gen-surv 1.2.0__tar.gz

gen_surv-1.2.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 [Diogo Ribeiro]
+
+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.

gen_surv-1.2.0/PKG-INFO

@@ -0,0 +1,192 @@
+Metadata-Version: 2.4
+Name: gen_surv
+Version: 1.2.0
+Summary: A Python package for simulating survival data, inspired by the R package genSurv
+License: MIT
+License-File: LICENSE
+Keywords: survival-analysis,simulation,cox-model,markov-model,time-dependent,statistics
+Author: Diogo Ribeiro
+Author-email: diogo.debastos.ribeiro@gmail.com
+Requires-Python: >=3.11,<3.14
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Healthcare Industry
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Mathematics
+Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
+Requires-Dist: click (>=8.3.0,<9.0.0)
+Requires-Dist: lifelines (>=0.30.3,<0.31.0)
+Requires-Dist: matplotlib (>=3.10.7,<4.0.0)
+Requires-Dist: numpy (>=2.3.3,<3.0.0)
+Requires-Dist: pandas (>=2.3.3,<3.0.0)
+Requires-Dist: pyarrow (>=21.0.0,<22.0.0)
+Requires-Dist: pyreadr (>=0.5.3,<0.6.0)
+Requires-Dist: typer (>=0.19.2,<0.20.0)
+Project-URL: Documentation, https://gensurvpy.readthedocs.io/en/latest/
+Project-URL: Homepage, https://github.com/DiogoRibeiro7/genSurvPy
+Project-URL: Repository, https://github.com/DiogoRibeiro7/genSurvPy
+Description-Content-Type: text/markdown
+
+# gen_surv
+
+[![Coverage][cov-badge]][cov-link]
+[![Docs][docs-badge]][docs-link]
+[![PyPI][pypi-badge]][pypi-link]
+[![Tests][ci-badge]][ci-link]
+[![Python][py-badge]][pypi-link]
+
+[cov-badge]: https://codecov.io/gh/DiogoRibeiro7/genSurvPy/branch/main/graph/badge.svg
+[cov-link]: https://app.codecov.io/gh/DiogoRibeiro7/genSurvPy
+[docs-badge]: https://readthedocs.org/projects/gensurvpy/badge/?version=latest
+[docs-link]: https://gensurvpy.readthedocs.io/en/latest/
+[pypi-badge]: https://img.shields.io/pypi/v/gen_surv
+[pypi-link]: https://pypi.org/project/gen-surv/
+[ci-badge]: https://github.com/DiogoRibeiro7/genSurvPy/actions/workflows/ci.yml/badge.svg
+[ci-link]: https://github.com/DiogoRibeiro7/genSurvPy/actions/workflows/ci.yml
+[py-badge]: https://img.shields.io/pypi/pyversions/gen_surv
+[![GitHub stars](https://img.shields.io/github/stars/diogoribeiro7/genSurvPy.svg?style=social)](https://github.com/diogoribeiro7/genSurvPy/stargazers)
+[![GitHub forks](https://img.shields.io/github/forks/diogoribeiro7/genSurvPy.svg?style=social)](https://github.com/diogoribeiro7/genSurvPy/network/members)
+
+**gen_surv** is a Python library for simulating survival data and producing visualizations under a wide range of statistical models. Inspired by the R package [genSurv](https://cran.r-project.org/package=genSurv), it offers a unified interface for generating realistic datasets for research, teaching and benchmarking.
+
+---
+
+## Features
+
+- Cox proportional hazards model (CPHM)
+- Accelerated failure time models (log-normal, log-logistic, Weibull)
+- Continuous-time multi-state Markov model (CMM)
+- Time-dependent covariate model (TDCM)
+- Time-homogeneous hidden Markov model (THMM)
+- Mixture cure and piecewise exponential models
+- Competing risks generators (constant and Weibull hazards)
+- Visualization helpers built on matplotlib and lifelines
+- Scikit-learn compatible data generator
+- Conversion utilities for scikit-survival
+- Command-line interface for dataset creation and visualization
+
+## Installation
+
+Requires Python 3.11 or later (tested on 3.11, 3.12 and 3.13).
