def _execute(self, x):
"""Return the clipped data."""
if self.lower_bounds is not None:
x = numx.where(x >= self.lower_bounds, x, self.lower_bounds)
if self.upper_bounds is not None:
x = numx.where(x <= self.upper_bounds, x, self.upper_bounds)
return x
def _execute(self, x):
"""Return the clipped data."""
if self.lower_bounds is not None:
x = numx.where(x >= self.lower_bounds, x, self.lower_bounds)
if self.upper_bounds is not None:
x = numx.where(x <= self.upper_bounds, x, self.upper_bounds)
return x
def _execute(self, x):
"""Return the clipped data."""
# n.clip() does not work, since it does not accept None for one bound
if self.lower_bound is not None:
x = numx.where(x >= self.lower_bound, x, self.lower_bound)
if self.upper_bound is not None:
x = numx.where(x <= self.upper_bound, x, self.upper_bound)
return x
def _execute(self, x):
"""Return the clipped data."""
# n.clip() does not work, since it does not accept None for one bound
if self.lower_bound is not None:
x = numx.where(x >= self.lower_bound, x, self.lower_bound)
if self.upper_bound is not None:
x = numx.where(x <= self.upper_bound, x, self.upper_bound)
return x
def _execute(self, x):
"""Return the clipped data.
:param x: Data to clip.
:type x: numpy.ndarray
:return: The clipped data.
:rtype: numpy.ndarray
"""
if self.lower_bounds is not None:
x = numx.where(x >= self.lower_bounds, x, self.lower_bounds)
if self.upper_bounds is not None:
x = numx.where(x <= self.upper_bounds, x, self.upper_bounds)
return x
def _execute(self, x):
"""Return the clipped data.
:param x: Data to clip.
:type x: numpy.ndarray
:return: The clipped data.
:rtype: numpy.ndarray
"""
if self.lower_bounds is not None:
x = numx.where(x >= self.lower_bounds, x, self.lower_bounds)
if self.upper_bounds is not None:
x = numx.where(x <= self.upper_bounds, x, self.upper_bounds)
return x
def _execute(self, x):
"""Return the clipped data.
:param x: Data to clip.
:type x: numpy.ndarray
:return: The clipped data.
:rtype: numpy.ndarray
"""
# n.clip() does not work, since it does not accept None for one bound
if self.lower_bound is not None:
x = numx.where(x >= self.lower_bound, x, self.lower_bound)
if self.upper_bound is not None:
x = numx.where(x <= self.upper_bound, x, self.upper_bound)
return x
def _execute(self, x):
"""Return the clipped data.
:param x: Data to clip.
:type x: numpy.ndarray
:return: The clipped data.
:rtype: numpy.ndarray
"""
# n.clip() does not work, since it does not accept None for one bound
if self.lower_bound is not None:
x = numx.where(x >= self.lower_bound, x, self.lower_bound)
if self.upper_bound is not None:
x = numx.where(x <= self.upper_bound, x, self.upper_bound)
return x
def _stop_training(self):
Cumulator._stop_training(self)
k = self.k
M = self.data
N = M.shape[0]
if k > N:
err = ('k=%i must be less than'
' or equal to number of training points N=%i' % (k, N))
raise TrainingException(err)
if self.verbose:
print 'performing HLLE on %i points in %i dimensions...' % M.shape
# determines number of output dimensions: if desired_variance
# is specified, we need to learn it from the data. Otherwise,
# it's easy
learn_outdim = False
if self.output_dim is None:
if self.desired_variance is None:
self.output_dim = self.input_dim
else:
learn_outdim = True
# determine number of output dims, precalculate useful stuff
if learn_outdim:
Qs, sig2s, nbrss = self._adjust_output_dim()
d_out = self.output_dim
#dp = d_out + (d_out-1) + (d_out-2) + ...
