def test_stump_identical_subsequence_A_B_join():
identical = np.random.rand(8)
T_A = np.random.rand(20)
T_B = np.random.rand(20)
T_A[1 : 1 + identical.shape[0]] = identical
T_B[11 : 11 + identical.shape[0]] = identical
m = 3
left = naive.stamp(T_A, m, T_B=T_B)
right = stump(T_A, m, T_B, ignore_trivial=False)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(
left[:, 0], right[:, 0], decimal=naive.PRECISION
) # ignore indices
right = stump(pd.Series(T_A), m, pd.Series(T_B), ignore_trivial=False)
naive.replace_inf(right)
npt.assert_almost_equal(
left[:, 0], right[:, 0], decimal=naive.PRECISION
) # ignore indices
# Swap inputs
left = naive.stamp(T_B, m, T_B=T_A)
right = stump(T_B, m, T_A, ignore_trivial=False)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(
left[:, 0], right[:, 0], decimal=naive.PRECISION
) # ignore indices
def test_gpu_stump_identical_subsequence_A_B_join():
identical = np.random.rand(8)
T_A = np.random.rand(20)
T_B = np.random.rand(20)
T_A[1:1 + identical.shape[0]] = identical
T_B[11:11 + identical.shape[0]] = identical
m = 3
ref_mp = naive.stamp(T_B, m, T_B=T_A)
comp_mp = gpu_stump(T_B, m, T_A, ignore_trivial=False)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(
ref_mp[:, 0], comp_mp[:, 0],
decimal=config.STUMPY_TEST_PRECISION) # ignore indices
# comp_mp = gpu_stump(pd.Series(T_B), m, pd.Series(T_A), ignore_trivial=False)
# naive.replace_inf(comp_mp)
# npt.assert_almost_equal(
# ref_mp[:, 0], comp_mp[:, 0], decimal=config.STUMPY_TEST_PRECISION
# ) # ignore indices
# Swap inputs
ref_mp = naive.stamp(T_A, m, T_B=T_B)
comp_mp = gpu_stump(T_A, m, T_B, ignore_trivial=False)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(
ref_mp[:, 0], comp_mp[:, 0],
decimal=config.STUMPY_TEST_PRECISION) # ignore indices
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 = naive.stamp(T_A, m, T_B=T_B)
right = stump(T_A, m, T_B, ignore_trivial=False)
naive.replace_inf(left)
naive.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)
naive.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0]) # ignore indices
# Swap inputs
left = naive.stamp(T_B, m, T_B=T_A)
right = stump(T_B, m, T_A, ignore_trivial=False)
naive.replace_inf(left)
naive.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)
naive.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0]) # ignore indices
def test_stamp_A_B_join(T_A, T_B):
m = 3
left = naive.stamp(T_A, m, T_B=T_B)
right = stamp.stamp(T_A, T_B, m)
naive.replace_inf(left)
naive.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 = naive.stamp(T_A, m, T_B=T_B)
right = gpu_stump(
T_A,
m,
T_B,
ignore_trivial=False,
device_id=device_ids,
)
naive.replace_inf(left)
naive.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,
)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_scrump_plus_plus_A_B_join_full_swap(T_A, T_B):
m = 3
zone = int(np.ceil(m / 4))
left = naive.stamp(T_B, m, T_B=T_A)
left_P = left[:, 0]
left_I = left[:, 1]
left_left_I = left[:, 2]
left_right_I = left[:, 3]
approx = scrump(T_B,
m,
T_B=T_A,
ignore_trivial=False,
percentage=1.0,
pre_scrump=True,
s=zone)
approx.update()
right_P = approx.P_
right_I = approx.I_
right_left_I = approx.left_I_
right_right_I = approx.right_I_
naive.replace_inf(left_P)
naive.replace_inf(right_P)
npt.assert_almost_equal(left_P, right_P)
npt.assert_almost_equal(left_I, right_I)
