def evaluate_functional_correctness()

in human_eval_infilling/evaluation.py [0:0]

• 6 lines of code
• 1 McCabe index (conditional complexity)

def evaluate_functional_correctness(
    benchmark_name: str,
    sample_file: str,
    k: List[int] = [1, 10, 100],
    n_workers: int = 4,
    timeout: float = 3.0,