INSPIRE-MEDS 0.0.1__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (34) hide show
  1. inspire_meds-0.0.1/.github/workflows/code-quality-main.yaml +31 -0
  2. inspire_meds-0.0.1/.github/workflows/code-quality-pr.yaml +45 -0
  3. inspire_meds-0.0.1/.github/workflows/python-build.yaml +99 -0
  4. inspire_meds-0.0.1/.github/workflows/tests.yaml +48 -0
  5. inspire_meds-0.0.1/.gitignore +162 -0
  6. inspire_meds-0.0.1/.pre-commit-config.yaml +137 -0
  7. inspire_meds-0.0.1/CONTRIBUTING.md +175 -0
  8. inspire_meds-0.0.1/LICENSE +21 -0
  9. inspire_meds-0.0.1/PKG-INFO +83 -0
  10. inspire_meds-0.0.1/README.md +45 -0
  11. inspire_meds-0.0.1/pyproject.toml +42 -0
  12. inspire_meds-0.0.1/setup.cfg +4 -0
  13. inspire_meds-0.0.1/src/INSPIRE_MEDS/__init__.py +38 -0
  14. inspire_meds-0.0.1/src/INSPIRE_MEDS/__main__.py +90 -0
  15. inspire_meds-0.0.1/src/INSPIRE_MEDS/commands.py +79 -0
  16. inspire_meds-0.0.1/src/INSPIRE_MEDS/configs/ETL.yaml +45 -0
  17. inspire_meds-0.0.1/src/INSPIRE_MEDS/configs/__init__.py +0 -0
  18. inspire_meds-0.0.1/src/INSPIRE_MEDS/configs/event_configs.yaml +456 -0
  19. inspire_meds-0.0.1/src/INSPIRE_MEDS/configs/main.yaml +25 -0
  20. inspire_meds-0.0.1/src/INSPIRE_MEDS/configs/pre_MEDS.yaml +16 -0
  21. inspire_meds-0.0.1/src/INSPIRE_MEDS/configs/runner.yaml +7 -0
  22. inspire_meds-0.0.1/src/INSPIRE_MEDS/configs/table_preprocessors.yaml +197 -0
  23. inspire_meds-0.0.1/src/INSPIRE_MEDS/dataset.yaml +13 -0
  24. inspire_meds-0.0.1/src/INSPIRE_MEDS/download.py +301 -0
  25. inspire_meds-0.0.1/src/INSPIRE_MEDS/pre_MEDS.py +258 -0
  26. inspire_meds-0.0.1/src/INSPIRE_MEDS.egg-info/PKG-INFO +83 -0
  27. inspire_meds-0.0.1/src/INSPIRE_MEDS.egg-info/SOURCES.txt +32 -0
  28. inspire_meds-0.0.1/src/INSPIRE_MEDS.egg-info/dependency_links.txt +1 -0
  29. inspire_meds-0.0.1/src/INSPIRE_MEDS.egg-info/entry_points.txt +2 -0
  30. inspire_meds-0.0.1/src/INSPIRE_MEDS.egg-info/requires.txt +29 -0
  31. inspire_meds-0.0.1/src/INSPIRE_MEDS.egg-info/top_level.txt +1 -0
  32. inspire_meds-0.0.1/static/pypi_trusted_publisher_example.png +0 -0
  33. inspire_meds-0.0.1/tests/e2e_demo_test.py +56 -0
  34. inspire_meds-0.0.1/tests/operations_synthetic.csv +1 -0
@@ -0,0 +1,31 @@
1
+ # Same as `code-quality-pr.yaml` but triggered on commit to main branch
2
+ # and runs on all files (instead of only the changed ones)
3
+
4
+ name: Code Quality Main
5
+
6
+ on:
7
+ push:
8
+ branches: [main]
9
+
10
+ jobs:
11
+ code-quality:
12
+ runs-on: ubuntu-latest
13
+
14
+ strategy:
15
+ matrix:
16
+ python-version: ["3.12"]
17
+
18
+ steps:
19
+ - uses: actions/checkout@v4
20
+
21
+ - name: Set up Python ${{ matrix.python-version }}
22
+ uses: actions/setup-python@v5
23
+ with:
24
+ python-version: ${{ matrix.python-version }}
25
+
26
+ - name: Install packages
27
+ run: |
28
+ pip install .[dev]
29
+
30
+ - name: Run pre-commits
31
+ uses: pre-commit/action@v3.0.1
@@ -0,0 +1,45 @@
1
+ # This workflow finds which files were changed, prints them,
2
+ # and runs `pre-commit` on those files.
