from collections import defaultdict


def reliability_table(results: list[tuple[float, bool]], bins: int = 5) -> None:
    """results: (confidence, was_correct) pairs from a labelled eval set."""
    buckets: dict[int, list[bool]] = defaultdict(list)
    for conf, correct in results:
        buckets[min(int(conf * bins), bins - 1)].append(correct)

    print(f"{'bucket':<12}{'n':>6}{'accuracy':>10}")
    for b in range(bins):
        hits = buckets.get(b, [])
        lo, hi = b / bins, (b + 1) / bins
        acc = f"{sum(hits) / len(hits):.2f}" if hits else "-"
        print(f"{lo:.1f}-{hi:.1f}".ljust(12) + f"{len(hits):>6}{acc:>10}")


def coverage_curve(results: list[tuple[float, bool]], thresholds=(0.5, 0.7, 0.8, 0.9, 0.95)) -> None:
    """For each threshold: share of items automated, and accuracy on that share."""
    total = len(results)
    print(f"{'threshold':<11}{'coverage':>10}{'sel. accuracy':>15}")
    for t in thresholds:
        kept = [ok for conf, ok in results if conf >= t]
        cov = len(kept) / total
        acc = sum(kept) / len(kept) if kept else float("nan")
        print(f"{t:<11}{cov:>10.1%}{acc:>15.1%}")