Feature: New group aware time-based cross validation 

There are situations when sliding_period or group_vfold_cv is not exactly what is needed for a good cross validation.

I've seen some libraries in python implementing GroupTimeSeriesSplit:

* [mlxtend.evaluate.GroupTimeSeriesSplit](https://github.com/rasbt/mlxtend/blob/master/mlxtend/evaluate/time_series.py)
* [sklego.model_selection.GroupTimeSeriesSplit](https://github.com/koaning/scikit-lego/blob/main/sklego/model_selection.py#L287)

They are based on some kaggle notebooks and stackoverflow answers:

* [Cross-validation for grouped time-series (panel) data](https://stackoverflow.com/a/66642037/481463)
* [Found the Holy Grail: GroupTimeSeriesSplit](https://www.kaggle.com/code/jorijnsmit/found-the-holy-grail-grouptimeseriessplit)

I also see that this feature is currently being developed in scikit-learn:
* [Feature request: Group aware Time-based cross validation](https://github.com/scikit-learn/scikit-learn/issues/14257)


Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Description

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions