Merge pull request #303 from sodascience/develop

Release 1.0.2

.github/workflows/joss-paper-draft.yml

@@ -0,0 +1,28 @@
+name: Draft PDF
+on: 
+  push:
+      paths:
+        - docs/paper/**
+        - .github/workflows/joss-paper-draft.yml
+
+jobs:
+  paper:
+    runs-on: ubuntu-latest
+    name: Paper Draft
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Build draft PDF
+        uses: openjournals/openjournals-draft-action@master
+        with:
+          journal: joss
+          # This should be the path to the paper within your repo.
+          paper-path: docs/paper/paper.md
+      - name: Upload
+        uses: actions/upload-artifact@v4
+        with:
+          name: paper
+          # This is the output path where Pandoc will write the compiled
+          # PDF. Note, this should be the same directory as the input
+          # paper.md
+          path: docs/paper/paper.pdf

.github/workflows/python-package.yml → .github/workflows/python-test.yml

@@ -1,13 +1,13 @@
 # This workflow will install Python dependencies, run tests and lint with a variety of Python versions
 # For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
 
-name: Python package
+name: Lint, test, documentation, plugins
 
 on:
   push:
     branches: [ main ]
   pull_request:
-    branches: [ main ]
+    branches: [ develop ]
   schedule:
     - cron: "0 0 * * 0"
 

.gitignore

@@ -141,8 +141,13 @@ dmypy.json
 
 #DS_Store
 .DS_Store
-.DS_Store
 docs/source/images/pipeline.afphoto~lock~
 docs/source/images/.$ClassDiagram.drawio.bkp
 docs/source/images/.$distributions.drawio.bkp
+
+# JOSS paper artefacts
+docs/paper/*.jats
+docs/paper/media
+
+# Generated api docs stuff
 docs/source/api/generated

docs/paper/build_command.txt

@@ -0,0 +1,8 @@
+
+On windows:
+
+docker run --rm --volume %cd%/docs/paper:/data --env JOURNAL=joss openjournals/inara
+
+on unix:
+
+docker run --rm --volume $PWD/docs/paper:/data --user $(id -u):$(id -g) --env JOURNAL=joss openjournals/inara

