moose-fs 0.1.0__tar.gz

moose_fs-0.1.0/.github/workflows/doc.yml

@@ -0,0 +1,71 @@
+name: Documentation
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+concurrency:
+  group: docs-${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: write
+  pages: write
+  id-token: write
+
+jobs:
+  build_and_deploy:
+    name: Build Docs
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up uv and Python
+        uses: astral-sh/setup-uv@v3
+        with:
+          python-version: '3.11'
+
+      - name: Create project venv
+        run: uv venv --python 3.11
+
+      - name: Install docs dependencies
+        run: |
+          uv pip install -e . -e .[docs]
+          uv pip install build
+
+      - name: Ensure root directory is included in PYTHONPATH
+        run: |
+          export PYTHONPATH=$PYTHONPATH:$(pwd)
+          echo $PYTHONPATH
+
+      - name: Build package
+        run: uv run python -m build
+
+      - name: Clean build directory
+        run: |
+          rm -rf docs/build/* || true
+
+      - name: Build docs (sphinx)
+        if: ${{ hashFiles('docs/source/conf.py') != '' }}
+        run: |
+          export PYTHONPATH=$(pwd)
+          echo "Building docs with PYTHONPATH: $PYTHONPATH"
+          uv run sphinx-build -b html docs/source docs/build/html -v
+
+      - name: Deploy to GitHub Pages
+        if: ${{ hashFiles('docs/source/conf.py') != '' && github.event_name == 'push' }}
+        uses: peaceiris/actions-gh-pages@v3
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: ./docs/build/html
+
+      - name: Verify Imports
+        run: |
+          uv run python -c "import moosefs.core.pareto; print('moosefs.core.pareto imported successfully')"
+          uv run python -c "import moosefs.feature_selection_pipeline; print('moosefs.feature_selection_pipeline imported successfully')"

moose_fs-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,53 @@
+# This workflow builds the distribution and uploads to PyPI.
+
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+
+env:
+  PYTHON_VERSION: '3.11'
+
+permissions:
+  contents: write
+
+jobs:
+  build-and-publish:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up uv and Python 🐍
+        uses: astral-sh/setup-uv@v3
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - name: Create project venv
+        run: uv venv --python ${{ env.PYTHON_VERSION }}
+
+      - name: Install build tools
+        run: uv pip install -e . -e .[dev]
+
+      - name: Build binary wheel and source tarball 🔨
+        run: uv run python -m build
+
+      - name: Verify distribution
+        run: uv run twine check dist/*
+
+      - name: Show built artifacts
+        run: ls -l dist
+
+      - name: Upload built artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/*
+          retention-days: 7
+
+      - name: Publish distribution 📦 to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          password: ${{ secrets.PYPI_API_TOKEN }}

moose_fs-0.1.0/.github/workflows/tests.yml

@@ -0,0 +1,64 @@
+name: tests
+
+on:
+  push:
+    branches:
+      - main
+      - '**'
+  pull_request:
+
+concurrency:
+  group: tests-${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: [ '3.9', '3.10', '3.11', '3.12' ]
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up uv and Python
+        uses: astral-sh/setup-uv@v3
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Create project venv
+        run: uv venv --python ${{ matrix.python-version }}
+
+      - name: Install dev dependencies (editable)
+        run: uv pip install -e . -e .[dev]
+
+      - name: Verify imports
+        run: uv run python -c "import moosefs; print('import ok')"
+
+      - name: Ruff format check
+        run: uv run ruff format --check .
+
+      - name: Ruff lint
+        run: uv run ruff check --output-format=github .
+
+      - name: Run pytest
+        run: uv run pytest -q --maxfail=1 --disable-warnings
+
+      - name: Upload junit/coverage (if any)
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: test-artifacts-py${{ matrix.python-version }}
+          path: |
+            ./.pytest_cache/**
+            ./coverage.xml
+          if-no-files-found: ignore
+          retention-days: 7
+
+      - name: Build package
+        run: uv run python -m build
+
+      - name: Verify distribution
+        run: uv run twine check dist/*

moose_fs-0.1.0/.gitignore

@@ -0,0 +1,48 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+dist/
+*.egg-info/
+eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+
+# Virtual environments
+.venv/
+venv/
+ENV/
+env/
+
+# Test, coverage, and cache
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.coverage
+coverage.xml
+
+# IDE/editor settings
+.vscode/
+.idea/
+.history/
+
+# OS files
+.DS_Store
+
+# Project-specific
+results/
+tests/test_experiment/
+docs/build/
+uv.lock

