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
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],
config.STUMPY_TEST_PRECISION) # 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],
config.STUMPY_TEST_PRECISION) # 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],
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_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_A_B_join(T_A, T_B):
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, right)
right = aamp(pd.Series(T_A), m, pd.Series(T_B), ignore_trivial=False)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_aamp_self_join(T_A, T_B):
m = 3
left = naive.aamp(T_B, m)
right = aamp(T_B, m)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
right = aamp(pd.Series(T_B), m)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
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_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_aamp_self_join(T_A, T_B):
m = 3
for p in [1.0, 2.0, 3.0]:
ref_mp = naive.aamp(T_B, m, p=p)
comp_mp = aamp(T_B, m, p=p)
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, p=p)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
def test_aamp_constant_subsequence_self_join():
T_A = np.concatenate(
(np.zeros(20, dtype=np.float64), np.ones(5, dtype=np.float64)))
m = 3
left = naive.aamp(T_A, m)
right = aamp(T_A, m, ignore_trivial=True)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0]) # ignore indices
right = aamp(pd.Series(T_A), m, ignore_trivial=True)
naive.replace_inf(right)
npt.assert_almost_equal(left[:, 0], right[:, 0]) # ignore indices
def test_aamp_constant_subsequence_self_join():
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 = 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
comp_mp = aamp(pd.Series(T_A), m, ignore_trivial=True)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp[:, 0], comp_mp[:, 0]) # ignore indices
def test_scraamp_self_join_full(T_A, T_B):
m = 3
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)
ref_mp = aamp(T_B, m, ignore_trivial=True)
ref_P = ref_mp[:, 0]
ref_I = ref_mp[:, 1]
ref_left_I = ref_mp[:, 2]
ref_right_I = ref_mp[:, 3]
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_stump(T, m):
if T.ndim > 1:
T = T.copy()
T = T[0]
ref = stumpy.aamp(T, m)
comp = stumpy.stump(T, m, normalize=False)
npt.assert_almost_equal(ref, comp)
def __init__(self, T, m, excl_zone=None, egress=True):
"""
Initialize the `stumpi` object
Parameters
----------
T : ndarray
The time series or sequence for which the unnormalized matrix profile and
matrix profile indices will be returned
m : int
Window size
excl_zone : int, default None
The half width for the exclusion zone relative to the current
sliding window
egress : bool, default True
If set to `True`, the oldest data point in the time series is removed and
the time series length remains constant rather than forever increasing
"""
self._T = T.copy()
self._T = np.asarray(self._T)
core.check_dtype(self._T)
self._m = m
self._n = self._T.shape[0]
if excl_zone is not None: # pragma: no cover
self._excl_zone = excl_zone
else:
self._excl_zone = int(np.ceil(self._m / 4))
self._egress = egress
mp = stumpy.aamp(self._T, self._m)
self._P = mp[:, 0]
self._I = mp[:, 1]
self._left_I = mp[:, 2]
self._left_P = np.empty(self._P.shape)
self._left_P[:] = np.inf
self._T_isfinite = np.isfinite(self._T)
self._T, self._T_subseq_isfinite = core.preprocess_non_normalized(
self._T, self._m)
self._T_squared = np.sum(core.rolling_window(self._T * self._T,
self._m),
axis=1)
# Retrieve the left matrix profile values
for i, j in enumerate(self._left_I):
if j >= 0:
D = core.mass_absolute(self._T[i:i + self._m],
self._T[j:j + self._m])
self._left_P[i] = D[0]
Q = self._T[-m:]
self._QT = core.sliding_dot_product(Q, self._T)
if self._egress:
self._QT_new = np.empty(self._QT.shape[0])
self._n_appended = 0
def test_motifs(T, m):
if T.ndim > 1:
T = T.copy()
T = T[0]
mp = stumpy.aamp(T, m)
ref = stumpy.aamp_motifs(T, mp[:, 0])
comp = stumpy.motifs(T, mp[:, 0], normalize=False)
npt.assert_almost_equal(ref, comp)
def test_aamp_identical_subsequence_self_join():
identical = np.random.rand(8)
T_A = np.random.rand(20)
T_A[1:1 + identical.shape[0]] = identical
T_A[11:11 + identical.shape[0]] = identical
m = 3
ref_mp = naive.aamp(T_A, m)
comp_mp = 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],
decimal=config.STUMPY_TEST_PRECISION) # ignore indices
comp_mp = aamp(pd.Series(T_A), m, ignore_trivial=True)
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_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_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))
left = naive.aamp(T, m)
right = aamp(T, m, ignore_trivial=True)
naive.replace_inf(left)
naive.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_aamp_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 / 4))
ref_mp = naive.aamp(T_B_sub, m)
comp_mp = aamp(T_B_sub, m, ignore_trivial=True)
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_sub), m, ignore_trivial=True)
naive.replace_inf(comp_mp)
npt.assert_almost_equal(ref_mp, comp_mp)
def test_aamp_one_constant_subsequence_A_B_join():
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.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]) # 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]) # 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]) # ignore indices
def test_scraamp_A_B_join_full(T_A, T_B):
m = 3
ref_mp = naive.aamp(T_A, m, T_B=T_B)
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_A,
m,
T_B,
ignore_trivial=False,
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)
ref_mp = aamp(T_A, m, T_B=T_B, ignore_trivial=False)
ref_P = ref_mp[:, 0]
ref_I = ref_mp[:, 1]
ref_left_I = ref_mp[:, 2]
ref_right_I = ref_mp[:, 3]
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 naive_right_mp(data, m, normalize=True):
if normalize:
mp = stump(data, m)
else:
mp = aamp(data, m)
k = mp.shape[0]
right_nn = np.zeros((k, m))
right_indices = [np.arange(IR, IR + m) for IR in mp[:, 3].tolist()]
right_nn[:] = data[np.array(right_indices)]
if normalize:
mp[:, 0] = np.linalg.norm(
core.z_norm(core.rolling_window(data, m), 1) -
core.z_norm(right_nn, 1),
axis=1,
)
else:
mp[:, 0] = np.linalg.norm(core.rolling_window(data, m) - right_nn,
axis=1)
inf_indices = np.argwhere(mp[:, 3] < 0).flatten()
mp[inf_indices, 0] = np.inf
mp[inf_indices, 3] = inf_indices
return mp
def test_aamp_floss_inf_nan(substitute, substitution_locations):
T = np.random.uniform(-1000, 1000, [64])
m = 5
n = 30
data = T.copy()
for substitution_location in substitution_locations:
data[:] = T[:]
data[substitution_location] = substitute
old_data = data[:n]
mp = naive_right_mp(old_data, m, normalize=False)
comp_mp = aamp(old_data, m)
k = mp.shape[0]
rolling_Ts = core.rolling_window(data[1:], n)
L = 5
excl_factor = 1
custom_iac = _iac(k, bidirectional=False)
stream = floss(comp_mp,
old_data,
m,
L,
excl_factor,
custom_iac=custom_iac,
normalize=False)
last_idx = n - m + 1
excl_zone = int(np.ceil(m / 4))
zone_start = max(0, k - excl_zone)
for i, ref_T in enumerate(rolling_Ts):
mp[:, 1] = -1
mp[:, 2] = -1
mp[:] = np.roll(mp, -1, axis=0)
mp[-1, 0] = np.inf
mp[-1, 3] = last_idx + i
D = naive.aamp_distance_profile(ref_T[-m:], ref_T, m)
D[zone_start:] = np.inf
ref_T_isfinite = np.isfinite(ref_T)
ref_T_subseq_isfinite = np.all(core.rolling_window(
ref_T_isfinite, m),
axis=1)
D[~ref_T_subseq_isfinite] = np.inf
update_idx = np.argwhere(D < mp[:, 0]).flatten()
mp[update_idx, 0] = D[update_idx]
mp[update_idx, 3] = last_idx + i
ref_cac_1d = _cac(
mp[:, 3] - i - 1,
L,
bidirectional=False,
excl_factor=excl_factor,
custom_iac=custom_iac,
)
ref_mp = mp.copy()
ref_P = ref_mp[:, 0]
ref_I = ref_mp[:, 3]
stream.update(ref_T[-1])
comp_cac_1d = stream.cac_1d_
comp_P = stream.P_
comp_I = stream.I_
comp_T = stream.T_
naive.replace_inf(ref_P)
naive.replace_inf(comp_P)
npt.assert_almost_equal(ref_cac_1d, comp_cac_1d)
npt.assert_almost_equal(ref_P, comp_P)
npt.assert_almost_equal(ref_I, comp_I)
npt.assert_almost_equal(ref_T, comp_T)
def test_aamp_int_input():
with pytest.raises(TypeError):
aamp(np.arange(10), 5)