mirror of
https://github.com/SheffieldML/GPy.git
synced 2026-06-08 15:05:15 +02:00
Merged and fixed conflicts, names still need changing accordingly
This commit is contained in:
Ricardo
commit
b3eeacd956
55 changed files with 912 additions and 927 deletions
|
|
@ -1,9 +1,9 @@
|
|||
# Copyright (c) 2012, GPy authors (see AUTHORS.txt).
|
||||
# Licensed under the BSD 3-clause license (see LICENSE.txt)
|
||||
|
||||
from GP import GP
|
||||
from sparse_GP import sparse_GP
|
||||
from FITC import FITC
|
||||
from model import *
|
||||
from parameterised import *
|
||||
import priors
|
||||
from GPy.core.gp import GP
|
||||
from GPy.core.sparse_gp import SparseGP
|
||||
from FITC import FITC
|
||||
|
|
|
|||
|
|
@ -46,12 +46,12 @@ class GP(GPBase):
|
|||
#alpha = np.dot(self.Ki, self.likelihood.Y)
|
||||
alpha,_ = linalg.lapack.flapack.dpotrs(self.L, self.likelihood.Y,lower=1)
|
||||
|
||||
self.dL_dK = 0.5 * (tdot(alpha) - self.D * self.Ki)
|
||||
self.dL_dK = 0.5 * (tdot(alpha) - self.input_dim * self.Ki)
|
||||
else:
|
||||
#tmp = mdot(self.Ki, self.likelihood.YYT, self.Ki)
|
||||
tmp, _ = linalg.lapack.flapack.dpotrs(self.L, np.asfortranarray(self.likelihood.YYT), lower=1)
|
||||
tmp, _ = linalg.lapack.flapack.dpotrs(self.L, np.asfortranarray(tmp.T), lower=1)
|
||||
self.dL_dK = 0.5 * (tmp - self.D * self.Ki)
|
||||
self.dL_dK = 0.5 * (tmp - self.input_dim * self.Ki)
|
||||
|
||||
def _get_params(self):
|
||||
return np.hstack((self.kern._get_params_transformed(), self.likelihood._get_params()))
|
||||
|
|
@ -89,7 +89,7 @@ class GP(GPBase):
|
|||
model for a new variable Y* = v_tilde/tau_tilde, with a covariance
|
||||
matrix K* = K + diag(1./tau_tilde) plus a normalization term.
|
||||
"""
|
||||
return -0.5 * self.D * self.K_logdet + self._model_fit_term() + self.likelihood.Z
|
||||
return -0.5 * self.input_dim * self.K_logdet + self._model_fit_term() + self.likelihood.Z
|
||||
|
||||
|
||||
def _log_likelihood_gradients(self):
|
||||
|
|
@ -117,7 +117,7 @@ class GP(GPBase):
|
|||
var = Kxx - np.sum(np.multiply(KiKx, Kx), 0)
|
||||
var = var[:, None]
|
||||
if stop:
|
||||
debug_this
|
||||
debug_this # @UndefinedVariable
|
||||
return mu, var
|
||||
|
||||
def predict(self, Xnew, which_parts='all', full_cov=False):
|
||||
|
|
@ -131,12 +131,12 @@ class GP(GPBase):
|
|||
:type which_parts: ('all', list of bools)
|
||||
:param full_cov: whether to return the folll covariance matrix, or just the diagonal
|
||||
:type full_cov: bool
|
||||
:rtype: posterior mean, a Numpy array, Nnew x self.D
|
||||
:rtype: posterior mean, a Numpy array, Nnew x self.input_dim
|
||||
:rtype: posterior variance, a Numpy array, Nnew x 1 if full_cov=False, Nnew x Nnew otherwise
|
||||
:rtype: lower and upper boundaries of the 95% confidence intervals, Numpy arrays, Nnew x self.D
|
||||
:rtype: lower and upper boundaries of the 95% confidence intervals, Numpy arrays, Nnew x self.input_dim
|
||||
|
||||
|
||||
If full_cov and self.D > 1, the return shape of var is Nnew x Nnew x self.D. If self.D == 1, the return shape is Nnew x Nnew.
