feat: 標註工具與試跑 (#5)

標籤白名單、標註指示、批次切分、合併與檢查、抽查清單，以及 100 句試跑結果。 Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-14 17:35:09 +00:00
parent 9cf8196a3e
commit c85e00a56e
6 changed files with 329 additions and 0 deletions
@@ -0,0 +1,74 @@
+#!/usr/bin/env python3
+"""把對白切成給標註 sub-agent 的批次檔。
+
+用法：
+  make_batches.py <dialogues.jsonl> <輸出目錄> --pilot N   # 試跑：分層抽樣 N 句
+  make_batches.py <dialogues.jsonl> <輸出目錄> --all       # 全量：規則未判定或中信心的對白
+
+每批一個 jsonl，一行一句，附前後各 2 句對白當輪流發言的線索。
+批次檔不含規則判定的說話者，讓標註獨立，之後才能拿來和規則比對。
+"""
+import argparse
+import json
+import random
+from collections import defaultdict
+from pathlib import Path
+
+
+def short(rec, n=60):
+    t = rec["text"]
+    return {"id": rec["id"], "text": t if len(t) <= n else t[:n] + "…"}
+
+
+def with_neighbors(recs):
+    by_chapter = defaultdict(list)
+    for r in recs:
+        by_chapter[(r["volume"], r["chapter"])].append(r)
+    index = {}
+    for rows in by_chapter.values():
+        for i, r in enumerate(rows):
+            index[r["id"]] = {"prev": [short(x) for x in rows[max(0, i - 2):i]], "next": [short(x) for x in rows[i + 1:i + 3]]}
+    return index
+
+
+def pilot_sample(recs, n, seed):
+    rng = random.Random(seed)
+    unlabeled = [r for r in recs if not r["speaker"]]
+    medium = [r for r in recs if r["confidence"] == "medium"]
+    high = [r for r in recs if r["confidence"] == "high"]
+    take = [(unlabeled, n // 2), (medium, n // 4), (high, n - n // 2 - n // 4)]
+    out = []
+    for pool, k in take:
+        out += rng.sample(pool, min(k, len(pool)))
+    rng.shuffle(out)
+    return out
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("dialogues")
+    ap.add_argument("outdir")
+    ap.add_argument("--pilot", type=int)
+    ap.add_argument("--all", action="store_true")
+    ap.add_argument("--batch-size", type=int, default=25)
+    ap.add_argument("--seed", type=int, default=7)
+    a = ap.parse_args()
+    if bool(a.pilot) == a.all:
+        ap.error("--pilot N 與 --all 擇一")
+    recs = [json.loads(line) for line in Path(a.dialogues).read_text(encoding="utf-8").splitlines()]
+    nb = with_neighbors(recs)
+    chosen = pilot_sample(recs, a.pilot, a.seed) if a.pilot else [r for r in recs if r["confidence"] != "high"]
+    out = Path(a.outdir)
+    out.mkdir(parents=True, exist_ok=True)
+    for i in range(0, len(chosen), a.batch_size):
+        path = out / f"batch-{i // a.batch_size + 1:03d}.jsonl"
+        with path.open("w", encoding="utf-8") as fh:
+            for r in chosen[i:i + a.batch_size]:
+                item = {k: r[k] for k in ("id", "text", "before", "after", "prev_par", "next_par", "candidates", "suspect_duplicate")}
+                item.update(nb[r["id"]])
+                fh.write(json.dumps(item, ensure_ascii=False) + "\n")
+    print(f"{len(chosen)} 句 -> {(len(chosen) + a.batch_size - 1) // a.batch_size} 批 -> {out}")
+
+
+if __name__ == "__main__":
+    main()