def solve_linear(self, regparam):
self.regparam = regparam
X1, X2 = self.X1, self.X2
Y = self.Y.reshape((X1.shape[0], X2.shape[0]), order='F')
if not self.trained:
self.trained = True
svals1, V, rsvecs1 = decomposition.decomposeDataMatrix(X1.T)
self.svals1 = svals1.T
self.evals1 = multiply(self.svals1, self.svals1)
self.V = V
self.rsvecs1 = mat(rsvecs1)
if X1.shape == X2.shape and (X1 == X2).all():
svals2, U, rsvecs2 = svals1, V, rsvecs1
else:
svals2, U, rsvecs2 = decomposition.decomposeDataMatrix(X2.T)
self.svals2 = svals2.T
self.evals2 = multiply(self.svals2, self.svals2)
self.U = U
self.rsvecs2 = mat(rsvecs2)
self.VTYU = V.T * Y * U
kronsvals = self.svals1 * self.svals2.T
newevals = divide(kronsvals, multiply(kronsvals, kronsvals) + regparam)
self.W = multiply(self.VTYU, newevals)
self.W = self.rsvecs1.T * self.W * self.rsvecs2
self.model = LinearPairwiseModel(self.W)
def solve_linear(self, regparam1, regparam2):
self.regparam1 = regparam1
self.regparam2 = regparam2
X1, X2 = self.X1, self.X2
Y = self.Y.reshape((X1.shape[0], X2.shape[0]), order='F')
if not self.trained:
self.trained = True
svals1, V, rsvecs1 = decomposition.decomposeDataMatrix(X1.T)
self.svals1 = svals1.T
self.evals1 = np.multiply(self.svals1, self.svals1)
self.V = V
self.rsvecs1 = np.mat(rsvecs1)
if X1.shape == X2.shape and (X1 == X2).all():
svals2, U, rsvecs2 = svals1, V, rsvecs1
else:
svals2, U, rsvecs2 = decomposition.decomposeDataMatrix(X2.T)
self.svals2 = svals2.T
self.evals2 = np.multiply(self.svals2, self.svals2)
self.U = U
self.rsvecs2 = np.mat(rsvecs2)
self.VTYU = V.T * Y * U
self.newevals1 = 1. / (self.evals1 + regparam1)
self.newevals2 = 1. / (self.evals2 + regparam2)
newevals = self.newevals1 * self.newevals2.T
newevals = np.multiply(self.svals1, self.newevals1) * np.multiply(self.svals2, self.newevals2).T
self.W = np.multiply(self.VTYU, newevals)
self.W = self.rsvecs1.T * self.W * self.rsvecs2
self.model = LinearPairwiseModel(self.W)
def solve_linear(self, regparam):
self.regparam = regparam
X1, X2 = self.X1, self.X2
Y = self.Y.reshape((X1.shape[0], X2.shape[0]), order='F')
if not self.trained:
self.trained = True
svals1, V, rsvecs1 = decomposition.decomposeDataMatrix(X1.T)
self.svals1 = svals1.T
self.evals1 = multiply(self.svals1, self.svals1)
self.V = V
self.rsvecs1 = mat(rsvecs1)
if X1.shape == X2.shape and (X1 == X2).all():
svals2, U, rsvecs2 = svals1, V, rsvecs1
else:
svals2, U, rsvecs2 = decomposition.decomposeDataMatrix(X2.T)
self.svals2 = svals2.T
self.evals2 = multiply(self.svals2, self.svals2)
self.U = U
self.rsvecs2 = mat(rsvecs2)
self.VTYU = V.T * Y * U
kronsvals = self.svals1 * self.svals2.T
newevals = divide(kronsvals, multiply(kronsvals, kronsvals) + regparam)
self.W = multiply(self.VTYU, newevals)
self.W = self.rsvecs1.T * self.W * self.rsvecs2
self.model = LinearPairwiseModel(self.W)
def solve_linear_conditional_ranking(self, regparam):
self.regparam = regparam
X1, X2 = self.X1, self.X2
Y = self.Y.reshape((X1.shape[0], X2.shape[0]), order='F')
if not self.trained:
self.trained = True
svals1, V, rsvecs1 = decomposition.decomposeDataMatrix(X1.T)
self.svals1 = svals1.T
self.evals1 = multiply(self.svals1, self.svals1)
self.V = V
self.rsvecs1 = mat(rsvecs1)
qlen = X2.shape[0]
onevec = (1./math.sqrt(qlen))*mat(ones((qlen,1)))
C = mat(eye(qlen))-onevec*onevec.T
svals2, U, rsvecs2 = decomposition.decomposeDataMatrix(X2.T * C)
self.svals2 = svals2.T
self.evals2 = multiply(self.svals2, self.svals2)
self.U = U
self.rsvecs2 = mat(rsvecs2)
self.VTYU = V.T * Y * C * U
