Metadata-Version: 2.1
Name: rolch
Version: 0.1.7
Summary: Methods for online / incremental estimation of distributional regression models
Author-email: Simon Hirsch <simon.hirsch@stud.uni-due.de>, Jonathan Berrisch <jonathan.berrisch@uni-due.de>, Florian Ziel <florian.ziel@uni-due.de>
Project-URL: Homepage, https://github.com/simon-hirsch/rolch
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE.txt
Requires-Dist: scipy<2.0.0,>=1.00
Requires-Dist: numpy<2.0.0,>=1.2
Requires-Dist: numba<1.0.0,>=0.59.1

# ROLCH: Regularized Online Learning for Conditional Heteroskedasticity

[![Open Source Love](https://badges.frapsoft.com/os/v2/open-source.svg?v=103)](https://github.com/ellerbrock/open-source-badges/) [![License: MIT](https://img.shields.io/badge/License-MIT-red.svg)](https://opensource.org/licenses/MIT) 

## Introduction

This package provides online estimation of models for distributional regression respectively models for conditional heteroskedastic data. The main contribution is an online/incremental implementation of the generalized additive models for location, shape and scale (GAMLSS, see [Rigby & Stasinopoulos, 2005](https://academic.oup.com/jrsssc/article-abstract/54/3/507/7113027)) developed in [Hirsch, Berrisch & Ziel, 2024](https://arxiv.org/abs/2407.08750).

Please have a look at the [documentation](https://simon-hirsch.github.io/rolch/) or the [example notebook](https://github.com/simon-hirsch/rolch/blob/main/example.ipynb).

We're actively working on the package and welcome contributions from the community. Have a look at the [Release Notes](https://github.com/simon-hirsch/rolch/releases) and the [Issue Tracker](https://github.com/simon-hirsch/rolch/issues).

## Install from PyPI

The package is available from [pypi](https://pypi.org/project/rolch/).

1) `pip install rolch`. 
2) Enjoy

## Install from source:

1) Clone this repo.
2) Install the necessary dependencies from the `requirements.txt` using `conda create --name <env> --file requirements.txt`. 
3) Run `python3 -m build` to build the wheel.
4) Run `pip install dist/rolch-0.1.0-py3-none-any.whl` with the accurate version. If necessary, append `--force-reinstall`
5) Enjoy.

## Authors

- Simon Hirsch, University of Duisburg-Essen & Statkraft
- Jonathan Berrisch, University of Duisburg-Essen
- Florian Ziel, University of Duisburg-Essen

## Acknowledgements

Simon is employed at Statkraft and gratefully acknowledges support received from Statkraft for his PhD studies. This work contains the author's opinion and not necessarily reflects Statkraft's position.

## Dependencies

`ROLCH` is designed to have minimal dependencies. We rely on `python>=3.10`, `numpy`, `numba` and `scipy` in a reasonably up-to-date versions.

## Formater

We use `ruff` and `black`.
