从scipy稀疏矩阵中求n个随机零元

这是一种基于拒绝抽样的方法。根据示例中的数字,随机选择的索引可能为零,因此这是一种相对有效的方法。

from scipy import sparse

dims = (281903, 281903)

mat = sparse.lil_matrix(dims, dtype=np.int)

for _ in range(1000):
    x, y = np.random.randint(0, dims[0], 2)
    mat[x, y] = 1


def sample_zero_forever(mat):
    nonzero_or_sampled = set(zip(*mat.nonzero()))
    while True:
        t = tuple(np.random.randint(0, mat.shape[0], 2))
        if t not in nonzero_or_sampled:
            yield t
            nonzero_or_sampled.add(t)


def sample_zero_n(mat, n=100):
    itr = sample_zero_forever(mat)
    return [next(itr) for _ in range(n)]