kronsvals = self.svals1 * self.svals2.T
newevals = divide(kronsvals, multiply(kronsvals, kronsvals) + regparam)
self.W = multiply(self.VTYU, newevals)
self.W = self.rsvecs1.T * self.W * self.rsvecs2
self.model = LinearPairwiseModel(self.W)
def solve_linear_conditional_ranking(self, regparam):
self.regparam = regparam
X1, X2 = self.X1, self.X2
Y = self.Y.reshape((X1.shape[0], X2.shape[0]), order='F')
if not self.trained:
self.trained = True
svals1, V, rsvecs1 = decomposition.decomposeDataMatrix(X1.T)
self.svals1 = svals1.T
self.evals1 = multiply(self.svals1, self.svals1)
self.V = V
self.rsvecs1 = mat(rsvecs1)
qlen = X2.shape[0]
onevec = (1./math.sqrt(qlen))*mat(ones((qlen,1)))
C = mat(eye(qlen))-onevec*onevec.T
svals2, U, rsvecs2 = decomposition.decomposeDataMatrix(X2.T * C)
self.svals2 = svals2.T
self.evals2 = multiply(self.svals2, self.svals2)
self.U = U
self.rsvecs2 = mat(rsvecs2)
self.VTYU = V.T * Y * C * U
kronsvals = self.svals1 * self.svals2.T
newevals = divide(kronsvals, multiply(kronsvals, kronsvals) + regparam)
self.W = multiply(self.VTYU, newevals)
self.W = self.rsvecs1.T * self.W * self.rsvecs2
self.model = LinearPairwiseModel(self.W)
def solve_linear(self, regparam1, regparam2):
self.regparam1 = regparam1
self.regparam2 = regparam2
X1, X2 = self.X1, self.X2
Y = self.Y.reshape((X1.shape[0], X2.shape[0]), order='F')
if not self.trained:
self.trained = True
svals1, V, rsvecs1 = decomposition.decomposeDataMatrix(X1.T)
self.svals1 = svals1.T
self.evals1 = np.multiply(self.svals1, self.svals1)
self.V = V
self.rsvecs1 = np.mat(rsvecs1)
if X1.shape == X2.shape and (X1 == X2).all():
svals2, U, rsvecs2 = svals1, V, rsvecs1
else:
svals2, U, rsvecs2 = decomposition.decomposeDataMatrix(X2.T)
self.svals2 = svals2.T
self.evals2 = np.multiply(self.svals2, self.svals2)
self.U = U
self.rsvecs2 = np.mat(rsvecs2)
self.VTYU = V.T * Y * U
self.newevals1 = 1. / (self.evals1 + regparam1)
self.newevals2 = 1. / (self.evals2 + regparam2)
newevals = self.newevals1 * self.newevals2.T
newevals = np.multiply(self.svals1, self.newevals1) * np.multiply(
self.svals2, self.newevals2).T
self.W = np.multiply(self.VTYU, newevals)
self.W = self.rsvecs1.T * self.W * self.rsvecs2
self.model = LinearPairwiseModel(self.W)
def decompositionFromPool(self, rpool):
kernel = rpool['kernel_obj']
self.X = rpool['train_features']
if rpool.has_key('basis_vectors'):
basis_vectors = rpool['basis_vectors']
else:
basis_vectors = None
if "bias" in rpool:
self.bias = float(rpool["bias"])
else:
self.bias = 0.
if basis_vectors != None or self.X.shape[1] > self.X.shape[0]:
#First possibility: subset of regressors has been invoked
if basis_vectors != None:
K_r = kernel.getKM(self.X).T
Krr = kernel.getKM(basis_vectors)
svals, evecs, U, Z = decomposition.decomposeSubsetKM(K_r, Krr)
#Second possibility: dual mode if more attributes than examples
else:
K = kernel.getKM(self.X).T
svals, evecs = decomposition.decomposeKernelMatrix(K)
U, Z = None, None
#Third possibility, primal decomposition
else:
#Invoking getPrimalDataMatrix adds the bias feature
X = getPrimalDataMatrix(self.X,self.bias)
svals, evecs, U = decomposition.decomposeDataMatrix(X.T)
U, Z = None, None
return svals, evecs, U, Z
def decompositionFromPool(self, rpool):
kernel = rpool[data_sources.KERNEL_OBJ]
self.X = rpool[data_sources.TRAIN_FEATURES]
if rpool.has_key(data_sources.BASIS_VECTORS):
bvectors = rpool[data_sources.BASIS_VECTORS]
else:
bvectors = None
if "bias" in rpool:
self.bias = float(rpool["bias"])
else:
self.bias = 0.
