sktime: A Unified Interface for Machine Learning with Time Series
About
We present sktime -- a new scikit-learn compatible Python library with a unified interface for machine learning with time series. Time series data gives rise to various distinct but closely related learning tasks, such as forecasting and time series classification, many of which can be solved by reducing them to related simpler tasks. We discuss the main rationale for creating a unified interface, including reduction, as well as the design of sktime's core API, supported by a clear overview of common time series tasks and reduction approaches.
Markus L\"oning, Anthony Bagnall, Sajaysurya Ganesh, Viktor Kazakov, Jason Lines, Franz J. Kir\'aly• 2019
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Time-series classification | CHARACTER TRAJ. (test) | Accuracy0.9 | 88 | |
| Time-series classification | Japanese Vowels (test) | Accuracy96.8 | 28 | |
| Time-series classification | AtrialFibrillation (AF) (test) | Accuracy33.3 | 15 | |
| Time-series classification | StandWalkJump (SWJ) (test) | Accuracy46.7 | 15 | |
| Time-series classification | SpokenArabicDigits (SAD) (test) | Accuracy52.4 | 13 | |
| Time-series classification | ShakGWZ (test) | Accuracy68 | 12 | |
| Time-series classification | AllGeWX (test) | Accuracy27.3 | 12 | |
| Time-series classification | GPebbleZ1 (test) | Accuracy59.9 | 12 | |
| Time-series classification | GPebbleZ2 (test) | Accuracy41.8 | 12 | |
| Time-series classification | AsphReg (test) | Accuracy91.6 | 12 |
Showing 10 of 29 rows