# Standard library only. Saved real outputs; no new API call.
import csv
import json
import random
from pathlib import Path

rows = json.loads(Path(__file__).with_name("observed-rows.json").read_text())
if len({row["id"] for row in rows}) != len(rows):
    raise ValueError("Duplicate row ID")
for row in rows:
    probabilities = row["probabilities"]
    if not probabilities or any(not 0 <= p <= 1 for p in probabilities.values()):
        raise ValueError("Invalid probabilities")
    row["uncertainty"] = round(1 - max(probabilities.values()), 6)
ranked = sorted(rows, key=lambda row: (-row["uncertainty"], row["id"]))
review = ranked[:2]
remaining = [row for row in ranked if row not in review]
audit = random.Random(7).sample(remaining, min(1, len(remaining)))
output = Path.cwd() / "review-queue.csv"
# Exclusive creation avoids replacing someone's completed annotations.
with output.open("x", newline="", encoding="utf-8") as file:
    writer = csv.DictWriter(file, fieldnames=["id", "text", "predicted", "uncertainty", "selection", "reviewed_label"])
    writer.writeheader()
    for kind, selected in [("uncertainty", review), ("audit", audit)]:
        for row in selected:
            writer.writerow({**{k: row[k] for k in ["id", "text", "predicted", "uncertainty"]}, "selection": kind, "reviewed_label": ""})
print(json.dumps({"review_ids": [r["id"] for r in review], "audit_ids": [r["id"] for r in audit], "output": output.name}))
