Skip to content
This repository was archived by the owner on Dec 20, 2024. It is now read-only.

feat: Allow noncontinuous date ranges in dataloader #129

Draft
wants to merge 3 commits into
base: develop
Choose a base branch
from

Conversation

HCookie
Copy link
Member

@HCookie HCookie commented Nov 8, 2024

  • Provides noncontinuous ranges of dates
  • Checks for overlap between training, validation and test

Requires ecmwf/anemoi-datasets#118

Allows

training:
  dataset: ${dataloader.dataset}
  ranges: 
    - [1970, 1980]
    - [1990, 2020]
  frequency: ${data.frequency}
  drop:  []


validation:
  dataset: ${dataloader.dataset}
  ranges: 
    - [1981, 1989]
    - [2021, 2021]
  frequency: ${data.frequency}
  drop:  []

Closes ecmwf/anemoi-core#17

- Provides noncontinuous ranges of dates
- Checks for overlap between training, validation and test
- Requires ecmwf/anemoi-datasets#118
@HCookie HCookie self-assigned this Nov 8, 2024
@floriankrb
Copy link
Member

Let's have a look at https://anemoi-datasets.readthedocs.io/en/latest/using/missing.html and have a chat.

How will you handle the last date of the first interval?
You do not want to train using x_i = 1980.12.31 18:00 and x_i+1 = 1990.01.01 00:00.

In the config, it may turn into this :

training:
  concat:
     -  dataset: ${dataloader.dataset}
         start: 1970
         end: 1980
     -  dataset: ${dataloader.dataset}
         start: 1990
         end: 2020
  frequency: ${data.frequency}
  how_to_handle_the_date_1980_12_31: 'raise'/'skip'...

@HCookie HCookie marked this pull request as draft November 13, 2024 14:53
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Allow noncontinous time ranges in datasets for training and validation
2 participants