if bvectors != None or self.X.shape[1] > self.X.shape[0]:
K = kernel.getKM(self.X).T
#First possibility: subset of regressors has been invoked
if bvectors != None:
svals, evecs, U, Z = decomposition.decomposeSubsetKM(
K, bvectors)
#Second possibility: dual mode if more attributes than examples
else:
svals, evecs = decomposition.decomposeKernelMatrix(K)
U, Z = None, None
#Third possibility, primal decomposition
else:
#Invoking getPrimalDataMatrix adds the bias feature
X = getPrimalDataMatrix(self.X, self.bias)
svals, evecs, U = decomposition.decomposeDataMatrix(X.T)
U, Z = None, None
return svals, evecs, U, Z
def decompositionFromPool(self, rpool):
kernel = rpool['kernel_obj']
self.X = rpool['train_features']
if rpool.has_key('basis_vectors'):
basis_vectors = rpool['basis_vectors']
else:
basis_vectors = None
if "bias" in rpool:
self.bias = float(rpool["bias"])
else:
self.bias = 0.
if basis_vectors != None or self.X.shape[1] > self.X.shape[0]:
#First possibility: subset of regressors has been invoked
if basis_vectors != None:
K_r = kernel.getKM(self.X).T
Krr = kernel.getKM(basis_vectors)
svals, evecs, U, Z = decomposition.decomposeSubsetKM(K_r, Krr)
#Second possibility: dual mode if more attributes than examples
else:
K = kernel.getKM(self.X).T
svals, evecs = decomposition.decomposeKernelMatrix(K)
U, Z = None, None
#Third possibility, primal decomposition
else:
#Invoking getPrimalDataMatrix adds the bias feature
X = getPrimalDataMatrix(self.X, self.bias)
svals, evecs, U = decomposition.decomposeDataMatrix(X.T)
U, Z = None, None
return svals, evecs, U, Z
def decompositionFromPool(self, rpool):
kernel = rpool[data_sources.KERNEL_OBJ]
self.X = rpool[data_sources.TRAIN_FEATURES]
if rpool.has_key(data_sources.BASIS_VECTORS):
bvectors = rpool[data_sources.BASIS_VECTORS]
else:
bvectors = None
if "bias" in rpool:
self.bias = float(rpool["bias"])
else:
self.bias = 0.
if bvectors != None or self.X.shape[1] > self.X.shape[0]:
K = kernel.getKM(self.X).T
#First possibility: subset of regressors has been invoked
if bvectors != None:
svals, evecs, U, Z = decomposition.decomposeSubsetKM(K, bvectors)
#Second possibility: dual mode if more attributes than examples
else:
svals, evecs = decomposition.decomposeKernelMatrix(K)
U, Z = None, None
#Third possibility, primal decomposition
else:
#Invoking getPrimalDataMatrix adds the bias feature
X = getPrimalDataMatrix(self.X,self.bias)
svals, evecs, U = decomposition.decomposeDataMatrix(X.T)
U, Z = None, None
return svals, evecs, U, Z
def decompositionFromPool(self, rpool):
kernel = rpool['kernel_obj']
self.X = array_tools.as_2d_array(rpool['X'], True)
if rpool.has_key('basis_vectors'):
basis_vectors = array_tools.as_2d_array(rpool['basis_vectors'], True)
if not self.X.shape[1] == basis_vectors.shape[1]:
raise Exception("X and basis_vectors have different number of columns")
else:
basis_vectors = None
if "bias" in rpool:
self.bias = float(rpool["bias"])
else:
self.bias = 1.
if basis_vectors != None or self.X.shape[1] > self.X.shape[0]:
#First possibility: subset of regressors has been invoked
if basis_vectors != None:
K_r = kernel.getKM(self.X).T
Krr = kernel.getKM(basis_vectors)
svals, evecs, U, Z = decomposition.decomposeSubsetKM(K_r, Krr)
#Second possibility: dual mode if more attributes than examples
else:
K = kernel.getKM(self.X).T
svals, evecs = decomposition.decomposeKernelMatrix(K)
U, Z = None, None
#Third possibility, primal decomposition
else:
#Invoking getPrimalDataMatrix adds the bias feature
X = getPrimalDataMatrix(self.X,self.bias)
svals, evecs, U = decomposition.decomposeDataMatrix(X.T)
U, Z = None, None
return svals, evecs, U, Z
def solve_linear_conditional_ranking(self, regparam):
"""Trains conditional ranking KronRLS, that ranks objects from
domain 2 against objects from domain 1.