|
||||
If full_cov and self.input_dim > 1, the return shape of var is Nnew x Nnew x self.input_dim. If self.input_dim == 1, the return shape is Nnew x Nnew.
|
||||
This is to allow for different normalizations of the output dimensions.
|
||||
|
||||
"""
|
||||
|
|
@ -18,15 +18,15 @@ class GPBase(model.model):
|
|||
self.kern = kernel
|
||||
self.likelihood = likelihood
|
||||
assert self.X.shape[0] == self.likelihood.data.shape[0]
|
||||
self.N, self.D = self.likelihood.data.shape
|
||||
self.N, self.output_dim = self.likelihood.data.shape
|
||||
|
||||
if normalize_X:
|
||||
self._Xmean = X.mean(0)[None, :]
|
||||
self._Xstd = X.std(0)[None, :]
|
||||
self.X = (X.copy() - self._Xmean) / self._Xstd
|
||||
else:
|
||||
self._Xmean = np.zeros((1,self.input_dim))
|
||||
self._Xstd = np.ones((1,self.input_dim))
|
||||
self._Xmean = np.zeros((1, self.input_dim))
|
||||
self._Xstd = np.ones((1, self.input_dim))
|
||||
|
||||
model.model.__init__(self)
|
||||
|
||||
|
|
@ -70,7 +70,7 @@ class GPBase(model.model):
|
|||
else:
|
||||
m, v = self._raw_predict(Xnew, which_parts=which_parts, full_cov=True)
|
||||
Ysim = np.random.multivariate_normal(m.flatten(), v, samples)
|
||||
gpplot(Xnew, m, m - 2 * np.sqrt(np.diag(v)[:, None]), m + 2 * np.sqrt(np.diag(v))[:, None,], axes=ax)
|
||||
gpplot(Xnew, m, m - 2 * np.sqrt(np.diag(v)[:, None]), m + 2 * np.sqrt(np.diag(v))[:, None, ], axes=ax)
|
||||
for i in range(samples):
|
||||
ax.plot(Xnew, Ysim[i, :], Tango.colorsHex['darkBlue'], linewidth=0.25)
|
||||
ax.plot(self.X[which_data], self.likelihood.Y[which_data], 'kx', mew=1.5)
|
||||
|
|
@ -108,19 +108,19 @@ class GPBase(model.model):
|
|||
|
||||
if self.X.shape[1] == 1:
|
||||
|
||||
Xu = self.X * self._Xstd + self._Xmean # NOTE self.X are the normalized values now
|
||||
Xu = self.X * self._Xstd + self._Xmean # NOTE self.X are the normalized values now
|
||||
|
||||
Xnew, xmin, xmax = x_frame1D(Xu, plot_limits=plot_limits)
|
||||
m, var, lower, upper = self.predict(Xnew, which_parts=which_parts)
|
||||
for d in range(m.shape[1]):
|
||||
gpplot(Xnew, m[:,d], lower[:,d], upper[:,d],axes=ax)
|
||||
ax.plot(Xu[which_data], self.likelihood.data[which_data,d], 'kx', mew=1.5)
|
||||
gpplot(Xnew, m[:, d], lower[:, d], upper[:, d], axes=ax)
|
||||
ax.plot(Xu[which_data], self.likelihood.data[which_data, d], 'kx', mew=1.5)
|
||||
ymin, ymax = min(np.append(self.likelihood.data, lower)), max(np.append(self.likelihood.data, upper))
|
||||
ymin, ymax = ymin - 0.1 * (ymax - ymin), ymax + 0.1 * (ymax - ymin)
|
||||
ax.set_xlim(xmin, xmax)
|
||||
ax.set_ylim(ymin, ymax)
|
||||
|
||||
elif self.X.shape[1] == 2: # FIXME
|
||||
elif self.X.shape[1] == 2: # FIXME
|
||||
resolution = resolution or 50
|
||||
Xnew, xx, yy, xmin, xmax = x_frame2D(self.X, plot_limits, resolution)
|
||||
x, y = np.linspace(xmin[0], xmax[0], resolution), np.linspace(xmin[1], xmax[1], resolution)
|
||||
|
|
|
|||
|
|
@ -23,7 +23,7 @@ class model(parameterised):
|
|||
