def test_hypersphere(dimensions, rng):
n = 150 * dimensions
if dimensions < 1:
with pytest.raises(ValueError):
dist = dists.UniformHypersphere().sample(1, dimensions)
else:
dist = dists.UniformHypersphere()
samples = dist.sample(n, dimensions, rng=rng)
assert samples.shape == (n, dimensions)
assert np.allclose(np.mean(samples, axis=0), 0, atol=0.1)
hist, _ = np.histogramdd(samples, bins=5)
assert np.allclose(hist - np.mean(hist), 0, atol=0.1 * n)
def test_hypersphere_surface(dimensions, rng):
n = 150 * dimensions
dist = dists.UniformHypersphere(surface=True)
samples = dist.sample(n, dimensions, rng=rng)
assert samples.shape == (n, dimensions)
assert np.allclose(npext.norm(samples, axis=1), 1)
assert np.allclose(np.mean(samples, axis=0), 0, atol=0.25 / dimensions)
def test_hypersphere_volume(min_magnitude, d, rng):
n = 150 * d
dist = dists.UniformHypersphere(min_magnitude=min_magnitude)
samples = dist.sample(n, d, rng=rng)
assert samples.shape == (n, d)
assert np.allclose(np.mean(samples, axis=0), 0, atol=0.1)
assert np.all(npext.norm(samples, axis=1) >= min_magnitude)
def test_cosine_intercept(d, p, rng):
"""Tests CosineSimilarity inverse cdf for finding intercepts."""
pytest.importorskip('scipy') # betaincinv
num_samples = 250
exp_dist = dists.UniformHypersphere(surface=True)
act_dist = dists.CosineSimilarity(d)
dots = exp_dist.sample(num_samples, d, rng=rng)[:, 0]
# Find the desired intercept so that dots >= c with probability p
c = act_dist.ppf(1 - p)
assert np.allclose(np.sum(dots >= c) / float(num_samples), p, atol=0.05)
def test_distorarrayparam():
"""DistOrArrayParams can be distributions or samples."""
class Test(object):
dp = dists.DistOrArrayParam(default=None, sample_shape=['*', '*'])
inst = Test()
inst.dp = dists.UniformHypersphere()
assert isinstance(inst.dp, dists.UniformHypersphere)
inst.dp = np.array([[1], [2], [3]])
assert np.all(inst.dp == np.array([[1], [2], [3]]))
with pytest.raises(ValueError):
inst.dp = 'a'
# Sample must have correct dims
with pytest.raises(ValueError):
inst.dp = np.array([1])
def test_distorarrayparam_sample_shape():
"""sample_shape dictates the shape of the sample that can be set."""
class Test(object):
dp = dists.DistOrArrayParam(default=None, sample_shape=['d1', 10])
d1 = 4
inst = Test()
# Distributions are still cool
inst.dp = dists.UniformHypersphere()
assert isinstance(inst.dp, dists.UniformHypersphere)
# Must be shape (4, 10)
inst.dp = np.ones((4, 10))
assert np.all(inst.dp == np.ones((4, 10)))
with pytest.raises(ValueError):
inst.dp = np.ones((10, 4))
assert np.all(inst.dp == np.ones((4, 10)))
def test_cosine_similarity(d, rng):
"""Tests CosineSimilarity sampling."""
num_samples = 2500
num_bins = 5
# Check that it gives a single dimension from UniformHypersphere
exp_dist = dists.UniformHypersphere(surface=True)
act_dist = dists.CosineSimilarity(d)
exp = exp_dist.sample(num_samples, d, rng=rng)[:, 0]
act = act_dist.sample(num_samples, rng=rng)
exp_hist, _ = np.histogram(exp, bins=num_bins)
act_hist, _ = np.histogram(act, bins=num_bins)
assert np.all(np.abs(np.asfarray(exp_hist - act_hist) / num_samples) < 0.1)
def test_hypersphere_warns(rng):
with pytest.warns(UserWarning):
dists.UniformHypersphere(surface=True, min_magnitude=0.1)
def test_hypersphere_dimension_fail(rng):
with pytest.raises(ValueError):
dists.UniformHypersphere(0).sample(1, 0)
