def test_inspection_of_both_sides_of_splitting_plane(self):
'''
While walking down the kdtree, find_closest chooses to inspect points
in the left_child or right_child of a node based on whether the
ref_location is on the "left" or "right" side of the splitting plane
created by the node.
If the ref_location is closer to the splitting plane than to the
current closest, then the true closest neighbor might be on the other
side of the splitting plane.
If find_closest is doing *everything else* correctly *except*
inspecting both sides of the splitting plane (when necessary),
then find_closest will return "D" as the closest neighbor here,
rather than "E".
'''
neighbors_coords = [
('A', 1.00, 1.00),
('B', 1.20, 2.00),
('C', 2.50, 3.50),
('D', 3.50, 2.80),
('E', 3.70, 0.80),
('F', 4.25, 1.80),
('G', 6.00, 5.60)
]
neighbors_df = TestFindClosest.coords_to_df(neighbors_coords)
ref_location = (3.36, 0.9)
tree = build_kd_tree(neighbors_df)
result = find_closest(ref_location, tree)
self.assertEqual(result.name, "E")
self.assertEqual(result.coordinates, (3.7, 0.8))
def test_1000_random_10D_points(self): total_runs = 5 num_dimensions = 10 for run_num in range(1, total_runs + 1): print( "Testing 1000 random 10D points, run" + "%d/%d" % (run_num, total_runs) ) def rand_val(): # Choose values between -1 and 1. r = random.randint(-1000, 1000) while r == 0: r = random.randint(-1000, 1000) return 1. / r # Make 10 random points, with 10 random names. neighbors_coords = [ (uuid.uuid4().hex,) + tuple((rand_val() for _ in range(num_dimensions))) for _ in range(1000) ] neighbors_df = TestFindClosest.coords_to_df(neighbors_coords) # Generate a random reference location. ref_location = tuple(rand_val() for _ in range(num_dimensions)) tree = build_kd_tree(neighbors_df) result = find_closest(ref_location, tree) expected_name, expected_coords = find_closest_with_brute_force( neighbors_df, ref_location ) self.assertEqual(result.name, expected_name) self.assertEqual(result.coordinates, expected_coords)
def test_basic(self):
neighbors_coords = [
('A', -6, 3),
('B', 2, 2.2),
('C', 3, -6),
]
neighbors_df = TestFindClosest.coords_to_df(neighbors_coords)
ref_location = (-1, -2)
tree = build_kd_tree(neighbors_df)
result = find_closest(ref_location, tree)
self.assertEqual(result.name, "B")
self.assertEqual(result.coordinates, (2, 2.2))
def test_all_neighbors_equal(self):
neighbors_coords = [
('A', 1.1, 1.3),
('B', 1.1, 1.3),
]
neighbors_df = TestFindClosest.coords_to_df(neighbors_coords)
ref_location = (-1, -2)
tree = build_kd_tree(neighbors_df)
result = find_closest(ref_location, tree)
# Not testing the name here. The algorithm does not
# promise stable traversal of the tree.
self.assertEqual(result.coordinates, (1.1, 1.3))