def uniqueSubseqs(seqs, length, maxDist, tieDims=False):
"""return a set of subseqs such that no subseq is within maxDist of any
other subseq and all original subseqs are within maxDist of one of the
subseqs returned; basically a greedy unique operator where uniqueness
is defined by L2^2 distance within maxDist"""
seqs = asListOrTuple(seqs)
is1D = len(seqs[0].shape) == 1
if tieDims or is1D:
# zip trick so that we always return two lists (occurIdxs and Xnorms)
return zip(
*[uniqueSubseqsInSignals(seqs, length, maxDist, norm='each_mean')])
else:
nDims = seqs[0].shape[1]
occurIdxs = []
Xnorms = []
for dim in range(nDims): # for each dimension
print("finding unique seqs in dim %d" % (dim, ))
signals = map(lambda seq: seq[:, dim], seqs)
signalOccurIdxs, Xnorm = uniqueSubseqsInSignals(signals,
length,
maxDist,
norm='each_mean')
print("found %d unique seqs" % (len(signalOccurIdxs), ))
occurIdxs.append(signalOccurIdxs)
Xnorms.append(Xnorm)
return occurIdxs, Xnorms
def uniqueSubseqs(seqs, length, maxDist, tieDims=False):
"""return a set of subseqs such that no subseq is within maxDist of any
other subseq and all original subseqs are within maxDist of one of the
subseqs returned; basically a greedy unique operator where uniqueness
is defined by L2^2 distance within maxDist"""
seqs = asListOrTuple(seqs)
is1D = len(seqs[0].shape) == 1
if tieDims or is1D:
# zip trick so that we always return two lists (occurIdxs and Xnorms)
return zip(*[uniqueSubseqsInSignals(seqs, length, maxDist, norm='each_mean')])
else:
nDims = seqs[0].shape[1]
occurIdxs = []
Xnorms = []
for dim in range(nDims): # for each dimension
print("finding unique seqs in dim %d" % (dim,))
signals = map(lambda seq: seq[:, dim], seqs)
signalOccurIdxs, Xnorm = uniqueSubseqsInSignals(signals, length, maxDist, norm='each_mean')
print("found %d unique seqs" % (len(signalOccurIdxs),))
occurIdxs.append(signalOccurIdxs)
Xnorms.append(Xnorm)
return occurIdxs, Xnorms
def pairwiseDists(seqs,
length,
norm='each',
tieDims=False,
pad=True,
removeZeros=True,
k=-1):
seqs = asListOrTuple(seqs)
nDims = 1
if len(seqs[0].shape) < 2 or tieDims:
Xnorm, _, _ = window.flattened_subseqs_of_length(seqs,
length,
norm=norm)
else:
nDims = seqs[0].shape[1]
# bypass flattening--each dim of each seq is treated as a separate
# 1D seq; we end up with a long list whose elements are 1D vectors,
# each of which was originally a column within some ND array in seqs
#
# note that this may do weird things if there's more than one seq
# because the dims for each seq are sequential, rather than the seqs
# for each dim
separatedByDim = map(lambda X: colsAsList(X), seqs)
flatSeqs = flattenListOfLists(separatedByDim)
flatSeqs = map(lambda v: v.flatten(),
flatSeqs) # col vects -> 1D arrays
Xnorm, _, _ = window.flattened_subseqs_of_length(flatSeqs,
length,
norm='each')
nSamples, m = Xnorm.shape
rowsPerDim = nSamples / nDims
print "----- pairwiseDists"
print "length", length
print "origSeqs[0] shape", seqs[0].shape
print "nsamples, m, rowsPerDim", Xnorm.shape, rowsPerDim
print "-----"
if pad:
paddingLen = length - 1
else:
paddingLen = 0
