````markdown
# Federated GLM
[](https://pypi.org/project/federated-glm/)
[](LICENSE)
[](https://pypi.org/project/federated-glm/)
**Federated GLM** is a Python package for simulating **federated learning** with **generalized linear models (GLMs)**. It supports Gaussian, Binomial, and Poisson families, and allows flexible experimentation with elastic net regularization, client data partitioning, and convergence diagnostics.
---
## 🔧 Features
- Federated learning framework with `average` or `weighted` aggregation
- Supports **Gaussian**, **Binomial**, and **Poisson** GLM families
- Elastic Net, Lasso, and Ridge regularization (proximal updates)
- Utilities for synthetic data generation and partitioning across clients
- Model evaluation with R², RMSE, accuracy, Poisson deviance, etc.
- Examples for comparing centralized and federated learning
- Simple API and complete test coverage
---
## 📦 Installation
```bash
pip install git+https://github.com/mhmdamini/federated-glm.git
````
To install with development or example dependencies:
```bash
pip install "federated-glm[dev]"
pip install "federated-glm[examples]"
```
---
## 🛠 Quick Start
Here’s a minimal example using Gaussian regression:
```python
from federated_glm import PersonalizedFederatedGLM, FederatedLearningManager, DataGenerator, ModelEvaluator
# Generate synthetic data
X, y, family = DataGenerator.generate_glm_data("gaussian", n=200, p=3)
# Split train/test
X_train, X_test = X[:150], X[150:]
y_train, y_test = y[:150], y[150:]
# Partition data across clients
client_data = DataGenerator.partition_data(X_train, y_train, n_clients=3)
# Train a federated model
manager = FederatedLearningManager()
manager.fit(client_data, family, n_rounds=10)
# Predict and evaluate
y_pred = manager.predict(X_test, family)
metrics = ModelEvaluator.evaluate(y_test, y_pred, "gaussian")
print("R² Score:", metrics["r2_score"])
print("RMSE:", metrics["rmse"])
```
For personalized federated learning, it will be:
```python
pfed = PersonalizedFederatedGLM(method='pfedme')
pfed.fit(client_data, family, n_rounds=20)
```
Where method can be 'pfedme', 'perfedavg', and 'local_adaptation'.
---
## 📁 Project Structure
```
federated-glm/
├── federated_glm/ # Core package
│ ├── core.py # Federated GLM base class with proximal optimization
│ ├── federation.py # Federated learning manager
│ ├── evaluation.py # Model evaluation metrics
│ ├── utils.py # Data generation & partitioning utilities
│ └── __init__.py
│ └── personalized.py. # personalized federated learning
├── examples/ # Usage examples
│ └── basic_example.py
│ └── simple_example.py
│ └── personalized_example.py
├── tests/ # Unit and integration tests
│ └── test_basic.py
├── requirements.txt
├── setup.py
├── LICENSE
└── README.md
```
---
## 📈 Examples
Run the full demo script:
```bash
python examples/basic_example.py
```
This includes:
* Federated and personalized federated learning vs centralized performance comparison
* Convergence visualization
* Comparison of regularization strategies (ordinary, lasso, elastic net)
---
## ✅ Supported GLM Families
| Family | Link Function | Use Case |
| -------- | ------------- | -------------------------------- |
| Gaussian | Identity | Regression on continuous targets |
| Binomial | Logit | Binary classification |
| Poisson | Log | Count data modeling |
---
## 🧪 Testing
To run tests:
```bash
pip install "federated-glm[dev]"
pytest tests/
```
---
## 📚 Documentation
Documentation is available in the [GitHub README](https://github.com/mhmdamini/federated-glm#readme).
---
## 📜 License
This project is licensed under the [MIT License](LICENSE).
---
## 👨💻 Author
**Mohammad Amini**
Ph.D. Student at University of Florida
[m.amini@ufl.edu](mailto:m.amini@ufl.edu)
[GitHub: @mhmdamini](https://github.com/mhmdamini)
---
## 🙌 Acknowledgements
* Built on [StatsModels](https://www.statsmodels.org/) and [Scikit-learn](https://scikit-learn.org/)
* Inspired by research in federated learning, GLMs, and distributed optimization
---
## 📬 Contributing & Issues
Please open issues or submit pull requests via the [GitHub repository](https://github.com/mhmdamini/federated-glm).