+
+Install the latest release from PyPI:
+
+```bash
+pip install gen-surv
+```
+
+`gen_surv` installs matplotlib and lifelines for visualization. Support for scikit-survival is optional; install it to enable integration with the scikit-survival ecosystem or to run the full test suite:
+
+```bash
+pip install scikit-survival
+```
+
+To develop locally with all extras:
+
+```bash
+git clone https://github.com/DiogoRibeiro7/genSurvPy.git
+cd genSurvPy
+poetry install --with dev
+```
+
+On Debian/Ubuntu you may need `build-essential gfortran libopenblas-dev` to build scikit-survival.
+
+## Development
+
+Before committing changes, install the pre-commit hooks and run the tests:
+
+```bash
+pre-commit install
+pre-commit run --all-files
+pytest
+```
+
+Tests that depend on optional packages such as scikit-survival are skipped automatically when those packages are missing.
+
+## Usage
+
+### Python API
+
+```python
+from gen_surv import generate, export_dataset, to_sksurv
+from gen_surv.visualization import plot_survival_curve
+
+sim = generate(
+    model="cphm",
+    n=100,
+    beta=0.5,
+    covariate_range=2.0,
+    model_cens="uniform",
+    cens_par=1.0,
+)
+
+plot_survival_curve(sim)
+export_dataset(sim, "survival_data.rds")
+
+# convert for scikit-survival
+sks_dataset = to_sksurv(sim)
+```
+
+See the [usage guide](https://gensurvpy.readthedocs.io/en/latest/getting_started.html) for more examples.
+
+### Command Line
+
+Generate datasets and plots without writing Python code:
+
+```bash
+python -m gen_surv dataset cphm --n 1000 -o survival.csv
+
+python -m gen_surv visualize survival.csv --output survival_plot.png
+```
+
+`visualize` accepts custom column names via `--time-col` and `--status-col` and can stratify by group with `--group-col`.
+
+## Supported Models
+
+| Model | Description |
+|-------|-------------|
+| **CPHM** | Cox proportional hazards |
+| **AFT** | Accelerated failure time (log-normal, log-logistic, Weibull) |
+| **CMM** | Continuous-time multi-state Markov |
+| **TDCM** | Time-dependent covariates |
+| **THMM** | Time-homogeneous hidden Markov |
+| **Competing Risks** | Multiple event types with cause-specific hazards |
+| **Mixture Cure** | Models long-term survivors |
+| **Piecewise Exponential** | Flexible baseline hazard via intervals |
+
+More details on each algorithm are available in the [Algorithms](https://gensurvpy.readthedocs.io/en/latest/algorithms.html) page. For additional background, see the [theory guide](https://gensurvpy.readthedocs.io/en/latest/theory.html).
+
+## Documentation
+
+Full documentation is hosted on [Read the Docs](https://gensurvpy.readthedocs.io/en/latest/). It includes installation instructions, tutorials, API references and a bibliography.
+
+To build the docs locally:
+
+```bash
+cd docs
+make html
+```
+
+Open `build/html/index.html` in your browser to view the result.
+
+## License
+
+This project is licensed under the MIT License. See [LICENSE](LICENSE) for details.
+
+## Citation
+
+If you use **gen_surv** in your research, please cite the project using the metadata in [CITATION.cff](CITATION.cff).
+
+## Author
+
+**Diogo Ribeiro** — [ESMAD - Instituto Politécnico do Porto](https://esmad.ipp.pt)
+
+- ORCID: <https://orcid.org/0009-0001-2022-7072>
+- Professional email: <dfr@esmad.ipp.pt>
+- Personal email: <diogo.debastos.ribeiro@gmail.com>
+- GitHub: [@DiogoRibeiro7](https://github.com/DiogoRibeiro7)
+

