def test_stump_two_constant_subsequences_A_B_join():
T_A = np.concatenate(
(np.zeros(10, dtype=np.float64), np.ones(10, dtype=np.float64)))
T_B = np.concatenate(
(np.zeros(20, dtype=np.float64), np.ones(5, dtype=np.float64)))
m = 3
left = utils.naive_stamp(T_A, m, T_B=T_B)
right = stump(T_A, m, T_B, ignore_trivial=False)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0]) # ignore indices
right = stump(pd.Series(T_A), m, pd.Series(T_B), ignore_trivial=False)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0]) # ignore indices
# Swap inputs
left = utils.naive_stamp(T_B, m, T_B=T_A)
right = stump(T_B, m, T_A, ignore_trivial=False)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0]) # ignore indices
right = stump(pd.Series(T_B), m, pd.Series(T_A), ignore_trivial=False)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0]) # ignore indices
def test_scrump_A_B_join_full(T_A, T_B):
m = 3
zone = int(np.ceil(m / 4))
left = utils.naive_stamp(T_A, m, T_B=T_B)
right_gen = scrump(T_A,
m,
T_B,
ignore_trivial=False,
percentage=1.0,
pre_scrump=False)
right = next(right_gen)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, :2], right)
# change roles
left = utils.naive_stamp(T_B, m, T_B=T_A)
right_gen = scrump(T_B,
m,
T_A,
ignore_trivial=False,
percentage=1.0,
pre_scrump=False)
right = next(right_gen)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, :2], right)
def test_stamp_A_B_join(T_A, T_B):
m = 3
left = utils.naive_stamp(T_A, m, T_B=T_B)
right = stamp.stamp(T_A, T_B, m)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, :2], right)
def test_stomp_A_B_join(T_A, T_B):
m = 3
left = utils.naive_stamp(T_A, m, T_B=T_B)
right = stomp._stomp(T_A, m, T_B, ignore_trivial=False)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_stump_nan_inf_A_B_join(T_A, T_B, substitute_A, substitute_B,
substitution_locations):
m = 3
T_A_sub = T_A.copy()
T_B_sub = T_B.copy()
for substitution_location_B in substitution_locations:
for substitution_location_A in substitution_locations:
T_A_sub[:] = T_A[:]
T_B_sub[:] = T_B[:]
T_A_sub[substitution_location_A] = substitute_A
T_B_sub[substitution_location_B] = substitute_B
left = utils.naive_stamp(T_A_sub, m, T_B=T_B_sub)
right = stump(T_A_sub, m, T_B_sub, ignore_trivial=False)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
right = stump(pd.Series(T_A_sub),
m,
pd.Series(T_B_sub),
ignore_trivial=False)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_stumped_A_B_join(T_A, T_B, dask_cluster):
with Client(dask_cluster) as dask_client:
m = 3
left = utils.naive_stamp(T_A, m, T_B=T_B)
right = stumped(dask_client, T_A, m, T_B, ignore_trivial=False)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_stamp_self_join(T_A, T_B):
m = 3
zone = int(np.ceil(m / 2))
left = utils.naive_stamp(T_B, m, exclusion_zone=zone)
right = stamp.stamp(T_B, T_B, m, ignore_trivial=True)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, :2], right)
def test_stumped_self_join_df(T_A, T_B, dask_cluster):
with Client(dask_cluster) as dask_client:
m = 3
zone = int(np.ceil(m / 4))
left = utils.naive_stamp(T_B, m, exclusion_zone=zone)
right = stumped(dask_client, pd.Series(T_B), m, ignore_trivial=True)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_stump_self_join_larger_window(T_A, T_B):
for m in [8, 16, 32]:
if len(T_B) > m:
zone = int(np.ceil(m / 4))
left = utils.naive_stamp(T_B, m, exclusion_zone=zone)
right = stomp._stomp(T_B, m, ignore_trivial=True)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_one_constant_subsequence_A_B_join(dask_cluster):
with Client(dask_cluster) as dask_client:
T_A = np.random.rand(20)
T_B = np.concatenate(
(np.zeros(20, dtype=np.float64), np.ones(5, dtype=np.float64)))
m = 3
left = utils.naive_stamp(T_A, m, T_B=T_B)
right = stumped(dask_client, T_A, m, T_B, ignore_trivial=False)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0]) # ignore indices
def test_one_constant_subsequence_self_join_df(dask_cluster):
with Client(dask_cluster) as dask_client:
T_A = np.concatenate(
(np.zeros(20, dtype=np.float64), np.ones(5, dtype=np.float64)))
m = 3
zone = int(np.ceil(m / 4))
left = utils.naive_stamp(T_A, m, exclusion_zone=zone)
right = stumped(dask_client, pd.Series(T_A), m, ignore_trivial=True)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0]) # ignore indices
def test_stamp_nan_zero_mean_self_join():
T = np.array([-1, 0, 1, np.inf, 1, 0, -1])
m = 3
zone = int(np.ceil(m / 2))
left = utils.naive_stamp(T, m, exclusion_zone=zone)
right = stamp.stamp(T, T, m, ignore_trivial=True)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, :2], right)
def test_gpu_stump_A_B_join(T_A, T_B):
m = 3
left = utils.naive_stamp(T_A, m, T_B=T_B)
right = gpu_stump(T_A, m, T_B, ignore_trivial=False)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
right = gpu_stump(pd.Series(T_A), m, pd.Series(T_B), ignore_trivial=False)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_gpu_stump_self_join(T_A, T_B):
m = 3
zone = int(np.ceil(m / 4))