3
+
4
+ # Inspired by the sktime library:
5
+ # https://github.com/alan-turing-institute/sktime/blob/main/.github/workflows/test.yml
6
+
7
+ name: Code Quality PR
8
+
9
+ on:
10
+ pull_request:
11
+ branches: [main, "release/*", "dev"]
12
+
13
+ jobs:
14
+ code-quality:
15
+ runs-on: ubuntu-latest
16
+
17
+ strategy:
18
+ matrix:
19
+ python-version: ["3.12"]
20
+
21
+ steps:
22
+ - uses: actions/checkout@v4
23
+
24
+ - name: Set up Python ${{ matrix.python-version }}
25
+ uses: actions/setup-python@v5
26
+ with:
27
+ python-version: ${{ matrix.python-version }}
28
+
29
+ - name: Install packages
30
+ run: |
31
+ pip install .[dev]
32
+
33
+ - name: Find modified files
34
+ id: file_changes
35
+ uses: trilom/file-changes-action@v1.2.4
36
+ with:
37
+ output: " "
38
+
39
+ - name: List modified files
40
+ run: echo '${{ steps.file_changes.outputs.files}}'
41
+
42
+ - name: Run pre-commits
43
+ uses: pre-commit/action@v3.0.1
44
+ with:
45
+ extra_args: --files ${{ steps.file_changes.outputs.files}}
@@ -0,0 +1,99 @@
1
+ name: Publish Python 🐍 distribution 📦 to PyPI and TestPyPI
2
+
3
+ on: push
4
+
5
+ jobs:
6
+ build:
7
+ name: Build distribution 📦
8
+ runs-on: ubuntu-latest
9
+
10
+ strategy:
11
+ matrix:
12
+ python-version: ["3.12"]
13
+
14
+ steps:
15
+ - uses: actions/checkout@v4
16
+ - name: Set up Python ${{ matrix.python-version }}
17
+ uses: actions/setup-python@v5
18
+ with:
19
+ python-version: ${{ matrix.python-version }}
20
+ - name: Install pypa/build
21
+ run: >-
22
+ python3 -m
23
+ pip install
24
+ build
25
+ --user
26
+ - name: Build a binary wheel and a source tarball
27
+ run: python3 -m build
28
+ - name: Store the distribution packages
29
+ uses: actions/upload-artifact@v4
30
+ with:
31
+ name: python-package-distributions
32
+ path: dist/
33
+
34
+ publish-to-pypi:
35
+ name: >-
36
+ Publish Python 🐍 distribution 📦 to PyPI
37
+ if: startsWith(github.ref, 'refs/tags/') # only publish to PyPI on tag pushes
38
+ needs:
39
+ - build
40
+ runs-on: ubuntu-latest
41
+ environment:
42
+ name: pypi
43
+ url: https://pypi.org/p/MEDS-transforms # Replace <package-name> with your PyPI project name
44
+ permissions:
45
+ id-token: write # IMPORTANT: mandatory for trusted publishing
46
+
47
+ steps:
48
+ - name: Download all the dists
49
+ uses: actions/download-artifact@v4
50
+ with:
51
+ name: python-package-distributions
52
+ path: dist/
53
+
54
+ - name: Publish distribution 📦 to PyPI
55
+ uses: pypa/gh-action-pypi-publish@release/v1
56
+
57
+ github-release:
58
+ name: >-
59
+ Sign the Python 🐍 distribution 📦 with Sigstore
60
+ and upload them to GitHub Release
61
+ needs:
62
+ - publish-to-pypi
63
+ runs-on: ubuntu-latest
64
+
65
+ permissions:
66
+ contents: write # IMPORTANT: mandatory for making GitHub Releases
67
+ id-token: write # IMPORTANT: mandatory for sigstore
68
+
69
+ steps:
70
+ - name: Download all the dists
71
+ uses: actions/download-artifact@v4
72
+ with:
73
+ name: python-package-distributions
74
+ path: dist/
75
+
76
+ - name: Sign the dists with Sigstore
77
+ uses: sigstore/gh-action-sigstore-python@v3.0.0
78
+ with:
79
+ inputs: >-
80
+ ./dist/*.tar.gz
81
+ ./dist/*.whl
82
+ - name: Create GitHub Release
83
+ env:
84
+ GITHUB_TOKEN: ${{ github.token }}
85
+ run: >-
86
+ gh release create
87
+ '${{ github.ref_name }}'
88
+ --repo '${{ github.repository }}'
89
+ --notes ""
90
+ - name: Upload artifact signatures to GitHub Release
91
+ env:
92
+ GITHUB_TOKEN: ${{ github.token }}
93
+ # Upload to GitHub Release using the `gh` CLI.
94
+ # `dist/` contains the built packages, and the
95
+ # sigstore-produced signatures and certificates.
96
+ run: >-
97
+ gh release upload
98
+ '${{ github.ref_name }}' dist/**
99
+ --repo '${{ github.repository }}'
@@ -0,0 +1,48 @@
1
+ name: Tests
2
+
3
+ on:
4
+ push:
5
+ branches: [main]
6
+ pull_request:
7
+ branches: [main, "release/*", "dev"]
8
+
9
+ jobs:
10
+ run_tests_ubuntu:
11
+ runs-on: ubuntu-latest
12
+
13
+ strategy:
14
+ matrix:
15
+ python-version: ["3.11", "3.12"]
16
+ fail-fast: false
17
+
18
+ timeout-minutes: 30
19
+
20
+ steps:
21
+ - name: Checkout
22
+ uses: actions/checkout@v4
23
+
24
+ - name: Set up Python ${{ matrix.python-version }}
25
+ uses: actions/setup-python@v5
26
+ with:
27
+ python-version: ${{ matrix.python-version }}
28
+
29
+ - name: Install packages
30
+ run: |
31
+ pip install -e .[tests]
32
+
33
+ #----------------------------------------------
34
+ # run test suite
35
+ #----------------------------------------------
36
+ - name: Run tests
37
+ run: |
38
+ pytest src/ tests/ -v --doctest-modules --cov=src --junitxml=junit.xml -s
39
+
40
+ - name: Upload coverage to Codecov
41
+ uses: codecov/codecov-action@v4.0.1
42
+ with:
43
+ token: ${{ secrets.CODECOV_TOKEN }}
44
+ - name: Upload test results to Codecov
45
+ if: ${{ !cancelled() }}
46
+ uses: codecov/test-results-action@v1
47
+ with:
48
+ token: ${{ secrets.CODECOV_TOKEN }}
@@ -0,0 +1,162 @@
1
+ # Byte-compiled / optimized / DLL files
2
+ __pycache__/
3
+ *.py[cod]
4
+ *$py.class
5
+
6
+ # C extensions
7
+ *.so
8
+
9
+ # Distribution / packaging
10
+ .Python
11
+ build/
12
+ develop-eggs/
13
+ dist/
14
+ downloads/
15
+ eggs/
16
+ .eggs/
17
+ lib/
18
+ lib64/
19
+ parts/
20
+ sdist/
21
+ var/
22
+ wheels/
23
+ share/python-wheels/
24
+ *.egg-info/
25
+ .installed.cfg
26
+ *.egg
27
+ MANIFEST
28
+
29
+ # PyInstaller
30
+ # Usually these files are written by a python script from a template
31
+ # before PyInstaller builds the exe, so as to inject date/other infos into it.