# print "Xnorm stats:", np.mean(Xnorm, axis=1), np.std(Xnorm, axis=1)
# D = np.zeros((nSamples, nSamples+paddingLen*nDims)) # 0 pad at end so samples line up
Dtensor = np.zeros((nDims, rowsPerDim, rowsPerDim + paddingLen))
# D = np.zeros((nSamples, nSamples))
maxPossibleDist = 2**2 * m
maxIdx = 0
for dim in range(nDims):
# extract subseqs associated with this dim
minIdx = maxIdx
maxIdx += rowsPerDim
Xdim = Xnorm[minIdx:maxIdx]
# compute dists to each one
for i, row in enumerate(Xdim):
if removeZeros:
if np.sum(row * row) < 1.e-6:
Dtensor[dim, i, :rowsPerDim] = maxPossibleDist
continue
diffs = Xdim - row
diffs_sq = diffs * diffs
# dMinIdx = minIdx + dim*paddingLen
# dMaxIdx = dMinIdx + rowsPerDim
dists = np.sum(diffs_sq, axis=1)
# D[minIdx + i, dMinIdx:dMaxIdx] = dists
Dtensor[dim, i, :rowsPerDim] = dists
# only keep k lowest dists
if k > 0:
for j in np.arange(rowsPerDim):
col = Dtensor[dim, :, j]
highestIdxs = np.argsort(col)[k:]
Dtensor[dim, highestIdxs, j] = maxPossibleDist
# return Dtensor, D, Xnorm
return Dtensor, Xnorm
def pairwiseDists(seqs, length, norm='each', tieDims=False, pad=True, removeZeros=True, k=-1): seqs = asListOrTuple(seqs) nDims = 1 if len(seqs[0].shape) < 2 or tieDims: Xnorm, _, _ = window.flattened_subseqs_of_length(seqs, length, norm=norm) else: nDims = seqs[0].shape[1] # bypass flattening--each dim of each seq is treated as a separate # 1D seq; we end up with a long list whose elements are 1D vectors, # each of which was originally a column within some ND array in seqs # # note that this may do weird things if there's more than one seq # because the dims for each seq are sequential, rather than the seqs # for each dim separatedByDim = map(lambda X: colsAsList(X), seqs) flatSeqs = flattenListOfLists(separatedByDim) flatSeqs = map(lambda v: v.flatten(), flatSeqs) # col vects -> 1D arrays Xnorm, _, _ = window.flattened_subseqs_of_length(flatSeqs, length, norm='each') nSamples, m = Xnorm.shape rowsPerDim = nSamples / nDims print "----- pairwiseDists" print "length", length print "origSeqs[0] shape", seqs[0].shape print "nsamples, m, rowsPerDim", Xnorm.shape, rowsPerDim print "-----" if pad: paddingLen = length - 1 else: paddingLen = 0 # print "Xnorm stats:", np.mean(Xnorm, axis=1), np.std(Xnorm, axis=1) # D = np.zeros((nSamples, nSamples+paddingLen*nDims)) # 0 pad at end so samples line up Dtensor = np.zeros((nDims, rowsPerDim, rowsPerDim+paddingLen)) # D = np.zeros((nSamples, nSamples)) maxPossibleDist = 2**2 * m maxIdx = 0 for dim in range(nDims): # extract subseqs associated with this dim minIdx = maxIdx maxIdx += rowsPerDim Xdim = Xnorm[minIdx:maxIdx] # compute dists to each one for i, row in enumerate(Xdim): if removeZeros: if np.sum(row*row) < 1.e-6: Dtensor[dim, i, :rowsPerDim] = maxPossibleDist continue diffs = Xdim - row diffs_sq = diffs * diffs # dMinIdx = minIdx + dim*paddingLen # dMaxIdx = dMinIdx + rowsPerDim dists = np.sum(diffs_sq, axis=1) # D[minIdx + i, dMinIdx:dMaxIdx] = dists Dtensor[dim, i,:rowsPerDim] = dists # only keep k lowest dists if k > 0: for j in np.arange(rowsPerDim): col = Dtensor[dim, :, j] highestIdxs = np.argsort(col)[k:] Dtensor[dim, highestIdxs, j] = maxPossibleDist # return Dtensor, D, Xnorm return Dtensor, Xnorm