Skip to content

Commit

Permalink
addition of Facet team photos, initial FAQs and git badges (#97)
Browse files Browse the repository at this point in the history
* updates the Readme with gitbadges. Links will need to be added once things are created (for example packages) and have been left empty to ensure it is obvious they require updating
* add the initial FAQs section
* adds the BCG Facet team personnel photos to the about us section of the documentation
  • Loading branch information
jason-bentley authored Oct 13, 2020
1 parent 6531b07 commit d653487
Show file tree
Hide file tree
Showing 11 changed files with 115 additions and 66 deletions.
24 changes: 23 additions & 1 deletion README.rst
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,9 @@
model inspection and model-based simulation to enable better explanations of your
machine learning models.

TODO - add git badges as substitutions
|azure_pypi| |azure_conda| |azure_devops_master_ci| |code_cov|
|python_versions| |code_style| |documentation_status|
|made_with_sphinx_doc| |License_badge|

Installation
---------------------
Expand Down Expand Up @@ -233,3 +235,23 @@ The `shap <https://github.com/slundberg/shap>`_ implementation is used to estima
shapley vectors which are being decomposed into the synergy, redundancy, and
independence vectors.

.. |azure_conda| image::
:target:
.. |azure_pypi| image::
:target:
.. |azure_devops_master_ci| image::
:target:
.. |code_cov| image::
:target:
.. |documentation_status| image::
:target:

.. |python_versions| image:: https://img.shields.io/badge/python-3.7|3.8-blue.svg
:target: https://www.python.org/downloads/release/python-380/

.. |code_style| image:: https://img.shields.io/badge/code%20style-black-000000.svg
:target: https://github.com/psf/black
.. |made_with_sphinx_doc| image:: https://img.shields.io/badge/Made%20with-Sphinx-1f425f.svg
:target: https://www.sphinx-doc.org/
.. |license_badge| image:: https://img.shields.io/badge/License-Apache%202.0-olivegreen.svg
:target: https://opensource.org/licenses/Apache-2.0
Binary file added _static/facet_banner.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
87 changes: 24 additions & 63 deletions sphinx/source/about_us.rst
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ Our Story

Industry standard packages for machine learning (scikit-learn) and model inspection
(shap) are critical for best practice Data Science. However, combining these into
an efficient and reproducible process the yields deep insights into industrial and
an efficient and reproducible process that yields deep insights for industrial and
business processes can be challenging and time consuming. We found this to be a common
challenge for our global data science teams across 100s of projects every year.

Expand All @@ -31,7 +31,7 @@ get FACET! Little geometry humour there, we apologise. FACET implements a newly
developed algorithm to explain how variables of a
predictive model collaborate to predict outcomes by identifying patterns across the
explanations of many individual predictions. This advanced model inspection allows
strong independent factors to be identified and the explored via simulation to
strong independent factors to be identified and then explored via simulation to
understand optimal values for the predictive target of interest.

Our Team
Expand All @@ -43,72 +43,33 @@ okay that was the last geometry pun we promise.

**FACET Team at BCG Gamma**

.. raw:: html
+-------------------+-------------------+-------------------+-------------------+
| |JasonB| | |MaloG| | |KonstantinH| | |JanI| |
| Jason Bentley | Malo Grisard | Konstantin Hemker | Jan Ittner |
+-------------------+-------------------+-------------------+-------------------+
| |RicardoK| | |FlorentM| | |JoergS| | |
| Ricardo Kennedy | Florent Martin | Joerg Schneider | |
+-------------------+-------------------+-------------------+-------------------+
+-------------------+-------------------+-------------------+-------------------+

<style>
* {
box-sizing: border-box;
}
.column {
float: left;
width: 25%;
padding: 15px;
}
/* Clearfix (clear floats) */
.row::after {
content: "";
clear: both;
display: table;
}
</style>
</head>
<body>

