static spatiotemporal train/val/test splits for dataset
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 25/100
- Issue type
- Feature
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- python
- Domain
- data, machine-learning
Research direction
The issue proposes static spatiotemporal train, validation, and test splits for a large xarray dataset, with sample sizes, strides, holdout regions, and an optional land mask. Start by reviewing the existing prototype mentioned in the issue and determine where this functionality belongs. Done would be an agreed design and an implementation that returns coordinate dictionaries for each split.
Written by the indexing model from the issue text.
Description
Is your feature request related to a problem?
Unable to create easy, good static splits for train val and test sets of an xarray dataset for Deep Learning
Describe the solution you'd like
Is your feature request related to a problem?
Hi everyone,
I’d like to open the discussion about adding functionality to create static spatiotemporal train, validation, and test splits from a single large xarray dataset (e.g., global-scale data).
The goal is to generate these splits based on:
The spatial and temporal size of each sample
The stride between samples
A list of user-defined validation and test regions (as static spatiotemporal holdouts)
Potentially a land mask, used to ignore samples which only contain ocean, or land data.
The expected output would be, for each split, a list of dictionaries containing the coordinates (start and end) of each slice. This structure would make it straightforward to iterate over samples in a dataloader.
Keeping the validation and test regions static is important to ensure consistent model evaluation and comparability across experiments.
I am already working on a prototype for this with my work, and wanted to open the discussion to gather feedback and seeing if and to which library this could be a contribution!
Describe alternatives you've considered
none, it doesnt exist yet
Additional context
No response
- Dominant language
- Python
- Stars
- 4.2k
- Forks
- 1.5k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 74
Getting set up
Starts the project's dev container in your browser, under your own GitHub account.
- No Dockerfile or Docker Compose file
- Has a pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from pydata/xarray
-
xarray removes axis grid from pcolormeshPossibly taken @Sealdot claimed this today. Openbug needs triage
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
Maintainers usually reply within 1 day
-
`DataTree.map_over_datasets` behavior can be obscure sometimesPossibly taken @mohansree14 claimed this 24 days ago. Openneeds triage
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
pydata/xarray#11813 · 1 comment ·
Maintainers usually reply within 1 day
-
Comparing attrs that contain a dict of NumPy arrays raises ValueError in identical / assert_identicalPossibly taken @SohamXYZDev claimed this 29 days ago. Openbug needs triage
Difficulty 2/5 1-3 hours Newbie friendliness 73/100
pydata/xarray#11777 · 1 comment ·
Maintainers usually reply within 1 day
-
RangeIndex` with datetime64 bounds cannot be printed (`Unknown format code 'g'`)Possibly taken @d-chambers claimed this 60 days ago. Openbug
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
pydata/xarray#11598 · 3 comments ·
Maintainers usually reply within 1 day
-
DataTree constructor error message says dict even though dict is not acceptedPossibly taken @aryansk claimed this 100 days ago. Openbug contrib-good-first-issue topic-DataTree topic-error reporting
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
pydata/xarray#11514 · 2 comments ·
Maintainers usually reply within 1 day
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
abetlen/llama-cpp-python#2424 ·
Maintainers usually reply within 1 day
-
Bug IronPython Python 3
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
pyrevitlabs/pyRevit#4184 ·
Maintainers usually reply within 1 day
-
Difficulty 1/5 Under an hour Newbie friendliness 74/100
jqueryscript/awesome-claude-code#1009 ·
-
tests
Difficulty 2/5 1-3 hours Newbie friendliness 66/100
Maintainers usually reply within 3 days
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
Maintainers usually reply within 1 day