dp = d_out * (d_out + 1) / 2
if min(k, N) <= d_out:
err = ('k=%i and n=%i (number of input data points) must be'
' larger than output_dim=%i' % (k, N, d_out))
raise TrainingException(err)
if k < 1 + d_out + dp:
wrn = ('The number of neighbours, k=%i, is smaller than'
' 1 + output_dim + output_dim*(output_dim+1)/2 = %i,'
' which might result in unstable results.' %
(k, 1 + d_out + dp))
_warnings.warn(wrn, MDPWarning)
#build the weight matrix
#XXX for faster implementation, W should be a sparse matrix
W = numx.zeros((N, dp * N), dtype=self.dtype)
if self.verbose:
print ' - constructing [%i x %i] weight matrix...' % W.shape
for row in range(N):
if learn_outdim:
nbrs = nbrss[row, :]
else:
# -----------------------------------------------
# find k nearest neighbors
# -----------------------------------------------
M_Mi = M - M[row]
nbrs = numx.argsort((M_Mi**2).sum(1))[1:k + 1]
#-----------------------------------------------
# center the neighborhood using the mean
#-----------------------------------------------
nbrhd = M[nbrs] # this makes a copy
nbrhd -= nbrhd.mean(0)
#-----------------------------------------------
# compute local coordinates
# using a singular value decomposition
#-----------------------------------------------
U, sig, VT = svd(nbrhd)
nbrhd = U.T[:d_out]
del VT
#-----------------------------------------------
# build Hessian estimator
#-----------------------------------------------
Yi = numx.zeros((dp, k), dtype=self.dtype)
ct = 0
for i in range(d_out):
Yi[ct:ct + d_out - i, :] = nbrhd[i] * nbrhd[i:, :]
ct += d_out - i
Yi = numx.concatenate(
[numx.ones((1, k), dtype=self.dtype), nbrhd, Yi], 0)
#-----------------------------------------------
# orthogonalize linear and quadratic forms
# with QR factorization
# and make the weights sum to 1
#-----------------------------------------------
if k >= 1 + d_out + dp:
Q, R = numx_linalg.qr(Yi.T)
w = Q[:, d_out + 1:d_out + 1 + dp]
else:
q, r = _mgs(Yi.T)
w = q[:, -dp:]
S = w.sum(0) #sum along columns
#if S[i] is too small, set it equal to 1.0
# this prevents weights from blowing up
S[numx.where(numx.absolute(S) < 1E-4)] = 1.0
#print w.shape, S.shape, (w/S).shape
#print W[nbrs, row*dp:(row+1)*dp].shape
W[nbrs, row * dp:(row + 1) * dp] = w / S
#-----------------------------------------------
# To find the null space, we want the
# first d+1 eigenvectors of W.T*W
# Compute this using an svd of W
#-----------------------------------------------
if self.verbose:
msg = (' - finding [%i x %i] '
'null space of weight matrix...' % (d_out, N))
print msg
#XXX future work:
#XXX use of upcoming ARPACK interface for bottom few eigenvectors
#XXX of a sparse matrix will significantly increase the speed
#XXX of the next step
if self.svd:
sig, U = nongeneral_svd(W.T, range=(2, d_out + 1))
Y = U * numx.sqrt(N)
else:
WW = mult(W, W.T)
# regularizes the eigenvalues, does not change the eigenvectors:
W_diag_idx = numx.arange(N)
WW[W_diag_idx, W_diag_idx] += 0.01
sig, U = symeig(WW, range=(2, self.output_dim + 1), overwrite=True)
Y = U * numx.sqrt(N)
del WW
del W
#-----------------------------------------------
# Normalize Y
#
# Alternative way to do it:
# we need R = (Y.T*Y)^(-1/2)
# do this with an SVD of Y del VT
# Y = U*sig*V.T
# Y.T*Y = (V*sig.T*U.T) * (U*sig*V.T)
# = V * (sig*sig.T) * V.T
# = V * sig^2 V.T
# so
# R = V * sig^-1 * V.T
# The code is:
# U, sig, VT = svd(Y)
# del U
# S = numx.diag(sig**-1)
# self.training_projection = mult(Y, mult(VT.T, mult(S, VT)))
#-----------------------------------------------
if self.verbose:
print ' - normalizing null space...'
C = sqrtm(mult(Y.T, Y))
self.training_projection = mult(Y, C)
def _stop_training(self):
Cumulator._stop_training(self)
k = self.k
M = self.data
N = M.shape[0]
if k > N:
err = ('k=%i must be less than'
' or equal to number of training points N=%i' % (k, N))
raise TrainingException(err)
if self.verbose:
print 'performing HLLE on %i points in %i dimensions...' % M.shape
# determines number of output dimensions: if desired_variance
# is specified, we need to learn it from the data. Otherwise,
# it's easy
learn_outdim = False
if self.output_dim is None:
if self.desired_variance is None:
self.output_dim = self.input_dim
else:
learn_outdim = True
# determine number of output dims, precalculate useful stuff
if learn_outdim:
Qs, sig2s, nbrss = self._adjust_output_dim()
d_out = self.output_dim
#dp = d_out + (d_out-1) + (d_out-2) + ...
dp = d_out*(d_out+1)/2
if min(k, N) <= d_out:
err = ('k=%i and n=%i (number of input data points) must be'
' larger than output_dim=%i' % (k, N, d_out))
raise TrainingException(err)
if k < 1+d_out+dp:
wrn = ('The number of neighbours, k=%i, is smaller than'
' 1 + output_dim + output_dim*(output_dim+1)/2 = %i,'
' which might result in unstable results.'
