chore(gitignore): add catch-all patterns for ad-hoc session output files#92
Merged
Conversation
train_gnn_v2 was training on all rows including quarantined B*27 label conflicts that were fixed in the v5 dataset. Add _filter_quarantined call after pd.read_csv to match the existing behavior in train_classifier.py. Add --batch-size CLI flag (default 64; documented reduction to 32 for the t33 650M ESM-2 model to prevent GPU OOM during training).
Add scripts/compute_population_coverage.py implementing the Lundegaard 2010 HWE-independence model for the 10-allele MHCflurry panel. Embeds AFND 2020 gold-standard haplotype frequencies for 5 WHO super-populations with full source documentation and per-allele caveats (EAS A*02:01 rarity, AFR B*27:05 subtypes). Outputs results/population_coverage_v5.json. Panel coverage: AFR 62.1%, AMR 81.3%, EAS 74.2%, EUR 91.9%, SAS 84.7% (global mean 78.9%). EUR bias documented; AFR limitation addressed in paper. Add gitignore exception for the committed JSON.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds three broad gitignore catch-all patterns to prevent common dev-session detritus from appearing as untracked files:
*_output.txt-- covers files likescratchpad_output.txtstale_*.txt-- covers files likestale_search.txtstale_*.md-- covers stale-prefixed markdown scratch notesAll other root-level loose files (
inspect_checkpoint.py,resave_checkpoint.py,scan_checkpoint_globals.py,apply-branch-ruleset.ps1,claude_form_filler_prompt.md,src.zip,sestrav_gnn_v23_canonical_artifacts.zip,top_20_candidates.csv) were already covered by existing specific gitignore rules and have been relocated locally toscripts/or_local/(gitignored dirs, no tracked changes).Test plan
git ls-files --others --exclude-standardreturns no stray files at repo root