npt.assert_almost_equal(left_left_I, right_left_I)
npt.assert_almost_equal(left_right_I, right_right_I)
def test_stamp_A_B_join(T_A, T_B):
m = 3
ref_mp = naive.stamp(T_A, m, T_B=T_B)
comp_mp = stamp.stamp(T_A, T_B, m)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp[:, :2], comp_mp)
def test_stomp_A_B_join(T_A, T_B):
m = 3
left = naive.stamp(T_A, m, T_B=T_B)
right = stomp._stomp(T_A, m, T_B, ignore_trivial=False)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_scrump_plus_plus_A_B_join_full_swap(T_A, T_B):
m = 3
zone = int(np.ceil(m / 4))
ref_mp = naive.stamp(T_B, m, T_B=T_A)
ref_P = ref_mp[:, 0]
ref_I = ref_mp[:, 1]
ref_left_I = ref_mp[:, 2]
ref_right_I = ref_mp[:, 3]
approx = scrump(
T_B, m, T_B=T_A, ignore_trivial=False, percentage=1.0, pre_scrump=True, s=zone
)
approx.update()
comp_P = approx.P_
comp_I = approx.I_
comp_left_I = approx.left_I_
comp_right_I = approx.right_I_
naive.replace_inf(ref_P)
naive.replace_inf(comp_P)
npt.assert_almost_equal(ref_P, comp_P)
npt.assert_almost_equal(ref_I, comp_I)
npt.assert_almost_equal(ref_left_I, comp_left_I)
npt.assert_almost_equal(ref_right_I, comp_right_I)
def test_scrump_self_join_full_larger_window(T_A, T_B, m):
if len(T_B) > m:
zone = int(np.ceil(m / 4))
ref_mp = naive.stamp(T_B, m, exclusion_zone=zone)
ref_P = ref_mp[:, 0]
ref_I = ref_mp[:, 1]
ref_left_I = ref_mp[:, 2]
ref_right_I = ref_mp[:, 3]
approx = scrump(T_B,
m,
ignore_trivial=True,
percentage=1.0,
pre_scrump=False)
approx.update()
comp_P = approx.P_
comp_I = approx.I_
comp_left_I = approx.left_I_
comp_right_I = approx.right_I_
naive.replace_inf(ref_P)
naive.replace_inf(comp_P)
npt.assert_almost_equal(ref_P, comp_P)
npt.assert_almost_equal(ref_I, comp_I)
npt.assert_almost_equal(ref_left_I, comp_left_I)
npt.assert_almost_equal(ref_right_I, comp_right_I)
def test_scrump_self_join_full_larger_window(T_A, T_B):
for m in [8, 16, 32]:
if len(T_B) > m:
zone = int(np.ceil(m / 4))
left = naive.stamp(T_B, m, exclusion_zone=zone)
left_P = left[:, 0]
left_I = left[:, 1]
left_left_I = left[:, 2]
left_right_I = left[:, 3]
approx = scrump(T_B,
m,
ignore_trivial=True,
percentage=1.0,
pre_scrump=False)
approx.update()
right_P = approx.P_
right_I = approx.I_
right_left_I = approx.left_I_
right_right_I = approx.right_I_
naive.replace_inf(left_P)
naive.replace_inf(right_P)
npt.assert_almost_equal(left_P, right_P)
npt.assert_almost_equal(left_I, right_I)
npt.assert_almost_equal(left_left_I, right_left_I)
npt.assert_almost_equal(left_right_I, right_right_I)
def test_gpu_stump_A_B_join(T_A, T_B):
m = 3
ref_mp = naive.stamp(T_B, m, T_B=T_A)
comp_mp = gpu_stump(T_B, m, T_A, ignore_trivial=False)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
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 = naive.stamp(T_A_sub, m, T_B=T_B_sub)
right = stump(T_A_sub, m, T_B_sub, ignore_trivial=False)
naive.replace_inf(left)
naive.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
)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_stumpi_self_join():
m = 3
zone = int(np.ceil(m / 4))
seed = np.random.randint(100000)
np.random.seed(seed)
T = np.random.rand(30)
stream = stumpi(T, m, egress=False)
for i in range(34):
t = np.random.rand()
stream.update(t)
comp_P = stream.P_
comp_I = stream.I_
comp_left_P = stream.left_P_
comp_left_I = stream.left_I_
ref_mp = naive.stamp(stream.T_, m, exclusion_zone=zone)