We welcome contributions to:
* Support more GLM families (e.g., Negative Binomial, Gamma)
* Extend to real-world datasets
* Add differential privacy or secure aggregation
---
Raw data
{
"_id": null,
"home_page": "https://github.com/mhmdamini/federated-glm",
"name": "federated-glm",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "federated-learning, glm, machine-learning, statistics, personalization",
"author": "Mohammad Amini",
"author_email": "m.amini@ufl.edu",
"download_url": "https://files.pythonhosted.org/packages/9f/a0/bd534727cf94f761e1be818cca57c0fae0e0b8aef2a0ed1e71f26abd503e/federated_glm-0.2.0.tar.gz",
"platform": null,
"description": "````markdown\n# Federated GLM\n\n[](https://pypi.org/project/federated-glm/)\n[](LICENSE)\n[](https://pypi.org/project/federated-glm/)\n\n**Federated GLM** is a Python package for simulating **federated learning** with **generalized linear models (GLMs)**. It supports Gaussian, Binomial, and Poisson families, and allows flexible experimentation with elastic net regularization, client data partitioning, and convergence diagnostics.\n\n---\n\n## \ud83d\udd27 Features\n\n- Federated learning framework with `average` or `weighted` aggregation\n- Supports **Gaussian**, **Binomial**, and **Poisson** GLM families\n- Elastic Net, Lasso, and Ridge regularization (proximal updates)\n- Utilities for synthetic data generation and partitioning across clients\n- Model evaluation with R\u00b2, RMSE, accuracy, Poisson deviance, etc.\n- Examples for comparing centralized and federated learning\n- Simple API and complete test coverage\n\n---\n\n## \ud83d\udce6 Installation\n\n```bash\npip install git+https://github.com/mhmdamini/federated-glm.git\n````\n\nTo install with development or example dependencies:\n\n```bash\npip install \"federated-glm[dev]\"\npip install \"federated-glm[examples]\"\n```\n\n---\n\n## \ud83d\udee0 Quick Start\n\nHere\u2019s a minimal example using Gaussian regression:\n\n```python\nfrom federated_glm import PersonalizedFederatedGLM, FederatedLearningManager, DataGenerator, ModelEvaluator\n\n# Generate synthetic data\nX, y, family = DataGenerator.generate_glm_data(\"gaussian\", n=200, p=3)\n\n# Split train/test\nX_train, X_test = X[:150], X[150:]\ny_train, y_test = y[:150], y[150:]\n\n# Partition data across clients\nclient_data = DataGenerator.partition_data(X_train, y_train, n_clients=3)\n\n# Train a federated model\nmanager = FederatedLearningManager()\nmanager.fit(client_data, family, n_rounds=10)\n\n# Predict and evaluate\ny_pred = manager.predict(X_test, family)\nmetrics = ModelEvaluator.evaluate(y_test, y_pred, \"gaussian\")\n\nprint(\"R\u00b2 Score:\", metrics[\"r2_score\"])\nprint(\"RMSE:\", metrics[\"rmse\"])\n\n```\n\nFor personalized federated learning, it will be:\n\n```python\npfed = PersonalizedFederatedGLM(method='pfedme')\npfed.fit(client_data, family, n_rounds=20)\n```\nWhere method can be 'pfedme', 'perfedavg', and 'local_adaptation'.\n\n---\n\n## \ud83d\udcc1 Project Structure\n\n```\nfederated-glm/\n\u251c\u2500\u2500 federated_glm/ # Core package\n\u2502 \u251c\u2500\u2500 core.py # Federated GLM base class with proximal optimization\n\u2502 \u251c\u2500\u2500 federation.py # Federated learning manager\n\u2502 \u251c\u2500\u2500 evaluation.py # Model evaluation metrics\n\u2502 \u251c\u2500\u2500 utils.py # Data generation & partitioning utilities\n\u2502 \u2514\u2500\u2500 __init__.py\n\u2502 \u2514\u2500\u2500 personalized.py. # personalized federated learning\n\u251c\u2500\u2500 examples/ # Usage examples\n\u2502 \u2514\u2500\u2500 basic_example.py\n\u2502 \u2514\u2500\u2500 simple_example.py\n\u2502 \u2514\u2500\u2500 personalized_example.py\n\u251c\u2500\u2500 tests/ # Unit and integration tests\n\u2502 \u2514\u2500\u2500 test_basic.py\n\u251c\u2500\u2500 requirements.txt\n\u251c\u2500\u2500 setup.py\n\u251c\u2500\u2500 LICENSE\n\u2514\u2500\u2500 README.md\n```\n\n---\n\n## \ud83d\udcc8 Examples\n\nRun the full demo script:\n\n```bash\npython examples/basic_example.py\n```\n\nThis