def test_aamp_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
ref_mp = naive.aamp(T_A, m, T_B=T_B)
comp_mp = aamp(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
comp_mp = aamp(pd.Series(T_A), m, pd.Series(T_B), 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.aamp(T_B, m, T_B=T_A)
comp_mp = aamp(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 = aamp(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
def test_aamp_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.aamp(T_A, m, T_B=T_B)
right = aamp(T_A, m, T_B, ignore_trivial=False)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0],
config.STUMPY_TEST_PRECISION) # ignore indices
right = aamp(pd.Series(T_A), m, pd.Series(T_B), ignore_trivial=False)
naive.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0],
config.STUMPY_TEST_PRECISION) # ignore indices
# Swap inputs
left = naive.aamp(T_B, m, T_B=T_A)
right = aamp(T_B, m, T_A, ignore_trivial=False)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0],
config.STUMPY_TEST_PRECISION) # ignore indices
def test_gpu_aamp_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.aamp(T_A, m, T_B=T_B)
comp_mp = gpu_aamp(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
# comp_mp = gpu_aamp(pd.Series(T_A), m, pd.Series(T_B), 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.aamp(T_B, m, T_B=T_A)
comp_mp = gpu_aamp(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
def test_aamp_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
ref_mp = naive.aamp(T_A_sub, m, T_B=T_B_sub)
comp_mp = aamp(T_A_sub, m, T_B_sub, ignore_trivial=False)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
comp_mp = aamp(pd.Series(T_A_sub),
m,
pd.Series(T_B_sub),
ignore_trivial=False)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
def test_aamp_motifs_two_motifs():
# Fix seed, because in some case motifs can be off by an index resulting in test
# fails, which is caused since one of the motifs is not repeated perfectly in T.
np.random.seed(1234)
# The time series is random noise with two motifs for m=10:
# * (almost) identical step functions at indices 10, 110 and 210
# * identical linear slopes at indices 70 and 170
T = np.random.normal(size=300)
m = 20
T[10:30] = 1
T[12:28] = 2
# This is not part of the motif in the aamp case
T[110:130] = 3
T[112:128] = 6
T[120] = 6.6
T[210:230] = 1
T[212:228] = 2
T[220] = 1.9
# naive.distance(naive.z_norm(T[10:30]), naive.z_norm(T[110:130])) = 0.47
# naive.distance(naive.z_norm(T[10:30]), naive.z_norm(T[210:230])) = 0.24
# naive.distance(naive.z_norm(T[110:130]), naive.z_norm(T[210:230])) = 0.72
# Hence T[10:30] is the motif representative for this motif
T[70:90] = np.arange(m) * 0.1
T[170:190] = np.arange(m) * 0.1
# naive.distance(naive.z_norm(T[70:90]), naive.z_norm(T[170:190])) = 0.0
max_motifs = 2
mp = naive.aamp(T, m)
# left_indices = [[70, 170], [10, 210]]
left_profile_values = [
[0.0, 0.0],
[
0.0,
naive.distance(T[10:30], T[210:230]),
],
]
right_distance_values, right_indices = aamp_motifs(
T,
mp[:, 0],
max_motifs=max_motifs,
max_distance=0.5,
cutoff=np.inf,
)
# We ignore indices because of sorting ambiguities for equal distances.
# As long as the distances are correct, the indices will be too.
npt.assert_almost_equal(left_profile_values,
right_distance_values,
decimal=6)
# Reset seed
np.random.seed(None)
def test_gpu_aamp_A_B_join(T_A, T_B):
m = 3
ref_mp = naive.aamp(T_B, m, T_B=T_A)
comp_mp = gpu_aamp(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_scraamp_plus_plus_A_B_join_full_swap(T_A, T_B):
m = 3
zone = int(np.ceil(m / 4))
ref_mp = naive.aamp(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 = scraamp(
T_B, m, T_B=T_A, ignore_trivial=False, percentage=1.0, pre_scraamp=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_aamp_motifs_one_motif():
# The top motif for m=3 is a [0 1 0] at indices 0 and 5, while the occurrence
# at index 9 is not a motif in the aamp case.
T = np.array(
[0.0, 1.0, 0.0, -1.0, -1.0, 0.0, 1.0, 0.0, -0.5, 2.0, 3.0, 2.0])
m = 3
max_motifs = 1
left_indices = [[0, 5]]
left_profile_values = [[0.0, 0.0]]
for p in [1.0, 2.0, 3.0]:
mp = naive.aamp(T, m, p=p)
right_distance_values, right_indices = aamp_motifs(
T,
mp[:, 0],
max_motifs=max_motifs,
max_distance=0.001,
cutoff=np.inf,
p=p,
)
npt.assert_array_equal(left_indices, right_indices)
npt.assert_almost_equal(left_profile_values,
right_distance_values,
decimal=4)
def test_scraamp_self_join_full_larger_window(T_A, T_B, m):
if len(T_B) > m:
zone = int(np.ceil(m / 4))
ref_mp = naive.aamp(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 = scraamp(T_B,
m,
ignore_trivial=True,
percentage=1.0,
pre_scraamp=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_aampi_self_join():
m = 3
zone = int(np.ceil(m / 4))
seed = np.random.randint(100000)
np.random.seed(seed)
n = 30
T = np.random.rand(n)
stream = aampi(T, m, egress=False)
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.aamp(stream.T_, m)
left_P = left[:, 0]
left_I = left[:, 1]
left_left_P = np.full(left_P.shape, np.inf)
left_left_I = left[:, 2]
for i, j in enumerate(left_left_I):
if j >= 0:
D = core.mass_absolute(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)
n = 30
T = np.random.rand(n)
T = pd.Series(T)
stream = aampi(T, m, egress=False)
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_aampi_self_join():
m = 3
seed = np.random.randint(100000)
np.random.seed(seed)
n = 30
T = np.random.rand(n)
stream = aampi(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.aamp(stream.T_, m)
ref_P = ref_mp[:, 0]
ref_I = ref_mp[:, 1]
ref_left_P = np.full(ref_P.shape, np.inf)
ref_left_I = ref_mp[:, 2]
for i, j in enumerate(ref_left_I):
if j >= 0:
D = core.mass_absolute(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)
n = 30
T = np.random.rand(n)
T = pd.Series(T)
stream = aampi(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_gpu_aamp_A_B_join(T_A, T_B):
m = 3
for p in [1.0, 2.0, 3.0]:
ref_mp = naive.aamp(T_B, m, T_B=T_A, p=p)
comp_mp = gpu_aamp(T_B, m, T_A, ignore_trivial=False, p=p)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
def test_aamped_A_B_join(T_A, T_B, dask_cluster):
with Client(dask_cluster) as dask_client:
m = 3
left = naive.aamp(T_A, m, T_B=T_B)
right = aamped(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_aamped_self_join_df(T_A, T_B, dask_cluster):
with Client(dask_cluster) as dask_client:
m = 3
left = naive.aamp(T_B, m)
right = aamped(dask_client, pd.Series(T_B), m)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_aamped_A_B_join(T_A, T_B, dask_cluster):
with Client(dask_cluster) as dask_client:
m = 3
ref_mp = naive.aamp(T_A, m, T_B=T_B)
comp_mp = aamped(dask_client, T_A, m, T_B, ignore_trivial=False)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
def test_aamped_self_join_df(T_A, T_B, dask_cluster):
with Client(dask_cluster) as dask_client:
m = 3
ref_mp = naive.aamp(T_B, m)
comp_mp = aamped(dask_client, pd.Series(T_B), m)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
def test_gpu_aamp_self_join_larger_window(T_A, T_B, m):
if len(T_B) > m:
zone = int(np.ceil(m / 4))
left = naive.aamp(T_B, m, exclusion_zone=zone)
right = gpu_aamp(T_B, m, ignore_trivial=True)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_aamped_self_join(T_A, T_B, dask_cluster):
with Client(dask_cluster) as dask_client:
m = 3
for p in [1.0, 2.0, 3.0]:
ref_mp = naive.aamp(T_B, m, p=p)
comp_mp = aamped(dask_client, T_B, m, p=p)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
def test_aamped_self_join_larger_window(T_A, T_B, m, dask_cluster):
with Client(dask_cluster) as dask_client:
if len(T_B) > m:
left = naive.aamp(T_B, m)
right = aamped(dask_client, T_B, m)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_gpu_aamp_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.aamp(T_A, m, exclusion_zone=zone)
comp_mp = gpu_aamp(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_aamped_self_join_larger_window(T_A, T_B, m, dask_cluster):
with Client(dask_cluster) as dask_client:
if len(T_B) > m:
ref_mp = naive.aamp(T_B, m)
comp_mp = aamped(dask_client, T_B, m)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
def test_gpu_aamp_self_join_larger_window(T_A, T_B, m):
if len(T_B) > m:
zone = int(np.ceil(m / 4))
ref_mp = naive.aamp(T_B, m, exclusion_zone=zone)
comp_mp = gpu_aamp(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_aamped_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
ref_mp = naive.aamp(T_A, m)
comp_mp = aamped(dask_client, pd.Series(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_aampdist_vect_k(T_A, T_B, k):
m = 3
n_A = T_A.shape[0]
n_B = T_B.shape[0]
j = n_A - m + 1 # `k` is reserved for `P_ABBA` selection
P_ABBA = np.empty(2 * j, dtype=np.float64)
ref_mpdist_vect = np.empty(n_B - n_A + 1)
k = min(int(k), P_ABBA.shape[0] - 1)
for i in range(n_B - n_A + 1):
P_ABBA[:j] = naive.aamp(T_A, m, T_B[i : i + n_A])[:, 0]
P_ABBA[j:] = naive.aamp(T_B[i : i + n_A], m, T_A)[:, 0]
P_ABBA.sort()
ref_mpdist_vect[i] = P_ABBA[min(k, P_ABBA.shape[0] - 1)]
comp_mpdist_vect = _aampdist_vect(T_A, T_B, m, k=k)
npt.assert_almost_equal(ref_mpdist_vect, comp_mpdist_vect)
def test_aamp_nan_zero_mean_self_join():
T = np.array([-1, 0, 1, np.inf, 1, 0, -1])
m = 3
ref_mp = naive.aamp(T, m)
comp_mp = aamp(T, 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_aamp_nan_zero_mean_self_join():
T = np.array([-1, 0, 1, np.inf, 1, 0, -1])
m = 3
zone = int(np.ceil(m / 4))
ref_mp = naive.aamp(T, m, exclusion_zone=zone)
comp_mp = gpu_aamp(T, m, ignore_trivial=True)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
def test_aamp_self_join(T_A, T_B):
m = 3
ref_mp = naive.aamp(T_B, m)
comp_mp = aamp(T_B, m)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
comp_mp = aamp(pd.Series(T_B), m)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
def test_aamped_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
ref_mp = naive.aamp(T, m)
comp_mp = aamped(dask_client, T, m, ignore_trivial=True)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
def test_aamp_A_B_join(T_A, T_B):
m = 3
ref_mp = naive.aamp(T_A, m, T_B=T_B)
comp_mp = aamp(T_A, m, T_B, ignore_trivial=False)
naive.replace_inf(ref_mp)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
comp_mp = aamp(pd.Series(T_A), m, pd.Series(T_B), ignore_trivial=False)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
def test_aamped_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
ref_mp = naive.aamp(T_A, m, T_B=T_B)
comp_mp = aamped(dask_client, 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
