https://github.com/dirmeier/reconcile

:open_hands: Probabilistic reconciliation of time series forecasts
https://github.com/dirmeier/reconcile

forecasting reconciliation timeseries

Last synced: 3 months ago
JSON representation

:open_hands: Probabilistic reconciliation of time series forecasts

• Host: GitHub
• URL: https://github.com/dirmeier/reconcile
• Owner: dirmeier
• License: apache-2.0
• Created: 2022-10-23T12:45:33.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-07-20T09:30:27.000Z (6 months ago)
• Last Synced: 2024-09-20T12:08:42.899Z (3 months ago)
• Topics: forecasting, reconciliation, timeseries
• Language: Python
• Homepage:
• Size: 83 KB
• Stars: 4
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# reconcile

[![status](http://www.repostatus.org/badges/latest/concept.svg)](http://www.repostatus.org/#concept)

[![ci](https://github.com/dirmeier/reconcile/actions/workflows/ci.yaml/badge.svg)](https://github.com/dirmeier/reconcile/actions/workflows/ci.yaml)

[![version](https://img.shields.io/pypi/v/probabilistic-reconciliation.svg?colorB=black&style=flat)](https://pypi.org/project/probabilistic-reconciliation/)

> Probabilistic reconciliation of time series forecasts

## About

Reconcile implements probabilistic time series forecast reconciliation methods introduced in

1) Zambon, Lorenzo, Dario Azzimonti, and Giorgio Corani. ["Probabilistic reconciliation of forecasts via importance sampling."](https://doi.org/10.48550/arXiv.2210.02286) arXiv preprint arXiv:2210.02286 (2022).

2) Panagiotelis, Anastasios, et al. ["Probabilistic forecast reconciliation: Properties, evaluation and score optimisation."](https://doi.org/10.1016/j.ejor.2022.07.040) European Journal of Operational Research (2022).

The package implements methods to compute summing/aggregation matrices for grouped and hierarchical time series and reconciliation methods for probabilistic forecasts based on sampling and optimization,

and in the near future also some recent forecasting methods, such as proposed in [Benavoli, *et al.* (2021)](https://doi.org/10.1007/978-3-030-91445-5_2) or [Corani *et al.*, (2020)](https://arxiv.org/abs/2009.08102) via [GPJax](https://github.com/JaxGaussianProcesses/GPJax).

## Examples

An example timeseries forecast application using GPs can be found in `examples/reconciliation.py` and a **case study on probabilistic forecast reconciliation of stock index data** can be found [here](https://dirmeier.github.io/etudes/probabilistic_reconciliation.html).

## Installation

Make sure to have a working `JAX` installation. Depending whether you want to use CPU/GPU/TPU,

please follow [these instructions](https://github.com/google/jax#installation).

To install the package from PyPI, call:

```bash

pip install probabilistic-reconciliation

```

To install the latest GitHub , just call the following on the

command line:

```bash

pip install git+https://github.com/dirmeier/reconcile@

```

## Author

Simon Dirmeier sfyrbnd @ pm me