gen_surv-1.2.0/README.md

@@ -0,0 +1,158 @@
+# gen_surv
+
+[![Coverage][cov-badge]][cov-link]
+[![Docs][docs-badge]][docs-link]
+[![PyPI][pypi-badge]][pypi-link]
+[![Tests][ci-badge]][ci-link]
+[![Python][py-badge]][pypi-link]
+
+[cov-badge]: https://codecov.io/gh/DiogoRibeiro7/genSurvPy/branch/main/graph/badge.svg
+[cov-link]: https://app.codecov.io/gh/DiogoRibeiro7/genSurvPy
+[docs-badge]: https://readthedocs.org/projects/gensurvpy/badge/?version=latest
+[docs-link]: https://gensurvpy.readthedocs.io/en/latest/
+[pypi-badge]: https://img.shields.io/pypi/v/gen_surv
+[pypi-link]: https://pypi.org/project/gen-surv/
+[ci-badge]: https://github.com/DiogoRibeiro7/genSurvPy/actions/workflows/ci.yml/badge.svg
+[ci-link]: https://github.com/DiogoRibeiro7/genSurvPy/actions/workflows/ci.yml
+[py-badge]: https://img.shields.io/pypi/pyversions/gen_surv
+[![GitHub stars](https://img.shields.io/github/stars/diogoribeiro7/genSurvPy.svg?style=social)](https://github.com/diogoribeiro7/genSurvPy/stargazers)
+[![GitHub forks](https://img.shields.io/github/forks/diogoribeiro7/genSurvPy.svg?style=social)](https://github.com/diogoribeiro7/genSurvPy/network/members)
+
+**gen_surv** is a Python library for simulating survival data and producing visualizations under a wide range of statistical models. Inspired by the R package [genSurv](https://cran.r-project.org/package=genSurv), it offers a unified interface for generating realistic datasets for research, teaching and benchmarking.
+
+---
+
+## Features
+
+- Cox proportional hazards model (CPHM)
+- Accelerated failure time models (log-normal, log-logistic, Weibull)
+- Continuous-time multi-state Markov model (CMM)
+- Time-dependent covariate model (TDCM)
+- Time-homogeneous hidden Markov model (THMM)
+- Mixture cure and piecewise exponential models
+- Competing risks generators (constant and Weibull hazards)
+- Visualization helpers built on matplotlib and lifelines
+- Scikit-learn compatible data generator
+- Conversion utilities for scikit-survival
+- Command-line interface for dataset creation and visualization
+
+## Installation
+
+Requires Python 3.11 or later (tested on 3.11, 3.12 and 3.13).
+
+Install the latest release from PyPI:
+
+```bash
+pip install gen-surv
+```
+
+`gen_surv` installs matplotlib and lifelines for visualization. Support for scikit-survival is optional; install it to enable integration with the scikit-survival ecosystem or to run the full test suite:
+
+```bash
+pip install scikit-survival
+```
+
+To develop locally with all extras:
+
+```bash
+git clone https://github.com/DiogoRibeiro7/genSurvPy.git
+cd genSurvPy
+poetry install --with dev
+```
+
+On Debian/Ubuntu you may need `build-essential gfortran libopenblas-dev` to build scikit-survival.
+
+## Development
+
+Before committing changes, install the pre-commit hooks and run the tests:
+
+```bash
+pre-commit install
+pre-commit run --all-files
+pytest
+```
+
+Tests that depend on optional packages such as scikit-survival are skipped automatically when those packages are missing.
+
+## Usage
+
+### Python API
+
+```python
+from gen_surv import generate, export_dataset, to_sksurv
+from gen_surv.visualization import plot_survival_curve
+
+sim = generate(
+    model="cphm",
+    n=100,
+    beta=0.5,
+    covariate_range=2.0,
+    model_cens="uniform",
+    cens_par=1.0,
+)
+
+plot_survival_curve(sim)
+export_dataset(sim, "survival_data.rds")
+
+# convert for scikit-survival
+sks_dataset = to_sksurv(sim)
+```
+
+See the [usage guide](https://gensurvpy.readthedocs.io/en/latest/getting_started.html) for more examples.
+
+### Command Line
+
+Generate datasets and plots without writing Python code:
+
+```bash
+python -m gen_surv dataset cphm --n 1000 -o survival.csv
+
+python -m gen_surv visualize survival.csv --output survival_plot.png
+```
+
+`visualize` accepts custom column names via `--time-col` and `--status-col` and can stratify by group with `--group-col`.
+
+## Supported Models
+
+| Model | Description |
+|-------|-------------|
+| **CPHM** | Cox proportional hazards |
+| **AFT** | Accelerated failure time (log-normal, log-logistic, Weibull) |
+| **CMM** | Continuous-time multi-state Markov |
+| **TDCM** | Time-dependent covariates |
+| **THMM** | Time-homogeneous hidden Markov |
+| **Competing Risks** | Multiple event types with cause-specific hazards |
+| **Mixture Cure** | Models long-term survivors |
+| **Piecewise Exponential** | Flexible baseline hazard via intervals |
+
+More details on each algorithm are available in the [Algorithms](https://gensurvpy.readthedocs.io/en/latest/algorithms.html) page. For additional background, see the [theory guide](https://gensurvpy.readthedocs.io/en/latest/theory.html).
+
+## Documentation
+
+Full documentation is hosted on [Read the Docs](https://gensurvpy.readthedocs.io/en/latest/). It includes installation instructions, tutorials, API references and a bibliography.
+
+To build the docs locally:
+
+```bash
+cd docs
+make html
+```
+
+Open `build/html/index.html` in your browser to view the result.
+
+## License
+
+This project is licensed under the MIT License. See [LICENSE](LICENSE) for details.
+
+## Citation
+
+If you use **gen_surv** in your research, please cite the project using the metadata in [CITATION.cff](CITATION.cff).
+
+## Author
+
+**Diogo Ribeiro** — [ESMAD - Instituto Politécnico do Porto](https://esmad.ipp.pt)
+
+- ORCID: <https://orcid.org/0009-0001-2022-7072>
+- Professional email: <dfr@esmad.ipp.pt>
+- Personal email: <diogo.debastos.ribeiro@gmail.com>
+- GitHub: [@DiogoRibeiro7](https://github.com/DiogoRibeiro7)

