Merge pull request #178 from centre-for-humanities-computing/mb/updat…

…e_repo_structure_for_v2

ci: update repo structure and CI/CD for v2

.devcontainer/devcontainer.json

@@ -0,0 +1,37 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the
+// README at: https://github.com/devcontainers/templates/tree/main/src/docker-existing-dockerfile
+{
+	"name": "Existing Dockerfile",
+	"build": {
+		// Sets the run context to one level up instead of the .devcontainer folder.
+		"context": "..",
+		// Update the 'dockerFile' property if you aren't using the standard 'Dockerfile' filename.
+		"dockerfile": "../Dockerfile.dev"
+	},
+	// "features": {},
+	"customizations": {
+		"vscode": {
+			"extensions": [
+				"GitHub.copilot",
+				"charliermarsh.ruff",
+				"ms-python.python",
+				"ms-python.vscode-pylance",
+				"ms-python.black-formatter",
+				"GitHub.vscode-pull-request-github"
+			]
+		}
+	},
+	"features": {
+		"ghcr.io/devcontainers/features/github-cli:1": {}
+	},
+	"postStartCommand": "make install"
+	// Features to add to the dev container. More info: https://containers.dev/features.
+	// "features": {},
+	// Use 'forwardPorts' to make a list of ports inside the container available locally.
+	// "forwardPorts": [],
+	// Uncomment the next line to run commands after the container is created.
+	// Configure tool-specific properties.
+	// "customizations": {},
+	// Uncomment to connect as an existing user other than the container default. More info: https://aka.ms/dev-containers-non-root.
+	// "remoteUser": "devcontainer"
+}

.dockerignore

@@ -0,0 +1,157 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# data files
+**/*.jsonl
+*.ndjson
+*.csv
+*.parquet
+src/applications/dataset_validation/intercoder_reliability.ipynb
+data/test/*
+*.parquet
+
+# MacOS
+.DS_Store
+
+# Profiling
+*.prof
+
+#wandb
+wandb/*
+models/*
+
+# RProg
+*.Rproj
+*.Rproj.user
+.Rproj.user
+.Rhistory
+
+# Hydra
+outputs/*

.github/workflows/lint-and-build-and-test.yml

@@ -0,0 +1,34 @@
+name: 'lint and build dev container' 
+on: # rebuild any PRs and main branch changes
+  pull_request:
+  push:
+    branches:
+      - main
+
+
+jobs:
+  build-and-test:
+    concurrency:
+      group: "${{ github.workflow }} @ ${{ github.ref }}"
+      cancel-in-progress: true
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout (GitHub)
+        uses: actions/checkout@v3
+
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v2 
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Pre-build dev container image
+        uses: devcontainers/[email protected]
+        with:
+          imageName: ghcr.io/centre-for-humanities-computing/danish-foundation-models-devcontainer
+          cacheFrom: ghcr.io/centre-for-humanities-computing/danish-foundation-models-devcontainer
+          push: filter
+          refFilterForPush: refs/heads/main
+          runCmd:
+            make validate

.pre-commit-config.yaml

@@ -1,13 +1,11 @@
 repos:
--   repo: https://github.com/psf/black
-    rev: 22.10.0
+  - repo: https://github.com/psf/black
+    rev: 23.9.1
     hooks:
-    - id: black
--   repo: https://github.com/PyCQA/isort
-    rev: 5.10.1
+      - id: black
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.1.0
     hooks:
-    -   id: isort
-# -   repo: https://gitlab.com/pycqa/flake8
-#     rev: 3.8.4
-#     hooks:
-#     - id: flake8
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]

.vscode/settings.json

@@ -0,0 +1,8 @@
+{
+    "python.analysis.typeCheckingMode": "strict",
+    "python.testing.pytestArgs": [
+        "src"
+    ],
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true,
+}

Dockerfile.dev

@@ -0,0 +1,13 @@
+FROM python:3.11-bullseye
+
+# Set the working directory to /app
+WORKDIR /app
+
+# Dev experience
+COPY makefile ./
+COPY pyproject.toml ./
+RUN make install
+
+# Install the app
+COPY . /app
+RUN pip install -e .

README.md

@@ -73,6 +73,17 @@ You can contribute both:
 -  Validation tasks can even be private benchmarks where you only wish to share the performance metrics.
 - And probably in many other ways
 
+## Setting up development environment
+### Method 1: Dev container
+By far the easiest way is to use our included development container. If you're using VSCode:
+
+* Ensure you have either [Orbstack](https://orbstack.dev) or [Docker](https://docker.com) installed 
+* Press this button: [![Open in Dev Container](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/centre-for-humanities-computing/danish-foundation-models/)
+* Select "From Dockerfile"
+* Press "OK" on the feature screen
+
+### Method 2: Manual install
+Install as you usually would, replicating the commands in the `Dockerfile.dev`.
 
 ## Current Contributors and Collaborators
 This project has collaborators across industry, national institutions and research centers. This project uses compute resources supplied by [Ucloud](https://docs.cloud.sdu.dk/index.html) through the [DeiC e-infrastructure grant](https://www.deic.dk/en/supercomputing/Apply-for-HPC-resources).