def test_early_abandoned():
"""Test euclidean distance."""
assert pytest.approx(np.sqrt(2), 0.0000001) ==\
distance.early_abandoned_dist(np.array([1., 1.]),
np.array([2., 2.]), np.inf)
a = np.array([0.5, 0.8, 0.9])
b = np.array([-0.15, 0.38, 0.92])
assert pytest.approx(0.7741447, 0.0000001) ==\
distance.early_abandoned_dist(a, b, np.inf)
assert 1 == np.isnan(distance.early_abandoned_dist(a, b, 0.1))
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,
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)