Release candidate for 0.0.4

.editorconfig

@@ -0,0 +1,13 @@
+root = true
+
+[*]
+charset = utf-8
+end_of_line = lf
+indent_size = 4
+indent_style = space
+insert_final_newline = true
+max_line_length = 110
+tab_width = 4
+
+[{*.yaml,*.yml}]
+indent_size = 2

.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: "3.12"
+      - 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/gh-action-sigstore-python@v2.1.1
+        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

@@ -33,9 +33,14 @@ jobs:
       #----------------------------------------------
       - name: Run tests
         run: |
-          pytest -v --doctest-modules --cov=src -s
+          pytest -v --doctest-modules --cov=src --junitxml=junit.xml -s --ignore=docs
 
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4.0.1
         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

@@ -1,7 +1,7 @@
 default_language_version:
   python: python3.12
 
-exclude: "sample_data|docs/MIMIC_IV_tutorial/wandb_reports"
+exclude: "docs/index.md|MIMIC-IV_Example/README.md|eICU_Example/README.md"
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
@@ -95,10 +95,12 @@ repos:
           - mdformat-gfm
           - mdformat-tables
           - mdformat_frontmatter
-          - mdformat-myst
           - mdformat-black
           - mdformat-config
           - mdformat-shfmt
+          - mdformat-mkdocs
+          - mdformat-toc
+          - mdformat-admon
 
   # word spelling linter
   - repo: https://github.com/codespell-project/codespell
@@ -124,8 +126,4 @@ repos:
       - id: nbqa-isort
         args: ["--profile=black"]
       - id: nbqa-flake8
-        args:
-          [
-            "--extend-ignore=E203,E402,E501,F401,F841",
-            "--exclude=logs/*,data/*",
-          ]
+        args: ["--extend-ignore=E203,E402,E501,F401,F841", "--exclude=logs/*,data/*"]

.readthedocs.yaml

@@ -0,0 +1,21 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the version of Python and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.12"
+
+python:
+  install:
+    - method: pip
+      path: .
+      extra_requirements:
+        - docs
+
+mkdocs:
+  configuration: mkdocs.yml

MIMIC-IV_Example/README.md

@@ -72,14 +72,14 @@ several steps:
 This is a step in a few parts:
 
 1. Join a few tables by `hadm_id` to get the right times in the right rows for processing. In
-   particular, we need to join:
-   - the `hosp/diagnoses_icd` table with the `hosp/admissions` table to get the `dischtime` for each
-     `hadm_id`.
-   - the `hosp/drgcodes` table with the `hosp/admissions` table to get the `dischtime` for each `hadm_id`.
+    particular, we need to join:
+    - the `hosp/diagnoses_icd` table with the `hosp/admissions` table to get the `dischtime` for each
+        `hadm_id`.
+    - the `hosp/drgcodes` table with the `hosp/admissions` table to get the `dischtime` for each `hadm_id`.
 2. Convert the patient's static data to a more parseable form. This entails:
-   - Get the patient's DOB in a format that is usable for MEDS, rather than the integral `anchor_year` and
-     `anchor_offset` fields.
-   - Merge the patient's `dod` with the `deathtime` from the `admissions` table.
+    - Get the patient's DOB in a format that is usable for MEDS, rather than the integral `anchor_year` and
+        `anchor_offset` fields.
+    - Merge the patient's `dod` with the `deathtime` from the `admissions` table.
 
 After these steps, modified files or symlinks to the original files will be written in a new directory which
 will be used as the input to the actual MEDS extraction ETL. We'll use `$MIMICIV_PREMEDS_DIR` to denote this
@@ -104,24 +104,24 @@ subdirectories of the same root directory).
 This is a step in 4 parts:
 
 1. Sub-shard the raw files. Run this command as many times simultaneously as you would like to have workers
-   performing this sub-sharding step. See below for how to automate this parallelism using hydra launchers.
+    performing this sub-sharding step. See below for how to automate this parallelism using hydra launchers.
 
-   This step uses the `./scripts/extraction/shard_events.py` script. See `joint_script*.sh` for the expected
-   format of the command.
+    This step uses the `./scripts/extraction/shard_events.py` script. See `joint_script*.sh` for the expected
+    format of the command.
 
 2. Extract and form the patient splits and sub-shards. The `./scripts/extraction/split_and_shard_patients.py`
-   script is used for this step. See `joint_script*.sh` for the expected format of the command.
+    script is used for this step. See `joint_script*.sh` for the expected format of the command.
 
 3. Extract patient sub-shards and convert to MEDS events. The
-   `./scripts/extraction/convert_to_sharded_events.py` script is used for this step. See `joint_script*.sh` for
-   the expected format of the command.
+    `./scripts/extraction/convert_to_sharded_events.py` script is used for this step. See `joint_script*.sh` for
+    the expected format of the command.
 
 4. Merge the MEDS events into a single file per patient sub-shard. The
-   `./scripts/extraction/merge_to_MEDS_cohort.py` script is used for this step. See `joint_script*.sh` for the
-   expected format of the command.
+    `./scripts/extraction/merge_to_MEDS_cohort.py` script is used for this step. See `joint_script*.sh` for the
+    expected format of the command.
 
 5. (Optional) Generate preliminary code statistics and merge to external metadata. This is not performed
-   currently in the `joint_script*.sh` scripts.
+    currently in the `joint_script*.sh` scripts.
 
 ## Limitations / TO-DOs: