First version

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,4 @@
+<!---
+Thank you for your soon-to-be pull request. Before you submit this, please
+double check to make sure that you've added an entry to CHANGELOG.md.
+-->

.github/workflows/lint.yml

@@ -0,0 +1,15 @@
+name: Ruff
+on: [push, pull_request]
+jobs:
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v4
+      - name: Install Poetry
+        uses: snok/install-poetry@v1
+      - name: Install nox
+        run: pip install nox
+      - name: Run ruff linter via nox session
+        run: nox -s lint

.github/workflows/python-package.yml

@@ -0,0 +1,32 @@
+# This workflow will install Python dependencies, run tests with a range of Python versions
+
+name: tests
+
+on: [push, pull_request]
+
+jobs:
+  tests:
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        python-version: [
+          '3.8',
+          '3.9',
+          '3.10',
+          '3.11',
+          '3.12',
+        ]
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install Poetry
+      uses: snok/install-poetry@v1
+    - name: Install package and dependencies
+      run: poetry install
+    - name: Test with pytest
+      run: poetry run pytest -vs

.pre-commit-config.yaml

@@ -0,0 +1,19 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.3.2
+    hooks:
+      # Run the linter.
+      - id: ruff
+        args: [ --fix ]
+      # Run the formatter.
+      - id: ruff-format

CHANGELOG.md

@@ -0,0 +1,4 @@
+# Changelog
+
+## v0.1.0
+First release.

README.md

@@ -0,0 +1,45 @@
+# omop-cdm
+
+Python SQLAlchemy table definitions of the [OHDSI OMOP CDM](https://ohdsi.github.io/CommonDataModel/).
+
+## Installation
+
+omop-cdm requires Python >= 3.8.
+
+Install from PyPI:
+```shell
+pip install omop-cdm
+```
+
+## Usage
+
+See [User documentation](docs/README.md)
+
+## Supported databases
+The omop-cdm table definitions are tested to be compatible with PostgreSQL.
+
+Though not officially supported, omop-cdm doesn't use postgres-specific features
+of SQLAlchemy, so it can likely be used for other database types as well.
+
+## CDM versions
+omop-cdm contains table defintions for the following CDM versions:
+- CDM 5.4
+- CDM 5.3.1
+- CDM 6.0.0 ([not recommended](https://ohdsi.github.io/CommonDataModel/cdm60.html#NOTE_ABOUT_CDM_v60))
+
+## Development
+
+### Setup steps
+
+- Make sure [Poetry](https://python-poetry.org/docs/#installation) is installed.
+- Install the project and dependencies via `poetry install`.
+- Set up the pre-commit hook scripts via `poetry run pre-commit install`.
+
+### Nox sessions
+
+Several developer actions (e.g. run tests, code format, lint) are available
+via [nox](https://nox.thea.codes/en/stable/) sessions.
+For a complete list, run:
+```shell
+nox --list
+```

noxfile.py

@@ -0,0 +1,47 @@
+import nox  # type: ignore
+
+nox.options.sessions = [
+    "tests",
+    "lint",
+]
+
+python = [
+    "3.8",
+    "3.9",
+    "3.10",
+    "3.11",
+    "3.12",
+]
+
+
+@nox.session(python=python)
+def tests(session: nox.Session):
+    """Run test suite."""
+    session.run("poetry", "install", external=True)
+    session.run("pytest", "--cov=src")
+    session.notify("coverage")
+
+
+@nox.session
+def coverage(session: nox.Session):
+    """Generate pytest code coverage report."""
+    session.run("coverage", "report", "--show-missing")
+
+
+@nox.session(reuse_venv=True, name="format")
+def format_all(session: nox.Session):
+    """Format codebase with ruff."""
+    session.run("poetry", "install", "--only", "dev", external=True)
+    session.run("ruff", "format")
+    # format imports according to isort via ruff check
+    session.run("ruff", "check", "--select", "I", "--fix")
+
+
+@nox.session(reuse_venv=True)
+def lint(session: nox.Session):
+    """Run ruff linter."""
+    session.run("poetry", "install", "--only", "dev", external=True)
+    # Run the ruff linter
+    session.run("ruff", "check")
+    # Check if any code requires formatting via ruff format
+    session.run("ruff", "format", "--diff")

pyproject.toml

@@ -0,0 +1,35 @@
+[tool.poetry]
+name = "omop-cdm"
+version = "0.1.0"
+description = "SQLAlchemy ORM of the OHDSI OMOP CDM"
+authors = [
+    "Spayralbe <[email protected]>",
+]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.8"
+sqlalchemy = "^2.0.4"
+
+
+[tool.poetry.group.dev.dependencies]
+nox = "^2024.3.2"
+ruff = "^0.3.2"
+pre-commit = "^3.5.0"
+
+[tool.poetry.group.test.dependencies]
+pytest = "^8.1.1"
+pytest-cov = "^4.1.0"
+testcontainers = {version = ">=3.7.1", extras = ["postgres"]}
+psycopg2-binary = "^2.9.9"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+
+[tool.pytest.ini_options]
+addopts = "--import-mode=importlib"
+pythonpath = [
+    ".",
+]

ruff.toml

@@ -0,0 +1,38 @@
+src = ["src", "."]
+
+[lint]
+select = [
+    # pycodestyle
+    "E", "W",
+    # Pyflakes
+    "F",
+    # pyupgrade
+    "UP",
+    # flake8-bugbear
+    "B",
+    # flake8-simplify
+    "SIM",
+    # flake8-builtins
+    "A",
+    # flake8-return
+    "RET",
+    # flake8-pytest-style
+    "PT",
+    # flake8-use-pathlib
+    "PTH",
+    # flake8-self
+    "SLF",
+    # flake8-comprehensions
+    "C4",
+    # Ruff-specific rules
+    "RUF",
+    # isort
+    "I",
+]
+
+[lint.isort]
+known-first-party = ["omop_cdm"]
+
+# Ignore import violations in all `__init__.py` files
+[lint.per-file-ignores]
+"__init__.py" = ["E402", "F401"]

src/omop_cdm/__init__.py

@@ -0,0 +1 @@
+from omop_cdm.constants import NAMING_CONVENTION

src/omop_cdm/constants.py

@@ -0,0 +1,33 @@
+"""Module containing the placeholder schema names as used in the ORM."""
+
+# These are the placeholder schema names as used in the ORM table
+# definitions. They will be replaced with actual schema names at runtime
+# by providing a schema_translate_map to your SQLAlchemy engine.
+VOCAB_SCHEMA = "vocabulary_schema"
+CDM_SCHEMA = "cdm_schema"
+
+# Some often used foreign keys are added as variables for convenience.
+FK_CONCEPT_ID = f"{VOCAB_SCHEMA}.concept.concept_id"
+FK_VOCABULARY_ID = f"{VOCAB_SCHEMA}.vocabulary.vocabulary_id"
+FK_DOMAIN_ID = f"{VOCAB_SCHEMA}.domain.domain_id"
+FK_CONCEPT_CLASS_ID = f"{VOCAB_SCHEMA}.concept_class.concept_class_id"
+FK_PERSON_ID = f"{CDM_SCHEMA}.person.person_id"
+FK_VISIT_OCCURRENCE_ID = f"{CDM_SCHEMA}.visit_occurrence.visit_occurrence_id"
+FK_VISIT_DETAIL_ID = f"{CDM_SCHEMA}.visit_detail.visit_detail_id"
+FK_PROVIDER_ID = f"{CDM_SCHEMA}.provider.provider_id"
+FK_CARE_SITE_ID = f"{CDM_SCHEMA}.care_site.care_site_id"
+FK_LOCATION_ID = f"{CDM_SCHEMA}.location.location_id"
+
+# This object should be used to set the naming_convention parameter of
+# the SQLAlchemy MetaData object. Using it makes sure that the naming of
+# constraints and indexes is deterministic and not left up to the DBMS.
+# It's also needed when dropping these, as SQLAlchemy requires that
+# they have a name for them to be dropped. See:
+# https://docs.sqlalchemy.org/en/20/core/constraints.html#configuring-constraint-naming-conventions
+NAMING_CONVENTION = {
+    "ix": "ix_%(table_name)s_%(column_0_N_name)s",
+    "uq": "uq_%(table_name)s_%(column_0_name)s",
+    "ck": "ck_%(table_name)s_%(constraint_name)s",
+    "fk": "fk_%(table_name)s_%(column_0_name)s_%(referred_table_name)s",
+    "pk": "pk_%(table_name)s",
+}

src/omop_cdm/dynamic/cdm531/__init__.py

@@ -0,0 +1,79 @@
+"""
+OMOP CDM Version 5.3.1.
+
+Generated from OMOP CDM release 5.3.1 using sqlacodegen 3.0.0rc5.
+DDL from https://github.com/OHDSI/CommonDataModel/tree/v5.3.1.
+
+
+
+Deviations from standard model
+
+Removed
+
+attribute_definition
+cohort_attribute
+
+
+Added
+
+stem_table
+source_to_concept_map_version
+
+
+Updated
+
+source_to_concept_map
+    source_code from VARCHAR(50) --> VARCHAR(1000)
+    If using a separate vocab schema, STCM is created in the CDM schema
+
+"""
+
+from omop_cdm.dynamic.cdm531.clinical_data import (
+    BaseConditionOccurrenceCdm531,
+    BaseDeathCdm531,
+    BaseDeviceExposureCdm531,
+    BaseDrugExposureCdm531,
+    BaseFactRelationshipCdm531,
+    BaseMeasurementCdm531,
+    BaseNoteCdm531,
+    BaseNoteNlpCdm531,
+    BaseObservationCdm531,
+    BaseObservationPeriodCdm531,
+    BasePersonCdm531,
+    BaseProcedureOccurrenceCdm531,
+    BaseSpecimenCdm531,
+    BaseStemTableCdm531,
+    BaseVisitDetailCdm531,
+    BaseVisitOccurrenceCdm531,
+)
+from omop_cdm.dynamic.cdm531.derived_elements import (
+    BaseConditionEraCdm531,
+    BaseDoseEraCdm531,
+    BaseDrugEraCdm531,
+)
+from omop_cdm.dynamic.cdm531.health_economics import (
+    BaseCostCdm531,
+    BasePayerPlanPeriodCdm531,
+)
+from omop_cdm.dynamic.cdm531.health_system_data import (
+    BaseCareSiteCdm531,
+    BaseLocationCdm531,
+    BaseProviderCdm531,
+)
+from omop_cdm.dynamic.cdm531.metadata import (
+    BaseCdmSourceCdm531,
+    BaseMetadataCdm531,
+)
+from omop_cdm.dynamic.cdm531.vocabularies import (
+    BaseConceptAncestorCdm531,
+    BaseConceptCdm531,
+    BaseConceptClassCdm531,
+    BaseConceptRelationshipCdm531,
+    BaseConceptSynonymCdm531,
+    BaseDomainCdm531,
+    BaseDrugStrengthCdm531,
+    BaseRelationshipCdm531,
+    BaseSourceToConceptMapCdm531,
+    BaseSourceToConceptMapVersionCdm531,
+    BaseVocabularyCdm531,
+)