federated-rsf 0.1.0__tar.gz

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

@@ -0,0 +1,38 @@
+name: Publish to PyPI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+  release:
+    types: [published]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - run: pip install -e ".[test]"
+      - run: pytest
+
+  publish:
+    needs: test
+    runs-on: ubuntu-latest
+    if: github.event_name == 'release' && github.event.action == 'published'
+    environment:
+      name: pypi
+      url: https://pypi.org/p/federated-rsf
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - run: pip install build
+      - run: python -m build
+      - uses: pypa/gh-action-pypi-publish@release/v1

federated_rsf-0.1.0/.gitignore

@@ -0,0 +1,209 @@
+*.pkl
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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
+
+# 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
+
+# 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
+
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# 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
+.envrc
+.venv
+env/
+venv/
+311env/
+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 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/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

federated_rsf-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Jonas H
+
+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.

federated_rsf-0.1.0/PKG-INFO

@@ -0,0 +1,204 @@
+Metadata-Version: 2.4
+Name: federated-rsf
+Version: 0.1.0
+Summary: Implementation of Federated Random Survival Forest for partially overlapping data.
+Author-email: Jonas Harriehausen <jonas.harriehausen@uni-giessen.de>
+License: MIT
+License-File: LICENSE
+Requires-Python: >=3.11
+Requires-Dist: joblib>=1.5.0
+Requires-Dist: numpy>=2.0.0
+Requires-Dist: pandas>=2.3.0
+Requires-Dist: scikit-learn>=1.8.0
+Requires-Dist: scikit-survival>=0.27.0
+Provides-Extra: dev
+Requires-Dist: jupyter; extra == 'dev'
+Requires-Dist: pytest-cov; extra == 'dev'
+Requires-Dist: pytest>=9.0.0; extra == 'dev'
+Provides-Extra: test
+Requires-Dist: pytest-cov; extra == 'test'
+Requires-Dist: pytest>=9.0.0; extra == 'test'
+Description-Content-Type: text/markdown
+
+# Federated Random Survival Forest for Partially overlapping Data
+
+federated-rsf is a python implementation of the Federated Random Survival Forest algorithm for partially overlapping data.
+
+## Overview
+
+Federated Random Survival Forest (federated-rsf) enables training
+random survival forest models across multiple institutions without sharing raw data.
+It is designed for partially overlapping feature spaces and privacy-sensitive
+biomedical datasets.
+
+## Features
+
+- Federated survival random forest training
+- Support for partially overlapping feature spaces
+- Compatible with scikit-survival data structures and evaluation methods
+- Privacy-preserving model aggregation
+
+
+## Installation
+
+### Dependencies
+
+federated-rsf requires:
+- numpy (>=2.0.0)
+- pandas (>=2.3.0)
+- scikit-learn(>=1.8.0)
+- scikit-survival (>=0.27.0)
+
+### User installation
+
+The easiest way to install federated-rsf is using pip
+```
+pip install -U federated-rsf
+```
+
+To install in editable mode, clone the repository and then install it using pip
+```bash
+git https://github.com/HauschildLab/FRSF4POD.git
+cd FRSF4POD
+pip install -U .
+```
+
+To install in editable mode it with optional testing or development libraries uses
+```bash
+pip install -U -e .[dev]
+```
+or
+```bash
+pip install -U -e .[test]
+```
+
+## Quick Start
+
+federated-rsf uses three main steps to train federated models.
+- First the local data schema of all the clients has to be unified into a global schema