self.priors = None
|
||||
self.optimization_runs = []
|
||||
self.sampling_runs = []
|
||||
self.preferred_optimizer = 'tnc'
|
||||
self.preferred_optimizer = 'scg'
|
||||
#self._set_params(self._get_params()) has been taken out as it should only be called on leaf nodes
|
||||
def _get_params(self):
|
||||
raise NotImplementedError, "this needs to be implemented to use the model class"
|
||||
|
|
|
|||
|
|
@ -85,7 +85,7 @@ class parameterised(object):
|
|||
else:
|
||||
return self._get_params()[matches]
|
||||
else:
|
||||
raise AttributeError, "no parameter matches %s" % name
|
||||
raise AttributeError, "no parameter matches %s" % regexp
|
||||
|
||||
def __setitem__(self, name, val):
|
||||
"""
|
||||
|
|
|
|||
|
|
@ -99,9 +99,9 @@ class MultivariateGaussian:
|
|||
assert len(self.var.shape) == 2
|
||||
assert self.var.shape[0] == self.var.shape[1]
|
||||
assert self.var.shape[0] == self.mu.size
|
||||
self.D = self.mu.size
|
||||
self.input_dim = self.mu.size
|
||||
self.inv, self.hld = pdinv(self.var)
|
||||
self.constant = -0.5 * self.D * np.log(2 * np.pi) - self.hld
|
||||
self.constant = -0.5 * self.input_dim * np.log(2 * np.pi) - self.hld
|
||||
|
||||
def summary(self):
|
||||
raise NotImplementedError
|
||||
|
|
@ -121,7 +121,7 @@ class MultivariateGaussian:
|
|||
return np.random.multivariate_normal(self.mu, self.var, n)
|
||||
|
||||
def plot(self):
|
||||
if self.D == 2:
|
||||
if self.input_dim == 2:
|
||||
rvs = self.rvs(200)
|
||||
pb.plot(rvs[:, 0], rvs[:, 1], 'kx', mew=1.5)
|
||||
xmin, xmax = pb.xlim()
|
||||
|
|
|
|||
|
|
@ -8,7 +8,7 @@ from scipy import linalg
|
|||
from ..likelihoods import Gaussian
|
||||
from gp_base import GPBase
|
||||
|
||||
class sparse_GP(GPBase):
|
||||
class SparseGP(GPBase):
|
||||
"""
|
||||
Variational sparse GP model
|
||||
|
||||
|
|
@ -21,9 +21,9 @@ class sparse_GP(GPBase):
|
|||
:param X_variance: The uncertainty in the measurements of X (Gaussian variance)
|
||||
:type X_variance: np.ndarray (N x input_dim) | None
|
||||
:param Z: inducing inputs (optional, see note)
|
||||
:type Z: np.ndarray (M x input_dim) | None
|
||||
:param M : Number of inducing points (optional, default 10. Ignored if Z is not None)
|
||||
:type M: int
|
||||
:type Z: np.ndarray (num_inducing x input_dim) | None
|
||||
:param num_inducing : Number of inducing points (optional, default 10. Ignored if Z is not None)
|
||||
:type num_inducing: int
|
||||
:param normalize_(X|Y) : whether to normalize the data before computing (predictions will be in original scales)
|
||||
:type normalize_(X|Y): bool
|
||||
"""
|
||||
|
|
@ -32,7 +32,7 @@ class sparse_GP(GPBase):
|
|||
GPBase.__init__(self, X, likelihood, kernel, normalize_X=normalize_X)
|
||||
|
||||
self.Z = Z
|
||||
self.M = Z.shape[0]
|
||||
self.num_inducing = Z.shape[0]
|
||||
self.likelihood = likelihood
|
||||
|
||||
if X_variance is None:
|
||||
|
|
@ -85,7 +85,7 @@ class sparse_GP(GPBase):
|
|||
|
||||
|
||||
# factor B
|
||||
