Skeletons for parameterized models.
Backbones for parameterized models.
Spines was built to provide a skeleton for Model classes: a common interface for users to build models around (with some tools and utilities which take advantage of having the commonalities). It's similar, in structure, to some of scikit-learn's underlying Estimator classes - but with a unified set of functions for all models, namely:
The transform method is the only one that's required, though the other two are likely useful most of the time. Spines is absolutely not a replacement for scikit-learn (or any other data/machine-learning library) it's simply a useful framework for building your own models (leveraging any library) in a standardized and convenient way.
The latest documentation is hosted at https://spines.reathedocs.io/.
To install spines use your package manager of choice, an example using
$ pipenv install spines
This project is licensed under the MIT License, for more information see the LICENSE file.
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.