includes:\n\n* Federated and personalized federated learning vs centralized performance comparison\n* Convergence visualization\n* Comparison of regularization strategies (ordinary, lasso, elastic net)\n\n---\n\n## \u2705 Supported GLM Families\n\n| Family | Link Function | Use Case |\n| -------- | ------------- | -------------------------------- |\n| Gaussian | Identity | Regression on continuous targets |\n| Binomial | Logit | Binary classification |\n| Poisson | Log | Count data modeling |\n\n---\n\n## \ud83e\uddea Testing\n\nTo run tests:\n\n```bash\npip install \"federated-glm[dev]\"\npytest tests/\n```\n\n---\n\n## \ud83d\udcda Documentation\n\nDocumentation is available in the [GitHub README](https://github.com/mhmdamini/federated-glm#readme).\n\n---\n\n## \ud83d\udcdc License\n\nThis project is licensed under the [MIT License](LICENSE).\n\n---\n\n## \ud83d\udc68\u200d\ud83d\udcbb Author\n\n**Mohammad Amini**\nPh.D. Student at University of Florida\n[m.amini@ufl.edu](mailto:m.amini@ufl.edu)\n[GitHub: @mhmdamini](https://github.com/mhmdamini)\n\n---\n\n## \ud83d\ude4c Acknowledgements\n\n* Built on [StatsModels](https://www.statsmodels.org/) and [Scikit-learn](https://scikit-learn.org/)\n* Inspired by research in federated learning, GLMs, and distributed optimization\n\n---\n\n## \ud83d\udcec Contributing & Issues\n\nPlease open issues or submit pull requests via the [GitHub repository](https://github.com/mhmdamini/federated-glm).\n\nWe welcome contributions to:\n\n* Support more GLM families (e.g., Negative Binomial, Gamma)\n* Extend to real-world datasets\n* Add differential privacy or secure aggregation\n\n---\n",
"bugtrack_url": null,
"license": null,
"summary": "A library for federated learning and personalized federated learning with Generalized Linear Models",
"version": "0.2.0",
"project_urls": {
"Bug Reports": "https://github.com/mhmdamini/federated-glm/issues",
"Documentation": "https://github.com/mhmdamini/federated-glm#readme",
"Homepage": "https://github.com/mhmdamini/federated-glm",
"Source": "https://github.com/mhmdamini/federated-glm"
},
"split_keywords": [
"federated-learning",
" glm",
" machine-learning",
" statistics",
" personalization"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "7c32b4df39d1ac6f1a5fc6f3889f13d7e8a0f83565d296fc2f944b4ae875f387",
"md5": "c2b8d1bb599a6c067def73e620182681",
"sha256": "75620a747da54fef910e38b7402b608c874673e90a3ca00c4cfd56bc73a8e51f"
},
"downloads": -1,
"filename": "federated_glm-0.2.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c2b8d1bb599a6c067def73e620182681",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 11085,
"upload_time": "2025-07-13T10:58:36",
"upload_time_iso_8601": "2025-07-13T10:58:36.185044Z",
"url": "https://files.pythonhosted.org/packages/7c/32/b4df39d1ac6f1a5fc6f3889f13d7e8a0f83565d296fc2f944b4ae875f387/federated_glm-0.2.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "9fa0bd534727cf94f761e1be818cca57c0fae0e0b8aef2a0ed1e71f26abd503e",
"md5": "875ea7cef723f483d19459fd9a241d6c",
"sha256": "3beb8c97dabde7633b9e2989f871047f0d623ed47d5efff6f669a308b3d73b8e"
},
"downloads": -1,
"filename": "federated_glm-0.2.0.tar.gz",
"has_sig": false,
"md5_digest": "875ea7cef723f483d19459fd9a241d6c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 13324,
"upload_time": "2025-07-13T10:58:37",
"upload_time_iso_8601": "2025-07-13T10:58:37.158310Z",
"url": "https://files.pythonhosted.org/packages/9f/a0/bd534727cf94f761e1be818cca57c0fae0e0b8aef2a0ed1e71f26abd503e/federated_glm-0.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-13 10:58:37",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "mhmdamini",
"github_project": "federated-glm",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "numpy",
"specs": [
[
">=",
"1.21.0"
]
]
},
{
"name": "scipy",
"specs": [
[
">=",
"1.7.0"
]
]
},
{
"name": "statsmodels",
"specs": [
[
">=",
"0.13.0"
]
]
},
{
"name": "scikit-learn",
"specs": [
[
">=",
"1.0.0"
]
]
},
{
"name": "pandas",
"specs": [
[
">=",
"1.3.0"
]
]
}
],
"lcname": "federated-glm"
}
JSON
