kemal
e308253039
- fit.py: exact and binned nearest-neighbour searches use one distance matrix per searched bin (first-minimum rule kept); fit 2.6 s -> 1.4 s per GSA sample, still bit-identical to the oracle - scripts/validate_p3_large.py: refits 1.2.0 and 1.1.2 transforms for every vendor GTC and reports ULP distances per field - cloud trial runs scripts/cloud/tasks/<TASK>.sh (TASK=p3 default; p1p2 = previous validation + ingest)
13 lines
835 B
Bash
Executable File
13 lines
835 B
Bash
Executable File
#!/bin/bash
|
|
# Phase P1/P2 validation on the 1000 Genomes Omni2.5 set + `simurg ingest` at scale.
|
|
# Args: <data dir with bpm/egt/csv and data/> <results dir>
|
|
set -uo pipefail
|
|
D=$1; OUT=$2
|
|
.venv/bin/python scripts/validate_p1_large.py --root $D/data --bpm $D/HumanOmni2.5-4v1-Multi_B.bpm \
|
|
--egt $D/HumanOmni2.5-4v1-Multi_B.egt --csv $D/HumanOmni2.5-4v1_B.csv --out $OUT/summary.json \
|
|
--workers "$(nproc)" || echo "validation reported differences (see summary.json)"
|
|
/usr/bin/time -v .venv/bin/simurg ingest --bpm $D/HumanOmni2.5-4v1-Multi_B.bpm --idats $D/data \
|
|
--out /work/ingest --threads "$(nproc)" --quiet 2> $OUT/ingest_time.txt || echo "ingest exit code $?"
|
|
cp /work/ingest/ingest_summary.tsv $OUT/ingest_summary.tsv 2>/dev/null || true
|
|
cp /work/ingest/run_manifest.json $OUT/ingest_run_manifest.json 2>/dev/null || true
|