Add JOSS paper

paper/build.sh

@@ -0,0 +1,10 @@
+#!/usr/bin/env bash
+
+DIR=$(realpath $(dirname "$0"))
+
+docker run --rm \
+    --volume $DIR:/data \
+    --user $(id -u):$(id -g) \
+    --env JOURNAL=joss \
+    --platform linux/amd64 \
+    openjournals/inara

paper/entr-build.sh

@@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+
+DIR=$(realpath $(dirname "$0"))
+
+FILES=$(find "$DIR" \
+    -iname "*.md" \
+    -o -iname "*.bib")
+
+echo "Running build.sh..."
+
+echo "$FILES" | entr -s "$DIR/build.sh"
+
+echo "Build finished"

paper/paper.bib

@@ -0,0 +1,311 @@
+@article{julia,
+  doi       = {10.1137/141000671},
+  url       = {https://doi.org/10.1137%2F141000671},
+  year      = 2017,
+  month     = {jan},
+  publisher = {Society for Industrial {\&} Applied Mathematics ({SIAM})},
+  volume    = {59},
+  number    = {1},
+  pages     = {65--98},
+  author    = {Jeff Bezanson and Alan Edelman and Stefan Karpinski and Viral B. Shah},
+  title     = {Julia: A Fresh Approach to Numerical Computing},
+  journal   = {{SIAM} Review}
+}
+
+@article{ashari2013performance,
+  title={Performance comparison between Na{\"\i}ve {B}ayes, decision tree and k-nearest neighbor in searching alternative design in an energy simulation tool},
+  author={Ashari, Ahmad and Paryudi, Iman and Tjoa, A Min},
+  journal={International Journal of Advanced Computer Science and Applications},
+  volume={4},
+  number={11},
+  year={2013},
+  publisher={Citeseer},
+  doi={10.14569/IJACSA.2013.041105}
+}
+
+@article{barredo2020explainable,
+  title={{Explainable Artificial Intelligence (XAI)}: Concepts, taxonomies, opportunities and challenges toward responsible {AI}},
+  author={Barredo Arrieta, Alejandro and D{\'i}az-Rodr{\'i}guez, Natalia and Del Ser, Javier and Bennetot, Adrien and Tabik, Siham and Barbado, Alberto and Garc{\'i}a, Salvador and Gil-L{\'o}pez, Sergio and Molina, Daniel and Benjamins, Richard and others},
+  journal={Information fusion},
+  volume={58},
+  pages={82--115},
+  year={2020},
+  publisher={Elsevier},
+  doi={10.1016/j.inffus.2019.12.012}
+}
+
+@article{benard2021sirus,
+title={{SIRUS: Stable and Interpretable RUle Set for classification}},
+author={Cl{\'e}ment B{\'e}nard and G{\'e}rard Biau and S{\'e}bastien Da Veiga and Erwan Scornet},
+volume={15},
+journal={Electronic Journal of Statistics},
+number={1},
+publisher={Institute of Mathematical Statistics and Bernoulli Society},
+pages={427 -- 505},
+year={2021},
+doi={10.1214/20-EJS1792},
+URL={https://doi.org/10.1214/20-EJS1792}
+}
+
+@inproceedings{benard2021interpretable,
+  title={Interpretable random forests via rule extraction},
+  author={B{\'e}nard, Cl{\'e}ment and Biau, G{\'e}rard and Da Veiga, S{\'e}bastien and Scornet, Erwan},
+  booktitle={International Conference on Artificial Intelligence and Statistics},
+  pages={937--945},
+  year={2021},
+  organization={PMLR}
+}
+
+@article{biau2016random,
+  title={A random forest guided tour},
+  author={Biau, G{\'e}rard and Scornet, Erwan},
+  journal={Test},
+  volume={25},
+  pages={197--227},
+  year={2016},
+  publisher={Springer},
+  doi={10.1007/s11749-016-0481-7}
+}
+
+@article{blaom2020mlj,
+  title={{MLJ}: A {J}ulia package for composable machine learning},
+  author={Anthony D. Blaom and Franz Kiraly and Thibaut Lienart and Yiannis Simillides and Diego Arenas and Sebastian J. Vollmer},
+  year={2020},
+  publisher={The Open Journal},
+  volume={5},
+  number={55},
+  pages={2704},
+  journal={Journal of Open Source Software},
+  doi={10.21105/joss.02704}
+}
+
+@article{breiman2001random,
