| """Rewrite DAD per-frame action labels in cot_corpus_v3 manifests per user rule: |
| |
| DAD positives (event at t=3s of 4s @ 25fps clip): |
| → all 8 frames of every tick → ALERT |
| → tick_action = ALERT |
| DAD negatives (no event): |
| → all 8 frames → SILENT |
| → tick_action = SILENT |
| |
| No OBSERVE state for DAD. |
| |
| Reads: data/cot_corpus_v3/v4_sft_{train,val,test}_full.jsonl |
| Writes: data/cot_corpus_v3/v4_sft_{train,val,test}_full_relabeled.jsonl |
| """ |
| from __future__ import annotations |
| import json |
| import logging |
| from collections import Counter |
| from pathlib import Path |
|
|
| ROOT = Path("PROJECT_ROOT") |
| COT_DIR = ROOT / "data/cot_corpus_v3" |
| SPLITS = ["v4_sft_train_full", "v4_sft_val_full", "v4_sft_test_full"] |
|
|
| logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s") |
| logger = logging.getLogger("dad_relabel") |
|
|
|
|
| def is_dad_positive(rec: dict) -> bool: |
| """A DAD record is positive iff its tta_raw indicates a known accident. |
| DAD positives have tta_raw > 0 in the manifest (they're aligned so the |
| last frame is near t=3s, the hardcoded event time).""" |
| tta = rec.get("tick_tta_raw", -1.0) |
| return rec.get("source") == "dad" and tta is not None and tta >= 0 |
|
|
|
|
| def relabel_dad(rec: dict) -> tuple[dict, str]: |
| """Return (new_record, change_kind) where change_kind ∈ {kept, alert, silent}.""" |
| if rec.get("source") != "dad": |
| return rec, "kept" |
|
|
| new = dict(rec) |
| if is_dad_positive(rec): |
| |
| new["actions_per_frame"] = ["ALERT"] * 8 |
| new["tick_action"] = "ALERT" |
| change = "alert" |
| else: |
| |
| new["actions_per_frame"] = ["SILENT"] * 8 |
| new["tick_action"] = "SILENT" |
| change = "silent" |
| return new, change |
|
|
|
|
| def process_split(split_tag: str) -> dict: |
| in_path = COT_DIR / f"{split_tag}.jsonl" |
| out_path = COT_DIR / f"{split_tag}_relabeled.jsonl" |
| if not in_path.exists(): |
| logger.warning(f"[skip] {in_path} not found") |
| return {} |
|
|
| n_total = n_dad = n_alert = n_silent = n_other = 0 |
| before_tick = Counter() |
| after_tick = Counter() |
| by_src = Counter() |
| with in_path.open() as fin, out_path.open("w") as fout: |
| for ln in fin: |
| ln = ln.strip() |
| if not ln: continue |
| rec = json.loads(ln) |
| n_total += 1 |
| src = rec.get("source", "?") |
| by_src[src] += 1 |
| before_tick[(src, rec.get("tick_action", "?"))] += 1 |
|
|
| new, kind = relabel_dad(rec) |
| if src == "dad": |
| n_dad += 1 |
| if kind == "alert": n_alert += 1 |
| elif kind == "silent": n_silent += 1 |
| else: n_other += 1 |
| after_tick[(new.get("source", "?"), new.get("tick_action", "?"))] += 1 |
| fout.write(json.dumps(new) + "\n") |
|
|
| logger.info(f"[{split_tag}] N={n_total} DAD records={n_dad} " |
| f"→ ALERT={n_alert} → SILENT={n_silent} unchanged={n_other}") |
| logger.info(f"[{split_tag}] saved → {out_path}") |
| return { |
| "split": split_tag, |
| "in_path": str(in_path), |
| "out_path": str(out_path), |
| "n_total": n_total, |
| "n_dad": n_dad, |
| "n_dad_positive_to_alert": n_alert, |
| "n_dad_negative_to_silent": n_silent, |
| "by_source_before": {f"{k[0]}/{k[1]}": v for k, v in sorted(before_tick.items()) |
| if k[0] == "dad"}, |
| "by_source_after": {f"{k[0]}/{k[1]}": v for k, v in sorted(after_tick.items()) |
| if k[0] == "dad"}, |
| } |
|
|
|
|
| def main(): |
| out_summary = [] |
| for tag in SPLITS: |
| out_summary.append(process_split(tag)) |
| summary_path = COT_DIR / "_relabel_dad_summary.json" |
| summary_path.write_text(json.dumps(out_summary, indent=2)) |
| logger.info(f"[summary] saved → {summary_path}") |
|
|
| |
| print("\n=== DAD RELABEL SUMMARY ===") |
| for s in out_summary: |
| print(f"\n{s['split']}: {s['n_dad']} DAD records → " |
| f"{s['n_dad_positive_to_alert']} ALERT, {s['n_dad_negative_to_silent']} SILENT") |
| print(" before:") |
| for k, v in s["by_source_before"].items(): |
| print(f" {k}: {v}") |
| print(" after:") |
| for k, v in s["by_source_after"].items(): |
| print(f" {k}: {v}") |
|
|
|
|
| if __name__ == "__main__": |
| main() |
|
|
