def test_merge():
t = TDigest()
t2 = TDigest()
t3 = TDigest()
a = np.random.uniform(0, 1, N)
b = np.random.uniform(2, 3, N)
data = np.concatenate([a, b])
t2.update(a)
t3.update(b)
t2_centroids = t2.centroids()
t.merge(t2, t3)
assert t.min() == min(t2.min(), t3.min())
assert t.max() == max(t2.max(), t3.max())
assert t.size() == t2.size() + t3.size()
# Check no mutation of args
assert (t2.centroids() == t2_centroids).all()
# *Quantile
q = np.array([0.001, 0.01, 0.1, 0.3, 0.5, 0.7, 0.9, 0.99, 0.999])
est = t.quantile(q)
q_est = quantiles_to_q(data, est)
np.testing.assert_allclose(q, q_est, atol=0.012, rtol=0)
# *CDF
x = q_to_x(data, q)
q_est = t.cdf(x)
np.testing.assert_allclose(q, q_est, atol=0.005)
with pytest.raises(TypeError):
t.merge(t2, 'not a tdigest')
def test_small_w():
eps = np.finfo('f8').eps
t = TDigest()
t.update(gamma, eps)
assert t.size() == 0
assert len(t.centroids()) == 0
t = TDigest()
t.add(1, eps)
assert t.size() == 0
assert len(t.centroids()) == 0
def test_scale():
t = TDigest()
t.update(uniform)
for factor in [0.5, 2]:
t2 = t.scale(factor)
assert t is not t2
assert t.size() * factor == t2.size()
assert t.min() == t2.min()
assert t.max() == t2.max()
a = t.centroids()
b = t2.centroids()
np.testing.assert_array_equal(a['mean'], b['mean'])
np.testing.assert_allclose(a['weight'] * factor, b['weight'])
for val in [-0.5, 0, np.nan, np.inf]:
with pytest.raises(ValueError):
t.scale(val)
with pytest.raises(TypeError):
t.scale('foobar')
# Test scale compacts
eps = np.finfo('f8').eps
t = TDigest()
t.update([1, 2, 3, 4, 5],
[1, 1000, 1, 10000, 1])
t2 = t.scale(eps)
assert len(t2.centroids()) == 2
# Compacts to 0
t = TDigest()
t.update([1, 2, 3, 4, 5])
t2 = t.scale(eps)
assert len(t2.centroids()) == 0
def test_empty():
t = TDigest()
assert t.size() == 0
assert len(t.centroids()) == 0
assert np.isnan(t.min())
assert np.isnan(t.max())
assert np.isnan(t.quantile(0.5))
assert np.isnan(t.cdf(0.5))