32
+ *.manifest
33
+ *.spec
34
+
35
+ # Installer logs
36
+ pip-log.txt
37
+ pip-delete-this-directory.txt
38
+
39
+ # Unit test / coverage reports
40
+ htmlcov/
41
+ .tox/
42
+ .nox/
43
+ .coverage
44
+ .coverage.*
45
+ .cache
46
+ nosetests.xml
47
+ coverage.xml
48
+ *.cover
49
+ *.py,cover
50
+ .hypothesis/
51
+ .pytest_cache/
52
+ cover/
53
+
54
+ # Translations
55
+ *.mo
56
+ *.pot
57
+
58
+ # Django stuff:
59
+ *.log
60
+ local_settings.py
61
+ db.sqlite3
62
+ db.sqlite3-journal
63
+
64
+ # Flask stuff:
65
+ instance/
66
+ .webassets-cache
67
+
68
+ # Scrapy stuff:
69
+ .scrapy
70
+
71
+ # Sphinx documentation
72
+ docs/_build/
73
+
74
+ # PyBuilder
75
+ .pybuilder/
76
+ target/
77
+
78
+ # Jupyter Notebook
79
+ .ipynb_checkpoints
80
+
81
+ # IPython
82
+ profile_default/
83
+ ipython_config.py
84
+
85
+ # pyenv
86
+ # For a library or package, you might want to ignore these files since the code is
87
+ # intended to run in multiple environments; otherwise, check them in:
88
+ # .python-version
89
+
90
+ # pipenv
91
+ # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
92
+ # However, in case of collaboration, if having platform-specific dependencies or dependencies
93
+ # having no cross-platform support, pipenv may install dependencies that don't work, or not
94
+ # install all needed dependencies.
95
+ #Pipfile.lock
96
+
97
+ # poetry
98
+ # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
99
+ # This is especially recommended for binary packages to ensure reproducibility, and is more
100
+ # commonly ignored for libraries.
101
+ # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
102
+ #poetry.lock
103
+
104
+ # pdm
105
+ # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
106
+ #pdm.lock
107
+ # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
108
+ # in version control.
109
+ # https://pdm.fming.dev/latest/usage/project/#working-with-version-control
110
+ .pdm.toml
111
+ .pdm-python
112
+ .pdm-build/
113
+
114
+ # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
115
+ __pypackages__/
116
+
117
+ # Celery stuff
118
+ celerybeat-schedule
119
+ celerybeat.pid
120
+
121
+ # SageMath parsed files
122
+ *.sage.py
123
+
124
+ # Environments
125
+ .env
126
+ .venv
127
+ env/
128
+ venv/
129
+ ENV/
130
+ env.bak/
131
+ venv.bak/
132
+
133
+ # Spyder project settings
134
+ .spyderproject
135
+ .spyproject
136
+
137
+ # Rope project settings
138
+ .ropeproject
139
+
140
+ # mkdocs documentation
141
+ /site
142
+
143
+ # mypy
144
+ .mypy_cache/
145
+ .dmypy.json
146
+ dmypy.json
147
+
148
+ # Pyre type checker
149
+ .pyre/
150
+
151
+ # pytype static type analyzer
152
+ .pytype/
153
+
154
+ # Cython debug symbols
155
+ cython_debug/
156
+
157
+ # PyCharm
158
+ # JetBrains specific template is maintained in a separate JetBrains.gitignore that can
159
+ # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
160
+ # and can be added to the global gitignore or merged into this file. For a more nuclear
161
+ # option (not recommended) you can uncomment the following to ignore the entire idea folder.