% (k, 1+d_out+dp))
_warnings.warn(wrn, MDPWarning)
#build the weight matrix
#XXX for faster implementation, W should be a sparse matrix
W = numx.zeros((N, dp*N), dtype=self.dtype)
if self.verbose:
print ' - constructing [%i x %i] weight matrix...' % W.shape
for row in range(N):
if learn_outdim:
nbrs = nbrss[row, :]
else:
# -----------------------------------------------
# find k nearest neighbors
# -----------------------------------------------
M_Mi = M-M[row]
nbrs = numx.argsort((M_Mi**2).sum(1))[1:k+1]
#-----------------------------------------------
# center the neighborhood using the mean
#-----------------------------------------------
nbrhd = M[nbrs] # this makes a copy
nbrhd -= nbrhd.mean(0)
#-----------------------------------------------
# compute local coordinates
# using a singular value decomposition
#-----------------------------------------------
U, sig, VT = svd(nbrhd)
nbrhd = U.T[:d_out]
del VT
#-----------------------------------------------
# build Hessian estimator
#-----------------------------------------------
Yi = numx.zeros((dp, k), dtype=self.dtype)
ct = 0
for i in range(d_out):
Yi[ct:ct+d_out-i, :] = nbrhd[i] * nbrhd[i:, :]
ct += d_out-i
Yi = numx.concatenate([numx.ones((1, k), dtype=self.dtype),
nbrhd, Yi], 0)
#-----------------------------------------------
# orthogonalize linear and quadratic forms
# with QR factorization
# and make the weights sum to 1
#-----------------------------------------------
if k >= 1+d_out+dp:
Q, R = numx_linalg.qr(Yi.T)
w = Q[:, d_out+1:d_out+1+dp]
else:
q, r = _mgs(Yi.T)
w = q[:, -dp:]
S = w.sum(0) #sum along columns
#if S[i] is too small, set it equal to 1.0
# this prevents weights from blowing up
S[numx.where(numx.absolute(S)<1E-4)] = 1.0
#print w.shape, S.shape, (w/S).shape
#print W[nbrs, row*dp:(row+1)*dp].shape
W[nbrs, row*dp:(row+1)*dp] = w / S
#-----------------------------------------------
# To find the null space, we want the
# first d+1 eigenvectors of W.T*W
# Compute this using an svd of W
#-----------------------------------------------
if self.verbose:
msg = (' - finding [%i x %i] '
'null space of weight matrix...' % (d_out, N))
print msg
#XXX future work:
#XXX use of upcoming ARPACK interface for bottom few eigenvectors
#XXX of a sparse matrix will significantly increase the speed
#XXX of the next step
if self.svd:
sig, U = nongeneral_svd(W.T, range=(2, d_out+1))
Y = U*numx.sqrt(N)
else:
WW = mult(W, W.T)
# regularizes the eigenvalues, does not change the eigenvectors:
W_diag_idx = numx.arange(N)
WW[W_diag_idx, W_diag_idx] += 0.01
sig, U = symeig(WW, range=(2, self.output_dim+1), overwrite=True)
Y = U*numx.sqrt(N)
del WW
del W
#-----------------------------------------------
# Normalize Y
#
# Alternative way to do it:
# we need R = (Y.T*Y)^(-1/2)
# do this with an SVD of Y del VT
# Y = U*sig*V.T
# Y.T*Y = (V*sig.T*U.T) * (U*sig*V.T)
# = V * (sig*sig.T) * V.T
# = V * sig^2 V.T
# so
# R = V * sig^-1 * V.T
# The code is:
# U, sig, VT = svd(Y)
# del U
# S = numx.diag(sig**-1)
# self.training_projection = mult(Y, mult(VT.T, mult(S, VT)))
#-----------------------------------------------
if self.verbose:
print ' - normalizing null space...'
C = sqrtm(mult(Y.T, Y))
self.training_projection = mult(Y, C)
