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_single():
t = TDigest()
t.add(10)
assert t.min() == 10
assert t.max() == 10
assert t.size() == 1
assert t.quantile(0) == 10
assert t.quantile(0.5) == 10
assert t.quantile(1) == 10
assert t.cdf(9) == 0
assert t.cdf(10) == 0.5
assert t.cdf(11) == 1
def test_weights():
t = TDigest()
t.add(1, 10)
assert t.size() == 10
x = np.arange(5)
w = np.array([1, 2, 1, 2, 1])
t = TDigest()
t.update(x, 10)
assert t.size() == len(x) * 10
t = TDigest()
t.update(x, w)
assert t.size() == w.sum()
def test_update_non_numeric_errors():
data = np.array(['foo', 'bar', 'baz'])
t = TDigest()
with pytest.raises(TypeError):
t.update(data)
with pytest.raises(TypeError):
t.update(1, data)
with pytest.raises(TypeError):
t.add('foo')
with pytest.raises(TypeError):
t.add(1, 'foo')
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_nonfinite():
t = TDigest()
data = gamma.copy()
data[::10] = np.nan
data[::7] = np.inf
t.update(data)
finite = data[np.isfinite(data)]
assert t.size() == len(finite)
assert t.min() == finite.min()
assert t.max() == finite.max()
t = TDigest()
t.add(np.nan)
t.add(np.inf)
t.add(-np.inf)
assert t.size() == 0
for w in [np.inf, -np.inf, np.nan]:
t = TDigest()
with pytest.raises(ValueError):
t.add(1, w)
w = np.array([1, 2, w, 3, 4])
t = TDigest()
with pytest.raises(ValueError):
t.update(np.ones(5), w)
