CAUTION: the skpro package is currently undergoing major rearchitecting and should not be used in deployment.
If you find this package interesting and would like to contribute, kindly contact the sktime developers in the skpro & probabilistic forecasting workstream on discord.
A supervised domain-agnostic framework that allows for probabilistic modelling, namely the prediction of probability distributions for individual data points.
The package offers a variety of features and specifically allows for
- the implementation of probabilistic prediction strategies in the supervised contexts
- comparison of frequentist and Bayesian prediction methods
- strategy optimization through hyperparamter tuning and ensemble methods (e.g. bagging)
- workflow automation
List of developers and contributors
Documentation
The full documentation is available here.
Installation
Installation is easy using Python's package manager
$ pip install skpro
Contributing & Citation
We welcome contributions to the skpro project. Please read our contribution guide.
If you use skpro in a scientific publication, we would appreciate citations.