From 04f929e3d04b81f48d7770fc8e0f27a3d8bd33db Mon Sep 17 00:00:00 2001
From: Martin Hirzel <hirzel@gmail.com>
Date: Fri, 4 Aug 2023 17:59:52 -0400
Subject: [PATCH] Added origin links for non-OpenML fairness datasets and
 references to recent Lale papers.

Signed-off-by: Martin Hirzel <hirzel@gmail.com>
---
 docs/papers.rst             | 49 +++++++++++++++++++++++++++++++++++--
 lale/lib/aif360/__init__.py |  3 +++
 lale/lib/aif360/datasets.py |  8 ++++--
 3 files changed, 56 insertions(+), 4 deletions(-)

diff --git a/docs/papers.rst b/docs/papers.rst
index 1706c90c6..a65011efb 100644
--- a/docs/papers.rst
+++ b/docs/papers.rst
@@ -4,7 +4,7 @@ Papers
 
 "Pipeline Combinators for Gradual AutoML".
 Guillaume Baudart, Martin Hirzel, Kiran Kate, Parikshit Ram, Avraham Shinnar, and Jason Tsay.
-Conference on Neural Information Processing Systems (NeurIPS), December 2021.
+Conference on Neural Information Processing Systems (NeurIPS), pages 19705-19718, December 2021.
 https://proceedings.neurips.cc/paper/2021/file/a3b36cb25e2e0b93b5f334ffb4e4064e-Paper.pdf
 
 **This is the preferred citation for the Lale project.**
@@ -17,9 +17,54 @@ https://proceedings.neurips.cc/paper/2021/file/a3b36cb25e2e0b93b5f334ffb4e4064e-
       booktitle = "Advances in Neural Information Processing Systems (NeurIPS)",
       year = 2021,
       month = dec,
+      pages = "19705--19718",
       url = "https://proceedings.neurips.cc/paper/2021/file/a3b36cb25e2e0b93b5f334ffb4e4064e-Paper.pdf" }
 
 
+"Searching for Fairer Machine Learning Ensembles,
+Michael Feffer, Martin Hirzel, Samuel C. Hoffman, Kiran Kate, Parikshit Ram, and Avraham Shinnar.
+Conference on Automated Machine Learning (AutoML), September 2023. 
+
+.. code:: BibTeX
+
+    @InProceedings{feffer_et_al_2023,
+      title = "Searching for Fairer Machine Learning Ensembles",
+      author = "Feffer, Michael and Hirzel, Martin and Hoffman, Samuel C. and Kate, Kiran and Ram, Parikshit and Shinnar, Avraham",
+      booktitle = "Conference on Automated Machine Learning (AutoML)",
+      year = 2023,
+      month = sep }
+
+
+"A Suite of Fairness Datasets for Tabular Classification",
+Martin Hirzel and Michael Feffer.
+ arXiv:2308.00133 [cs.LG], July 2023.
+https://arxiv.org/abs/2308.00133
+
+.. code:: BibTeX
+
+    @Misc{hirzel_feffer_2023,
+      title = "A Suite of Fairness Datasets for Tabular Classification",
+      author = "Hirzel, Martin and Feffer, Michael",
+      year = 2023,
+      month = jul,
+      url = "https://arxiv.org/abs/2308.00133" }
+
+
+"AI for Low-Code for AI",
+Nikitha Rao, Jason Tsay, Kiran Kate, Vincent J. Hellendoorn, and Martin Hirzel.
+arXiv:2305.20015 [cs.SE], May 2023.
+https://arxiv.org/abs/2305.20015
+
+.. code:: BibTeX
+
+    @Misc{rao_et_al_2023,
+      title = "{AI} for Low-Code for {AI}",
+      author = "Rao, Nikitha and Tsay, Jason and Kate, Kiran and Hellendoorn, Vincent J. and Hirzel, Martin",
+      year = 2023,
+      month = may,
+      url = "https://arxiv.org/abs/2305.20015" }
+
+
 "Gradual AutoML using Lale".
 Kiran Kate, Martin Hirzel, Parikshit Ram, Avraham Shinnar, and Jason Tsay.
 Tutorial at Conference on Knowledge Discovery and Data Mining (KDD-Tutorial), August 2022.
@@ -33,7 +78,7 @@ https://doi.org/10.1145/3534678.3542630
       booktitle = "Tutorial at the Conference on Knowledge Discovery and Data Mining (KDD-Tutorial)",
       year = 2022,
       month = aug,
-      pages = "pages 4794--4795",
+      pages = "4794--4795",
       url = "https://doi.org/10.1145/3534678.3542630" }
 
 
diff --git a/lale/lib/aif360/__init__.py b/lale/lib/aif360/__init__.py
index f49b943d9..b51609c4e 100644
--- a/lale/lib/aif360/__init__.py
+++ b/lale/lib/aif360/__init__.py
@@ -66,6 +66,8 @@
 
 Datasets:
 =========
+`datasets module docstring`_
+
 * `fetch_adult_df`_
 * `fetch_bank_df`_
 * `fetch_compas_df`_
@@ -174,6 +176,7 @@
 .. _`equal_opportunity_difference`: lale.lib.aif360.util.html#lale.lib.aif360.util.equal_opportunity_difference
 .. _`f1_and_disparate_impact`: lale.lib.aif360.util.html#lale.lib.aif360.util.f1_and_disparate_impact
 .. _`fair_stratified_train_test_split`: lale.lib.aif360.util.html#lale.lib.aif360.util.fair_stratified_train_test_split
+.. _`datasets module docstring`: https://lale.readthedocs.io/en/latest/modules/lale.lib.aif360.datasets.html
 .. _`fetch_adult_df`: lale.lib.aif360.datasets.html#lale.lib.aif360.datasets.fetch_adult_df
 .. _`fetch_bank_df`: lale.lib.aif360.datasets.html#lale.lib.aif360.datasets.fetch_bank_df
 .. _`fetch_compas_df`: lale.lib.aif360.datasets.html#lale.lib.aif360.datasets.fetch_compas_df
diff --git a/lale/lib/aif360/datasets.py b/lale/lib/aif360/datasets.py
index b34efbacf..250bd7ad7 100644
--- a/lale/lib/aif360/datasets.py
+++ b/lale/lib/aif360/datasets.py
@@ -16,17 +16,21 @@
 
 See the notebook `demo_fairness_datasets`_ for an example for using
 the functions, along with some tables and figures about them.
+There is also an `arxiv paper`_ about these datasets.
 Some of the fetcher methods have a `preprocess` argument that
 defaults to False.
 The notebook does not use that argument, instead demonstrating how
 to do any required preprocessing in the context of a Lale pipeline.
-Most of the datasets are from `OpenML`_, and most of the datasets
-have been used in various papers.
+Most of the datasets are from `OpenML`_, a few are from `meps.ahrq`_ or
+ `ProPublica`_, and most of the datasets have been used in various papers.
 The Lale library does not distribute the datasets themselves, it only
 provides methods for downloading them.
 
 .. _`demo_fairness_datasets`: https://github.com/IBM/lale/blob/master/examples/demo_fairness_datasets.ipynb
+.. _`arXiv paper`: https://arxiv.org/abs/2308.00133
 .. _`OpenML`: https://www.openml.org/
+.. _`meps.ahrq`: https://meps.ahrq.gov/data_stats/data_use.jsp
+.. _`ProPublica`: https://github.com/propublica/compas-analysis
 """
 
 import logging