self.B = np.eye(self.M) + self.A
|
||||
self.B = np.eye(self.num_inducing) + self.A
|
||||
self.LB = jitchol(self.B)
|
||||
|
||||
# TODO: make a switch for either first compute psi1V, or VV.T
|
||||
|
|
@ -99,16 +99,16 @@ class sparse_GP(GPBase):
|
|||
|
||||
# Compute dL_dKmm
|
||||
tmp = tdot(self._LBi_Lmi_psi1V)
|
||||
self.DBi_plus_BiPBi = backsub_both_sides(self.LB, self.D * np.eye(self.M) + tmp)
|
||||
self.DBi_plus_BiPBi = backsub_both_sides(self.LB, self.input_dim * np.eye(self.num_inducing) + tmp)
|
||||
tmp = -0.5 * self.DBi_plus_BiPBi
|
||||
tmp += -0.5 * self.B * self.D
|
||||
tmp += self.D * np.eye(self.M)
|
||||
tmp += -0.5 * self.B * self.input_dim
|
||||
tmp += self.input_dim * np.eye(self.num_inducing)
|
||||
self.dL_dKmm = backsub_both_sides(self.Lm, tmp)
|
||||
|
||||
# Compute dL_dpsi # FIXME: this is untested for the heterscedastic + uncertain inputs case
|
||||
self.dL_dpsi0 = -0.5 * self.D * (self.likelihood.precision * np.ones([self.N, 1])).flatten()
|
||||
self.dL_dpsi0 = -0.5 * self.input_dim * (self.likelihood.precision * np.ones([self.N, 1])).flatten()
|
||||
self.dL_dpsi1 = np.dot(self.Cpsi1V, self.likelihood.V.T)
|
||||
dL_dpsi2_beta = 0.5 * backsub_both_sides(self.Lm, self.D * np.eye(self.M) - self.DBi_plus_BiPBi)
|
||||
dL_dpsi2_beta = 0.5 * backsub_both_sides(self.Lm, self.input_dim * np.eye(self.num_inducing) - self.DBi_plus_BiPBi)
|
||||
|
||||
if self.likelihood.is_heteroscedastic:
|
||||
if self.has_uncertain_inputs:
|
||||
|
|
@ -135,24 +135,24 @@ class sparse_GP(GPBase):
|
|||
raise NotImplementedError, "heteroscedatic derivates not implemented"
|
||||
else:
|
||||
# likelihood is not heterscedatic
|
||||
self.partial_for_likelihood = -0.5 * self.N * self.D * self.likelihood.precision + 0.5 * self.likelihood.trYYT * self.likelihood.precision ** 2
|
||||
self.partial_for_likelihood += 0.5 * self.D * (self.psi0.sum() * self.likelihood.precision ** 2 - np.trace(self.A) * self.likelihood.precision)
|
||||
self.partial_for_likelihood = -0.5 * self.N * self.input_dim * self.likelihood.precision + 0.5 * self.likelihood.trYYT * self.likelihood.precision ** 2
|
||||
self.partial_for_likelihood += 0.5 * self.input_dim * (self.psi0.sum() * self.likelihood.precision ** 2 - np.trace(self.A) * self.likelihood.precision)
|
||||
self.partial_for_likelihood += self.likelihood.precision * (0.5 * np.sum(self.A * self.DBi_plus_BiPBi) - np.sum(np.square(self._LBi_Lmi_psi1V)))
|
||||
|
||||
def log_likelihood(self):
|
||||
""" Compute the (lower bound on the) log marginal likelihood """
|
||||
if self.likelihood.is_heteroscedastic:
|
||||
A = -0.5 * self.N * self.D * np.log(2.*np.pi) + 0.5 * np.sum(np.log(self.likelihood.precision)) - 0.5 * np.sum(self.likelihood.V * self.likelihood.Y)
|
||||
B = -0.5 * self.D * (np.sum(self.likelihood.precision.flatten() * self.psi0) - np.trace(self.A))
|
||||
A = -0.5 * self.N * self.input_dim * np.log(2.*np.pi) + 0.5 * np.sum(np.log(self.likelihood.precision)) - 0.5 * np.sum(self.likelihood.V * self.likelihood.Y)