<div class="row">
<div class="column">
<img src="_static/JBentley.jpg" style="width:100%">
<p>Jason Bentley</p>
</div>
<div class="column">
<img src="_static/MGrisard.jpg" style="width:100%">
<p>Malo Grisard</p>
</div>
<div class="column">
<img src="_static/KHemker.jpg" style="width:100%">
<p>Konstantin Hemker</p>
</div>
<div class="column">
<img src="_static/JIttner.jpg" style="width:100%">
<p>Jan Ittner</p>
</div>
</div>

<div class="row">
<div class="column">
<img src="_static/RKennedy.jpg" style="width:100%">
<p>Ricardo Kennedy</p>
</div>
<div class="column">
<img src="_static/FMartin.jpg" style="width:100%">
<p>Florent Martin</p>
</div>
<div class="column">
<img src="_static/JSchneider.jpg" style="width:100%">
<p>Joerg Schneider</p>
</div>
<div class="column">
<img src="" style="width:100%">
<p></p>
</div>
</div>

</body>
.. |JasonB| image:: _static/team_contributors/Jason_Bentley.jpg
:class: team_pic

.. |MaloG| image:: _static/team_contributors/Malo_Grisard.jpg
:class: team_pic

.. |KonstantinH| image:: _static/team_contributors/Konstantin_Hemker.jpg
:class: team_pic

.. |JanI| image:: _static/team_contributors/Jan_Ittner.jpg
:class: team_pic

.. |RicardoK| image:: _static/team_contributors/Ricardo_Kennedy.jpg
:class: team_pic

.. |FlorentM| image:: _static/team_contributors/Florent_Martin.jpg
:class: team_pic

.. |JoergS| image:: _static/team_contributors/Joerg_Schneider.jpg
:class: team_pic

70 changes: 68 additions & 2 deletions sphinx/source/faqs.rst
Original file line number Diff line number Diff line change
@@ -1,4 +1,70 @@
.. _faqs:

FAQs
===========
FAQ
===

Below you can find answers to commonly asked questions. If you don't see your answer
there you could also try posting on `stackoverflow <https://stackoverflow.com/>`_.

1. **What if I find a bug or have an idea for a new feature?**

For bug reports or feature requests please use our
`GitHub issue tracker <https://github.com/BCG-Gamma/facet/issues>`_.
For any other enquiries please feel free to contact us at our mailing list (add link).

2. **How does FACET's novel algorithm calculate feature redundancy and synergy?**

Please keep an eye out for our publication coming soon. In the meantime please feel
free to explore the GammaScope article (add link) to get a good introduction to
using the algorithm.

3. **How can I contribute?**

We welcome contributors! If you have minor changes in mind that would like to
contribute, please feel free to create a pull request and be sure to follow the
developer guidelines. For large or extensive changes please feel free to open an
issue, or reach out to us at our mailing list (add link) first to discuss.

4. **How can I perform standard plotting of SHAP values as done in the**
`shap <https://github.com/slundberg/shap>`_ **library?**

You can do this by creating an output of SHAP values from the fit LearnerInspector
as in the example shown below.

.. code-block:: Python
# run inspector
inspector = LearnerInspector(
n_jobs=-3,
verbose=False,
).fit(crossfit=ranker.best_model_crossfit)
# get shap values and associated data
shap_data = inspector.shap_plot_data()
shap.summary_plot(shap_values=shap_data.shap_values, features=shap_data.features)
5. **How can I extract CV performance metrics from the LearnerRanker to create my
own summaries or figures?**

You can extract the desired information as a data frame from the fitted
LearnerRanker object.

.. code-block:: Python
# after fitting a ranker
cv_result_df = ranker.summary_report()
Citation
--------
If you use FACET in your work please cite us as follows:

Bibtex entry::

@manual{
title={FACET},
author={FACET Team at BCG Gamma},
year={2020},
note={Python package version 1.0.0)
}

0 comments on commit d653487

Please sign in to comment.