Welcome to sktime#

A unified framework for machine learning with time series.



  • unified API for ML/AI with time series, for model building, fitting, application, and validation

  • support for a variety of learning tasks including forecasting, time series classification, regression, clustering.

  • composite model building, including pipelines with transformations, ensembles, tuning, reduction

  • interactive user experience with scikit-learn like interface 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.