Merge pull request #344 from sodascience/develop

Release 1.1.0

.github/workflows/core-ci.yml

@@ -0,0 +1,82 @@
+name: Continuous integration for development
+
+on:
+  pull_request:
+    branches: [ main, develop ]
+  push:
+    branches: [ main, develop ]
+
+jobs:
+  check:
+    name: Lint and check types
+    strategy:
+      fail-fast: true
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+    runs-on: "ubuntu-latest"
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install ".[check,extra]"
+      - name: Lint with Ruff
+        run: ruff check metasyn
+      - name: Check types with MyPy
+        run: mypy metasyn  
+
+  test:
+    name: Run test suite
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        include:
+            - os: macos-latest
+              python-version: "3.12"
+            - os: windows-latest
+              python-version: "3.12"
+    runs-on: ${{ matrix.os }}
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install ".[test,extra]"
+    - name: Test with pytest
+      run: pytest tests
+    - name: Check notebook output
+      if: ${{ matrix.os != 'macos-latest' }}
+      run: pytest --nbval-lax examples
+    - name: Test basic example
+      run: python examples/basic_example.py
+    - name: Test CLI configuration example
+      run: |
+        pip install git+https://github.com/sodascience/metasyn-disclosure-control
+        pip install .
+        metasyn create-meta metasyn/demo/demo_titanic.csv --config examples/config_files/example_config.toml
+
+  build-docs:
+    name: Build documentation
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.x"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install ".[docs]"
+    - name: Build docs
+      run: sphinx-build -M html docs/source docs/build 

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

@@ -1,4 +1,4 @@
-name: Draft PDF
+name: Build paper draft PDF
 on: 
   push:
       paths:

.github/workflows/python-publish.yml

@@ -1,11 +1,6 @@
 # This workflow will upload a Python Package using Twine when a release is created
 # For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
 
-# This workflow uses actions that are not certified by GitHub.
-# They are provided by a third-party and are governed by
-# separate terms of service, privacy policy, and support
-# documentation.
-
 name: Upload Python Package
 
 on:
@@ -17,13 +12,11 @@ permissions:
 
 jobs:
   deploy:
-
     runs-on: ubuntu-latest
-
     steps:
     - uses: actions/checkout@v4
     - name: Set up Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: '3.x'
     - name: Install dependencies

.github/workflows/release-dockerhub.yml

@@ -1,4 +1,4 @@
-name: Release Dockerhub
+name: Release dockerfile to Dockerhub
 
 on:
   push:

.github/workflows/scheduled-ci.yml

@@ -0,0 +1,71 @@
+name: Scheduled CI suite on main and dev branches
+
+on:
+  schedule: 
+    - cron: "0 0 * * 0"
+  workflow_dispatch: # also allow manual trigger
+
+jobs:
+  check:
+    name: Lint and check types
+    strategy:
+      fail-fast: false
+      matrix:
+        branch: ["main", "develop"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+    runs-on: "ubuntu-latest"
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ matrix.branch }}
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install ".[check,extra]"
+      - name: Lint with Ruff
+        run: ruff check metasyn
+      - name: Check types with MyPy
+        run: mypy metasyn  
+
+  test:
+    name: Run test suite
+    strategy:
+      fail-fast: false
+      matrix:
+        branch: ["main", "develop"]
+        os: [ubuntu-latest]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        include:
+            - os: macos-latest
+              python-version: "3.12"
+            - os: windows-latest
+              python-version: "3.12"
+    runs-on: ${{ matrix.os }}
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        ref: ${{ matrix.branch }}
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install ".[test,extra]"
+    - name: Test with pytest
+      run: pytest tests
+    - name: Check notebook output
+      if: ${{ matrix.os != 'macos-latest' }}
+      run: pytest --nbval-lax examples
+    - name: Test basic example
+      run: python examples/basic_example.py
+    - name: Test CLI configuration example
+      run: |
+        pip install git+https://github.com/sodascience/metasyn-disclosure-control
+        pip install .
+        metasyn create-meta metasyn/demo/demo_titanic.csv --config examples/example_config.toml

.gitignore

@@ -151,3 +151,6 @@ docs/paper/media
 
 # Generated api docs stuff
 docs/source/api/generated
+
+# uv stuff
+uv.lock

.readthedocs.yaml

@@ -10,18 +10,15 @@ build:
   os: ubuntu-20.04
   tools:
     python: "3.9"
-    # You can also specify other tool versions:
-    # nodejs: "16"
-    # rust: "1.55"
-    # golang: "1.17"
 
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
-   configuration: docs/source/conf.py
+  configuration: docs/source/conf.py
 
 # Optionally declare the Python requirements required to build your docs
 python:
-   install:
-   - requirements: docs/requirements.txt
-   - method: pip
-     path: .
+  install:
+  - method: pip
+    path: .
+    extra_requirements:
+      - docs

README.md

@@ -17,7 +17,7 @@
 
 __Generate synthetic tabular data__ in a transparent, understandable, and privacy-friendly way. Metasyn makes it possible for owners of sensitive data to create test data, do open science, improve code reproducibility, encourage data reuse, and enhance accessibility of their datasets, without worrying about leaking private information. 
 
-With metasyn you can __fit__ a model to an existing dataframe, __export__ it to a transparent and auditable `.json` file, and __synthesize__ a dataframe that looks a lot like the real one. In contrast to most other synthetic data software, we make the explicit choice to strictly limit the statistical information in our model in order to adhere to the highest privacy standards.
+With metasyn you can __fit__ a model to an existing dataframe, __save__ it to a transparent and auditable `.json` file, and __synthesize__ a dataframe that looks a lot like the real one. In contrast to most other synthetic data software, we make the explicit choice to strictly limit the statistical information in our model in order to adhere to the highest privacy standards.
 
 ## Highlights
 - 👋 __Accessible__. Metasyn is designed to be easy to use and understand, and we do our best to be welcoming to newcomers and novice users. [Let us know](https://github.com/sodascience/metasyn/issues/new) if we can improve!

docs/paper/paper.bib

@@ -150,9 +150,16 @@ @inproceedings{ping2017datasynthesizer
 }
 
 @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},
-  doi={10.48550/arXiv.2404.17271}
+  title = {To democratize research with sensitive data,  we should make synthetic data more accessible},
+  volume = {5},
+  ISSN = {2666-3899},
+  url = {http://dx.doi.org/10.1016/j.patter.2024.101049},
+  DOI = {10.1016/j.patter.2024.101049},
+  number = {9},
+  journal = {Patterns},
+  publisher = {Elsevier BV},
+  author = {{van Kesteren},  Erik-Jan},
+  year = {2024},
+  month = sep,
+  pages = {101049}
 }