    seed to ``42`` by preceding each test command with ``FATF_SEED=42``, which\n    sets the environment variable responsible for that. More information about\n    the setup of the *Testing Environment* is available on the\n    `development \u003cdev_testing_env_\u003e`_ web page in the documentation.\n\nSubmitting a Pull Request\n-------------------------\n\nBefore opening a Pull Request, please have a look at the\n`Contributing \u003ccontrib_guide_\u003e`_ page to make sure that your code complies with\nour guidelines.\n\nHelp and Support\n================\n\nFor help please have a look at our\n`documentation web page \u003chttps://fat-forensics.org\u003e`_, especially the\n`Getting Started \u003cgetting_started_\u003e`_ page.\n\nCommunication\n-------------\n\nYou can reach out to us at:\n\n* our gitter_ channel for code-related development discussion; and\n* our `mailing list`_ for discussion about the project's future and the\n  direction of the development.\n\nMore information about the communication can be found in our documentation\non the `main page \u003chttps://fat-forensics.org/index.html#communication\u003e`_ and\non the\n`develop page \u003chttps://fat-forensics.org/development.html#communication\u003e`_.\n\nCitation\n--------\n\nIf you use FAT Forensics in a scientific publication, we would appreciate\ncitations! Information on how to cite use is available on the\n`citation \u003chttps://fat-forensics.org/getting_started/cite.html\u003e`_ web page in\nour documentation.\n\nAcknowledgements\n================\nThis project is the result of a collaborative research agreement between Thales\nand the University of Bristol with the initial funding provided by Thales.\n\n.. _SciPy: https://scipy.org/\n.. _NumPy: https://www.numpy.org/\n.. _scikit-learn: https://scikit-learn.org/stable/\n.. _matplotlib: https://matplotlib.org/\n.. _scikit-image: https://scikit-image.org/\n.. _Pillow: https://pillow.readthedocs.io/\n.. _`https://fat-forensics.org`: https://fat-forensics.org\n.. _inst: https://fat-forensics.org/getting_started/install_deps_os.html#installation-instructions\n.. _changelog: https://fat-forensics.org/changelog.html\n.. _dev_guide: https://fat-forensics.org/development.html\n.. _`https://github.com/fat-forensics/fat-forensics`: https://github.com/fat-forensics/fat-forensics\n.. _`https://pypi.org/project/fat-forensics`: https://pypi.org/project/fat-forensics\n.. _`https://github.com/fat-forensics/fat-forensics/issues`: https://github.com/fat-forensics/fat-forensics/issues\n.. _contrib_guide: https://fat-forensics.org/development.html#contributing-code\n.. _dev_testing: https://fat-forensics.org/development.html#testing\n.. _dev_testing_env: https://fat-forensics.org/development.html#testing-environment\n.. _getting_started: https://fat-forensics.org/getting_started/index.html\n.. _gitter: https://gitter.im/fat-forensics\n.. _`mailing list`: https://groups.google.com/forum/#!forum/fat-forensics\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffat-forensics%2Ffat-forensics","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffat-forensics%2Ffat-forensics","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffat-forensics%2Ffat-forensics/lists"}