feat: add temporal leakage audit for sequence model splits (#35)#78
Merged
Conversation
Closes #35 SHSequenceDataset and evaluate_sequence.py previously used torch.utils.data.random_split on the flat sample list, letting adjacent overlapping sliding windows from the same sequence leak across train/val/test. - SHSequenceDataset.split_by_sequence() splits at the sequence level (contiguous blocks), preserving temporal independence - check_split_leakage() asserts no sequence ID appears in >1 split - test_split_leakage.py programmatically verifies the invariant - Updated train_sequence.py and evaluate_sequence.py to use split_by_sequence - Added test run to Python ML CI job
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #35
Replaces
andom_split\ (leaky — shuffled flat sample list) with
\SHSequenceDataset.split_by_sequence()\ that splits at the sequence level
(first 80% of sequences ⇒ train, next 10% ⇒ val, last 10% ⇒ test).
Also adds \ est_split_leakage.py\ to programmatically verify the invariant
and runs it in CI.