| """Standalone validator: python validate.py SUB.csv""" | |
| import sys, csv, math, numpy as np, polars as pl | |
| out=sys.argv[1] | |
| ids=pl.read_csv('@@WORK@@/evaluation.csv',columns=['rowid'],schema_overrides={'rowid':pl.Utf8})['rowid'].to_list() | |
| raw=open(out,'rb').read(); errs=[] | |
| try: raw.decode('utf-8') | |
| except Exception: errs.append('not utf-8') | |
| with open(out,newline='',encoding='utf-8') as f: | |
| r=csv.reader(f); h=next(r); rows=list(r) | |
| if h!=['rowid','predicted_probability']: errs.append(f'header {h}') | |
| if len(rows)!=529390: errs.append(f'rows {len(rows)}') | |
| sid=[x[0] for x in rows] | |
| if len(set(sid))!=len(sid): errs.append('dup rowids') | |
| if set(sid)!=set(ids): errs.append('rowid set mismatch') | |
| v=np.array([float(x[1]) for x in rows]) | |
| if not (np.isfinite(v).all() and (v>=0).all() and (v<=1).all()): errs.append('bad values') | |
| print(f'rows={len(rows)} unique={len(set(sid))} min={v.min():.4g} mean={v.mean():.5g} max={v.max():.4g} distinct={len(np.unique(v))}') | |
| print('VALID' if not errs else 'INVALID '+';'.join(errs)) | |