left = utils.naive_stamp(T_B, m, exclusion_zone=zone)
right = gpu_stump(T_B, m, ignore_trivial=True)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
right = gpu_stump(pd.Series(T_B), m, ignore_trivial=True)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_stumped_nan_zero_mean_self_join(dask_cluster):
with Client(dask_cluster) as dask_client:
T = np.array([-1, 0, 1, np.inf, 1, 0, -1])
m = 3
zone = int(np.ceil(m / 4))
left = utils.naive_stamp(T, m, exclusion_zone=zone)
right = stumped(dask_client, T, m, ignore_trivial=True)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_gpu_stump_constant_subsequence_self_join():
T_A = np.concatenate((np.zeros(20, dtype=np.float64), np.ones(5, dtype=np.float64)))
m = 3
zone = int(np.ceil(m / 4))
left = utils.naive_stamp(T_A, m, exclusion_zone=zone)
right = gpu_stump(T_A, m, ignore_trivial=True)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0]) # ignore indices
right = gpu_stump(pd.Series(T_A), m, ignore_trivial=True)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0]) # ignore indices
def test_stumped_one_subsequence_inf_A_B_join(T_A, T_B,
substitution_location_B,
dask_cluster):
with Client(dask_cluster) as dask_client:
m = 3
T_B_sub = T_B.copy()
T_B_sub[substitution_location_B] = np.inf
left = utils.naive_stamp(T_A, m, T_B=T_B_sub)
right = stumped(dask_client, T_A, m, T_B_sub, ignore_trivial=False)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_naive_mstump():
T = np.random.uniform(-1000, 1000, [1, 1000]).astype(np.float64)
m = 20
zone = int(np.ceil(m / 4))
left = utils.naive_stamp(T[0], m, exclusion_zone=zone)
left_P = left[np.newaxis, :, 0].T
left_I = left[np.newaxis, :, 1].T
right_P, right_I = utils.naive_mstump(T, m, zone)
npt.assert_almost_equal(left_P, right_P)
npt.assert_almost_equal(left_I, right_I)
def test_parallel_gpu_stump_self_join(T_A, T_B):
device_ids = [device.id for device in cuda.list_devices()]
if len(T_B) > 10:
m = 3
zone = int(np.ceil(m / 4))
left = utils.naive_stamp(T_B, m, exclusion_zone=zone)
right = gpu_stump(T_B, m, ignore_trivial=True, device_id=device_ids,)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
right = gpu_stump(pd.Series(T_B), m, ignore_trivial=True, device_id=device_ids,)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_stamp_nan_inf_self_join(T_A, T_B, substitute_B, substitution_locations):
m = 3
T_B_sub = T_B.copy()
for substitution_location_B in substitution_locations:
T_B_sub[:] = T_B[:]
T_B_sub[substitution_location_B] = substitute_B
zone = int(np.ceil(m / 2))
left = utils.naive_stamp(T_B_sub, m, exclusion_zone=zone)
right = stamp.stamp(T_B_sub, T_B_sub, m, ignore_trivial=True)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, :2], right)
def test_stumped_one_subsequence_nan_self_join(
T_A, T_B, substitution_location_B, dask_cluster
):
with Client(dask_cluster) as dask_client:
m = 3
T_B_sub = T_B.copy()
T_B_sub[substitution_location_B] = np.nan
zone = int(np.ceil(m / 4))
left = utils.naive_stamp(T_B_sub, m, exclusion_zone=zone)
right = stumped(dask_client, T_B_sub, m, ignore_trivial=True)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_scrump_self_join_full(T_A, T_B):
m = 3
zone = int(np.ceil(m / 4))
left = utils.naive_stamp(T_B, m, exclusion_zone=zone)
right_gen = scrump(T_B,
m,
ignore_trivial=True,
percentage=1.0,
pre_scrump=False)
right = next(right_gen)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, :2], right)
def test_parallel_gpu_stump_A_B_join(T_A, T_B):
device_ids = [device.id for device in cuda.list_devices()]
if len(T_B) > 10:
m = 3
left = utils.naive_stamp(T_A, m, T_B=T_B)
right = gpu_stump(T_A, m, T_B, ignore_trivial=False, device_id=device_ids,)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
right = gpu_stump(
pd.Series(T_A),
m,
pd.Series(T_B),
ignore_trivial=False,
device_id=device_ids,
)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_gpu_stump_nan_inf_self_join(T_A, T_B, substitute_B, substitution_locations):
m = 3
stop = 16
T_B_sub = T_B.copy()[:stop]
for substitution_location_B in substitution_locations:
T_B_sub[:] = T_B[:stop]
T_B_sub[substitution_location_B] = substitute_B
zone = int(np.ceil(m / 4))
left = utils.naive_stamp(T_B_sub, m, exclusion_zone=zone)
right = gpu_stump(T_B_sub, m, ignore_trivial=True)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
right = gpu_stump(pd.Series(T_B_sub), m, ignore_trivial=True)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_stamp_nan_inf_A_B_join(
T_A, T_B, substitute_A, substitute_B, substitution_locations
):
m = 3
T_A_sub = T_A.copy()
T_B_sub = T_B.copy()
for substitution_location_B in substitution_locations:
for substitution_location_A in substitution_locations:
T_A_sub[:] = T_A[:]
T_B_sub[:] = T_B[:]
T_A_sub[substitution_location_A] = substitute_A
T_B_sub[substitution_location_B] = substitute_B
left = utils.naive_stamp(T_A_sub, m, T_B=T_B_sub)
right = stamp.stamp(T_A_sub, T_B_sub, m)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, :2], right)
