Package
Meta
Testing
Donation
Affiliation

Skforecast is a Python library that eases using scikit-learn regressors as single and multi-step forecasters. It also works with any regressor compatible with the scikit-learn API (LightGBM, XGBoost, CatBoost, ...).

Why use skforecast?

The fields of statistics and machine learning have developed many excellent regression algorithms that can be useful for forecasting, but applying them effectively to time series analysis can still be a challenge. To address this issue, the skforecast library provides a comprehensive set of tools for training, validation and prediction in a variety of scenarios commonly encountered when working with time series. The library is built using the widely used scikit-learn API, making it easy to integrate into existing workflows. With skforecast, users have access to a wide range of functionalities such as feature engineering, model selection, hyperparameter tuning and many others. This allows users to focus on the essential aspects of their projects and leave the intricacies of time series analysis to skforecast. In addition, skforecast is developed according to the following priorities:

• Fast and robust prototyping. ⚡
• Validation and backtesting methods to have a realistic assessment of model performance. 🔍
• Models must be deployed in production. 🔨
• Models must be interpretable. 🔮

Share Your Thoughts with Us

Thank you for choosing skforecast! We value your suggestions, bug reports and recommendations as they help us identify areas for improvement and ensure that skforecast meets the needs of the community. Please consider sharing your experiences, reporting bugs, making suggestions or even contributing to the codebase on GitHub. Together, let's make time series forecasting more accessible and accurate for everyone.

For detailed information on how to use and leverage the full potential of skforecast please refer to the comprehensive documentation available at:

https://skforecast.org 📚

The default installation of skforecast only installs hard dependencies.

pip install skforecast

Specific version:

pip install skforecast==0.12.0

Latest (unstable):

pip install git+https://github.com/JoaquinAmatRodrigo/skforecast#master

Install the full version (all dependencies):

pip install skforecast[full]

Install optional dependencies:

pip install skforecast[sarimax]

pip install skforecast[plotting]

pip install skforecast[deeplearning]

• Python >= 3.8

• numpy>=1.20, <1.27
• pandas>=1.2, <2.3
• tqdm>=4.57, <4.67
• scikit-learn>=1.2, <1.5
• optuna>=2.10, <3.7
• joblib>=1.1, <1.5

• matplotlib>=3.3, <3.9
• seaborn>=0.11, <0.14
• statsmodels>=0.12, <0.15
• pmdarima>=2.0, <2.1
• tensorflow>=2.13, <2.16

Visit the release notes to view all notable changes.

• Multiseries forecaster (Global Models) can be trained using series of different lengths and with different exogenous variables per series.
• Bayesian hyperparameter search is now available for all multiseries forecasters using optuna as the search engine.
• New functionality to select features using scikit-learn selectors (select_features and select_features_multiseries).
• Added new forecaster ForecasterRnn to create forecasting models based on deep learning (RNN and LSTM).
• New method to predict intervals conditioned on the range of the predicted values. This is can help to improve the interval coverage when the residuals are not homoscedastic (ForecasterAutoreg).
• All Recursive Forecasters are now able to differentiate the time series before modeling it.
• Bug fixes and performance improvements.

A Forecaster object in the skforecast library is a comprehensive container that provides essential functionality and methods for training a forecasting model and generating predictions for future points in time.

The skforecast library offers a variety of forecaster types, each tailored to specific requirements such as single or multiple time series, direct or recursive strategies, or custom predictors. Regardless of the specific forecaster type, all instances share the same API.

• Introduction to time series and forecasting

• Recursive multi-step forecasting

• Direct multi-step forecasting

• Independent multi-series forecasting

• Dependent multi-series forecasting (Multivariate forecasting)

• Backtesting (validation) of forecasting models

• Hyperparameter tuning and lags selection of forecasting models

• Probabilistic forecasting

• Using forecasters in production

English

• Skforecast: time series forecasting with Python and Scikit-learn

• ARIMA and SARIMAX models

• Forecasting with gradient boosting: skforecast, XGBoost, LightGBM and CatBoost

• Modelling time series trend with tree based models

• Forecasting energy demand with machine learning

• Forecasting web traffic with machine learning and Python

• Bitcoin price prediction with Python

• Prediction intervals in forecasting models

• Global Forecasting Models: Multi-series forecasting

• Global Forecasting Models: Comparative Analysis of Single and Multi-Series Forecasting Modeling

• Reducing the influence of Covid-19 on time series forecasting models

• Forecasting time series with missing values

• Intermittent demand forecasting

• Stacking ensemble of machine learning models to improve forecasting

Español

• Skforecast: forecasting series temporales con Python y Scikit-learn

• Modelos ARIMA y SARIMAX

• Forecasting con gradient boosting: skforecast, XGBoost, LightGBM y CatBoost

• Modelar series temporales con tendencia utilizando modelos de árboles

• Forecasting de la demanda eléctrica

• Forecasting de las visitas a una página web

• Predicción del precio de Bitcoin con Python

• Workshop predicción de series temporales con machine learning Universidad de Deusto / Deustuko Unibertsitatea

• Intervalos de predicción en modelos de forecasting

• Global Forecasting Models: Multi-series forecasting

• Predicción de demanda intermitente

Primarily, skforecast development consists of adding and creating new Forecasters, new validation strategies, or improving the performance of the current code. However, there are many other ways to contribute:

• Submit a bug report or feature request on GitHub Issues.
• Contribute a Jupyter notebook to our examples.
• Write unit or integration tests for our project.
• Answer questions on our issues, Stack Overflow, and elsewhere.
• Translate our documentation into another language.
• Write a blog post, tweet, or share our project with others.

For more information on how to contribute to skforecast, see our Contribution Guide.

Visit our authors section to meet all the contributors to skforecast.

If you use skforecast for a scientific publication, we would appreciate citations to the published software.

Zenodo

Amat Rodrigo, Joaquin, & Escobar Ortiz, Javier. (2024). skforecast (v0.12.0). Zenodo. https://doi.org/10.5281/zenodo.8382788

APA:

Amat Rodrigo, J., & Escobar Ortiz, J. (2024). skforecast (Version 0.12.0) [Computer software]. https://doi.org/10.5281/zenodo.8382788

BibTeX:

@software{skforecast,
author = {Amat Rodrigo, Joaquin and Escobar Ortiz, Javier},
title = {skforecast},
version = {0.12.0},
month = {4},
year = {2024},
license = {BSD-3-Clause},
url = {https://skforecast.org/},
doi = {10.5281/zenodo.8382788}
}

View the citation file.

If you found skforecast useful, you can support us with a donation. Your contribution will help to continue developing and improving this project. Many thanks!

BSD-3-Clause License