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_stump_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 = np.array(
[utils.naive_mass(Q, T_A, m) for Q in core.rolling_window(T_B, m)],
dtype=object)
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 = np.array(
[utils.naive_mass(Q, T_B, m) for Q in core.rolling_window(T_A, m)],
dtype=object)
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
def test_scrump_plus_plus_self_join(T_A, T_B, percentages):
m = 3
zone = int(np.ceil(m / 4))
for s in range(1, zone + 1):
for percentage in percentages:
seed = np.random.randint(100000)
np.random.seed(seed)
left_P, left_I = naive_prescrump(T_B,
m,
T_B,
s=s,
exclusion_zone=zone)
left = naive_scrump(T_B, m, T_B, percentage, zone, True, s)
for i in range(left.shape[0]):
if left_P[i] < left[i, 0]:
left[i, 0] = left_P[i]
left[i, 1] = left_I[i]
np.random.seed(seed)
right_gen = scrump(T_B,
m,
ignore_trivial=True,
percentage=percentage,
pre_scrump=True,
s=s)
right = next(right_gen)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_scrump_constant_subsequence_self_join(percentages):
T = np.concatenate((np.zeros(20,
dtype=np.float64), np.ones(5,
dtype=np.float64)))
m = 3
zone = int(np.ceil(m / 4))
for percentage in percentages:
seed = np.random.randint(100000)
np.random.seed(seed)
left = naive_scrump(T, m, T, percentage, zone, False, None)
np.random.seed(seed)
right_gen = scrump(T,
m,
ignore_trivial=True,
percentage=percentage,
pre_scrump=False)
right = next(right_gen)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, 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_scrump_nan_inf_self_join(T_A, T_B, substitute, substitution_locations,
percentages):
m = 3
T_B_sub = T_B.copy()
for substitution_location in substitution_locations:
T_B_sub[:] = T_B[:]
T_B_sub[substitution_location] = substitute
zone = int(np.ceil(m / 4))
for percentage in percentages:
seed = np.random.randint(100000)
np.random.seed(seed)
left = naive_scrump(T_B_sub, m, T_B_sub, percentage, zone, False,
None)
np.random.seed(seed)
right_gen = scrump(T_B_sub,
m,
percentage=percentage,
pre_scrump=False)
right = next(right_gen)
utils.replace_inf(left)
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 = np.array(
[
utils.naive_mass(Q, T_A_sub, m)
for Q in core.rolling_window(T_B_sub, m)
],
dtype=object,
)
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)
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_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_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_stumped_A_B_join(T_A, T_B, dask_client):
m = 3
left = np.array(
[utils.naive_mass(Q, T_A, m) for Q in core.rolling_window(T_B, m)],
dtype=object)
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_A_B_join(T_A, T_B):
m = 3
left = np.array(
[utils.naive_mass(Q, T_A, m) for Q in core.rolling_window(T_B, m)],
dtype=object)
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_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_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_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_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_stumped_A_B_join_df(T_A, T_B, dask_cluster):
with Client(dask_cluster) as dask_client:
m = 3
left = np.array(
[utils.naive_mass(Q, T_A, m) for Q in core.rolling_window(T_B, m)],
dtype=object,
)
right = stumped(
dask_client, pd.Series(T_A), m, pd.Series(T_B), ignore_trivial=False
)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left, right)
def test_two_constant_subsequences_A_B_join_swap(dask_client):
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 = np.array(
[utils.naive_mass(Q, T_B, m) for Q in core.rolling_window(T_A, m)],
dtype=object)
right = stumped(dask_client, 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
def test_stamp_self_join(T_A, T_B):
m = 3
zone = int(np.ceil(m / 2))
left = np.array(
[
utils.naive_mass(Q, T_B, m, i, zone, ignore_trivial=True)
for i, Q in enumerate(core.rolling_window(T_B, m))
],
dtype=object,
)
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_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_stumped_self_join_df(T_A, T_B, dask_client):
m = 3
zone = int(np.ceil(m / 4))
left = np.array(
[
utils.naive_mass(Q, T_B, m, i, zone, True)
for i, Q in enumerate(core.rolling_window(T_B, m))
],
dtype=object,
)
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_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_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_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_one_constant_subsequence_self_join_df(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 = np.array(
[
utils.naive_mass(Q, T_A, m, i, zone, True)
for i, Q in enumerate(core.rolling_window(T_A, m))
],
dtype=object,
)
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_stump_self_join_larger_window(T_A, T_B, dask_client):
for m in [8, 16, 32]:
if len(T_B) > m:
zone = int(np.ceil(m / 4))
left = np.array(
[
utils.naive_mass(Q, T_B, m, i, zone, True)
for i, Q in enumerate(core.rolling_window(T_B, m))
],
dtype=object,
)
right = stumped(dask_client, T_B, 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_stumped_one_subsequence_inf_A_B_join(
T_A, T_B, substitution_location_B, dask_client
):
m = 3
T_B_sub = T_B.copy()
T_B_sub[substitution_location_B] = np.inf
left = np.array(
[utils.naive_mass(Q, T_A, m) for Q in core.rolling_window(T_B_sub, m)],
dtype=object,
)
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_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 = np.array(
[
utils.naive_mass(Q, T, m, i, zone, True)
for i, Q in enumerate(core.rolling_window(T, m))
],
dtype=object,
)
right = stamp.stamp(T, T, m, ignore_trivial=True)
utils.replace_inf(left)
utils.replace_inf(right)
npt.assert_almost_equal(left[:, :2], right)