Pre public check

.github/workflows/ruff.yml

@@ -0,0 +1,21 @@
+# .github/workflows/ruff.yml
+name: Ruff Check
+
+on: [push, pull_request]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Install Python & Ruff
+        run: |
+          pip install ruff
+
+      - name: Lint
+        run: ruff check .
+
+      - name: Format check
+        run: ruff format --check .
+

.gitignore

@@ -1,160 +1,85 @@
-# Byte-compiled / optimized / DLL files
+# Customized utilities log files
+lohrasb.log
+
+# macOS system files
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# macOS folder attributes
+Icon?
+._*
+.Spotlight-V100
+.Trashes
+*.swp
+
+# Python bytecode
 __pycache__/
 *.py[cod]
 *$py.class
 
 # C extensions
 *.so
 
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
+# Virtual environments
+.venv/
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+.python-version
 
-# 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
+# Poetry local config
+poetry.toml
 
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
+# VS Code settings
+.vscode/
+
+# Jupyter and IPython
+.ipynb_checkpoints/
+profile_default/
+ipython_config.py
 
-# Unit test / coverage reports
-htmlcov/
+# Testing and coverage
+.coverage
+.cache/
+.pytest_cache/
 .tox/
 .nox/
-.coverage
-.coverage.*
-.cache
 nosetests.xml
 coverage.xml
 *.cover
 *.py,cover
 .hypothesis/
-.pytest_cache/
-cover/
 
-# Translations
-*.mo
-*.pot
+# Build artifacts
+build/
+dist/
+*.egg-info/
+.eggs/
+*.egg
+MANIFEST
 
-# Django stuff:
+# Logs and misc
 *.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .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
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/#use-with-ide
-.pdm.toml
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__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
+*.pot
+*.mo
+*.spec
+*.pyd
+*.pyo
 
-# mkdocs documentation
+# Site builds
 /site
 
-# mypy
+# Static analysis
 .mypy_cache/
 .dmypy.json
-dmypy.json
-
-# Pyre type checker
 .pyre/
-
-# pytype static type analyzer
 .pytype/
 
 # Cython debug symbols
 cython_debug/
 
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
+# Environment variables
+.env

.ruff.toml

@@ -0,0 +1,14 @@
+# .ruff.toml
+
+line-length = 120
+target-version = "py310"
+
+[lint]
+select = ["E", "F", "I", "B", "UP", "SIM"]
+ignore = ["F541"]
+
+[format]
+docstring-code-format = true
+
+[lint.per-file-ignores]
+"data/make_cardio_train_pickle.py" = ["UP009"]

Dockerfile

@@ -0,0 +1,22 @@
+# hash:sha256:6b212c24ad89ce60c5ad110a4239f9ecf823f2ab367e9fff719539640ecd4b5b
+FROM registry.codeocean.com/codeocean/py-r:python3.10.12-R4.3.2-JupyterLab4.0.10-RStudiorstudio-server-2023.12.0-369-ubuntu22.04
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+RUN pip3 install -U --no-cache-dir \
+    catboost==1.2.5 \
+    category-encoders==2.6.3 \
+    fasttreeshap==0.1.6 \
+    lightgbm==4.5.0 \
+    lohrasb==4.2.0 \
+    matplotlib==3.8.4 \
+    numpy==1.21.6 \
+    optuna-integration==3.6.0 \
+    pandas==1.3.5 \
+    ray==2.7.1 \
+    scikit-learn==1.0.2 \
+    seaborn \
+    shap==0.42.1 \
+    tune-sklearn==0.5.0 \
+    xgboost==2.1.1 \
+    zoish==5.0.4

Makefile

@@ -0,0 +1,9 @@
+# Makefile
+
+format:
+	ruff format .
+
+lint:
+	ruff check .
+
+check: format lint