Merge pull request #8 from mmcdermott/MEDS-DEV_v0

Initial set-up for MEDS-DEV

.github/workflows/code-quality-main.yaml

@@ -0,0 +1,24 @@
+# Same as `code-quality-pr.yaml` but triggered on commit to main branch
+# and runs on all files (instead of only the changed ones)
+
+name: Code Quality Main
+
+on:
+  push:
+    branches: [main]
+
+jobs:
+  code-quality:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v3
+        with:
+          python-version: "3.10"
+
+      - name: Run pre-commits
+        uses: pre-commit/[email protected]

.github/workflows/code-quality-pr.yaml

@@ -0,0 +1,38 @@
+# This workflow finds which files were changed, prints them,
+# and runs `pre-commit` on those files.
+
+# Inspired by the sktime library:
+# https://github.com/alan-turing-institute/sktime/blob/main/.github/workflows/test.yml
+
+name: Code Quality PR
+
+on:
+  pull_request:
+    branches: [main, "release/*", "dev"]
+
+jobs:
+  code-quality:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v3
+        with:
+          python-version: "3.10"
+
+      - name: Find modified files
+        id: file_changes
+        uses: trilom/[email protected]
+        with:
+          output: " "
+
+      - name: List modified files
+        run: echo '${{ steps.file_changes.outputs.files}}'
+
+      - name: Run pre-commits
+        uses: pre-commit/[email protected]
+        with:
+          extra_args: --files ${{ steps.file_changes.outputs.files}}

.github/workflows/python-build.yaml

@@ -0,0 +1,95 @@
+name: Publish Python 🐍 distribution 📦 to PyPI and TestPyPI
+
+on: push
+
+jobs:
+  build:
+    name: Build distribution 📦
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+      - name: Install pypa/build
+        run: >-
+          python3 -m
+          pip install
+          build
+          --user
+      - name: Build a binary wheel and a source tarball
+        run: python3 -m build
+      - name: Store the distribution packages
+        uses: actions/upload-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+  publish-to-pypi:
+    name: >-
+      Publish Python 🐍 distribution 📦 to PyPI
+    if: startsWith(github.ref, 'refs/tags/') # only publish to PyPI on tag pushes
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/MEDS-transforms # Replace <package-name> with your PyPI project name
+    permissions:
+      id-token: write # IMPORTANT: mandatory for trusted publishing
+
+    steps:
+      - name: Download all the dists
+        uses: actions/download-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+      - name: Publish distribution 📦 to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+  github-release:
+    name: >-
+      Sign the Python 🐍 distribution 📦 with Sigstore
+      and upload them to GitHub Release
+    needs:
+      - publish-to-pypi
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: write # IMPORTANT: mandatory for making GitHub Releases
+      id-token: write # IMPORTANT: mandatory for sigstore
+
+    steps:
+      - name: Download all the dists
+        uses: actions/download-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+      - name: Sign the dists with Sigstore
+        uses: sigstore/[email protected]
+        with:
+          inputs: >-
+            ./dist/*.tar.gz
+            ./dist/*.whl
+      - name: Create GitHub Release
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        run: >-
+          gh release create
+          '${{ github.ref_name }}'
+          --repo '${{ github.repository }}'
+          --notes ""
+      - name: Upload artifact signatures to GitHub Release
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        # Upload to GitHub Release using the `gh` CLI.
+        # `dist/` contains the built packages, and the
+        # sigstore-produced signatures and certificates.
+        run: >-
+          gh release upload
+          '${{ github.ref_name }}' dist/**
+          --repo '${{ github.repository }}'

.github/workflows/tests.yaml

@@ -0,0 +1,46 @@
+name: Tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main, "release/*", "dev"]
+
+jobs:
+  run_tests_ubuntu:
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false
+
+    timeout-minutes: 30
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v3
+        with:
+          python-version: "3.10"
+
+      - name: Install packages
+        run: |
+          pip install -e .[tests]
+
+      #----------------------------------------------
+      #              run test suite
+      #----------------------------------------------
+      - name: Run tests
+        run: |
+          pytest -v --doctest-modules --cov=src --junitxml=junit.xml -s --ignore=docs
+
+      - name: Upload coverage to Codecov
+        uses: codecov/[email protected]
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+      - name: Upload test results to Codecov
+        if: ${{ !cancelled() }}
+        uses: codecov/test-results-action@v1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}