gen_surv-1.2.0/gen_surv/__init__.py

@@ -0,0 +1,104 @@
+"""Top-level package for ``gen_surv``.
+
+This module exposes the main functions and provides access to the package version.
+"""
+
+from importlib.metadata import PackageNotFoundError, version
+
+from .aft import gen_aft_log_logistic, gen_aft_log_normal, gen_aft_weibull
+from .bivariate import sample_bivariate_distribution
+from .censoring import (
+    CensoringModel,
+    GammaCensoring,
+    LogNormalCensoring,
+    WeibullCensoring,
+    rexpocens,
+    rgammacens,
+    rlognormcens,
+    runifcens,
+    rweibcens,
+)
+from .cmm import gen_cmm
+from .competing_risks import gen_competing_risks, gen_competing_risks_weibull
+from .cphm import gen_cphm
+from .export import export_dataset
+from .interface import generate
+from .mixture import cure_fraction_estimate, gen_mixture_cure
+from .piecewise import gen_piecewise_exponential
+from .sklearn_adapter import GenSurvDataGenerator
+from .tdcm import gen_tdcm
+from .thmm import gen_thmm
+
+# Get package version
+try:
+    __version__ = version("gen_surv")
+except PackageNotFoundError:  # pragma: no cover - fallback when package not installed
+    __version__ = "0.0.0"
+
+# Visualization tools (requires matplotlib and lifelines)
+try:
+    from .visualization import (  # noqa: F401
+        describe_survival,
+        plot_covariate_effect,
+        plot_hazard_comparison,
+        plot_survival_curve,
+    )
+
+    _has_visualization = True
+except ImportError:
+    _has_visualization = False
+
+# Optional scikit-survival integration
+try:
+    from .integration import from_sksurv, to_sksurv  # noqa: F401
+
+    _has_sksurv = True
+except ImportError:
+    _has_sksurv = False
+
+# Define exports
+__all__ = [
+    # Main interface
+    "generate",
+    "__version__",
+    # Individual generators
+    "gen_cphm",
+    "gen_cmm",
+    "gen_tdcm",
+    "gen_thmm",
+    "gen_aft_log_normal",
+    "gen_aft_weibull",
+    "gen_aft_log_logistic",
+    "gen_competing_risks",
+    "gen_competing_risks_weibull",
+    "gen_mixture_cure",
+    "cure_fraction_estimate",
+    "gen_piecewise_exponential",
+    # Helper functions
+    "sample_bivariate_distribution",
+    "runifcens",
+    "rexpocens",
+    "rweibcens",
+    "rlognormcens",
+    "rgammacens",
+    "WeibullCensoring",
+    "LogNormalCensoring",
+    "GammaCensoring",
+    "CensoringModel",
+    "export_dataset",
+    "GenSurvDataGenerator",
+]
+
+# Add optional exports if available
+if _has_sksurv:
+    __all__.extend(["to_sksurv", "from_sksurv"])
+
+if _has_visualization:
+    __all__.extend(
+        [
+            "plot_survival_curve",
+            "plot_hazard_comparison",
+            "plot_covariate_effect",
+            "describe_survival",
+        ]
+    )

gen_surv-1.2.0/gen_surv/__main__.py

@@ -0,0 +1,4 @@
+from gen_surv.cli import app
+
+if __name__ == "__main__":
+    app()