Digital Drosophila Archive
55 lines
2.1 KiB
Python
55 lines
2.1 KiB
Python
import hashlib
|
|
import importlib.util
|
|
import json
|
|
from pathlib import Path
|
|
|
|
MODEL = Path(__file__).resolve().parent
|
|
ROOT = Path('/data/digital-drosophila')
|
|
EXP = ROOT/'experiments/phase4af-author-fullgraph'
|
|
AD = ROOT/'experiments/phase4ad-author-semantics'
|
|
AE_MODEL = ROOT/'models/male-cns-lif/author-runtime-lab-v1'
|
|
AE_EXP = ROOT/'experiments/phase4ae-author-runtime'
|
|
CFG = json.loads((MODEL/'config.json').read_text(encoding='utf-8'))
|
|
|
|
def digest(path):
|
|
h = hashlib.sha256()
|
|
with Path(path).open('rb') as f:
|
|
for b in iter(lambda: f.read(8<<20), b''): h.update(b)
|
|
return h.hexdigest()
|
|
|
|
def save(path, value):
|
|
path = Path(path); path.parent.mkdir(parents=True, exist_ok=True)
|
|
with path.open('x', encoding='utf-8') as f:
|
|
json.dump(value, f, indent=2, ensure_ascii=False, allow_nan=False); f.write('\n')
|
|
|
|
def sources():
|
|
return {p.name: digest(p) for p in sorted(MODEL.iterdir())
|
|
if p.is_file() and p.name not in ('manifest.json', 'checksums.sha256')}
|
|
|
|
def check():
|
|
p = json.loads((EXP/'protocol/preregistered.json').read_text())
|
|
assert sources() == p['sources'], 'Source changed after preregistration'
|
|
for row in p['inputs']:
|
|
assert digest(ROOT/row['path']) == row['sha256'], row['path']
|
|
for row in json.loads((EXP/'protocol/graph-case-hashes.json').read_text()):
|
|
assert digest(EXP/row['path']) == row['sha256'], row['path']
|
|
return p
|
|
|
|
def integrity():
|
|
spec = importlib.util.spec_from_file_location('previous_ae_context', AE_MODEL/'context.py')
|
|
previous = importlib.util.module_from_spec(spec); spec.loader.exec_module(previous)
|
|
result = previous.integrity()
|
|
import sys
|
|
sys.path.insert(0, str(ROOT/'models/male-cns-lif/terminal-scope-diagnostic-v1'))
|
|
from diagnostic import manifest_check
|
|
for p in (AE_MODEL, AE_EXP):
|
|
result[str(p.relative_to(ROOT))] = manifest_check(p, digest)
|
|
assert all(r['pass'] for r in result.values())
|
|
return result
|
|
|
|
def output_bytes():
|
|
return sum(p.stat().st_size for p in EXP.rglob('*') if p.is_file())
|
|
|
|
def budget_check():
|
|
assert output_bytes() < CFG['new_output_budget_bytes'], 'New output budget exceeded'
|