Repository navigation
Conversation
The DeepTabMetric and deeptab.metrics docstrings said HPO and early stopping use higher_is_better to pick the optimisation direction, and listed CRPS as higher-is-better. Nothing reads the attribute: HPO minimises val_loss and early stopping follows monitor/mode, and CRPS is lower-is-better. Match the metrics API page. Fixes #599
The intro said the framework reads all three attributes automatically, which contradicts the corrected higher_is_better bullet below it. Refs #599
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fixes #599
Problem
The
DeepTabMetricdocstring saidhigher_is_bettersets the HPO optimisation direction and drives early stopping and checkpoint decisions, and called CRPS higher-is-better. Thedeeptab.metricspackage docstring said "the training loop and HPO use this". No code reads the attribute:optimize_hparams()minimisesval_loss, early stopping and checkpointing followmonitor/mode, andCRPS.higher_is_betterisFalse.Change
Docstrings only:
deeptab/metrics/base.pyanddeeptab/metrics/__init__.pydescribehigher_is_betteras descriptive metadata for reading the score, asdocs/api/metrics/index.rstalready does.deeptab.metricsoverview no longer says the framework reads all three metric attributes automatically; it calls them metadata attributes, which matches the correctedhigher_is_betterbullet.Checks
just test: 3236 passed, 46 skipped, 28 xfailed; coverage 91.29%just docs: build succeeded (warnings treated as errors)just check: all hooks passed (ruff, prettier, pyright)