docs/paper/paper.bib

@@ -0,0 +1,161 @@
+@misc{bates2019ons,
+  title={ONS methodology working paper series number 16—Synthetic data pilot},
+  author={Bates, AG and Spakulov{\'a}, I and Dove, I and Mealor, A},
+  year={2019}
+}
+
+@inproceedings{dwork2006differential,
+  title={Differential privacy},
+  author={Dwork, Cynthia},
+  booktitle={International colloquium on automata, languages, and programming},
+  pages={1--12},
+  year={2006},
+  organization={Springer}
+}
+
+@book{dewolf2012statistical,
+  title={Statistical disclosure control},
+  author={de Wolf, Peter-Paul},
+  year={2012},
+  publisher={Wiley \& Sons, Chichester}
+}
+
+@article{sweeney2002k,
+  title={k-anonymity: A model for protecting privacy},
+  author={Sweeney, Latanya},
+  journal={International journal of uncertainty, fuzziness and knowledge-based systems},
+  volume={10},
+  number={05},
+  pages={557--570},
+  year={2002},
+  publisher={World Scientific}
+}
+
+@misc{bond2015guidelines,
+  title={Guidelines for Output Checking. Eurostat},
+  author={Bond, S and Brandt, M and de Wolf, PP},
+  year={2015}
+}
+
+@article{dwork2010differential,
+  title={Differential privacy for statistics: What we know and what we want to learn},
+  author={Dwork, Cynthia and Smith, Adam},
+  journal={Journal of Privacy and Confidentiality},
+  volume={1},
+  number={2},
+  year={2010}
+}
+
+@book{hastie2009elements,
+  title={The elements of statistical learning: data mining, inference, and prediction},
+  author={Hastie, Trevor and Tibshirani, Robert and Friedman, Jerome H and Friedman, Jerome H},
+  volume={2},
+  year={2009},
+  publisher={Springer}
+}
+
+@inproceedings{akaike1973information,
+  title={Information theory and an extension of the maximum likelihood principle},
+  author={Akaike, H},
+  booktitle={2nd International Symposium on Information Theory},
+  pages={267--281},
+  year={1973},
+  organization={Akad{\'e}miai Kiad{\'o} Location Budapest, Hungary}
+}
+
+@article{neath2012bayesian,
+  title={The Bayesian information criterion: background, derivation, and applications},
+  author={Neath, Andrew A and Cavanaugh, Joseph E},
+  journal={Wiley Interdisciplinary Reviews: Computational Statistics},
+  volume={4},
+  number={2},
+  pages={199--203},
+  year={2012},
+  publisher={Wiley Online Library}
+}
+@software{vink2024polars,
+  author       = {Ritchie Vink and
+                  Stijn de Gooijer and
+                  Alexander Beedie and
+                  Marco Edward Gorelli and
+                  Weijie Guo and
+                  J van Zundert and
+                  Orson Peters and
+                  Gert Hulselmans and
+                  nameexhaustion and
+                  Cory Grinstead and
+                  Marshall and
+                  Gijs Burghoorn and
+                  chielP and
+                  Itamar Turner-Trauring and
+                  Matteo Santamaria and
+                  Daniël Heres and
+                  Lawrence Mitchell and
+                  Josh Magarick and
+                  ibENPC and
+                  Karl Genockey and
+                  Moritz Wilksch and
+                  Jorge Leitao and
+                  Mick van Gelderen and
+                  Petros Barbagiannis and
+                  Oliver Borchert and
+                  deanm0000 and
+                  Jonas Haag and
+                  Henry Harbeck and
+                  Liam Brannigan},
+  title        = {pola-rs/polars: Python Polars},
+  year         = 2024,
+  publisher    = {Zenodo},
+  version      = {py-1.4.1},
+  doi          = {10.5281/zenodo.7697217},
+  url          = {https://doi.org/10.5281/zenodo.7697217}
+}
+
+@article{wickham2014tidy,
+ title={Tidy Data},
+ volume={59},
+ url={https://www.jstatsoft.org/index.php/jss/article/view/v059i10},
+ doi={10.18637/jss.v059.i10},
+ abstract={A huge amount of effort is spent cleaning data to get it ready for analysis, but there has been little research on how to make data cleaning as easy and effective as possible. This paper tackles a small, but important, component of data cleaning: data tidying. Tidy datasets are easy to manipulate, model and visualize, and have a specific structure: each variable is a column, each observation is a row, and each type of observational unit is a table. This framework makes it easy to tidy messy datasets because only a small set of tools are needed to deal with a wide range of un-tidy datasets. This structure also makes it easier to develop tidy tools for data analysis, tools that both input and output tidy datasets. The advantages of a consistent data structure and matching tools are demonstrated with a case study free from mundane data manipulation chores.},
+ number={10},
+ journal={Journal of Statistical Software},
+ author={Wickham, Hadley},
+ year={2014},
+ pages={1–23}
+}
+
+# alternative synthetic data packages
+@article{nowok2016synthpop,
+  title={synthpop: Bespoke creation of synthetic data in R},
+  author={Nowok, Beata and Raab, Gillian M and Dibben, Chris},
+  journal={Journal of statistical software},
+  volume={74},
+  pages={1--26},
+  year={2016}
+}
+
+@article{templ2017simulation,
+  title={Simulation of synthetic complex data: The R package simPop},
+  author={Templ, Matthias and Meindl, Bernhard and Kowarik, Alexander and Dupriez, Olivier},
+  journal={Journal of Statistical Software},
+  volume={79},
+  number={10},
+  pages={1--38},
+  year={2017},
+  publisher={UCLA, Dept. of Statistics}
+}
+
+@inproceedings{ping2017datasynthesizer,
+  title={Datasynthesizer: Privacy-preserving synthetic datasets},
+  author={Ping, Haoyue and Stoyanovich, Julia and Howe, Bill},
+  booktitle={Proceedings of the 29th International Conference on Scientific and Statistical Database Management},
+  pages={1--5},
+  year={2017}
+}
+
+@article{vankesteren2024democratize,
+  title={To democratize research with sensitive data, we should make synthetic data more accessible},
+  author={{van Kesteren}, Erik-Jan},
+  journal={arXiv preprint arXiv:2404.17271},
+  year={2024}
+}