def find_best_discord_brute_force(series,
win_size,
global_registry,
z_threshold=0.01):
"""Early-abandoned distance-based discord discovery."""
best_so_far_distance = -1.0
best_so_far_index = -1
outerRegistry = global_registry.clone()
outer_idx = outerRegistry.get_next_unvisited()
while ~np.isnan(outer_idx):
outerRegistry.mark_visited(outer_idx)
candidate_seq = znorm(series[outer_idx:(outer_idx + win_size)],
z_threshold)
nnDistance = np.inf
innerRegistry = VisitRegistry(len(series) - win_size)
inner_idx = innerRegistry.get_next_unvisited()
while ~np.isnan(inner_idx):
innerRegistry.mark_visited(inner_idx)
if abs(inner_idx - outer_idx) > win_size:
curr_seq = znorm(series[inner_idx:(inner_idx + win_size)],
z_threshold)
dist = early_abandoned_dist(candidate_seq, curr_seq,
nnDistance)
if (~np.isnan(dist)) and (dist < nnDistance):
nnDistance = dist
inner_idx = innerRegistry.get_next_unvisited()
if ~(np.inf == nnDistance) and (nnDistance > best_so_far_distance):
best_so_far_distance = nnDistance
best_so_far_index = outer_idx
outer_idx = outerRegistry.get_next_unvisited()
return (best_so_far_index)
def find_best_discord_brute_force(series, win_size, global_registry, znorms):
"""Early-abandoned distance-based discord discovery."""
best_so_far_distance = -1.0
best_so_far_index = -1
outer_registry = global_registry.clone()
outer_idx = outer_registry.get_next_unvisited()
while ~np.isnan(outer_idx):
outer_registry.mark_visited(outer_idx)
candidate_seq = znorms[outer_idx]
nn_distance = np.inf
inner_registry = VisitRegistry(len(series) - win_size + 1)
inner_idx = inner_registry.get_next_unvisited()
while ~np.isnan(inner_idx):
inner_registry.mark_visited(inner_idx)
if abs(inner_idx - outer_idx) >= win_size:
curr_seq = znorms[inner_idx]
dist = early_abandoned_euclidean(candidate_seq, curr_seq,
nn_distance)
if (~np.isnan(dist)) and (dist < nn_distance):
nn_distance = dist
inner_idx = inner_registry.get_next_unvisited()
if ~(np.inf == nn_distance) and (nn_distance > best_so_far_distance):
best_so_far_distance = nn_distance
best_so_far_index = outer_idx
outer_idx = outer_registry.get_next_unvisited()
return best_so_far_index, best_so_far_distance
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())
def find_best_discord_brute_force(series,
win_size,
global_registry,
z_threshold=0.01):
"""Early-abandoned distance-based discord discovery."""
best_so_far_distance = -1.0
best_so_far_index = -1
outerRegistry = global_registry.clone()
# 随机找到一个未看过的index
outer_idx = outerRegistry.get_next_unvisited()
# 若 outer_idx 不是nan值 则进入循环 ~按位取反
while ~np.isnan(outer_idx):
# 标记看过outer_idx
outerRegistry.mark_visited(outer_idx)
# 标准化候选子序列 开始索引outer_indx 结束索引outer_idx+win_size-1
candidate_seq = znorm(series[outer_idx:(outer_idx + win_size)],
z_threshold)
# 与candidate_seq的开始索引相距不小于窗口大小的 开始索引所代表的子序列 与其的最小距离 (两子序列形状相似)
nnDistance = np.inf
# 为什么不是 len(series) - win_size + 1 ???
innerRegistry = VisitRegistry(len(series) - win_size)
inner_idx = innerRegistry.get_next_unvisited()
# 遍历所有开始索引 在两子序列距离大于窗口大小的条件下 找到与candidate_seq的最近距离nnDistance
while ~np.isnan(inner_idx):
innerRegistry.mark_visited(inner_idx)
# 若 inner_indx 与 outer_idx 距离 大于 窗口大小 即两子序列不能有重复部分且不相邻
if abs(inner_idx - outer_idx) > win_size:
curr_seq = znorm(series[inner_idx:(inner_idx + win_size)],
z_threshold)
# 计算 标准化后两序列的欧式距离
dist = early_abandoned_dist(candidate_seq, curr_seq,
nnDistance)
# 更新 nnDistance 使其逐渐变小
if (~np.isnan(dist)) and (dist < nnDistance):
nnDistance = dist
inner_idx = innerRegistry.get_next_unvisited()
# 更新 best_so_far_distance 和 best_so_far_index
"""
best_so_far_distance
max(min(distance))
相似性最小的子序列 与 距离最近的子序列 的距离
best_so_far_index
当前时间序列的异常子序列 开始索引
这段子序列在当前时间序列中与其他子序列的相似性是最小的
"""
if ~(np.inf == nnDistance) and (nnDistance > best_so_far_distance):
best_so_far_distance = nnDistance
best_so_far_index = outer_idx
outer_idx = outerRegistry.get_next_unvisited()
return (best_so_far_index, best_so_far_distance)