first commit

.github/conda/build.sh

@@ -0,0 +1 @@
+$PYTHON setup.py install --single-version-externally-managed --record=record.txt

.github/conda/meta.yaml

@@ -0,0 +1,46 @@
+{% set name = "biofit" %}
+
+package:
+  name: "{{ name|lower }}"
+  version: "{{ BIOFIT_VERSION }}"
+
+source:
+  path: ../../
+
+build:
+  noarch: python
+requirements:
+  host:
+    - python
+    - pip
+  run:
+    - python
+    - pip
+    - biocore
+    - filelock
+    - numpy >=1.17
+    - pyarrow >=8.0.0
+    - pyarrow-hotfix
+    - dill >=0.3.0,<0.3.8
+    - pandas
+    - requests >=2.19.0
+    - tqdm >=4.62.1
+    - xxhash
+    - multiprocess
+    - fsspec[http] >=2023.1.0,<=2023.10.0
+    - packaging
+    - pyyaml >=5.1
+    - scikit-learn >=1.4.0
+test:
+  imports:
+    - biofit
+about:
+  home: https://github.com/psmyth94/biofit
+  license: Apache-2.0
+  license_file: LICENSE
+  summary: A Python package for machine learning on omics datasets.
+  keywords:
+    - omics
+    - machine learning
+    - bioinformatics
+    - datasets

.github/workflows/ci_cd_pipeline.yml

@@ -0,0 +1,60 @@
+name: CI/CD Pipeline
+on:
+  push:
+    branches:
+      - main
+      - "ci-*"
+  pull_request:
+    branches:
+      - main
+jobs:
+  check_code_quality:
+    name: Check Code Quality
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - name: Set up Python 3.8
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.8"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[quality]
+      - name: Run Ruff code quality checks
+        run: |
+          ruff check tests src setup.py --output-format=github
+          ruff format --check tests src setup.py
+  tests:
+    needs: check_code_quality
+    strategy:
+      matrix:
+        test: [unit]
+        os: [ubuntu-latest, windows-latest]
+        python-version: ["3.8", "3.9", "3.10", "3.11"]
+    runs-on: ${{ matrix.os }}
+    continue-on-error: ${{ matrix.test == 'integration' }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install uv --upgrade
+          uv pip install --system "biofit[test] @ ."
+      - name: Run Tests
+        run: |
+          mkdir -p reports/${{ matrix.test }}_tests
+          python3 -m pytest -m ${{ matrix.test }} -n 2 --dist loadfile -sv ./tests/ --junitxml=reports/${{ matrix.test }}_tests/results.xml
+      - name: Upload Unit Test Results
+        uses: actions/upload-artifact@v3
+        with:
+          name: ${{ matrix.test }}-test-reports
+          path: reports/${{ matrix.test }}_tests/results.xml

.github/workflows/conda-release.yml

@@ -0,0 +1,36 @@
+name: Conda - Build
+on:
+  push:
+    tags:
+      - "[0-9]+.[0-9]+.[0-9]+*"
+env:
+  ANACONDA_API_TOKEN: ${{ secrets.ANACONDA_API_TOKEN }}
+jobs:
+  build_and_package:
+    runs-on: ubuntu-22.04
+    defaults:
+      run:
+        shell: bash -l {0}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - name: Install miniconda
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+          auto-update-conda: true
+          auto-activate-base: false
+          activate-environment: "build-biofit"
+          python-version: 3.8
+          channels: patrico49
+      - name: Setup conda env
+        run: |
+          conda install -c defaults anaconda-client conda-build
+      - name: Extract version
+        run: echo "BIOFIT_VERSION=`python setup.py --version`" >> $GITHUB_ENV
+      - name: Build conda packages
+        run: |
+          conda info
+          conda build .github/conda
+      - name: Upload to Anaconda
+        run: |
+          anaconda upload `conda build .github/conda --output -c conda-forge` --force

.github/workflows/pypi-release.yml

@@ -0,0 +1,35 @@
+name: PyPI - Release
+on:
+  push:
+    tags:
+      - "[0-9]+.[0-9]+.[0-9]+*"
+env:
+  PYPI_API_TOKEN: ${{ secrets.PYPI_API_TOKEN }}
+jobs:
+  build_and_publish:
+    runs-on: ubuntu-22.04
+    defaults:
+      run:
+        shell: bash -l {0}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.8
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install setuptools wheel twine
+      - name: Extract version
+        run: echo "BIOFIT_VERSION=$(python setup.py --version)" >> $GITHUB_ENV
+      - name: Build package
+        run: |
+          python setup.py sdist bdist_wheel
+      - name: Publish to PyPI
+        run: |
+          python -m twine upload dist/* --non-interactive
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}

.gitignore

@@ -0,0 +1,132 @@
+results/
+*.lock
+_dev
+# Ignore Nextflow-related files and directories
+.nextflow*
+work
+_dev/in_progress*
+.dev
+
+# Ignore data directory
+tests/data
+
+# anything not ipynb related
+tutorials/*
+!tutorials/*.ipynb
+
+
+# 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/
+*.egg-info/
+.installed.cfg
+*.egg
+.conda
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+cache*.arrow
+cache*.yaml
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+-checkpoint.ipynb
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+# According to https://pipenv.pypa.io/en/latest/advanced/#pipfile-vs-pipfilelock
+# PIPENV_VENV_IN_PROJECT=1
+Pipfile.lock
+
+# Poetry
+# https://python-poetry.org/docs/basic-usage/#configuring-poetry
+.poetry/
+
+# virtualenv
+venv/
+env/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# Idea project settings
+.idea/
+
+# PyCharm project settings
+.idea/
+
+# Visual Studio Code settings
+.vscode/
+.vs/
+
+# MyPy
+.mypy_cache/
+
+# pycodestyle
+.pytest_cache/
+
+#Docker
+*Dockerfile
+*dockerignore

.pre-commit-config.yaml

@@ -0,0 +1,9 @@
+repos:
+  - repo: https://github.com/charliermarsh/ruff-pre-commit # https://github.com/charliermarsh/ruff#usage
+    rev: 'v0.3.0'
+    hooks:
+      # Run the linter.
+      - id: ruff
+        args: [ --fix ]
+      # Run the formatter.
+      - id: ruff-format