"""Validation of the automatic labels (labeling/auto/*.jsonl) against the rules of labeling/labeling-rules.md. python3 labeling/scripts/validate.py # every station python3 labeling/scripts/validate.py NORDEND # one station python3 labeling/scripts/validate.py /labels.jsonl # a proposed file, before it is submitted (no `review` required) Errors (to fix): unreadable JSON, missing field, unknown family, malformed date, start >= end, label without `review` or without `id` (`python3 labeling/scripts/ids.py`), id not first in the line, duplicate id, exact duplicate, numeric value, local time, "probably not a movement". "Nothing to worry about" is right only with an established cause: to judge by reading, not by script. Flagged (to look at): overlaps of two labels of the same family on the same station. """ import glob import json import os import re import sys AUTO = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "auto") # ~/aimsight-labeling/auto, or through the labeling/ link FAMILIES = {"Visibility", "Obstruction", "Thermal displacement", "Displacement", "Target issue", "No data"} DATE = re.compile(r"^\d{4}-\d\d-\d\dT\d\d:\d\dZ$") # A decimal comma (names such as F4.2 and dates such as 05.10 carry a dot), or a number followed by a unit. NUMBER = re.compile(r"(? [text]. proposed: a label not yet submitted, without `review` nor `id`. For a caller (aimsight-app: a label written in auto/).""" errors = [] missing = ({"start", "end", "family", "description"} | (set() if proposed else {"review", "id"})) - e.keys() if missing: errors.append(f"missing field: {sorted(missing)}") if "id" in e and next(iter(e)) != "id": errors.append("id not first in the line (`python3 labeling/scripts/ids.py`)") if e.get("family") not in FAMILIES: errors.append(f"unknown family: {e.get('family')}") if not (DATE.match(e.get("start") or "") and DATE.match(e.get("end") or "")): return errors + ["malformed date"] if e["start"] >= e["end"]: errors.append(f"start >= end ({e['start']})") d = e.get("description") or "" if "description" in e and not d.strip(): errors.append("empty description") if m := NUMBER.search(d): errors.append(f"numeric value: \"{m.group(0)}\"") if m := FORBIDDEN.search(d): errors.append(f"forbidden: \"{m.group(0)}\"") return errors def main(): stations = sys.argv[1:] or sorted(os.path.basename(p)[:-6] for p in glob.glob(os.path.join(AUTO, "*.jsonl"))) errors, flagged, total = [], [], 0 for st in stations: seen, ids, labels = set(), set(), [] proposed = st.endswith(".jsonl") # a proposed file: its lines have no `review` nor `id` yet path = st if proposed else os.path.join(AUTO, f"{st}.jsonl") for n, line in enumerate(open(path, encoding="utf-8"), 1): if not line.strip(): continue total += 1 where = f"{st}#{n}" try: e = json.loads(line) except json.JSONDecodeError: errors.append(f"{where} unreadable JSON"); continue found = check(e, proposed) if "id" in e: if e["id"] in ids: found.append(f"duplicate id: {e['id']}") ids.add(e["id"]) errors += [f"{where} {f}" for f in found] if "malformed date" in found: continue key = (e["start"], e["end"], e.get("family"), e.get("description")) if key in seen: errors.append(f"{where} exact duplicate") seen.add(key) labels.append((where, e)) for i, (a, x) in enumerate(labels): for b, y in labels[i + 1:]: if x.get("family") == y.get("family") and x["start"] < y["end"] and y["start"] < x["end"]: flagged.append(f"{a} and {b}: two {x.get('family')} that overlap") print(f"{total} labels, {len(stations)} stations: {len(errors)} errors, {len(flagged)} overlaps to look at") for l in errors: print(" ERROR", l) for l in flagged[:40]: print(" to look at", l) if len(flagged) > 40: print(f" … and {len(flagged) - 40} other overlaps") sys.exit(1 if errors else 0) if __name__ == "__main__": main()