.pre-commit-config.yaml

@@ -0,0 +1,132 @@
+default_language_version:
+  python: python3.10
+
+exclude: "docs/index.md"
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+      # list of supported hooks: https://pre-commit.com/hooks.html
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-docstring-first
+      - id: check-yaml
+      - id: debug-statements
+      - id: detect-private-key
+      - id: check-executables-have-shebangs
+      - id: check-toml
+      - id: check-case-conflict
+      - id: check-added-large-files
+        args: [--maxkb, "800"]
+
+  # python code formatting
+  - repo: https://github.com/psf/black
+    rev: 23.7.0
+    hooks:
+      - id: black
+        args: [--line-length, "110"]
+
+  # python import sorting
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort
+        args: ["--profile", "black", "--filter-files", "-o", "wandb"]
+
+  - repo: https://github.com/PyCQA/autoflake
+    rev: v2.2.0
+    hooks:
+      - id: autoflake
+        args: [--in-place, --remove-all-unused-imports]
+
+  # python upgrading syntax to newer version
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.10.1
+    hooks:
+      - id: pyupgrade
+        args: [--py310-plus]
+
+  # python docstring formatting
+  - repo: https://github.com/myint/docformatter
+    rev: v1.7.5
+    hooks:
+      - id: docformatter
+        args: [--in-place, --wrap-summaries=110, --wrap-descriptions=110]
+
+  # python check (PEP8), programming errors and code complexity
+  - repo: https://github.com/PyCQA/flake8
+    rev: 6.1.0
+    hooks:
+      - id: flake8
+        args:
+          [
+            "--max-complexity=10",
+            "--extend-ignore",
+            "E402,E701,E251,E226,E302,W504,E704,E402,E401,C901,E203",
+            "--max-line-length=110",
+            "--exclude",
+            "logs/*,data/*",
+            "--per-file-ignores",
+            "__init__.py:F401",
+          ]
+
+  # yaml formatting
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v3.0.3
+    hooks:
+      - id: prettier
+        types: [yaml]
+
+  # shell scripts linter
+  - repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: v0.9.0.5
+    hooks:
+      - id: shellcheck
+
+  # md formatting
+  - repo: https://github.com/executablebooks/mdformat
+    rev: 0.7.17
+    hooks:
+      - id: mdformat
+        args: ["--number"]
+        additional_dependencies:
+          - mdformat-gfm
+          - mdformat-tables
+          - mdformat_frontmatter
+          - mdformat-black
+          - mdformat-config
+          - mdformat-shfmt
+          - mdformat-mkdocs
+          - mdformat-toc
+          - mdformat-admon
+
+  # word spelling linter
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.2.5
+    hooks:
+      - id: codespell
+        args:
+          - --skip=logs/**,data/**,*.ipynb,*.bib,env.yml,env_cpu.yml,*.svg,poetry.lock
+          - --ignore-words-list=ehr,crate,infarction
+
+  # jupyter notebook cell output clearing
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.6.1
+    hooks:
+      - id: nbstripout
+
+  # jupyter notebook linting
+  - repo: https://github.com/nbQA-dev/nbQA
+    rev: 1.7.0
+    hooks:
+      - id: nbqa-black
+        args: ["--line-length=110"]
+      - id: nbqa-isort
+        args: ["--profile=black"]
+      - id: nbqa-flake8
+        args:
+          [
+            "--extend-ignore=E203,E402,E501,F401,F841",
+            "--exclude=logs/*,data/*",
+          ]

README.md

@@ -1,22 +1,27 @@
-# The Platform for Inductive Experiments over Medical Data (PIE MD)
-This repository contains the dataset, task, model training recipes, and results for the PIE MD benchmarking
-effort for EHR machine learning. See [this google doc](https://docs.google.com/document/d/1s-AR0qfoPmwJW4G7cIxdV6Z_cSEDGUir9BhO92Vb3wo/edit?usp=sharing) for more details.
+# The MEDS Dynamic Extensible Validation (MEDS-DEV) Benchmark: Re-thinking Reproducibility and Validation in ML for Health
+
+This repository contains the dataset, task, model training recipes, and results for the MEDS-DEV benchmarking
+effort for EHR machine learning.
 
 Note that this repository is _not_ a place where functional code is stored. Rather, this repository stores
-configuration files, training recipes, results, etc. for the PIE MD benchmarking effort -- runnable code will
+configuration files, training recipes, results, etc. for the MEDS-DEV benchmarking effort -- runnable code will
 often come from other repositories, with suitable permalinks being present in the various configuration files
 or commit messages for associated contributions to this repository.
 
-## Contributing to PIE MD
+## Contributing to MEDS-DEV
 
 ### To Add a Model
+
 TODO
 
 ### To Add a Dataset
+
 TODO
 
 ### To Add a Task
+
 TODO
 
 ### To Add Results
+
 TODO