def test_query_haversine():
rng = check_random_state(0)
X = 2 * np.pi * rng.random_sample((40, 2))
bt = BallTree(X, leaf_size=1, metric='haversine')
dist1, ind1 = bt.query(X, k=5)
dist2, ind2 = brute_force_neighbors(X, X, k=5, metric='haversine')
assert_array_almost_equal(dist1, dist2)
assert_array_almost_equal(ind1, ind2)
def test_ball_tree_query_metrics(metric):
rng = check_random_state(0)
if metric in BOOLEAN_METRICS:
X = rng.random_sample((40, 10)).round(0)
Y = rng.random_sample((10, 10)).round(0)
elif metric in DISCRETE_METRICS:
X = (4 * rng.random_sample((40, 10))).round(0)
Y = (4 * rng.random_sample((10, 10))).round(0)
k = 5
bt = BallTree(X, leaf_size=1, metric=metric)
dist1, ind1 = bt.query(Y, k)
dist2, ind2 = brute_force_neighbors(X, Y, k, metric)
assert_array_almost_equal(dist1, dist2)
def test_gaussian_kde(n_samples=1000):
# Compare gaussian KDE results to scipy.stats.gaussian_kde
from scipy.stats import gaussian_kde
rng = check_random_state(0)
x_in = rng.normal(0, 1, n_samples)
x_out = np.linspace(-5, 5, 30)
for h in [0.01, 0.1, 1]:
bt = BallTree(x_in[:, None])
gkde = gaussian_kde(x_in, bw_method=h / np.std(x_in))
dens_bt = bt.kernel_density(x_out[:, None], h) / n_samples
dens_gkde = gkde.evaluate(x_out)
assert_array_almost_equal(dens_bt, dens_gkde, decimal=3)
def test_ball_tree_query_radius(n_samples=100, n_features=10):
rng = check_random_state(0)
X = 2 * rng.random_sample(size=(n_samples, n_features)) - 1
query_pt = np.zeros(n_features, dtype=float)
eps = 1E-15 # roundoff error can cause test to fail
bt = BallTree(X, leaf_size=5)
rad = np.sqrt(((X - query_pt)**2).sum(1))
for r in np.linspace(rad[0], rad[-1], 100):
ind = bt.query_radius([query_pt], r + eps)[0]
i = np.where(rad <= r + eps)[0]
ind.sort()
i.sort()
assert_array_almost_equal(i, ind)
def test_ball_tree_query(metric, k, dualtree, breadth_first):
rng = check_random_state(0)
X = rng.random_sample((40, DIMENSION))
Y = rng.random_sample((10, DIMENSION))
kwargs = METRICS[metric]
bt = BallTree(X, leaf_size=1, metric=metric, **kwargs)
dist1, ind1 = bt.query(Y,
k,
dualtree=dualtree,
breadth_first=breadth_first)
dist2, ind2 = brute_force_neighbors(X, Y, k, metric, **kwargs)
# don't check indices here: if there are any duplicate distances,
# the indices may not match. Distances should not have this problem.
assert_array_almost_equal(dist1, dist2)
def test_ball_tree_query_radius_distance(n_samples=100, n_features=10):
rng = check_random_state(0)
X = 2 * rng.random_sample(size=(n_samples, n_features)) - 1
query_pt = np.zeros(n_features, dtype=float)
eps = 1E-15 # roundoff error can cause test to fail
bt = BallTree(X, leaf_size=5)
rad = np.sqrt(((X - query_pt)**2).sum(1))
for r in np.linspace(rad[0], rad[-1], 100):
ind, dist = bt.query_radius([query_pt], r + eps, return_distance=True)
ind = ind[0]
dist = dist[0]
d = np.sqrt(((query_pt - X[ind])**2).sum(1))
assert_array_almost_equal(d, dist)
def test_ball_tree_kde(kernel,
h,
rtol,
atol,
breadth_first,
n_samples=100,
n_features=3):
rng = np.random.RandomState(0)
X = rng.random_sample((n_samples, n_features))
Y = rng.random_sample((n_samples, n_features))
bt = BallTree(X, leaf_size=10)
dens_true = compute_kernel_slow(Y, X, kernel, h)
dens = bt.kernel_density(Y,
h,
atol=atol,
rtol=rtol,
kernel=kernel,
breadth_first=breadth_first)
assert_allclose(dens, dens_true, atol=atol, rtol=max(rtol, 1e-7))
def test_ball_tree_pickle():
rng = check_random_state(0)
X = rng.random_sample((10, 3))
bt1 = BallTree(X, leaf_size=1)
# Test if BallTree with callable metric is picklable
bt1_pyfunc = BallTree(X, metric=dist_func, leaf_size=1, p=2)
ind1, dist1 = bt1.query(X)
ind1_pyfunc, dist1_pyfunc = bt1_pyfunc.query(X)
def check_pickle_protocol(protocol):
s = pickle.dumps(bt1, protocol=protocol)
bt2 = pickle.loads(s)
s_pyfunc = pickle.dumps(bt1_pyfunc, protocol=protocol)
bt2_pyfunc = pickle.loads(s_pyfunc)
ind2, dist2 = bt2.query(X)
ind2_pyfunc, dist2_pyfunc = bt2_pyfunc.query(X)
assert_array_almost_equal(ind1, ind2)
assert_array_almost_equal(dist1, dist2)
assert_array_almost_equal(ind1_pyfunc, ind2_pyfunc)
assert_array_almost_equal(dist1_pyfunc, dist2_pyfunc)
assert isinstance(bt2, BallTree)
for protocol in (0, 1, 2):
check_pickle_protocol(protocol)
def test_ball_tree_two_point(n_samples=100, n_features=3):
rng = check_random_state(0)
X = rng.random_sample((n_samples, n_features))
Y = rng.random_sample((n_samples, n_features))
r = np.linspace(0, 1, 10)
bt = BallTree(X, leaf_size=10)
D = DistanceMetric.get_metric("euclidean").pairwise(Y, X)
counts_true = [(D <= ri).sum() for ri in r]
def check_two_point(r, dualtree):
counts = bt.two_point_correlation(Y, r=r, dualtree=dualtree)
assert_array_almost_equal(counts, counts_true)
for dualtree in (True, False):
check_two_point(r, dualtree)