def test_equal_entries(self):
settings = {"cubes": 10, "overlap": 0.5}
# uniform data:
data = np.arange(0, 100)
data = data[:, np.newaxis]
lens = data
cov = Cover(settings["cubes"], settings["overlap"])
# Prefix'ing the data with an ID column
ids = np.array([x for x in range(lens.shape[0])])
lens = np.c_[ids, lens]
bins = cov.fit(lens)
bins = list(bins) # extract list from generator
assert len(bins) == settings["cubes"]
cube_entries = [cov.transform_single(lens, cube) for cube in bins]
for c1, c2 in list(zip(cube_entries, cube_entries[1:]))[2:]:
c1, c2 = c1[:, 0], c2[:, 0] # indices only
calced_overlap = len(set(list(c1)).intersection(set(list(c2)))) / max(
len(c1), len(c2)
)
assert calced_overlap == pytest.approx(0.5)
def test_entries_in_correct_cubes(self):
# TODO: this test is a little hacky
data_vals = np.arange(20)
data = np.zeros((20, 2))
data[:, 0] = np.arange(20, dtype=int) # Index row
data[:, 1] = data_vals
cover = Cover(n_cubes=10, perc_overlap=0.2)
cubes = cover.fit(data)
cubes = list(cubes)
entries = [cover.transform_single(data, cube) for cube in cubes]
# inside of each cube is there. Sometimes the edges don't line up.
for i in range(10):
assert data[2 * i] in entries[i]
assert data[2 * i + 1] in entries[i]
def test_perc_overlap(self, CoverClass):
"""
2 cubes with 50% overlap and a range of [0,1] should lead to two cubes with intervals:
[0, .75]
[.25, 1]
"""
data = np.array([[0, 0], [1, 0.25], [2, 0.5], [3, 0.75], [4, 1]])
cover = Cover(n_cubes=2, perc_overlap=0.5)
cubes = cover.fit(data)
cubes = list(cubes)
entries = [cover.transform_single(data, cube) for cube in cubes]
for i in (0, 1, 2, 3):
assert data[i] in entries[0]
for i in (1, 2, 3, 4):
assert data[i] in entries[1]
def test_125_replication(self):
# uniform data:
data = np.arange(0, 100)
data = data[:, np.newaxis]
lens = data
cov = Cover(10, 0.5)
# Prefix'ing the data with an ID column
ids = np.array([x for x in range(lens.shape[0])])
lens = np.c_[ids, lens]
bins = cov.fit(lens)
cube_entries = [cov.transform_single(lens, cube) for cube in bins]
overlaps = [
len(set(list(c1[:, 0])).intersection(set(list(c2[:, 0]))))
for c1, c2 in zip(cube_entries, cube_entries[1:])
]
assert (len(set(overlaps)) == 1
), "Each overlap should have the same number of entries. "
def test_transform_runs_with_diff_bins(self):
data = np.arange(30).reshape(10, 3)
c = Cover(n_cubes=[5, 10])
cubes = list(c.fit(data))
_ = c.transform_single(data, cubes[0])