scikit-matter

scikit-matter is a toolbox of methods developed in the computational chemical and materials science community, following the scikit-learn API and coding guidelines to promote usability and interoperability with existing workflows.

Features and Samples Selection

Supervised and unsupervised selection methods based on CUR matrix decomposition and Farthest Point Sampling.

Principal Covariates Regression

Utilises a combination between a PCA-like and a LR-like loss to determine the decomposition matrix to project feature into latent space

Metrics

Error measures for quantifying the linear decodable information capacity between features

Having problems or ideas?

Having a problem with scikit-matter? Please let us know by submitting an issue.

Submit new features or bug fixes through a pull request.

Citing scikit-matter

If you use scikit-matter for your work, please cite:

Goscinski A, Principe VP, Fraux G et al. scikit-matter : A Suite of Generalisable Machine Learning Methods Born out of Chemistry and Materials Science. Open Res Europe 2023, 3:81. 10.12688/openreseurope.15789.2

If you would like to contribute to scikit-matter, check out our Contributing page!