Metadata-Version: 2.1
Name: responsibly
Version: 0.1.3
Summary: Toolkit for Auditing and Mitigating Bias and Fairness of Machine Learning Systems 🔎🤖🧰
Home-page: https://docs.responsibly.ai
Author: Shlomi Hod
Author-email: shlomi.hod@gmail.com
License: MIT
Description: Responsibly
        ===========
        
        .. image:: https://img.shields.io/badge/docs-passing-brightgreen.svg
            :target: https://docs.responsibly.ai
        
        .. image:: https://img.shields.io/gitter/room/nwjs/nw.js.svg
           :alt: Join the chat at https://gitter.im/ResponsiblyAI/responsibly
           :target: https://gitter.im/ResponsiblyAI/responsibly
        
        .. image:: https://img.shields.io/github/workflow/status/ResponsiblyAI/responsibly/CI/master.svg
            :target: https://github.com/ResponsiblyAI/responsibly/actions/workflows/ci.yml
         
        .. image::  https://img.shields.io/coveralls/ResponsiblyAI/responsibly/master.svg
           :target: https://coveralls.io/r/ResponsiblyAI/responsibly
        
        .. image::  https://img.shields.io/scrutinizer/g/ResponsiblyAI/responsibly.svg
          :target: https://scrutinizer-ci.com/g/ResponsiblyAI/responsibly/?branch=master
        
        .. image::  https://img.shields.io/pypi/v/responsibly.svg
          :target: https://pypi.org/project/responsibly
        
        .. image::  https://img.shields.io/github/license/ResponsiblyAI/responsibly.svg
            :target: https://docs.responsibly.ai/about/license.html
        
        **Toolkit for Auditing and Mitigating Bias and Fairness**
        **of Machine Learning Systems 🔎🤖🧰**
        
        *Responsibly* is developed for **practitioners** and **researchers** in mind,
        but also for learners. Therefore, it is compatible with
        data science and machine learning tools of trade in Python,
        such as Numpy, Pandas, and especially **scikit-learn**.
        
        The primary goal is to be one-shop-stop for **auditing** bias
        and fairness of machine learning systems, and the secondary one
        is to mitigate bias and adjust fairness through
        **algorithmic interventions**.
        Besides, there is a particular focus on **NLP** models.
        
        *Responsibly* consists of three sub-packages:
        
        1. ``responsibly.dataset``
             Collection of common benchmark datasets from fairness research.
        
        2. ``responsibly.fairness``
             Demographic fairness in binary classification,
             including metrics and algorithmic interventions.
        
        3. ``responsibly.we``
             Metrics and debiasing methods for bias (such as gender and race)
             in word embedding.
        
        For fairness, *Responsibly*'s functionality is aligned with the book
        `Fairness and Machine Learning
        - Limitations and Opportunities <https://fairmlbook.org>`_
        by Solon Barocas, Moritz Hardt and Arvind Narayanan.
        
        If you would like to ask for a feature or report a bug,
        please open a
        `new issue <https://github.com/ResponsiblyAI/responsibly/issues/new>`_
        or write us in `Gitter <https://gitter.im/ResponsiblyAI/responsibly>`_.
        
        Requirements
        ------------
        
        -  Python 3.6+
        
        Installation
        ------------
        
        Install responsibly with pip:
        
        .. code:: sh
        
           $ pip install responsibly
        
        or directly from the source code:
        
        .. code:: sh
        
           $ git clone https://github.com/ResponsiblyAI/responsibly.git
           $ cd responsibly
           $ python setup.py install
        
        Citation
        --------
        
        If you have used *Responsibly* in a scientific publication,
        we would appreciate citations to the following:
        
        ::
        
          @Misc{,
            author = {Shlomi Hod},
            title =  {{Responsibly}: Toolkit for Auditing and Mitigating Bias and Fairness of Machine Learning Systems},
            year =   {2018--},
            url =    "http://docs.responsibly.ai/",
            note =   {[Online; accessed <today>]}
          }
        
        Revision History
        ================
        
        0.1.3 (2021/04/02)
        ------------------
        
        - Fix new pagacke dependencies
        
        - Switch from Travis CI to Github Actions
        
        0.1.2 (2020/09/15)
        ------------------
        
        - Fix Travis CI issues with pipenv
        
        - Fix bugs with word embedding bias
        
        0.1.1 (2019/08/04)
        ------------------
        
        - Fix a dependencies issue with ``smart_open``
        
        - Change URLs to https
        
        0.1.0 (2019/07/31)
        ------------------
        
        - Rename the project to ``responsibly`` from ``ethically``
        
        - Word embedding bias
        
          - Improve functionality of ``BiasWordEmbedding``
        
        - Threshold fairness interventions
        
          - Fix bugs with ROCs handling
          - Improve API and add functionality (``plot_thresholds``)
        
        0.0.5 (2019/06/14)
        ------------------
        
        - Word embedding bias
        
          - Fix bug in computing WEAT
        
          - Computing and plotting factual property
            association to projections on a bias direction,
            similar to WEFAT
        
        
        0.0.4 (2019/06/03)
        ------------------
        
        - Word embedding bias
        
          - Unrestricted ``most_similar``
        
          - Unrestricted ``generate_analogies``
        
          - Running specific experiments with ``calc_all_weat``
        
          - Plotting clustering by classification
            of biased neutral words
        
        
        0.0.3 (2019/04/10)
        ------------------
        
        - Fairness in Classification
        
          - Three demographic fairness criteria
        
            - Independence
            - Separation
            - Sufficiency
        
          - Equalized odds post-processing algorithmic interventions
          - Complete two notebook demos (FICO and COMPAS)
        
        - Word embedding bias
        
          - Measuring bias with WEAT method
        
        - Documentation improvements
        
        - Fixing security issues with dependencies
        
        
        0.0.2 (2018/09/01)
        ------------------
        
        - Word embedding bias
        
          - Generating analogies along the bias direction
          - Standard evaluations of word embedding (word pairs and analogies)
          - Plotting indirect bias
          - Scatter plot of bias direction projections between two word embedding
          - Improved verbose mode
        
        
        0.0.1 (2018/08/17)
        ------------------
        
        -  Gender debiasing for word embedding based on Bolukbasi et al.
        
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Text Processing :: Linguistic
Classifier: License :: OSI Approved :: MIT License
Classifier: Natural Language :: English
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Requires-Python: >=3.6, <3.9
Description-Content-Type: text/x-rst
