Metadata-Version: 2.1
Name: fracridge
Version: 0.5
Summary: Ridge regression with fraction regularization
Home-page: http://github.com/nrdg/fracridge
Author: Kendrick Kay and Ariel Rokem
Author-email: arokem@gmail.com
Maintainer: Ariel Rokem
Maintainer-email: arokem@gmail.com
License: BSD
Platform: OS Independent
Classifier: Development Status :: 3 - Alpha
Classifier: Environment :: Console
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Topic :: Scientific/Engineering
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: scikit-learn
Requires-Dist: numba
Requires-Dist: setuptools-scm
Requires-Dist: pillow

# fracridge

[![DOI](https://zenodo.org/badge/261540866.svg)](https://zenodo.org/badge/latestdoi/261540866)

Is an implementation of fractional ridge regression (FRR).

## Installation:

### Matlab

Download and copy the files from the [https://github.com/nrdg/fracridge/tree/master/matlab](Matlab directory) into your
Matlab path.

### Python

To install the release version:

    pip install fracridge

Or to install the development version:

    pip install -r requirements.txt
    pip install .

## Usage

### Matlab

    [coef,alphas] = fracridge(X,fracs,y,tol,mode)


### Python

There's a functional API:

    from fracridge import fracridge
    coefs, alphas = fracridge(X, y, fracs)

Or a sklearn-compatible OO API:

    from fracridge import FracRidge
    fr = FracRridge(fracs=fracs)
    fr.fit(X, y)
    coefs = fr.coef_
    alphas = fr.alpha_

## Online documentation

[https://nrdg.github.io/fracridge/](https://nrdg.github.io/fracridge/)

## How to cite

"Fractional ridge regression: a fast, interpretable reparameterization of ridge regression", Rokem & Kay (in preparation)


