Tính năng phần mềm · Lấy mẫu hồ chứa từ luồng

from random import Random

def reservoir_sample(items, size, seed):
    if type(size) is not int or not 0 <= size <= 32:
        raise ValueError("size.range")
    if type(seed) is not int or not 0 <= seed < 2**32:
        raise ValueError("seed.range")
    rng, sample, count = Random(seed), [], 0
    for index, item in enumerate(items):
        count = index + 1
        if count > 1000:
            raise ValueError("stream.limit")
        if index < size:
            sample.append(item)
        elif size:
            position = rng.randrange(count)
            if position < size:
                sample[position] = item
    if size > count:
        raise ValueError("stream.short")
    return sample