def subseqDists(x, y):
"""find the L2^2 distances between y and every subseq of x"""
y = y.flatten()
y = (y - np.mean(y)) / np.std(y)
# flatten Nd input seqs
origDims = len(x.shape)
stride = origDims # TODO allow stepping in more than one direction
x = x.flatten()
subseqs = window.sliding_window(x, len(y), stride)
subseqs = zNormalizeRows(subseqs)
return distsToRows(subseqs, y)
def subseqDists(x, y): """find the L2^2 distances between y and every subseq of x""" y = y.flatten() y = (y - np.mean(y)) / np.std(y) # flatten Nd input seqs origDims = len(x.shape) stride = origDims # TODO allow stepping in more than one direction x = x.flatten() subseqs = window.sliding_window(x, len(y), stride) subseqs = zNormalizeRows(subseqs) return distsToRows(subseqs, y)
def uniqueSubseqsInSignals(signal, length, maxDist, norm='each', tree=None):
X, _, _ = window.flattened_subseqs_of_length(signal, length, norm=norm)
Xnorm = zNormalizeRows(X, removeZeros=False)
# print("subseqsInSignals: signal has %d subseqs" % (len(Xnorm)))
# init kd tree--we can't give it any data yet because we only want to
# search through seqs that have been added to the dictionary
if tree is None:
width = Xnorm.shape[1]
tree = kd.create(dimensions=width)
signalOccurIdxs = {}
tree.add(Xnorm[0], 0)
for startIdx, subseq in enumerate(Xnorm[1:]):
if np.sum(subseq * subseq) < .001: # ignore zero seqs
continue
startIdx += 1 # since we skipped Xnorm[0]
neighbors = tree.search_knn(subseq, 2)
neighborIdx = -1
neighborDist = np.inf
# pull out whichever neighbor isn't the query
for node, dist in neighbors:
idx = node.metadata
if idx != startIdx:
neighborIdx = idx
neighborDist = dist
if neighborIdx < 0:
print "ERROR: knn returned <2 neighbors..."
print "Neighbors returned:", neighbors
assert (0)
# print "neighborDist", neighborDist, maxDist
if neighborDist < maxDist:
# store that the subseq happened at this idx too
l = signalOccurIdxs.get(neighborIdx, [])
l.append(startIdx)
# signalOccurIdxs[neighborIdx] = l
else:
# ah, so this can overwrite crap and yield too few features
signalOccurIdxs[startIdx] = [startIdx]
tree.add(subseq, startIdx)
# rebalance if startIdx is a power of 2, so we do so log(N) times
if 2**int(np.log2(startIdx)) == startIdx:
# print "rebalancing at start idx %d" % (startIdx,)
tree.rebalance()
# signalOccurIdxs[neighborIdx] = [startIdx]
# if res:
# nn, dist = res
# if dist <= maxDist:
# # store that the subseq happened at this idx too
# neighborID = nn.metadata
# signalOccurIdxs[neighborID].append(startIdx)
# continue
# neighborID = startIdx
# signalOccurIdxs[neighborID] = [startIdx]
# tree.add(subseq, neighborID)
return signalOccurIdxs, Xnorm # return Xnorm for convenience, although confusing...
def allZNormalizedSubseqs(seqs, length):
X, _, _ = window.flattened_subseqs_of_length(seqs, length, norm='each')
return zNormalizeRows(X, removeZeros=False)
def uniqueSubseqsInSignals(signal, length, maxDist, norm='each', tree=None):
X, _, _ = window.flattened_subseqs_of_length(signal, length, norm=norm)
Xnorm = zNormalizeRows(X, removeZeros=False)
# print("subseqsInSignals: signal has %d subseqs" % (len(Xnorm)))
# init kd tree--we can't give it any data yet because we only want to
# search through seqs that have been added to the dictionary
if tree is None:
width = Xnorm.shape[1]
tree = kd.create(dimensions=width)
signalOccurIdxs = {}
tree.add(Xnorm[0], 0)
for startIdx, subseq in enumerate(Xnorm[1:]):
if np.sum(subseq*subseq) < .001: # ignore zero seqs
continue
startIdx += 1 # since we skipped Xnorm[0]
neighbors = tree.search_knn(subseq, 2)
neighborIdx = -1
neighborDist = np.inf
# pull out whichever neighbor isn't the query
for node, dist in neighbors:
idx = node.metadata
if idx != startIdx:
neighborIdx = idx
neighborDist = dist
if neighborIdx < 0:
print "ERROR: knn returned <2 neighbors..."
print "Neighbors returned:", neighbors
assert(0)
# print "neighborDist", neighborDist, maxDist
if neighborDist < maxDist:
# store that the subseq happened at this idx too
l = signalOccurIdxs.get(neighborIdx, [])
l.append(startIdx)
# signalOccurIdxs[neighborIdx] = l
else:
# ah, so this can overwrite crap and yield too few features
signalOccurIdxs[startIdx] = [startIdx]
tree.add(subseq, startIdx)
# rebalance if startIdx is a power of 2, so we do so log(N) times
if 2**int(np.log2(startIdx)) == startIdx:
# print "rebalancing at start idx %d" % (startIdx,)
tree.rebalance()
# signalOccurIdxs[neighborIdx] = [startIdx]
# if res:
# nn, dist = res
# if dist <= maxDist:
# # store that the subseq happened at this idx too
# neighborID = nn.metadata
# signalOccurIdxs[neighborID].append(startIdx)
# continue
# neighborID = startIdx
# signalOccurIdxs[neighborID] = [startIdx]
# tree.add(subseq, neighborID)
return signalOccurIdxs, Xnorm # return Xnorm for convenience, although confusing...
def allZNormalizedSubseqs(seqs, length): X, _, _ = window.flattened_subseqs_of_length(seqs, length, norm='each') return zNormalizeRows(X, removeZeros=False)
