alan-turing-institute / alan-turing-institute/cloudcasting

Should we continue to disallow nans in predictions?

Open
#71 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
15
Forks
4
PR merge metrics
No merged PRs in 30d

Description

https://github.com/alan-turing-institute/cloudcasting/blob/d84dde0a2f115dc6d7f9f6dcbd5ff0d951b210b9/src/cloudcasting/models.py#L41-L43

Not fully convinced we need this now that our metrics handle NaNs gracefully.

Contributor guide

Open the contributing guide

Research direction

Start by reading the linked validation in src/cloudcasting/models.py around lines 41-43 and review how the existing metrics handle NaNs. Done means reaching and documenting a decision on whether predictions should continue to reject NaNs.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.