Metadata-Version: 2.4
Name: hklearn
Version: 0.26
Summary: Machine learning tools for hyperspectral mapping
Home-page: https://github.com/samthiele/hklearn
Author: Sam Thiele
Author-email: s.thiele@hzdr.de
License: MIT
Project-URL: Documentation, https://samthiele.github.io/hklearn/hklearn.html
Project-URL: Source, https://github.com/samthiele/hklearn
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: scikit-learn
Requires-Dist: scipy
Requires-Dist: natsort
Requires-Dist: dill
Requires-Dist: hylite
Dynamic: author
Dynamic: author-email
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license
Dynamic: license-file
Dynamic: project-url
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

<h1>
  <img src="hklearn-icon.png" alt="hklearn icon" height="40" align="absmiddle">
  <span>hklearn</span>
</h1>

### About

`hklearn` is a scikit-learn–oriented machine learning layer for multi-sensor hyperspectral geology. It sits on [`hylite`](https://github.com/hifexplo/hylite) and provides `Stack` (flatten, preprocess, folds) and `ModelSet` (features, estimators, ensembles) for classification and regression — mineral abundance, petrophysics, and related mapping tasks.

### Demonstration

For a short introduction, see `demo.ipynb`.

### Documentation

Documentation for `hklearn` can be found here:

[https://samthiele.github.io/hklearn/hklearn.html](https://samthiele.github.io/hklearn/hklearn.html)

### Citation

If `hklearn` has been useful for your work, please cite:

> [Thiele, S.T.; Kirsch, M.; Frenzel, M.; Tolosana-Delgado, R.; Kamath, A.V.; Guy, B.M.; Kim, Y.; Tuşa, L.; Járóka, T.; Gloaguen, R. Predicting Mineralogy with Hyperspectral Data: A Benchmark Dataset and Machine Learning Framework to Enable Hyperspectral Geometallurgy. *Minerals* 2026, 16, 674. doi:10.3390/min16070674](https://doi.org/10.3390/min16070674)