|
||||
B = -0.5 * self.input_dim * (np.sum(self.likelihood.precision.flatten() * self.psi0) - np.trace(self.A))
|
||||
else:
|
||||
A = -0.5 * self.N * self.D * (np.log(2.*np.pi) - np.log(self.likelihood.precision)) - 0.5 * self.likelihood.precision * self.likelihood.trYYT
|
||||
B = -0.5 * self.D * (np.sum(self.likelihood.precision * self.psi0) - np.trace(self.A))
|
||||
C = -self.D * (np.sum(np.log(np.diag(self.LB)))) # + 0.5 * self.M * np.log(sf2))
|
||||
A = -0.5 * self.N * self.input_dim * (np.log(2.*np.pi) - np.log(self.likelihood.precision)) - 0.5 * self.likelihood.precision * self.likelihood.trYYT
|
||||
B = -0.5 * self.input_dim * (np.sum(self.likelihood.precision * self.psi0) - np.trace(self.A))
|
||||
C = -self.input_dim * (np.sum(np.log(np.diag(self.LB)))) # + 0.5 * self.num_inducing * np.log(sf2))
|
||||
D = 0.5 * np.sum(np.square(self._LBi_Lmi_psi1V))
|
||||
return A + B + C + D + self.likelihood.Z
|
||||
|
||||
def _set_params(self, p):
|
||||
self.Z = p[:self.M * self.input_dim].reshape(self.M, self.input_dim)
|
||||
self.Z = p[:self.num_inducing * self.input_dim].reshape(self.num_inducing, self.input_dim)
|
||||
self.kern._set_params(p[self.Z.size:self.Z.size + self.kern.Nparam])
|
||||
self.likelihood._set_params(p[self.Z.size + self.kern.Nparam:])
|
||||
self._compute_kernel_matrices()
|
||||
|
|
@ -221,7 +221,7 @@ class sparse_GP(GPBase):
|
|||
|
||||
Bi, _ = linalg.lapack.flapack.dpotri(self.LB, lower=0) # WTH? this lower switch should be 1, but that doesn't work!
|
||||
symmetrify(Bi)
|
||||
Kmmi_LmiBLmi = backsub_both_sides(self.Lm, np.eye(self.M) - Bi)
|
||||
Kmmi_LmiBLmi = backsub_both_sides(self.Lm, np.eye(self.num_inducing) - Bi)
|
||||
|
||||
if X_variance_new is None:
|
||||
Kx = self.kern.K(self.Z, Xnew, which_parts=which_parts)
|
||||
|
|
@ -259,12 +259,12 @@ class sparse_GP(GPBase):
|
|||
:type which_parts: ('all', list of bools)
|
||||
:param full_cov: whether to return the folll covariance matrix, or just the diagonal
|
||||
:type full_cov: bool
|
||||
:rtype: posterior mean, a Numpy array, Nnew x self.D
|
||||
:rtype: posterior mean, a Numpy array, Nnew x self.input_dim
|
||||
:rtype: posterior variance, a Numpy array, Nnew x 1 if full_cov=False, Nnew x Nnew otherwise
|
||||
:rtype: lower and upper boundaries of the 95% confidence intervals, Numpy arrays, Nnew x self.D
|
||||
:rtype: lower and upper boundaries of the 95% confidence intervals, Numpy arrays, Nnew x self.input_dim
|
||||
|
||||
|
||||
If full_cov and self.D > 1, the return shape of var is Nnew x Nnew x self.D. If self.D == 1, the return shape is Nnew x Nnew.
|
||||
If full_cov and self.input_dim > 1, the return shape of var is Nnew x Nnew x self.input_dim. If self.input_dim == 1, the return shape is Nnew x Nnew.
|
||||
This is to allow for different normalizations of the output dimensions.
|
||||
|
||||
"""
|
||||
Loading…
Add table
Add a link
Reference in a new issue