search

AI4S2S / s2spy

A high-level python package integrating expert knowledge and artificial intelligence to boost (sub) seasonal forecasting
https://ai4s2s.readthedocs.io/
Apache License 2.0
20 stars 7 forks source link

Implementing the lag shifting (discard) method #19

Closed geek-yang closed 2 years ago

geek-yang commented 2 years ago

The lag shifting method will be implemented in the time.py module. When initializing the AdventCalendar object, a calendar with counting backward time intervals is created. The user need to provide the target time range and the maximum lag value to finalize the calendar by "trimming" those intervals.

For reference, the relevant legacy codes are: https://github.com/AI4S2S/proto/blob/0dd397f6101573544f10a55a4205e037e69acdfe/forecasting/func_models.py#L153

Our previous discussion about the design of this module can be found in https://github.com/AI4S2S/proto/issues/3.

geek-yang commented 2 years ago

This issue is not valid anymore based on the current design. It will be closed.