Parameters
----------
regparam : float, optional
regularization parameter, regparam > 0 (default=1.0)
Notes
-----
Minimizes RankRLS type of loss. Currently only linear kernel
supported. Including the code here is a hack, this should
probably be implemented as an independent learner.
"""
self.regparam = regparam
X1, X2 = self.X1, self.X2
Y = self.Y.reshape((X1.shape[0], X2.shape[0]), order='F')
svals1, V, rsvecs1 = decomposition.decomposeDataMatrix(X1.T)
self.svals1 = svals1.T
self.evals1 = np.multiply(self.svals1, self.svals1)
self.V = V
self.rsvecs1 = np.mat(rsvecs1)
qlen = X2.shape[0]
onevec = (1. / np.math.sqrt(qlen)) * np.mat(np.ones((qlen, 1)))
C = np.mat(np.eye(qlen)) - onevec * onevec.T
svals2, U, rsvecs2 = decomposition.decomposeDataMatrix(X2.T * C)
self.svals2 = svals2.T
self.evals2 = np.multiply(self.svals2, self.svals2)
self.U = U
self.rsvecs2 = np.mat(rsvecs2)
self.VTYU = V.T * Y * C * U
kronsvals = self.svals1 * self.svals2.T
newevals = np.divide(kronsvals,
np.multiply(kronsvals, kronsvals) + regparam)
self.W = np.multiply(self.VTYU, newevals)
self.W = self.rsvecs1.T * self.W * self.rsvecs2
self.predictor = LinearPairwisePredictor(np.array(self.W))
def solve(self, regparam1, regparam2):
"""Re-trains TwoStepRLS for the given regparams
Parameters
----------
regparam1: float
regularization parameter 1, regparam1 > 0
regparam2: float
regularization parameter 2, regparam2 > 0
Notes
-----
Computational complexity of re-training:
m = n_samples1, n = n_samples2, d = n_features1, e = n_features2
O(ed^2 + de^2) Linear version (assumption: d < m, e < n)
O(m^3 + n^3) Kernel version
"""
self.regparam1 = regparam1
self.regparam2 = regparam2
if self.kernelmode:
K1, K2 = self.K1, self.K2
Y = self.Y.reshape((K1.shape[0], K2.shape[0]), order='F')
#assert self.Y.shape == (self.K1.shape[0], self.K2.shape[0]), 'Y.shape!=(K1.shape[0],K2.shape[0]). Y.shape=='+str(Y.shape)+', K1.shape=='+str(self.K1.shape)+', K2.shape=='+str(self.K2.shape)
if not self.trained:
self.trained = True
evals1, V = decomposition.decomposeKernelMatrix(K1)
evals1 = np.mat(evals1).T
evals1 = np.multiply(evals1, evals1)
V = np.mat(V)
self.evals1 = evals1
self.V = V
evals2, U = decomposition.decomposeKernelMatrix(K2)
evals2 = np.mat(evals2).T
evals2 = np.multiply(evals2, evals2)
U = np.mat(U)
self.evals2 = evals2
self.U = U
self.VTYU = V.T * self.Y * U
#newevals = 1. / (self.evals1 * self.evals2.T + regparam)
self.newevals1 = 1. / (self.evals1 + regparam1)
self.newevals2 = 1. / (self.evals2 + regparam2)
newevals = self.newevals1 * self.newevals2.T
self.A = np.multiply(self.VTYU, newevals)
self.A = self.V * self.A * self.U.T
self.A = np.array(self.A)
#self.predictor = KernelPairwisePredictor(self.A)
label_row_inds, label_col_inds = np.unravel_index(np.arange(K1.shape[0] * K2.shape[0]), (K1.shape[0], K2.shape[0]))
label_row_inds = np.array(label_row_inds, dtype = np.int32)
label_col_inds = np.array(label_col_inds, dtype = np.int32)
self.predictor = KernelPairwisePredictor(self.A.ravel(), label_row_inds, label_col_inds)
#self.dsikm1 = la.inv(K1 + regparam1 * (np.mat(np.eye(K1.shape[0]))))
#self.dsikm2 = la.inv(K2 + regparam2 * (np.mat(np.eye(K2.shape[0]))))
else:
X1, X2 = self.X1, self.X2
