bayesian-sparse-gmm 0.1.0__tar.gz

bayesian_sparse_gmm-0.1.0/.flake8

@@ -0,0 +1,10 @@
+[flake8]
+max-line-length = 120
+extend-ignore = E203, W503, E501
+exclude =
+    .git,
+    __pycache__,
+    build,
+    dist,
+    .venv,
+    venv

bayesian_sparse_gmm-0.1.0/.github/workflows/release.yml

@@ -0,0 +1,72 @@
+name: CI/CD Release
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  test:
+    name: Test and Lint
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+    steps:
+      - name: Checkout Source Code
+        uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "pip"
+
+      - name: Install Development Dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[dev]
+
+      - name: Run Lint Checks
+        run: |
+          black --check src tests
+          isort --check-only src tests
+          flake8 src tests
+
+      - name: Run Unit Tests
+        run: pytest
+
+  publish:
+    name: Publish to PyPI
+    needs: test
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+    steps:
+      - name: Checkout Source Code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+
+      - name: Install Build Tools
+        run: |
+          python -m pip install --upgrade pip
+          pip install build twine
+
+      - name: Build Source and Wheel Distributions
+        run: python -m build
+
+      - name: Validate Package Metadata
+        run: twine check dist/*
+
+      - name: Upload to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          skip-existing: true

bayesian_sparse_gmm-0.1.0/.gitignore

@@ -0,0 +1,145 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+bin/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script containing a list of
+#  files to include or exclude inside the final binary
+*.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/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+.ipython/
+
+# pyenv
+#   For a library or app, you might want to share your .python-version if you
+#   use pyenv. Uncomment if needed.
+#.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if the platform is not identical, it may cause dependency resolution issues.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#.pdm.toml
+#.pdm-plugins/
+#  pdm build uses __pdm__
+__pdm__
+
+# PEP 582; used by e.g. github.com/lincolnloop/layman and 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
+
+# mkdocs documentation
+/site/
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# Projects
+/visualize/
+# /tests/
+/docs/
+/.benchmarks/

bayesian_sparse_gmm-0.1.0/PKG-INFO

@@ -0,0 +1,108 @@
+Metadata-Version: 2.4
+Name: bayesian-sparse-gmm
+Version: 0.1.0
+Summary: Bayesian Sparse Gaussian Mixture Model implementation in Python
+Author-email: Nam Nam <nampvh4436@gmail.com>
+License: MIT
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Requires-Dist: numpy>=1.20.0
+Requires-Dist: scikit-learn>=1.0.0
+Requires-Dist: scipy>=1.7.0
+Requires-Dist: tqdm>=4.60.0
+Provides-Extra: dev
+Requires-Dist: black>=22.0.0; extra == 'dev'
+Requires-Dist: flake8>=4.0.0; extra == 'dev'
+Requires-Dist: isort>=5.10.0; extra == 'dev'
+Requires-Dist: matplotlib>=3.5.0; extra == 'dev'
+Requires-Dist: pytest>=7.0.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# Bayesian Sparse GMM
+
+Bayesian Sparse Gaussian Mixture Model (GMM) implementation in Python.
+
+This model employs a sparsity-inducing prior (e.g., a Dirichlet distribution with parameter $\alpha_0 < 1$) over mixture component weights to automatically determine/prune the number of active components.
+
+## Installation
+
+To install the latest release:
+
+```bash
+pip install bayesian-sparse-gmm
+```
+
+Or for development (editable mode):
+
+```bash
+git clone https://github.com/Coalyx/bayesian-sparse-gmm.git
+cd bayesian-sparse-gmm
+pip install -e .
+```
+
+## Quick Start
+
+```python
+import numpy as np
+from sklearn.datasets import make_blobs
+from sklearn.preprocessing import StandardScaler
+from bayesian_sparse_gmm import BayesianSparseGMM
+
+# Append noise dimensions to true clusters to verify that the model successfully performs feature selection.
+rng = np.random.default_rng(42)
+X_clean, _ = make_blobs(n_samples=200, centers=3, n_features=2, cluster_std=0.5, random_state=42)
+X_noise = rng.normal(loc=0.0, scale=1.0, size=(200, 8))
+X = np.hstack([X_clean, X_noise])
+
+# Standardize features to satisfy the zero-mean assumptions in the prior structure.
+X = StandardScaler().fit_transform(X)
+
+model = BayesianSparseGMM(
+    K_max=5,
+    n_iter=300,
+    burn_in=100,
+    lambda_0=10.0,
+    lambda_1=0.05,
+    random_state=42,
+    verbose=0
+)
+model.fit(X)
+
+print(f"Number of active clusters: {model.n_clusters_}")
+print(f"Selected informative features: {model.selected_features_}")
+print(f"Feature inclusion probabilities: {model.feature_probabilities_.round(3)}")
+
+labels = model.predict(X)
+```
+
+## Development and Testing
+
+Install development dependencies:
+
+```bash
+pip install -e ".[dev]"
+```
+
+Run tests using `pytest`:
+
+```bash
+pytest
+```
+
+## Reference
+
+```bib
+@article{JMLR:v26:23-0142,
+  author  = {Dapeng Yao and Fangzheng Xie and Yanxun Xu},
+  title   = {Bayesian Sparse Gaussian Mixture Model for Clustering in High Dimensions},
+  journal = {Journal of Machine Learning Research},
+  year    = {2025},
+  volume  = {26},
+  number  = {21},
+  pages   = {1--50},
+  url     = {http://jmlr.org/papers/v26/23-0142.html}
+}
+```

