Metadata-Version: 2.1
Name: ForeTiS
Version: 0.0.1.1
Summary: state-of-the-art and easy-to-use time series forecasting
Home-page: https://github.com/grimmlab/ForeTiS
Author: Josef Eiglsperger, Florian Haselbeck; Dominik G. Grimm
Author-email: josef.eiglsperger@tum.de
License: MIT
Project-URL: Documentation, https://ForeTiS.readthedocs.io/
Project-URL: Source, https://github.com/grimmlab/ForeTiS
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: torch (>=1.11.0)
Requires-Dist: xgboost (>=1.5.2)
Requires-Dist: optuna (>=2.10.0)
Requires-Dist: sqlalchemy (==1.4.46)
Requires-Dist: joblib (>=1.1.0)
Requires-Dist: numpy (>=1.22.2)
Requires-Dist: pandas (>=1.4.1)
Requires-Dist: scikit-learn (>=1.0.2)
Requires-Dist: tensorflow (>=2.8.0)
Requires-Dist: tensorflow-probability (>=0.18)
Requires-Dist: statsmodels (>=0.13.2)
Requires-Dist: scipy (>=1.8.1)
Requires-Dist: pmdarima (>=2.0.1)
Requires-Dist: gpflow (>=2.5.2)
Requires-Dist: matplotlib (>=3.3.0)
Requires-Dist: changefinder (>=0.3)
Requires-Dist: bayesian-torch
Requires-Dist: blitz-bayesian-pytorch
Requires-Dist: tables (>=3.7.0)

<div align="left"><img src="https://raw.githubusercontent.com/grimmlab/ForeTiS/master/docs/image/Logo_ForeTiS_Text.png" height="80"/></div>

# ForeTiS: A Forecasting Time Series framework

[![Python 3.8](https://img.shields.io/badge/Python-3.8-3776AB)](https://www.python.org/downloads/release/python-388/)

ForeTiS is a Python framework that enables the rigorous training, comparison and analysis of time series forecasting for a variety of different models. 
ForeTiS includes multiple state-of-the-art prediction models or machine learning methods, respectively. 
These range from classical models, such as regularized linear regression over ensemble learners, e.g. XGBoost, to deep learning-based architectures, such as Multilayer Perceptron (MLP). 
To enable automatic hyperparameter optimization, we leverage state-of-the-art and efficient Bayesian optimization techniques. 
In addition, our framework is designed to allow an easy and straightforward integration and benchmarking of further prediction models.

## Documentation
For more information, installation guides, tutorials and much more, see our documentation: https://foretis.readthedocs.io/

## Contributors
This pipeline is developed and maintained by members of the [Bioinformatics lab](https://bit.cs.tum.de) lead by [Prof. Dr. Dominik Grimm](https://bit.cs.tum.de/team/dominik-grimm/):
- [Josef Eiglsperger, M.Sc.](https://bit.cs.tum.de/team/josef-eiglsperger/)
- [Florian Haselbeck, M.Sc.](https://bit.cs.tum.de/team/florian-haselbeck/)

## Citation
When using ForeTiS, please cite our publication:

**ForeTiS: A comprehensive time series forecasting framework in Python.** <br />
Josef Eiglsperger*, Florian Haselbeck* and Dominik G. Grimm. <br />
*Machine Learning with Applications, 2023.* [doi: 10.1016/j.mlwa.2023.100467](https://doi.org/10.1016/j.mlwa.2023.100467) <br />
**These authors have contributed equally to this work and share first authorship.* <br />