162
+ #.idea/
@@ -0,0 +1,137 @@
1
+ default_language_version:
2
+ python: python3.12
3
+
4
+ #exclude:
5
+
6
+ repos:
7
+ - repo: https://github.com/pre-commit/pre-commit-hooks
8
+ rev: v5.0.0
9
+ hooks:
10
+ # list of supported hooks: https://pre-commit.com/hooks.html
11
+ - id: trailing-whitespace
12
+ - id: end-of-file-fixer
13
+ - id: check-docstring-first
14
+ - id: check-yaml
15
+ - id: debug-statements
16
+ - id: detect-private-key
17
+ - id: check-executables-have-shebangs
18
+ - id: check-toml
19
+ - id: check-case-conflict
20
+ - id: check-added-large-files
21
+ args: [--maxkb, "800"]
22
+
23
+ # python code formatting
24
+ - repo: https://github.com/psf/black
25
+ rev: 24.10.0
26
+ hooks:
27
+ - id: black
28
+ args: [--line-length, "110"]
29
+
30
+ # python import sorting
31
+ - repo: https://github.com/PyCQA/isort
32
+ rev: 5.13.2
33
+ hooks:
34
+ - id: isort
35
+ args: ["--profile", "black", "--filter-files", "-o", "wandb"]
36
+
37
+ - repo: https://github.com/PyCQA/autoflake
38
+ rev: v2.3.1
39
+ hooks:
40
+ - id: autoflake
41
+ args: [--in-place, --remove-all-unused-imports]
42
+
43
+ # python upgrading syntax to newer version
44
+ - repo: https://github.com/asottile/pyupgrade
45
+ rev: v3.19.0
46
+ hooks:
47
+ - id: pyupgrade
48
+ args: [--py311-plus]
49
+
50
+ # python docstring formatting
51
+ # - repo: https://github.com/myint/docformatter
52
+ # rev: v1.7.5
53
+ # hooks:
54
+ # - id: docformatter
55
+ # name: docformatter
56
+ # entry: docformatter
57
+ # language: python
58
+ # args: [--in-place, --wrap-summaries=110, --wrap-descriptions=110]
59
+ # files: \.py$
60
+
61
+ # python check (PEP8), programming errors and code complexity
62
+ - repo: https://github.com/PyCQA/flake8
63
+ rev: 7.1.1
64
+ hooks:
65
+ - id: flake8
66
+ args:
67
+ [
68
+ "--max-complexity=10",
69
+ "--extend-ignore",
70
+ "E402,E701,E251,E226,E302,W504,E704,E402,E401,C901,E203",
71
+ "--max-line-length=110",
72
+ "--exclude",
73
+ "logs/*,data/*",
74
+ "--per-file-ignores",
75
+ "__init__.py:F401",
76
+ ]
77
+
78
+ # yaml formatting
79
+ - repo: https://github.com/pre-commit/mirrors-prettier
80
+ rev: v4.0.0-alpha.8
81
+ hooks:
82
+ - id: prettier
83
+ types: [yaml]
84
+ exclude: "environment.yaml"
85
+
86
+ # shell scripts linter
87
+ - repo: https://github.com/shellcheck-py/shellcheck-py
88
+ rev: v0.10.0.1
89
+ hooks:
90
+ - id: shellcheck
91
+
92
+ # md formatting
93
+ - repo: https://github.com/executablebooks/mdformat
94
+ rev: 0.7.18
95
+ hooks:
96
+ - id: mdformat
97
+ args: ["--number"]
98
+ additional_dependencies:
99
+ - mdformat-gfm
100
+ - mdformat-tables
101
+ - mdformat_frontmatter
102
+ - mdformat-black
103
+ - mdformat-config
104
+ - mdformat-shfmt
105
+ - mdformat-mkdocs
106
+ - mdformat-toc
107
+ - mdformat-admon
108
+
109
+ # word spelling linter
110
+ - repo: https://github.com/codespell-project/codespell
111
+ rev: v2.3.0
112
+ hooks:
113
+ - id: codespell
114
+ args:
115
+ - --skip=logs/**,data/**,*.ipynb,*.bib,env.yml,env_cpu.yml,*.svg,poetry.lock
116
+ - --ignore-words-list=ehr,crate
117
