unit8co / darts

A python library for user-friendly forecasting and anomaly detection on time series.
https://unit8co.github.io/darts/
Apache License 2.0
8.08k stars 881 forks source link

Is possible to add STL and MSTL forecast models? #2074

Closed PeterPirog closed 12 months ago

PeterPirog commented 12 months ago

Is possible to add STL and MSTL forecast models in darts? These models are very useful to find trend and seasonality for univariate time series. STL is for single seasonality and MSTL is for multiple seasonalities.

STL decomposition with ARIMA model can be used for forecasting

In some tasks is important to separate trend and seasonality to detect general direction of the process.

madtoinou commented 12 months ago

Hi @PeterPirog,

STL and MSTL are already implemented and accessible in the extract_trend_and_seasonality() method (documentation).

PeterPirog commented 12 months ago

@madtoinou , Thank You very much.