Y = self.Y.reshape((X1.shape[0], X2.shape[0]), order='F')
if not self.trained:
self.trained = True
svals1, V, rsvecs1 = decomposition.decomposeDataMatrix(X1.T)
self.svals1 = svals1.T
self.evals1 = np.multiply(self.svals1, self.svals1)
self.V = V
self.rsvecs1 = np.mat(rsvecs1)
if X1.shape == X2.shape and (X1 == X2).all():
svals2, U, rsvecs2 = svals1, V, rsvecs1
else:
svals2, U, rsvecs2 = decomposition.decomposeDataMatrix(X2.T)
self.svals2 = svals2.T
self.evals2 = np.multiply(self.svals2, self.svals2)
self.U = U
self.rsvecs2 = np.mat(rsvecs2)
self.VTYU = V.T * Y * U
self.newevals1 = 1. / (self.evals1 + regparam1)
self.newevals2 = 1. / (self.evals2 + regparam2)
newevals = np.multiply(self.svals1, self.newevals1) * np.multiply(self.svals2, self.newevals2).T
self.W = np.multiply(self.VTYU, newevals)
self.W = self.rsvecs1.T * self.W * self.rsvecs2
#self.predictor = LinearPairwisePredictor(self.W)
self.predictor = LinearPairwisePredictor(np.array(self.W))
def solve(self, regparam):
"""Re-trains KronRLS for the given regparam
Parameters
----------
regparam : float, optional
regularization parameter, regparam > 0
Notes
-----
Computational complexity of re-training:
m = n_samples1, n = n_samples2, d = n_features1, e = n_features2
O(ed^2 + de^2) Linear version (assumption: d < m, e < n)
O(m^3 + n^3) Kernel version
"""
self.regparam = regparam
if self.kernelmode:
K1, K2 = self.K1, self.K2
#assert self.Y.shape == (self.K1.shape[0], self.K2.shape[0]), 'Y.shape!=(K1.shape[0],K2.shape[0]). Y.shape=='+str(Y.shape)+', K1.shape=='+str(self.K1.shape)+', K2.shape=='+str(self.K2.shape)
if not self.trained:
self.trained = True
evals1, V = la.eigh(K1)
evals1 = np.mat(evals1).T
V = np.mat(V)
self.evals1 = evals1
self.V = V
evals2, U = la.eigh(K2)
evals2 = np.mat(evals2).T
U = np.mat(U)
self.evals2 = evals2
self.U = U
self.VTYU = V.T * self.Y * U
newevals = 1. / (self.evals1 * self.evals2.T + regparam)
self.A = np.multiply(self.VTYU, newevals)
self.A = self.V * self.A * self.U.T
self.A = np.asarray(self.A)
label_row_inds, label_col_inds = np.unravel_index(
np.arange(K1.shape[0] * K2.shape[0]),
(K1.shape[0], K2.shape[0]))
label_row_inds = np.array(label_row_inds, dtype=np.int32)
label_col_inds = np.array(label_col_inds, dtype=np.int32)
self.predictor = KernelPairwisePredictor(self.A.ravel(),
label_row_inds,
label_col_inds)
else:
X1, X2 = self.X1, self.X2
Y = self.Y.reshape((X1.shape[0], X2.shape[0]), order='F')
if not self.trained:
self.trained = True
svals1, V, rsvecs1 = decomposition.decomposeDataMatrix(X1.T)
self.svals1 = svals1.T
self.evals1 = np.multiply(self.svals1, self.svals1)
self.V = V
self.rsvecs1 = np.mat(rsvecs1)
if X1.shape == X2.shape and (X1 == X2).all():
svals2, U, rsvecs2 = svals1, V, rsvecs1
else:
svals2, U, rsvecs2 = decomposition.decomposeDataMatrix(
X2.T)
self.svals2 = svals2.T
self.evals2 = np.multiply(self.svals2, self.svals2)
self.U = U
self.rsvecs2 = np.mat(rsvecs2)
self.VTYU = V.T * Y * U
kronsvals = self.svals1 * self.svals2.T
newevals = np.divide(kronsvals,
np.multiply(kronsvals, kronsvals) + regparam)
self.W = np.multiply(self.VTYU, newevals)
self.W = self.rsvecs1.T * self.W * self.rsvecs2
self.predictor = LinearPairwisePredictor(np.array(self.W))
