Merge pull request #4 from DiogoRibeiro7/feat/first_commit

feat: implement THMM data generator and finalize full model suite

Author: DiogoRibeiro7

.github/workflows/test.yml

@@ -0,0 +1,31 @@
+name: Run Tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.9"
+
+      - name: Install Poetry
+        run: |
+          curl -sSL https://install.python-poetry.org | python3 -
+          echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+      - name: Install dependencies
+        run: poetry install
+
+      - name: Run tests
+        run: poetry run pytest

.gitignore

@@ -0,0 +1,52 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Poetry virtualenvs
+.env
+.venv
+poetry.lock
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+
+# Pytest
+.pytest_cache/
+
+# Jupyter Notebook checkpoints
+.ipynb_checkpoints
+
+# PyCharm
+.idea/
+
+# VSCode
+.vscode/
+
+# MacOS
+.DS_Store
+
+# System files
+Thumbs.db
+ehthumbs.db
+
+# Build artifacts
+build/
+dist/
+*.egg-info/
+
+# Temporary
+*.log
+*.tmp

LICENCE

@@ -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.

README.md

@@ -1,17 +1,68 @@
-# private_repo_template
+# gen_surv
+
+**gen_surv** is a Python package for simulating survival data under a variety of models, inspired by the R package [`genSurv`](https://cran.r-project.org/package=genSurv). It supports data generation for:
+
+- Cox Proportional Hazards Models (CPHM)
+- Continuous-Time Markov Models (CMM)
+- Time-Dependent Covariate Models (TDCM)
+- Time-Homogeneous Hidden Markov Models (THMM)
+
+---
+
+## 📦 Installation
+
+```bash
+poetry install
+```
+## ✨ Features
+
+- Consistent interface across models  
+- Censoring support (`uniform` or `exponential`)  
+- Easy integration with `pandas` and `NumPy`  
+- Suitable for benchmarking survival algorithms and teaching 
+
+## 🧪 Example
+
+```python
+from gen_surv.cphm import gen_cphm
+
+df = gen_cphm(
+    n=100,
+    model_cens="uniform",
+    cens_par=1.0,
+    beta=0.5,
+    covar=2.0
+)
+print(df.head())
+```
+
+## 🔧 Available Generators
+
+| Function     | Description                                |
+|--------------|--------------------------------------------|
+| `gen_cphm()` | Cox Proportional Hazards Model             |
+| `gen_cmm()`  | Continuous-Time Multi-State Markov Model   |
+| `gen_tdcm()` | Time-Dependent Covariate Model             |
+| `gen_thmm()` | Time-Homogeneous Markov Model              |
+
 
 ```text
+genSurvPy/
 gen_surv/
-├── gen_surv/
-│   ├── __init__.py
-│   ├── cphm.py           ← put CPHM logic here
-│   ├── validate.py       ← validation functions here
-│   ├── censoring.py      ← censoring functions here
-│   └── utils.py          ← for any shared tools
-├── tests/
-│   ├── __init__.py
-│   └── test_cphm.py      ← tests for CPHM
-├── pyproject.toml
-└── README.md             ← rename README.rst if you prefer
-LICENSE
-```
+├── cphm.py
+├── cmm.py
+├── tdcm.py
+├── thmm.py
+├── censoring.py
+├── validate.py
+examples/
+├── run_cphm.py
+├── run_cmm.py
+├── run_tdcm.py
+├── run_thmm.py
+└── utils.py         # optional for shared config (e.g. seeding)
+```
+
+## 🧠 License
+
+MIT License. See [LICENSE](LICENSE) for details.

gen_surv-stubs/gen_surv/__init__.pyi

@@ -0,0 +1,4 @@
+import numpy as np
+
+def runifcens(size: int, cens_par: float) -> np.ndarray: ...
+def rexpocens(size: int, cens_par: float) -> np.ndarray: ...

gen_surv-stubs/gen_surv/censoring.pyi

@@ -0,0 +1,5 @@
+from gen_surv.censoring import rexpocens as rexpocens, runifcens as runifcens
+from gen_surv.validate import validate_gen_cmm_inputs as validate_gen_cmm_inputs
+
+def generate_event_times(z1: float, beta: list, rate: list) -> dict: ...
+def gen_cmm(n, model_cens, cens_par, beta, covar, rate): ...

gen_surv-stubs/gen_surv/cmm.pyi

@@ -0,0 +1,6 @@
+import pandas as pd
+from gen_surv.censoring import rexpocens as rexpocens, runifcens as runifcens
+from gen_surv.validate import validate_gen_cphm_inputs as validate_gen_cphm_inputs
+
+def generate_cphm_data(n, rfunc, cens_par, beta, covariate_range): ...
+def gen_cphm(n: int, model_cens: str, cens_par: float, beta: float, covar: float) -> pd.DataFrame: ...

gen_surv-stubs/gen_surv/cphm.pyi

@@ -0,0 +1,5 @@
+from gen_surv.censoring import rexpocens as rexpocens, runifcens as runifcens
+from gen_surv.validate import validate_gen_tdcm_inputs as validate_gen_tdcm_inputs
+
+def generate_censored_observations(n, dist_par, model_cens, cens_par, beta, lam, b): ...
+def gen_tdcm(n, dist, corr, dist_par, model_cens, cens_par, beta, lam): ...

gen_surv-stubs/gen_surv/tdcm.pyi

@@ -0,0 +1,5 @@
+from gen_surv.censoring import rexpocens as rexpocens, runifcens as runifcens
+from gen_surv.validate import validate_gen_thmm_inputs as validate_gen_thmm_inputs
+
+def calculate_transitions(z1: float, cens_par: float, beta: list, rate: list, rfunc) -> dict: ...
+def gen_thmm(n, model_cens, cens_par, beta, covar, rate): ...