+  title={Random forests},
+  author={Breiman, Leo},
+  journal={Machine learning},
+  volume={45},
+  pages={5--32},
+  year={2001},
+  publisher={Springer},
+  doi={10.1023/A:1010933404324}
+}
+
+@inproceedings{chen2016xgboost,
+  title={{XGBoost}: A scalable tree boosting system},
+  author={Chen, Tianqi and Guestrin, Carlos},
+  booktitle={{Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining}},
+  pages={785--794},
+  year={2016},
+  doi={10.1145/2939672.2939785}
+}
+
+@article{cranmer2023interpretable,
+  title={Interpretable machine learning for science with {PySR} and {SymbolicRegression.jl}},
+  author={Cranmer, Miles},
+  journal={arXiv preprint arXiv:2305.01582},
+  year={2023},
+  doi={10.48550/arXiv.2305.01582}
+}
+
+@article{doshi2017towards,
+  title={Towards a rigorous science of interpretable machine learning},
+  author={Doshi-Velez, Finale and Kim, Been},
+  journal={arXiv preprint arXiv:1702.08608},
+  year={2017},
+  doi={10.48550/arXiv.1702.08608}
+}
+
+@book{eaton1995titanic,
+  title={Titanic: Triumph and tragedy},
+  author={Eaton, John P and Haas, Charles},
+  year={1995},
+  publisher={WW Norton \& Company}
+}
+
+@article{fisher1936use,
+  title={The use of multiple measurements in taxonomic problems},
+  author={Fisher, Ronald A},
+  journal={Annals of eugenics},
+  volume={7},
+  number={2},
+  pages={179--188},
+  year={1936},
+  publisher={Wiley Online Library},
+  doi={10.1111/j.1469-1809.1936.tb02137.x}
+}
+
+@misc{haberman1999survival,
+  author={Haberman, S},
+  title={{Haberman\'s Survival}},
+  year={1999},
+  howpublished={UCI Machine Learning Repository},
+  doi={10.24432/C5XK51},
+  url={https://doi.org/10.24432/C5XK51}
+}
+
+@misc{hanson2023discourse,
+  title={[ANN] SIRUS.jl v1.2: Interpretable Machine Learning via Rule Extraction},
+  author={Hanson, Eric},
+  year={2023},
+  url={https://discourse.julialang.org/t/ann-sirus-jl-v1-2-interpretable-machine-learning-via-rule-extraction/100932/3}
+}
+
+@article{harrison1978hedonic,
+  title={Hedonic housing prices and the demand for clean air},
+  author={Harrison, David and Rubinfeld, Daniel L},
+  journal={Journal of environmental economics and management},
+  volume={5},
+  number={1},
+  pages={81--102},
+  year={1978},
+  publisher={Elsevier},
+  doi={10.1016/0095-0696(78)90006-2}
+}
+
+@book{james2013introduction,
+  title={An introduction to statistical learning},
+  author={James, Gareth and Witten, Daniela and Hastie, Trevor and Tibshirani, Robert and others},
+  volume={112},
+  year={2013},
+  publisher={Springer},
+  doi={10.1007/978-1-0716-1418-1}
+}
+
+@article{lundberg2017unified,
+  title={A unified approach to interpreting model predictions},
+  author={Lundberg, Scott M and Lee, Su-In},
+  journal={Advances in neural information processing systems},
+  volume={30},
+  year={2017}
+}
+
+@book{molnar2022interpretable,
+  title={Interpretable machine learning},
+  author={Molnar, Christoph},
+  year={2022}
+}
+
+@software{grisel2023scikit,
+  author={Olivier Grisel and
+          Andreas Mueller and
+          Lars and
+          Alexandre Gramfort and
+          Gilles Louppe and
+          Thomas J. Fan and
+          Peter Prettenhofer and
+          Mathieu Blondel and
+          Vlad Niculae and
+          Joel Nothman and
+          Arnaud Joly and
+          Guillaume Lemaitre and
+          Loïc Estève and
+          Jake Vanderplas and
+          Jérémie du Boisberranger and
+          manoj kumar and
+          Hanmin Qin and
+          Nicolas Hug and
+          Nelle Varoquaux and
+          Robert Layton and
