def find_discords_brute_force(series, win_size = 1, num_discords=12,
z_threshold=0.01):
"""Early-abandoned distance-based discord discovery."""
discords = list()
globalRegistry = VisitRegistry(len(series))
globalRegistry.mark_visited_range(len(series) - win_size, len(series))
while (len(discords) < num_discords):
bestDiscord = find_best_discord_brute_force(series, win_size,
globalRegistry,
z_threshold)
if -1 == bestDiscord:
break
discords.append(bestDiscord)
mark_start = bestDiscord - win_size
if 0 > mark_start:
mark_start = 0
mark_end = bestDiscord + win_size
'''if len(series) < mark_end:
mark_end = len(series)'''
globalRegistry.mark_visited_range(mark_start, mark_end)
return discords
def find_discords_brute_force(series,
win_size,
num_discords=2,
znorm_threshold=0.01):
"""Early-abandoned distance-based discord discovery."""
discords = list()
globalRegistry = VisitRegistry(len(series) - win_size + 1)
znorms = np.array([
znorm(series[pos:pos + win_size], znorm_threshold)
for pos in range(len(series) - win_size + 1)
])
while len(discords) < num_discords:
bestDiscord = find_best_discord_brute_force(series, win_size,
globalRegistry, znorms)
if -1 == bestDiscord[0]:
break
discords.append(bestDiscord)
mark_start = max(0, bestDiscord[0] - win_size + 1)
mark_end = bestDiscord[0] + win_size
globalRegistry.mark_visited_range(mark_start, mark_end)
return discords
def test_sizing():
"""Test the registry."""
reg = VisitRegistry(77)
assert 77 == reg.get_unvisited_count()
reg.mark_visited(0)
assert 76 == reg.get_unvisited_count()
reg.mark_visited_range(70, 77)
assert 69 == reg.get_unvisited_count()
reg.mark_visited(0)
assert 69 == reg.get_unvisited_count()
reg.mark_visited(1)
assert 68 == reg.get_unvisited_count()
reg.mark_visited(reg.get_next_unvisited())
assert 67 == reg.get_unvisited_count()
reg.mark_visited_range(0, 77)
assert np.isnan(reg.get_next_unvisited())