========
About Us
========

Project Overview
================

mlQuantify is an open-source Python library for quantification, providing robust methods to estimate class prevalence with a practical and intuitive API. The library aims to make quantification algorithms and experimental protocols accessible to both researchers and practitioners in data science.

Most Importantly
================

mlQuantify was **heavily inspired by** `QuaPy <https://github.com/HLT-ISTI/QuaPy>`_, a leading library for quantification in Python, and by `scikit-learn <https://scikit-learn.org/stable/index.html>`_ for its simple, familiar interface and workflow design.

By combining key architectural elements, quantification strategies, and evaluation protocols from QuaPy with the ease-of-use and consistent patterns found in scikit-learn, mlQuantify offers a unified, modern experience for quantification tasks.

History
=======

mlQuantify was started in 2024 by Luiz Fernando Luth Junior and André Gustavo Maletzke, aiming to address the unique challenges and opportunities in quantification. Recognizing that quantification is a niche yet crucial task in real-world data scenarios, mlQuantify fills an essential gap in the Python machine learning ecosystem.

Governance & Contributors
=========================

mlQuantify is developed openly on GitHub. Bug reports, feature requests, and design discussions all take place in the public issue tracker, and contributions are welcome from anyone (see `How to Contribute`_).

Core Maintainers
----------------

.. list-table::
   :widths: 25 25
   :header-rows: 0

   * - .. image:: /images/luth_junior.jpeg
         :width: 120px
         :align: center

     - **Luiz Fernando Luth Junior**  
       *(lead developer, architect & documentation)*
   * - .. image:: /images/maletzke.jpg
         :width: 120px
         :align: center

     - **André Gustavo Maletzke**  
       *(engineering, research & documentation)*

.. note::

   For help, bug reports, or feature requests, please use our `GitHub issues <https://github.com/luizfernandolj/mlquantify/issues>`__ page rather than emailing contributors directly.

How to Contribute
=================

Whether you are a researcher, practitioner, or an open source enthusiast, you can contribute by:

- Submitting bug reports and feature requests.
- Proposing improvements through pull requests.
- Helping with documentation.
- Sharing quantification use cases and benchmarks.

For more details on contributing, see our `GitHub repository <https://github.com/luizfernandolj/mlquantify>`__.

Citing mlQuantify
=================

If you use mlQuantify in your research or applications, please cite the following:

Bibtex entry::

  @software{mlquantify,
    author = {Luiz Fernando Luth Junior and André Gustavo Maletzke},
    title = {mlQuantify: Quantification in Python},
    year = {2024},
    url = {https://github.com/luizfernandolj/mlquantify}
  }

Branding & Logo
===============

High-resolution logos are available in the `brand assets <https://github.com/luizfernandolj/mlquantify/tree/master/assets>`_ folder.

.. image:: /logos/logo_mlquantify.svg
   :align: center
   :width: 500px

Support
=======

mlQuantify is an independent, volunteer-maintained research project. The best
ways to support it are to contribute code or documentation, report issues, and
cite the library if it is useful in your own work (see `Citing mlQuantify`_).