test_random_projection.py 文件源码

def test_random_projection_embedding_quality():
    data, _ = make_sparse_random_data(8, 5000, 15000)
    eps = 0.2

    original_distances = euclidean_distances(data, squared=True)
    original_distances = original_distances.ravel()
    non_identical = original_distances != 0.0

    # remove 0 distances to avoid division by 0
    original_distances = original_distances[non_identical]

    for RandomProjection in all_RandomProjection:
        rp = RandomProjection(n_components='auto', eps=eps, random_state=0)
        projected = rp.fit_transform(data)

        projected_distances = euclidean_distances(projected, squared=True)
        projected_distances = projected_distances.ravel()

        # remove 0 distances to avoid division by 0
        projected_distances = projected_distances[non_identical]

        distances_ratio = projected_distances / original_distances

        # check that the automatically tuned values for the density respect the
        # contract for eps: pairwise distances are preserved according to the
        # Johnson-Lindenstrauss lemma
        assert_less(distances_ratio.max(), 1 + eps)
        assert_less(1 - eps, distances_ratio.min())