sktime and skforecast

These are complementary tools: skforecast specializes in univariate and multivariate forecasting with a scikit-learn-compatible API, while sktime provides a broader unified framework for time series tasks (classification, regression, forecasting) that can incorporate skforecast's models as estimators within its pipelines.

sktime
98
Verified
skforecast
93
Verified
Maintenance 23/25
Adoption 25/25
Maturity 25/25
Community 25/25
Maintenance 25/25
Adoption 22/25
Maturity 25/25
Community 21/25
Stars: 9,628
Forks: 1,947
Downloads: 1,138,253
Commits (30d): 23
Language: Python
License: BSD-3-Clause
Stars: 1,462
Forks: 184
Downloads: 98,347
Commits (30d): 62
Language: Python
License: BSD-3-Clause
No risk flags
No risk flags

About sktime

sktime/sktime

A unified framework for machine learning with time series

Provides dedicated algorithms for forecasting, classification, regression, clustering, and anomaly detection alongside scikit-learn-compatible tools for pipelining and ensembling. The unified API enables task reduction—applying algorithms designed for one time series task to another—while offering adapters to statsmodels, tsfresh, PyOD, and fbprophet for ecosystem interoperability.

About skforecast

skforecast/skforecast

Time series forecasting with machine learning models

Scores updated daily from GitHub, PyPI, and npm data. How scores work