+
118
+ # jupyter notebook cell output clearing
119
+ - repo: https://github.com/kynan/nbstripout
120
+ rev: 0.7.1
121
+ hooks:
122
+ - id: nbstripout
123
+
124
+ # jupyter notebook linting
125
+ - repo: https://github.com/nbQA-dev/nbQA
126
+ rev: 1.8.7
127
+ hooks:
128
+ - id: nbqa-black
129
+ args: ["--line-length=110"]
130
+ - id: nbqa-isort
131
+ args: ["--profile=black"]
132
+ - id: nbqa-flake8
133
+ args:
134
+ [
135
+ "--extend-ignore=E203,E402,E501,F401,F841",
136
+ "--exclude=logs/*,data/*",
137
+ ]
@@ -0,0 +1,175 @@
1
+ A template repository for a MEDS-Transforms powered extraction pipeline for a custom dataset. Once you have
2
+ customized the repository to your dataset (see instructions below), you will be able to run your extraction
3
+ pipeline with a few simple command-line commands, such as:
4
+
5
+ ```bash
6
+ pip install PACKAGE_NAME # you can do this locally or via PyPI
7
+ # Download your data or set download credentials
8
+ COMMAND_NAME root_output_dir=$ROOT_OUTPUT_DIR
9
+ ```
10
+
11
+ See the [MIMIC-IV MEDS Extraction ETL](https://github.com/rvandewater/MIMIC_IV_MEDS) for an end to end example!
12
+
13
+ ## How to use this repository
14
+
15
+ 1. Initialize a new repository using this template repository.
16
+ 2. Rename the directory after `src/` to the name of your package in python-friendly format (e.g.,
17
+ `MIMIC_IV_MEDS`).
18
+ 3. Customize the following code points:
19
+ - [`pyproject.toml`](#pyprojecttoml)
20
+ - [`src/.../__init__.py`](#srcinitpy)
21
+ - [`src/.../dataset.yaml`](#srcdatasetyaml)
22
+ - [`src/.../pre_MEDS.py`](#srcpre_medspy)
23
+ - [`src/.../event_configs.yaml`](#srcevent_configsyaml)
24
+ - [`README.md`](#readmemd)
25
+ - [`tests/e2e_demo_test.py`](#testse2e_demo_testpy)
26
+ 4. Customize the following external services:
27
+ - CodeCov
28
+ - PyPI
29
+
30
+ ### Code Points:
31
+
32
+ #### `pyproject.toml`
33
+
34
+ In the `pyproject.toml` file, you will need to update the following fields:
35
+
36
+ 1. Under `[project]`:
37
+ - `name = "ETL-MEDS"`: Update `ETL-MEDS` to the name of your package (e.g., `MIMIC-IV-MEDS`)
38
+ - `authors = [...]`: Update the author information to your name and email.
39
+ - `description = "..."`: Update the description to a brief description of your dataset.
40
+ - `dependencies = [...]`: Update the dependencies to include the necessary packages for your ETL pipeline
41
+ (if any additional packages are needed).
42
+ 2. Under `[project.scripts]`
43
+ - `MEDS_extract-sample_dataset = "INSPIRE_MEDS.__main__:main"`: Update `MEDS_extract-sample_dataset` to the
44
+ name of your command-line pipeline (e.g., `MIMIC-IV_extract`) and update `INSPIRE_MEDS` to the name of your
45
+ package that you would import in python (e.g., `MIMIC_IV_MEDS`). This will be the same as the directory
46
+ name between `src` and your actual code.
47
+ 3. Under `[project.urls]`
48
+ - `Homepage = "..."` Update the homepage to the URL of your GitHub repository.
49
+ - `Issues = "..."` Update the issues URL to the URL of your GitHub repository issues page.
