Welcome to sktime#

A unified framework for machine learning with time series.

Applications for sktime internships 2023 open!

Application deadline is May 19. Apply here


sktime provides an easy-to-use, flexible and modular open-source framework for a wide range of time series machine learning tasks. It offers scikit-learn compatible interfaces and model composition tools, with the goal to make the ecosystem more usable and interoperable as a whole. We build and sustain an open, diverse and self-governing community, welcoming new contributors from academia and industry through instructive documentation, mentoring and workshops.


  • unified API for machine learning with time series, for model specification, fitting, application, and validation

  • supported tasks include forecasting, time series classification, time series regression, time series clustering.

  • tools for composite model buildin including pipelining with transformations, ensembling, tuning and reduction

  • interactive user experience with scikit-learn like syntax conventions

Technical specification#

  • In-memory computation of a single machine, no distributed computing

  • Medium-sized data in pandas and NumPy based containers

  • Modular, principled and object-oriented API

  • Using interactive Python interpreter, no command-line interface or graphical user interface


Get Started

Get started using sktime quickly.

User Guide

Find user documentation.


Installation Guide.

API Reference

Understand sktime’s API.

Get Involved

Find out how you can contribute.


Information for developers.


Learn more about sktime.