def test_histogram():
t = TDigest()
data = np.random.normal(size=10000)
t.update(data)
hist, bins = t.histogram(100)
assert len(hist) == 100
assert len(bins) == 101
c = t.cdf(bins)
np.testing.assert_allclose((c[1:] - c[:-1]) * t.size(), hist)
min = t.min()
max = t.max()
eps = np.finfo('f8').eps
bins = np.array([min - 1, min - eps,
min, min + (max - min)/2, max,
max + eps, max + 1])
hist, bins2 = t.histogram(bins)
np.testing.assert_allclose(bins, bins2)
assert hist[0] == 0
assert hist[1] == 0
assert hist[-2] == 0
assert hist[-1] == 0
assert hist.sum() == t.size()
# range ignored when bins provided
hist2, bins2 = t.histogram(bins, range=(-5, -3))
np.testing.assert_allclose(hist, hist2)
np.testing.assert_allclose(bins, bins2)
def test_histogram_small_n():
t = TDigest()
t.add(1)
hist, bins = t.histogram(10)
assert len(hist) == 10
assert len(bins) == 11
assert bins[0] == 0.5
assert bins[-1] == 1.5
assert hist.sum() == 1
t.add(2)
hist, bins = t.histogram(10)
assert hist.sum() == 2
assert bins[0] == 1
assert bins[-1] == 2
hist, bins = t.histogram(range=(-5, -3))
assert hist.sum() == 0
def test_histogram_empty():
t = TDigest()
for b, r in [(5, None), (5, (-1, 1)), (np.arange(6), None)]:
hist, bins = t.histogram(bins=b, range=r)
assert len(hist) == 5
assert len(bins) == 6
if r is not None:
assert bins[0] == r[0]
assert bins[-1] == r[1]
assert (hist == 0).all()
assert (np.diff(bins) > 0).all()
def test_histogram_errors():
t = TDigest()
t.update(np.random.uniform(1000))
for r in [('a', 'b'), 1]:
with pytest.raises(TypeError):
t.histogram(range=r)
with pytest.raises(Exception):
t.histogram(range=1)
for r in [(np.nan, 1), (np.inf, 1), (1, np.nan), (1, np.inf)]:
with pytest.raises(ValueError):
t.histogram(range=r)
with pytest.raises(ValueError):
t.histogram(range=(1, 0))
for b in ['a', -1, np.arange(4).reshape((2, 2)),
np.arange(0, 10, -1), np.array([np.nan, 0, 1])]:
with pytest.raises(ValueError):
t.histogram(bins=b)