moose_fs-0.1.0/.pre-commit-config.yaml

@@ -0,0 +1,6 @@
+repos:
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.14.2
+    hooks:
+    -   id: ruff
+    -   id: ruff-format

moose_fs-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 CI4CB-lab
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

moose_fs-0.1.0/PKG-INFO

@@ -0,0 +1,232 @@
+Metadata-Version: 2.4
+Name: moose-fs
+Version: 0.1.0
+Summary: MOOSE-FS: Multi-Objective Optimized Ensemble Feature Selection
+Project-URL: Repository, https://github.com/CI4CB-lab/moosefs
+Project-URL: Documentation, https://CI4CB-lab.github.io/moosefs/
+Author-email: Arthur Babey <arthur.babey@heig-vd.ch>
+License: MIT
+License-File: LICENSE
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.9
+Requires-Dist: joblib
+Requires-Dist: mrmr-selection
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: pyyaml
+Requires-Dist: ranky
+Requires-Dist: scikit-learn>=1.5.0
+Requires-Dist: scipy>=1.11
+Requires-Dist: xgboost
+Provides-Extra: dev
+Requires-Dist: build>=1; extra == 'dev'
+Requires-Dist: coverage[toml]; extra == 'dev'
+Requires-Dist: pre-commit; extra == 'dev'
+Requires-Dist: pytest>=7; extra == 'dev'
+Requires-Dist: ruff>=0.14.2; extra == 'dev'
+Requires-Dist: sphinx-autodoc-typehints; extra == 'dev'
+Requires-Dist: sphinx-rtd-theme; extra == 'dev'
+Requires-Dist: sphinx>=7; extra == 'dev'
+Requires-Dist: twine>=5; extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: sphinx-autodoc-typehints; extra == 'docs'
+Requires-Dist: sphinx-rtd-theme; extra == 'docs'
+Requires-Dist: sphinx>=7; extra == 'docs'
+Provides-Extra: test
+Requires-Dist: coverage[toml]; extra == 'test'
+Requires-Dist: pytest>=7; extra == 'test'
+Description-Content-Type: text/markdown
+
+# MOOSE-FS
+
+[![tests](https://github.com/CI4CB-lab/moosefs/actions/workflows/tests.yml/badge.svg)](https://github.com/CI4CB-lab/moosefs/actions/workflows/tests.yml)
+[Documentation](https://CI4CB-lab.github.io/moosefs/)
+
+## Overview
+
+MOOSE-FS is a feature selection library that leverages an ensemble-based approach to optimize both predictive performance and stability. By combining multiple feature selection methods, merging strategies, and evaluation metrics, it provides a highly flexible and tunable pipeline for both classification and regression tasks. The package automates feature selection across multiple iterations and uses Pareto optimization to identify the best feature subsets.
+
+Users can define their feature selection process by:
+- Selecting feature selection methods from predefined options or implementing custom ones.
+- Choosing merging strategies to aggregate feature rankings.
+- Specifying performance metrics to evaluate selected features.
+- Configuring the number of features to select and the number of repetitions.
+- Working with either **classification** or **regression** problems.
+
+The library allows defining feature selectors, merging strategies, and metrics either as **class instances** or as **string identifiers**, which act as placeholders for built-in methods. The framework is modular and can be easily extended by adding new selection algorithms or merging strategies.
+
+---
+
+## Requirements
+
+- **Python** 3.9 or higher
+- **Dependencies**: Automatically installed from `pyproject.toml`.
+
+---
+
+## Installation
+
+### From Source
+
+To install the package from source, run:
+
+```bash
+pip install git+https://github.com/CI4CB-lab/moosefs.git
+```
+
+Alternatively, clone the repository and install locally:
+
+```bash
+git clone https://github.com/CI4CB-lab/moosefs.git
+cd moosefs
+pip install .
+```
+
+---
+
+## Using the Library
+
+### 1. Feature Selection Pipeline
+
+The core of MOOSE-FS is the `FeatureSelectionPipeline`, which provides a fully configurable workflow for feature selection. Users can specify:
+- Feature selection methods
+- Merging strategy
+- Evaluation metrics
+- Task type (classification or regression)
+- Number of features to select
+- Number of repetitions
+
+#### Example Usage
+
+```python
+# `data` can be a single DataFrame (last column = target)
+# or you can pass `X` and `y` separately.
+# Assume `data` is a pandas DataFrame whose last column "label" holds the targets.
+from moosefs import FeatureSelectionPipeline
+
+fs_methods = ["f_statistic_selector", "random_forest_selector", "svm_selector"]
+merging_strategy = "union_of_intersections_merger"
+
+pipeline = FeatureSelectionPipeline(
+    X=data.drop(columns=["label"]),
+    y=data["label"],
+    fs_methods=fs_methods,
+    merging_strategy=merging_strategy,
+    num_repeats=5,
+    task="classification",
+    num_features_to_select=10,
+)
+results = pipeline.run()
+```
+
+This will run feature selection, merge results using the chosen strategy, and return the best-selected features.
+
+### 2. Extensibility
+
+MOOSE-FS is designed to be easily extended. Users can implement custom:
+- **Feature selection methods**: Define a new feature selector class and integrate it into the pipeline.
+- **Merging strategies**: Implement a custom strategy to aggregate selected features.
+- **Metrics**: Add new evaluation metrics tailored to specific tasks.
+
+New methods can be used directly in the pipeline by passing the class or a corresponding identifier.
+
+---
+
+## Using the CLI
+
+Once installed, the pipeline can also be run from the command line using:
+
+```bash
+efs-pipeline
+```
+
+This command executes `scripts/main.py` using parameters from `scripts/config.yaml`. Users can specify a different config file:
+
+```bash
+efs-pipeline path/to/your_config.yaml
+```
+
+### Example `config.yaml`
+
+```yaml
+experiment:
+  name: "example_experiment"
+  results_path: "results/"
+  data_path: "data/input_data.csv"
+
+preprocessing:
+  normalize: true
+  handle_missing: true
+
+pipeline:
+  fs_methods: ["f_statistic_selector", "random_forest_selector"]
+  merging_strategy: "union_of_intersections_merger"
+  num_repeats: 5
+  task: "classification"
+  num_features_to_select: 10
+```
+
+### Results
+
+The results are saved in a structured directory under `results/example_experiment/`, including:
+- A **text file** summarizing the pipeline run.
+- A **CSV file** containing the final results.
+
+---
+
+## Code Structure
+
+- **`core/`**: Core modules for data processing, metrics, and stability computation.
+- **`feature_selection_pipeline.py`**: Defines the main feature selection workflow.
+- **`feature_selectors/`**: Implements feature selection methods (e.g., F-statistic, mutual information, RandomForest, SVM).
+- **`merging_strategies/`**: Implements merging strategies such as Borda count and union of intersections.
+
+---
+
+## Contributing
+
+Contributions are welcome! If you have ideas for improving MOOSE-FS, feel free to open an issue or submit a pull request.
+
+### Development (uv)
+
+This project uses uv for local environments and dependency management. The library builds via the existing PEP 517 backend (hatchling); uv only manages the environment, installs, and command execution.
+
+- Install/select Python 3.9+ and ensure `uv` is installed.
+- Create a local virtual environment in `.venv`:
+
+```bash
+uv venv --python 3.9
+```
+
+- Install dev dependencies (editable):
+
+```bash
+uv pip install -e ".[dev]"
+```
+
+- Install pre-commit hooks:
+
+```bash
+uv run pre-commit install
+```
+
+- Run formatting and linting:
+
+```bash
+uv run ruff format .
+uv run ruff check --fix .
+```
+
+- Run tests:
+
+```bash
+uv run pytest -q
+```
+---
+
+## License
+
+This project is licensed under the MIT License.