+to facilitate the aggregation of models.
+- Second is the training of the local-rsf models on the local data
+- Third is the aggregation and distribution of the local estimators from the clients.
+
+
+```python
+from federated_rsf.models import (
+    FederatedRandomSurvivalForest,
+    LocalRandomSurvivalForest,
+)
+from federated_rsf.preprocessing import SchemaAligner, SchemaCreator
+from federated_rsf.testing import create_dummy_data, federate_data
+
+```
+
+In this example we create a dummy dataset using the testing module.
+This module can be used valiate the federated learning pipeline is case of missing access to the actual data.
+
+```python
+# Parameters
+n_samples = 500
+n_features = 10
+n_clients = 5
+random_state = 0
+
+# Create Dummy Dataset
+X, y = create_dummy_data(
+    n_samples,
+    n_features,
+    random_state=random_state,
+)
+
+# Split Dataset samples up to all clients
+X_list, y_list = federate_data(
+    X,
+    y,
+    n_clients,
+    drop_feature_percentage=0.33,
+    random_state=random_state,
+)
+```
+
+Next the columns of the local datasets are aligned to a global schema using the `SchemaCreator` and the local
+```python
+# Create global Schema
+schema_creator = SchemaCreator(anonymize=False)
+local_columns = [DatasetSchema(X_local.columns) for X_local in X_list]
+dataset_schemas = schema_creator.fit_transform(local_columns)
+
+# Align local datasets
+X_list_aligned = []
+
+for X_local, schema in zip(X_list, dataset_schemas):
+    schema_aligner = SchemaAligner()
+    X_aligned = schema_aligner.fit_transform(X_local, schema)
+    X_list_aligned.append(X_aligned)
+```
+
+The local models can then be trained on the processed local data.
+
+```python
+# Train local models
+local_models: list[LocalRandomSurvivalForest] = []
+
+for X_local, y_local in zip(X_list_aligned, y_list):
+    local_model = LocalRandomSurvivalForest(
+        random_state=random_state,
+    )
+    local_model = local_model.fit(X_local, y_local)
+    local_models.append(local_model)
+```
+
+The trained local models are then aggregated and the estimators are redistributed using the federated model.
+
+```python
+# Distribute trees between local models
+fed_model = FederatedRandomSurvivalForest(local_models=local_models)
+fed_model.distribute_trees()
+```
+
+Lastly you can compare the local and the federated model performance for example using the predict `predict_survival_function` and `predict_cumulative_hazard_function`
+
+
+```python
+# Example visualization of survival function and cumulative hazard function
+client_index = 0
+n_lines = 5
+
+survival_local = local_models[client_index].predict_survival_function(
+    X_list_aligned[client_index]
+)
+
+hazard_local = local_models[client_index].predict_cumulative_hazard_function(
+    X_list_aligned[client_index]
+)
+
+local_models[client_index].use_federated_estimators()
+
+survival_federated = local_models[client_index].predict_survival_function(
+    X_list_aligned[client_index]
+)
+
+hazard_federated = local_models[client_index].predict_cumulative_hazard_function(
+    X_list_aligned[client_index]
+)
+from matplotlib import pyplot as plt
+
+for surv in [survival_local, survival_federated]:
+    for i, s in enumerate(surv[:n_lines]):
+        plt.step(s.x, s.y, where="post", label=str(i))
+    plt.ylabel("Survival probability")
+    plt.xlabel("Time in days")
+    plt.legend()
+    plt.grid(True)
+    plt.show()
+
+
+for hazard in [hazard_local, hazard_federated]:
+    for i, s in enumerate(hazard[:n_lines]):
+        plt.step(s.x, s.y, where="post", label=str(i))
+    plt.ylabel("Cumulative hazard")
+    plt.xlabel("Time in days")
+    plt.legend()
+    plt.grid(True)
+    plt.show()
+```

