rohitg00/ai-engineering-from-scratch · error · ValueError

n, c >= 0 and k > 0

Error message

n, c >= 0 and k > 0

What it means

Error "n, c >= 0 and k > 0" thrown in rohitg00/ai-engineering-from-scratch.

Source

Thrown at phases/19-capstone-projects/72-code-exec-metric/code/main.py:255

    if exit_code not in EXIT_CODES:
        exit_code = EXIT_ERROR
    if exit_code == EXIT_PASS and passed < total:
        exit_code = EXIT_ASSERTION_FAIL
    if exit_code == EXIT_ASSERTION_FAIL and passed == total and total > 0:
        exit_code = EXIT_PASS
    return ExecResult(score, exit_code, passed, total, detail=detail, per_assertion=results)


def score_code_exec(prediction: str, assertions: list[str], timeout_s: float = DEFAULT_TIMEOUT_S) -> float:
    code = extract_code(prediction)
    if code is None:
        return 0.0
    return run_candidate(code, assertions, timeout_s=timeout_s).score


def pass_at_k(n: int, c: int, k: int) -> float:
    if n < 0 or c < 0 or k <= 0:
        raise ValueError("n, c >= 0 and k > 0")
    if c > n:
        raise ValueError("c cannot exceed n")
    if k > n:
        return float(c > 0)
    if n - c < k:
        return 1.0
    log_prob = 0.0
    for i in range(k):
        log_prob += math.log(n - c - i) - math.log(n - i)
    return float(1.0 - math.exp(log_prob))


def pass_at_k_estimator(samples: list[list[bool]], ks: list[int]) -> dict[int, float]:
    out: dict[int, float] = {}
    for k in ks:
        per_task = []
        for sample in samples:
            n = len(sample)

View on GitHub (pinned to 39ea8a1c6d)

When it happens

Trigger: Thrown at phases/19-capstone-projects/72-code-exec-metric/code/main.py:255 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of rohitg00/ai-engineering-from-scratch@39ea8a1c6d (2026-08-26). Data as JSON: /api/errors/dca1888813263a70. Report an issue: GitHub.