moose_fs-0.1.0/README.md

@@ -0,0 +1,190 @@
+# MOOSE-FS
+
+[![tests](https://github.com/CI4CB-lab/moosefs/actions/workflows/tests.yml/badge.svg)](https://github.com/CI4CB-lab/moosefs/actions/workflows/tests.yml)
+[Documentation](https://CI4CB-lab.github.io/moosefs/)
+
+## Overview
+
+MOOSE-FS is a feature selection library that leverages an ensemble-based approach to optimize both predictive performance and stability. By combining multiple feature selection methods, merging strategies, and evaluation metrics, it provides a highly flexible and tunable pipeline for both classification and regression tasks. The package automates feature selection across multiple iterations and uses Pareto optimization to identify the best feature subsets.
+
+Users can define their feature selection process by:
+- Selecting feature selection methods from predefined options or implementing custom ones.
+- Choosing merging strategies to aggregate feature rankings.
+- Specifying performance metrics to evaluate selected features.
+- Configuring the number of features to select and the number of repetitions.
+- Working with either **classification** or **regression** problems.
+
+The library allows defining feature selectors, merging strategies, and metrics either as **class instances** or as **string identifiers**, which act as placeholders for built-in methods. The framework is modular and can be easily extended by adding new selection algorithms or merging strategies.
+
+---
+
+## Requirements
+
+- **Python** 3.9 or higher
+- **Dependencies**: Automatically installed from `pyproject.toml`.
+
+---
+
+## Installation
+
+### From Source
+
+To install the package from source, run:
+
+```bash
+pip install git+https://github.com/CI4CB-lab/moosefs.git
+```
+
+Alternatively, clone the repository and install locally:
+
+```bash
+git clone https://github.com/CI4CB-lab/moosefs.git
+cd moosefs
+pip install .
+```
+
+---
+
+## Using the Library
+
+### 1. Feature Selection Pipeline
+
+The core of MOOSE-FS is the `FeatureSelectionPipeline`, which provides a fully configurable workflow for feature selection. Users can specify:
+- Feature selection methods
+- Merging strategy
+- Evaluation metrics
+- Task type (classification or regression)
+- Number of features to select
+- Number of repetitions
+
+#### Example Usage
+
+```python
+# `data` can be a single DataFrame (last column = target)
+# or you can pass `X` and `y` separately.
+# Assume `data` is a pandas DataFrame whose last column "label" holds the targets.
+from moosefs import FeatureSelectionPipeline
+
+fs_methods = ["f_statistic_selector", "random_forest_selector", "svm_selector"]
+merging_strategy = "union_of_intersections_merger"
+
+pipeline = FeatureSelectionPipeline(
+    X=data.drop(columns=["label"]),
+    y=data["label"],
+    fs_methods=fs_methods,
+    merging_strategy=merging_strategy,
+    num_repeats=5,
+    task="classification",
+    num_features_to_select=10,
+)
+results = pipeline.run()
+```
+
+This will run feature selection, merge results using the chosen strategy, and return the best-selected features.
+
+### 2. Extensibility
+
+MOOSE-FS is designed to be easily extended. Users can implement custom:
+- **Feature selection methods**: Define a new feature selector class and integrate it into the pipeline.
+- **Merging strategies**: Implement a custom strategy to aggregate selected features.
+- **Metrics**: Add new evaluation metrics tailored to specific tasks.
+
+New methods can be used directly in the pipeline by passing the class or a corresponding identifier.
+
+---
+
+## Using the CLI
+
+Once installed, the pipeline can also be run from the command line using:
+
+```bash
+efs-pipeline
+```
+
+This command executes `scripts/main.py` using parameters from `scripts/config.yaml`. Users can specify a different config file:
+
+```bash
+efs-pipeline path/to/your_config.yaml
+```
+
+### Example `config.yaml`
+
+```yaml
+experiment:
+  name: "example_experiment"
+  results_path: "results/"
+  data_path: "data/input_data.csv"
+
+preprocessing:
+  normalize: true
+  handle_missing: true
+
+pipeline:
+  fs_methods: ["f_statistic_selector", "random_forest_selector"]
+  merging_strategy: "union_of_intersections_merger"
+  num_repeats: 5
+  task: "classification"
+  num_features_to_select: 10
+```
+
+### Results
+
+The results are saved in a structured directory under `results/example_experiment/`, including:
+- A **text file** summarizing the pipeline run.
+- A **CSV file** containing the final results.
+
+---
+
+## Code Structure
+
+- **`core/`**: Core modules for data processing, metrics, and stability computation.
+- **`feature_selection_pipeline.py`**: Defines the main feature selection workflow.
+- **`feature_selectors/`**: Implements feature selection methods (e.g., F-statistic, mutual information, RandomForest, SVM).
+- **`merging_strategies/`**: Implements merging strategies such as Borda count and union of intersections.
+
+---
+
+## Contributing
+
+Contributions are welcome! If you have ideas for improving MOOSE-FS, feel free to open an issue or submit a pull request.
+
+### Development (uv)
+
+This project uses uv for local environments and dependency management. The library builds via the existing PEP 517 backend (hatchling); uv only manages the environment, installs, and command execution.
+
+- Install/select Python 3.9+ and ensure `uv` is installed.
+- Create a local virtual environment in `.venv`:
+
+```bash
+uv venv --python 3.9
+```
+
+- Install dev dependencies (editable):
+
+```bash
+uv pip install -e ".[dev]"
+```
+
+- Install pre-commit hooks:
+
+```bash
+uv run pre-commit install
+```
+
+- Run formatting and linting:
+
+```bash
+uv run ruff format .
+uv run ruff check --fix .
+```
+
+- Run tests:
+
+```bash
+uv run pytest -q
+```
+---
+
+## License
+
+This project is licensed under the MIT License.