+          Adrin Jalali and
+          Jan Hendrik Metzen and
+          (Venkat) Raghav, Rajagopalan and
+          Johannes Schönberger and
+          Roman Yurchak and
+          Julien Jerphanion and
+          Tom Dupré la Tour and
+          Wei Li and
+          Lucy Liu and
+          Chiara Marmo},
+  title={scikit-learn/scikit-learn: Scikit-learn},
+  publisher={Zenodo},
+  year={2023},
+  doi={10.5281/zenodo.8363803},
+  url={https://doi.org/10.5281/zenodo.8363803}
+}
+
+@software{sadeghi2022decisiontree,
+  title={{DecisionTree.jl} - A {Julia} implementation of the {CART} {Decision Tree and Random Forest} algorithms},
+  author={Ben Sadeghi and Poom Chiarawongse and Kevin Squire and Daniel C. Jones and Andreas Noack and Cédric St-Jean and Rik Huijzer and Roland Schätzle and Ian Butterworth and Yu-Fong Peng and Anthony Blaom},
+  month = nov,
+  year = 2022,
+  publisher={Zenodo},
+  version={0.12.3},
+  doi={10.5281/zenodo.7359268}
+}
+
+@inproceedings{smith1988using,
+  title={Using the {ADAP} learning algorithm to forecast the onset of diabetes mellitus},
+  author={Smith, Jack W and Everhart, James E and Dickson, WC and Knowler, William C and Johannes, Robert Scott},
+  booktitle={Proceedings of the annual symposium on computer application in medical care},
+  pages={261},
+  year={1988},
+  organization={American Medical Informatics Association}
+}
+
+@article{taleb2020statistical,
+  title={Statistical consequences of fat tails: Real world preasymptotics, epistemology, and applications},
+  author={Taleb, Nassim Nicholas},
+  journal={arXiv preprint arXiv:2001.10488},
+  year={2020},
+  doi={10.48550/arXiv.2001.10488}
+}
+
+@article{innes2018flux,
+  title = {Flux: Elegant machine learning with {J}ulia},
+  author={Mike Innes},
+  journal = {Journal of Open Source Software},
+  doi={10.21105/joss.00602},
+  url={https://doi.org/10.21105/joss.00602},
+  year={2018},
+  publisher = {The Open Journal},
+  volume = {3},
+  number = {25},
+  pages = {602}
+}
+
+@article{ke2017lightgbm,
+  title={{LightGBM}: A highly efficient gradient boosting decision tree},
+  author={Ke, Guolin and Meng, Qi and Finley, Thomas and Wang, Taifeng and Chen, Wei and Ma, Weidong and Ye, Qiwei and Liu, Tie-Yan},
+  journal={Advances in neural information processing systems},
+  volume={30},
+  year={2017}
+}
+
+@article{lobianco2021betaml,
+  title={BetaML: The Beta Machine Learning Toolkit, a self-contained repository of Machine Learning algorithms in {J}ulia},
+  author={Antonello Lobianco},
+  doi={10.21105/joss.02849},
+  url={https://doi.org/10.21105/joss.02849},
+  year={2021},
+  publisher={The Open Journal},
+  journal={Journal of Open Source Software},
+  volume={6},
+  number={60},
+  pages={2849}
+}
+
+@inproceedings{shalev2007pegasos,
+  title={{Pegasos: Primal Estimated sub-GrAdient SOlver for SVM}},
+  author={Shalev-Shwartz, Shai and Singer, Yoram and Srebro, Nathan},
+  booktitle={Proceedings of the 24th international conference on Machine learning},
+  pages={807--814},
+  year={2007},
+  doi={10.1145/1273496.1273598}
+}
+
+@misc{wolberg1995breast,
+  author={Wolberg, William, Mangasarian, Olvi, Street, Nick, and Street, W.},
+  title={{Breast Cancer Wisconsin (Diagnostic)}},
+  year={1995},
+  howpublished={UCI Machine Learning Repository},
+  doi={10.24432/C5DW2B}
+}
+
+@inproceedings{yu2020veridical,
+  title={Veridical data science},
+  author={Yu, Bin},
+  booktitle={Proceedings of the 13th International Conference on Web Search and Data Mining},
+  pages={4--5},
+  year={2020},
+  doi={10.1073/pnas.1901326117}
+}