automl / automl/Auto-PyTorch

[feat] Dataset compression for time series forecasting tasks

Open
#440 0 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
Python
Stars
2.5k
Forks
300
PR merge metrics
No merged PRs in 30d

Description

NOTE: ISSUES ARE NOT FOR CODE HELP - Ask for Help at https://stackoverflow.com

Your issue may already be reported!
Also, please search on the [issue tracker](../) before creating one.

* **I'm submitting a ...**
- [x] feature request

# Issue Description
* Currently, `dataset_compression` is unavailable for `time-series forecasting` datasets as they need to be treated specifically. We need to do so by either:
- Reducing the number of series in the datasets
- Truncating the first parts of each series (if they have enough length for a training-validation split)

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.