def naive_across_series_nearest_neighbors(q, Ts):
"""
For multiple time series find, per individual time series, the subsequences closest
to a query.
Parameters
----------
q : ndarray
Query array or subsequence
Ts : list
List of time series for which to the nearest neighbors to `q`
Returns
-------
subseq_idx_nn : ndarray
Indices to subsequences in `Ts` that are closest to `q`
d : ndarray
Distances to subsequences in `Ts` that are closest to `q`
"""
k = len(Ts)
d = np.zeros(k, dtype=float)
subseq_idx_nn = np.zeros(k, dtype=int)
for i in range(k):
dp = naive.distance_profile(q, Ts[i], len(q))
subseq_idx_nn[i] = np.argmin(dp)
d[i] = dp[subseq_idx_nn[i]]
return subseq_idx_nn, d
def test_floss():
data = np.random.uniform(-1000, 1000, [64])
m = 5
n = 30
old_data = data[:n]
mp = naive_right_mp(old_data, m)
comp_mp = stump(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)
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.distance_profile(ref_T[-m:], ref_T, m)
D[zone_start:] = 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 naive_match(Q, T, excl_zone, max_distance):
m = Q.shape[0]
D = naive.distance_profile(Q, T, m)
matches = []
for i in range(D.size):
dist = D[i]
if dist <= max_distance:
matches.append(i)
# Removes indices that are inside the exclusion zone of some occurrence with
# a smaller distance to the query
matches.sort(key=lambda x: D[x])
result = []
while len(matches) > 0:
o = matches[0]
result.append([D[o], o])
matches = [
x for x in matches if x < o - excl_zone or x > o + excl_zone
]
return np.array(result, dtype=object)