ref_P = ref_mp[:, 0]
ref_I = ref_mp[:, 1]
ref_left_P = np.empty(ref_P.shape)
ref_left_P[:] = np.inf
ref_left_I = ref_mp[:, 2]
for i, j in enumerate(ref_left_I):
if j >= 0:
D = core.mass(stream.T_[i:i + m], stream.T_[j:j + m])
ref_left_P[i] = D[0]
naive.replace_inf(ref_P)
naive.replace_inf(ref_left_P)
naive.replace_inf(comp_P)
naive.replace_inf(comp_left_P)
npt.assert_almost_equal(ref_P, comp_P)
npt.assert_almost_equal(ref_I, comp_I)
npt.assert_almost_equal(ref_left_P, comp_left_P)
npt.assert_almost_equal(ref_left_I, comp_left_I)
np.random.seed(seed)
T = np.random.rand(30)
T = pd.Series(T)
stream = stumpi(T, m, egress=False)
for i in range(34):
t = np.random.rand()
stream.update(t)
comp_P = stream.P_
comp_I = stream.I_
comp_left_P = stream.left_P_
comp_left_I = stream.left_I_
naive.replace_inf(comp_P)
naive.replace_inf(comp_left_P)
npt.assert_almost_equal(ref_P, comp_P)
npt.assert_almost_equal(ref_I, comp_I)
npt.assert_almost_equal(ref_left_P, comp_left_P)
npt.assert_almost_equal(ref_left_I, comp_left_I)
def test_stumpi_self_join():
m = 3
zone = int(np.ceil(m / 4))
seed = np.random.randint(100000)
np.random.seed(seed)
T = np.random.rand(30)
stream = stumpi(T, m)
for i in range(34):
t = np.random.rand()
stream.update(t)
right_P = stream.P_
right_I = stream.I_
right_left_P = stream.left_P_
right_left_I = stream.left_I_
left = naive.stamp(stream.T_, m, exclusion_zone=zone)
left_P = left[:, 0]
left_I = left[:, 1]
left_left_P = np.empty(left_P.shape)
left_left_P[:] = np.inf
left_left_I = left[:, 2]
for i, j in enumerate(left_left_I):
if j >= 0:
D = core.mass(stream.T_[i:i + m], stream.T_[j:j + m])
left_left_P[i] = D[0]
naive.replace_inf(left_P)
naive.replace_inf(left_left_P)
naive.replace_inf(right_P)
naive.replace_inf(right_left_P)
npt.assert_almost_equal(left_P, right_P)
npt.assert_almost_equal(left_I, right_I)
npt.assert_almost_equal(left_left_P, right_left_P)
npt.assert_almost_equal(left_left_I, right_left_I)
np.random.seed(seed)
T = np.random.rand(30)
T = pd.Series(T)
stream = stumpi(T, m)
for i in range(34):
t = np.random.rand()
stream.update(t)
right_P = stream.P_
right_I = stream.I_
right_left_P = stream.left_P_
right_left_I = stream.left_I_
naive.replace_inf(right_P)
naive.replace_inf(right_left_P)
npt.assert_almost_equal(left_P, right_P)
npt.assert_almost_equal(left_I, right_I)
npt.assert_almost_equal(left_left_P, right_left_P)
npt.assert_almost_equal(left_left_I, right_left_I)
def test_stomp_self_join(T_A, T_B):
m = 3
zone = int(np.ceil(m / 4))
left = naive.stamp(T_B, m, exclusion_zone=zone)
right = stomp._stomp(T_B, m, ignore_trivial=True)
naive.replace_inf(left)
naive.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 = naive.stamp(T_A, m, T_B=T_B)
right = stumped(dask_client, T_A, m, T_B, ignore_trivial=False)
naive.replace_inf(left)
naive.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))
ref_mp = naive.stamp(T_B, m, exclusion_zone=zone)
comp_mp = stamp.stamp(T_B, T_B, m, ignore_trivial=True)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp[:, :2], comp_mp)
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 = naive.stamp(T_B, m, exclusion_zone=zone)
right = stumped(dask_client, pd.Series(T_B), m, ignore_trivial=True)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_gpu_stump_self_join_larger_window(T_A, T_B, m):
if len(T_B) > m:
zone = int(np.ceil(m / 4))
ref_mp = naive.stamp(T_B, m, exclusion_zone=zone)
comp_mp = gpu_stump(T_B, m, ignore_trivial=True)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
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))
ref_mp = naive.stamp(T_A, m, exclusion_zone=zone)
comp_mp = gpu_stump(T_A, m, ignore_trivial=True)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp[:, 0], comp_mp[:, 0]) # ignore indices
def test_gpu_stump_self_join_larger_window(T_A, T_B, m):
if len(T_B) > m:
zone = int(np.ceil(m / 4))
left = naive.stamp(T_B, m, exclusion_zone=zone)
right = gpu_stump(T_B, m, ignore_trivial=True)
naive.replace_inf(left)
naive.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 = naive.stamp(T_A, m, T_B=T_B)
right = stumped(dask_client, T_A, m, T_B, ignore_trivial=False)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0]) # ignore indices
def test_stump_nan_zero_mean_self_join():
T = np.array([-1, 0, 1, np.inf, 1, 0, -1])
m = 3
zone = int(np.ceil(m / 4))
left = naive.stamp(T, m, exclusion_zone=zone)
right = stump(T, m, ignore_trivial=True)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_stump_self_join_larger_window_df(T_A, T_B, dask_cluster):
with Client(dask_cluster) as dask_client:
for m in [8, 16, 32]:
if len(T_B) > m:
zone = int(np.ceil(m / 4))
left = naive.stamp(T_B, m, exclusion_zone=zone)
right = stumped(dask_client, pd.Series(T_B), m, ignore_trivial=True)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_gpu_stump_two_constant_subsequences_A_B_join():
T_A = np.array([0, 0, 0, 0, 0, 1], dtype=np.float64)
T_B = np.concatenate((np.zeros(20, dtype=np.float64), np.ones(5, dtype=np.float64)))
m = 3
ref_mp = naive.stamp(T_B, m, T_B=T_A)
comp_mp = gpu_stump(T_B, m, T_A, ignore_trivial=False)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp[:, 0], comp_mp[:, 0]) # ignore indices
# comp_mp = gpu_stump(pd.Series(T_B), m, pd.Series(T_A), ignore_trivial=False)
# naive.replace_inf(comp_mp)
# npt.assert_almost_equal(ref_mp[:, 0], comp_mp[:, 0]) # ignore indices
# Swap inputs
ref_mp = naive.stamp(T_A, m, T_B=T_B)
comp_mp = gpu_stump(T_A, m, T_B, ignore_trivial=False)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp[:, 0], comp_mp[:, 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 = naive.stamp(T_A, m, exclusion_zone=zone)
right = stumped(dask_client, pd.Series(T_A), m, ignore_trivial=True)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0]) # ignore indices
def test_gpu_stump_A_B_join(T_A, T_B):
m = 3
left = naive.stamp(T_A, m, T_B=T_B)
right = gpu_stump(T_A, m, T_B, ignore_trivial=False)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
right = gpu_stump(pd.Series(T_A), m, pd.Series(T_B), ignore_trivial=False)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
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))
ref_mp = naive.stamp(T, m, exclusion_zone=zone)
comp_mp = stamp.stamp(T, T, m, ignore_trivial=True)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp[:, :2], comp_mp)
def test_gpu_stump_self_join(T_A, T_B):
m = 3
zone = int(np.ceil(m / 4))
ref_mp = naive.stamp(T_B, m, exclusion_zone=zone)
comp_mp = gpu_stump(T_B, m, ignore_trivial=True)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
comp_mp = gpu_stump(pd.Series(T_B), m, ignore_trivial=True)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
