Metadata-Version: 2.4
Name: hdmseg
Version: 0.1.0
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: BSD License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Rust
Classifier: Operating System :: POSIX :: Linux
Classifier: Operating System :: MacOS
Classifier: Operating System :: Microsoft :: Windows
Classifier: Topic :: Scientific/Engineering :: Mathematics
Requires-Dist: numpy>=1.21
Summary: Population-consistent spectral segmentation by correspondence-collapsed consensus diffusion
Keywords: segmentation,diffusion-maps,spectral-clustering,morphometrics,shape
Home-Page: https://github.com/agporto/hdmseg
Author-email: Arthur Porto <agporto@gmail.com>
License-Expression: BSD-2-Clause
Requires-Python: >=3.9
Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
Project-URL: Changelog, https://github.com/agporto/hdmseg/blob/main/CHANGELOG.md
Project-URL: Homepage, https://github.com/agporto/hdmseg
Project-URL: Issues, https://github.com/agporto/hdmseg/issues
Project-URL: Repository, https://github.com/agporto/hdmseg

# hdmseg

Python bindings for population-consistent spectral segmentation by
correspondence-collapsed consensus diffusion.

```bash
python -m pip install "git+https://github.com/agporto/hdmseg.git#subdirectory=python"
```

```python
import hdmseg

segmentation = hdmseg.segment(X)  # X has shape (N, M, D)
segmentation.labels               # one region id per corresponding locus
```

The current implementation uses dense `M × M` operators and an exact dense
eigendecomposition. It is frame-free and is not a horizontal or hypoelliptic
diffusion-map implementation.

See the repository README and `docs/TUNING.md` for the method, complete API,
complexity limits, and development instructions.