50
+
51
+ #### `src/.../__init__.py`
52
+
53
+ In this file, you simply need to update the `__package_name__ = "INSPIRE_MEDS"` line to refer not to `INSPIRE_MEDS`
54
+ but to your new package import name (e.g., `MIMIC_IV_MEDS`)
55
+
56
+ #### `src/.../dataset.yaml`
57
+
58
+ In this file, you can add details about the dataset you are working with. This will be used to record metadata
59
+ about the dataset and to provide links from which the dataset can be downloaded. You'll need to modify:
60
+
61
+ 1. `dataset_name`: The name of the dataset.
62
+ 2. `raw_dataset_version`: The version this version of your pipeline is designed to work with.
63
+ 3. `urls`: This block contains the URLs from which the dataset can be downloaded. This field requires
64
+ additional commentary, explored below.
65
+
66
+ ##### URLs:
67
+
68
+ This field is an object and contains three sub-keys:
69
+
70
+ 1. `dataset`: The URLs for the full dataset.
71
+ 2. `demo`: The URLs for a smaller, open, demo version of the dataset.
72
+ 3. `common`: The URLs for shared metadata files or other shared resources.
73
+
74
+ Each of these sub-keys should be a list of either strings (plain URLs) or dictionaries containing the URL (in
75
+ the key `url`) and username and password authentication information (in the keys `username` and `password`).
76
+ Note that we _strongly_ recommend that you _do not_ include your username and password in the raw file.
77
+ Instead, leverage the OmegaConf resolvers to reference external environment variables or other secure methods
78
+ of storing this information. In the example in this repository, we include one URL with the following
79
+ configuration:
80
+
81
+ ```yaml
82
+ - url: EXAMPLE_CONTROLLED_URL
83
+ username: ${oc.env:DATASET_DOWNLOAD_USERNAME}
84
+ password: ${oc.env:DATASET_DOWNLOAD_PASSWORD}
85
+ ```
86
+
87
+ which would resolve to fill in the `username` and `password` from the environment variables
88
+ `DATASET_DOWNLOAD_USERNAME` and `DATASET_DOWNLOAD_PASSWORD`, respectively.
89
+
90
+ ###### What if my dataset doesn't support direct download/this style of downloading?
91
+
92
+ That's no problem! You can simply turn off downloading entirely by setting `do_download=False` in the
93
+ `configs/main.yaml` or on the command line when you run the pipeline and ensure that your data files are
94
+ manually downloaded and placed in the appropriate directory (the `raw_input_dir` in the `configs/main.yaml`).
95
+ If there is a technical issue with downloading the data through the format supported so far, you can also file
96
+ a [GitHub Issue](https://github.com/rvandewater/INSPIRE_MEDS_Template/issues) outlining your issue and we can
97
+ attempt to expand the supported libraries to cover your use case!
98
+
99
+ #### `pre_MEDS.py`
100
+
101
+ This script should be generally modified to include any "pre-MEDS" steps that are necessary to prepare the
102
+ dataset for MEDS-Transforms based extraction. Critically, these steps often include:
103
+
104
+ 1. De-compressing files or otherwise preparing the raw data for extraction at a technical level.
105
+ 2. Joining tables together so that all relevant rows include the unifying `subject_id`.
106
+ 3. Converting any offsets into timestamps.
107
+ 4. Any other modifications of interest.
108
+
109
+ See [MEDS-Transforms](TODO) for more documentation on the appropriate construction of the pre-MEDS script.
110
+
111
+ #### `event_configs.yaml`
112
+
113
+ This file is the configuration file for mapping the rows in your various raw data tables to MEDS events via
114
+ the MEDS-Transforms pipeline. See [MEDS-Transforms](TODO) for more documentation on the format and usage of
115
+ this file.