federated_rsf-0.1.0/README.md

@@ -0,0 +1,182 @@
+# Federated Random Survival Forest for Partially overlapping Data
+
+federated-rsf is a python implementation of the Federated Random Survival Forest algorithm for partially overlapping data.
+
+## Overview
+
+Federated Random Survival Forest (federated-rsf) enables training
+random survival forest models across multiple institutions without sharing raw data.
+It is designed for partially overlapping feature spaces and privacy-sensitive
+biomedical datasets.
+
+## Features
+
+- Federated survival random forest training
+- Support for partially overlapping feature spaces
+- Compatible with scikit-survival data structures and evaluation methods
+- Privacy-preserving model aggregation
+
+
+## Installation
+
+### Dependencies
+
+federated-rsf requires:
+- numpy (>=2.0.0)
+- pandas (>=2.3.0)
+- scikit-learn(>=1.8.0)
+- scikit-survival (>=0.27.0)
+
+### User installation
+
+The easiest way to install federated-rsf is using pip
+```
+pip install -U federated-rsf
+```
+
+To install in editable mode, clone the repository and then install it using pip
+```bash
+git https://github.com/HauschildLab/FRSF4POD.git
+cd FRSF4POD
+pip install -U .
+```
+
+To install in editable mode it with optional testing or development libraries uses
+```bash
+pip install -U -e .[dev]
+```
+or
+```bash
+pip install -U -e .[test]
+```
+
+## Quick Start
+
+federated-rsf uses three main steps to train federated models.
+- First the local data schema of all the clients has to be unified into a global schema
+to facilitate the aggregation of models.
+- Second is the training of the local-rsf models on the local data
+- Third is the aggregation and distribution of the local estimators from the clients.
+
+
+```python
+from federated_rsf.models import (
+    FederatedRandomSurvivalForest,
+    LocalRandomSurvivalForest,
+)
+from federated_rsf.preprocessing import SchemaAligner, SchemaCreator
+from federated_rsf.testing import create_dummy_data, federate_data
+
+```
+
+In this example we create a dummy dataset using the testing module.
+This module can be used valiate the federated learning pipeline is case of missing access to the actual data.
+
+```python
+# Parameters
+n_samples = 500
+n_features = 10
+n_clients = 5
+random_state = 0
+
+# Create Dummy Dataset
+X, y = create_dummy_data(
+    n_samples,
+    n_features,
+    random_state=random_state,
+)
+
+# Split Dataset samples up to all clients
+X_list, y_list = federate_data(
+    X,
+    y,
+    n_clients,
+    drop_feature_percentage=0.33,
+    random_state=random_state,
+)
+```
+
+Next the columns of the local datasets are aligned to a global schema using the `SchemaCreator` and the local
+```python
+# Create global Schema
+schema_creator = SchemaCreator(anonymize=False)
+local_columns = [DatasetSchema(X_local.columns) for X_local in X_list]
+dataset_schemas = schema_creator.fit_transform(local_columns)
+
+# Align local datasets
+X_list_aligned = []
+
+for X_local, schema in zip(X_list, dataset_schemas):
+    schema_aligner = SchemaAligner()
+    X_aligned = schema_aligner.fit_transform(X_local, schema)
+    X_list_aligned.append(X_aligned)
+```
+
+The local models can then be trained on the processed local data.
+
+```python
+# Train local models
+local_models: list[LocalRandomSurvivalForest] = []
+
+for X_local, y_local in zip(X_list_aligned, y_list):
+    local_model = LocalRandomSurvivalForest(
+        random_state=random_state,
+    )
+    local_model = local_model.fit(X_local, y_local)
+    local_models.append(local_model)
+```
+
+The trained local models are then aggregated and the estimators are redistributed using the federated model.
+
+```python
+# Distribute trees between local models
+fed_model = FederatedRandomSurvivalForest(local_models=local_models)
+fed_model.distribute_trees()
+```
+
+Lastly you can compare the local and the federated model performance for example using the predict `predict_survival_function` and `predict_cumulative_hazard_function`
+
+
+```python
+# Example visualization of survival function and cumulative hazard function
+client_index = 0
+n_lines = 5
+
+survival_local = local_models[client_index].predict_survival_function(
+    X_list_aligned[client_index]
+)
+
+hazard_local = local_models[client_index].predict_cumulative_hazard_function(
+    X_list_aligned[client_index]
+)
+
+local_models[client_index].use_federated_estimators()
+
+survival_federated = local_models[client_index].predict_survival_function(
+    X_list_aligned[client_index]
+)
+
+hazard_federated = local_models[client_index].predict_cumulative_hazard_function(
+    X_list_aligned[client_index]
+)
+from matplotlib import pyplot as plt
+
+for surv in [survival_local, survival_federated]:
+    for i, s in enumerate(surv[:n_lines]):
+        plt.step(s.x, s.y, where="post", label=str(i))
+    plt.ylabel("Survival probability")
+    plt.xlabel("Time in days")
+    plt.legend()
+    plt.grid(True)
+    plt.show()
+
+
+for hazard in [hazard_local, hazard_federated]:
+    for i, s in enumerate(hazard[:n_lines]):
+        plt.step(s.x, s.y, where="post", label=str(i))
+    plt.ylabel("Cumulative hazard")
+    plt.xlabel("Time in days")
+    plt.legend()
+    plt.grid(True)
+    plt.show()
+```