| """Compute frozen expert features on a fixed, paired corpus. No paper is used.""" |
| import hashlib,json,time |
| from pathlib import Path |
| import numpy as np |
| import torch |
| from app.experts import LMExperts,MeldExpert |
| from app.detectors import Detector |
| ROOT=Path(__file__).resolve().parents[1];OUT=ROOT/'work/research';torch.set_num_threads(2) |
| rows=[json.loads(l) for l in (OUT/'corpus.jsonl').read_text().splitlines()] |
| groups=sorted(set(r['group'] for r in rows));np.random.default_rng(1847).shuffle(groups) |
| splits={g:'train' if i<24 else 'selection' if i<32 else 'calibration' if i<40 else 'test' for i,g in enumerate(groups)} |
| (OUT/'splits.json').write_text(json.dumps(splits,indent=2)) |
| for kind in ['earlybird','lm','meld']: |
| path=OUT/(kind+'-scores.jsonl');done={} |
| if path.exists(): |
| for line in path.read_text().splitlines(): |
| r=json.loads(line);done[r['input_sha256']]=r |
| engine=Detector('earlybird') if kind=='earlybird' else LMExperts() if kind=='lm' else MeldExpert() |
| if kind=='earlybird':engine.load() |
| with path.open('a') as out: |
| for i,row in enumerate(rows): |
| sha=hashlib.sha256(row['text'].encode()).hexdigest() |
| if sha in done:continue |
| begin=time.time();result=engine.features(row['text']) if kind=='lm' else engine.analyze(row['text']) |
| record={k:v for k,v in row.items() if k!='text'}|{'input_sha256':sha,'split':splits[row['group']],'result':result,'seconds':time.time()-begin} |
| out.write(json.dumps(record)+'\n');out.flush() |
| if i%8==0:print(kind,i+1,'/',len(rows),'seconds',round(record['seconds'],2),flush=True) |
| if kind!='earlybird':engine.unload() |
| del engine |
| import gc;gc.collect() |
|
|