116
+
117
+ #### `README.md`
118
+
119
+ Insert badges like below:
120
+
121
+ ```markdown
122
+ [![PyPI - Version](https://img.shields.io/pypi/v/PACKAGE_NAME)](https://pypi.org/project/PACKAGE_NAME/)
123
+ [![Documentation Status](https://readthedocs.org/projects/REPO_NAME/badge/?version=latest)](https://REPO_NAME.readthedocs.io/en/stable/?badge=stable)
124
+ [![codecov](https://codecov.io/gh/rvandewater/REPO_NAME/graph/badge.svg?token=REPO_TOKEN)](https://codecov.io/gh/rvandewater/REPO_NAME)
125
+ [![tests](https://github.com/rvandewater/REPO_NAME/actions/workflows/tests.yaml/badge.svg)](https://github.com/rvandewater/REPO_NAME/actions/workflows/tests.yml)
126
+ [![code-quality](https://github.com/rvandewater/REPO_NAME/actions/workflows/code-quality-main.yaml/badge.svg)](https://github.com/rvandewater/REPO_NAME/actions/workflows/code-quality-main.yaml)
127
+ ![python](https://img.shields.io/badge/-Python_3.12-blue?logo=python&logoColor=white)
128
+ [![license](https://img.shields.io/badge/License-MIT-green.svg?labelColor=gray)](https://github.com/rvandewater/REPO_NAME#license)
129
+ [![PRs](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](https://github.com/rvandewater/REPO_NAME/pulls)
130
+ [![contributors](https://img.shields.io/github/contributors/rvandewater/REPO_NAME.svg)](https://github.com/rvandewater/REPO_NAME/graphs/contributors)
131
+ ```
132
+
133
+ #### `tests/e2e_demo_test.py`
134
+
135
+ If your dataset does not have an open demo version, you can remove this file, as there is no way to set up
136
+ automated testing of the end-to-end pipeline in a safe manner without a demo dataset.
137
+
138
+ If you do have a demo dataset, ensure that it is included in your `dataset.yaml` file and update the
139
+ `e2e_demo_test.py` file as follows:
140
+
141
+ 1. Update the command in the `command_parts` variable to match the command you set in your `pyproject.toml`
142
+ file for the executable for your pipeline (e.g., `MIMIC-IV_extract`).
143
+ 2. Remove the `pytest.mark.skip` decorator from the test function so that it runs successfully!
144
+
145
+ The test file (and the internal doctests, which can help unittest your `pre-MEDS` file) can then be run via
146
+ `pytest --doctest-modules -s` from the root directory to ensure correctness of your pipeline. These tests will
147
+ also be run on pull requests or pushes to the `main` branch of your repository via GitHub Actions, and test
148
+ code coverage will be tracked via CodeCov.
149
+
150
+ ### External Services
151
+
152
+ #### CodeCov
153
+
154
+ 1. Go to [CodeCov](https://codecov.io/) and add make an account or log-in as needed.
155
+ 2. Follow the instructions to configure your new repository with CodeCov.
156
+ 3. Copy the badge markdown from CodeCov and paste it into the `README.md` file. To find the badge markdown
157
+ link, go to your repository in CodeCov, click on the "Configuration" tab, click on the "Badges and
158
+ Graphs" option, then copy the markdown link from the top section and paste it in the corresponding line
159
+ of the README, in place of the default link included above.
160
+ 4. It will now track the test coverage of your ETL, including running the full pipeline against the linked
161
+ demo data you provide in `dataset.yaml`.
162
+
163
+ #### PyPI
164
+
165
+ 1. Go to [PyPI](https://pypi.org/) and add make an account or log-in as needed.
166
+ 2. Go to your account settings and go to the "Publishing" settings.
167
+ 3. Set up a new "Trusted Publisher" for your GitHub Repository (e.g., see the image below). Ensure your
168
+ package name matches in the trusted publisher and in your `pyproject.toml` file!
169
+ 4. Now, if, on the local command line, you run `git tag 0.0.1`, then `git push origin 0.0.1`, it will push a
170
+ new, tagged version of your code as of the local commit when you ran the command both to a new GitHub
171
+ Release and to PyPI. This will allow you to install your package via `pip install PACKAGE_NAME` and to manage
172
+ versions effectively!
173
+
174
+ Example trusted publisher set-up:
175
+ ![PyPI Trusted Publisher](https://github.com/rvandewater/INSPIRE_MEDS_Template/blob/main/static/pypi_trusted_publisher_example.png?raw=true)