bayesian_sparse_gmm-0.1.0/README.md

@@ -0,0 +1,85 @@
+# Bayesian Sparse GMM
+
+Bayesian Sparse Gaussian Mixture Model (GMM) implementation in Python.
+
+This model employs a sparsity-inducing prior (e.g., a Dirichlet distribution with parameter $\alpha_0 < 1$) over mixture component weights to automatically determine/prune the number of active components.
+
+## Installation
+
+To install the latest release:
+
+```bash
+pip install bayesian-sparse-gmm
+```
+
+Or for development (editable mode):
+
+```bash
+git clone https://github.com/Coalyx/bayesian-sparse-gmm.git
+cd bayesian-sparse-gmm
+pip install -e .
+```
+
+## Quick Start
+
+```python
+import numpy as np
+from sklearn.datasets import make_blobs
+from sklearn.preprocessing import StandardScaler
+from bayesian_sparse_gmm import BayesianSparseGMM
+
+# Append noise dimensions to true clusters to verify that the model successfully performs feature selection.
+rng = np.random.default_rng(42)
+X_clean, _ = make_blobs(n_samples=200, centers=3, n_features=2, cluster_std=0.5, random_state=42)
+X_noise = rng.normal(loc=0.0, scale=1.0, size=(200, 8))
+X = np.hstack([X_clean, X_noise])
+
+# Standardize features to satisfy the zero-mean assumptions in the prior structure.
+X = StandardScaler().fit_transform(X)
+
+model = BayesianSparseGMM(
+    K_max=5,
+    n_iter=300,
+    burn_in=100,
+    lambda_0=10.0,
+    lambda_1=0.05,
+    random_state=42,
+    verbose=0
+)
+model.fit(X)
+
+print(f"Number of active clusters: {model.n_clusters_}")
+print(f"Selected informative features: {model.selected_features_}")
+print(f"Feature inclusion probabilities: {model.feature_probabilities_.round(3)}")
+
+labels = model.predict(X)
+```
+
+## Development and Testing
+
+Install development dependencies:
+
+```bash
+pip install -e ".[dev]"
+```
+
+Run tests using `pytest`:
+
+```bash
+pytest
+```
+
+## Reference
+
+```bib
+@article{JMLR:v26:23-0142,
+  author  = {Dapeng Yao and Fangzheng Xie and Yanxun Xu},
+  title   = {Bayesian Sparse Gaussian Mixture Model for Clustering in High Dimensions},
+  journal = {Journal of Machine Learning Research},
+  year    = {2025},
+  volume  = {26},
+  number  = {21},
+  pages   = {1--50},
+  url     = {http://jmlr.org/papers/v26/23-0142.html}
+}
+```