apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-06 02:24:17 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

made the BGPLVM work in the new world order

Browse source
This commit is contained in:
James Hensman 2013-02-01 17:42:51 +00:00
parent f7d2fc6ca4
commit 2b756e96e1
3 changed files with 22 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

26
GPy/models/BGPLVM.py
View file

@ -5,10 +5,12 @@ import numpy as np
import pylab as pb import pylab as pb
import sys, pdb import sys, pdb
from GPLVM import GPLVM from GPLVM import GPLVM
from sparse_GP_regression import sparse_GP_regression from sparse_GP import sparse_GP
from GPy.util.linalg import pdinv from GPy.util.linalg import pdinv
from ..likelihoods import Gaussian
from .. import kern
class Bayesian_GPLVM(sparse_GP_regression, GPLVM): class Bayesian_GPLVM(sparse_GP, GPLVM):
""" """
Bayesian Gaussian Process Latent Variable Model Bayesian Gaussian Process Latent Variable Model
@ -20,15 +22,23 @@ class Bayesian_GPLVM(sparse_GP_regression, GPLVM):
:type init: 'PCA'|'random' :type init: 'PCA'|'random'
""" """
def __init__(self, Y, Q, init='PCA', **kwargs): def __init__(self, Y, Q, init='PCA', M=10, Z=None, **kwargs):
X = self.initialise_latent(init, Q, Y) X = self.initialise_latent(init, Q, Y)
if Z is None:
Z = np.random.permutation(X.copy())[:M]
else:
assert Z.shape[1]==X.shape[1]
kernel = kern.rbf(Q) + kern.white(Q)
S = np.ones_like(X) * 1e-2# S = np.ones_like(X) * 1e-2#
sparse_GP_regression.__init__(self, X, Y, X_uncertainty = S, **kwargs) sparse_GP.__init__(self, X, Gaussian(Y), X_uncertainty = S, Z=Z,**kwargs)
def _get_param_names(self): def _get_param_names(self):
X_names = sum([['X_%i_%i'%(n,q) for n in range(self.N)] for q in range(self.Q)],[]) X_names = sum([['X_%i_%i'%(n,q) for n in range(self.N)] for q in range(self.Q)],[])
S_names = sum([['S_%i_%i'%(n,q) for n in range(self.N)] for q in range(self.Q)],[]) S_names = sum([['S_%i_%i'%(n,q) for n in range(self.N)] for q in range(self.Q)],[])
return (X_names + S_names + sparse_GP_regression._get_param_names(self)) return (X_names + S_names + sparse_GP._get_param_names(self))
def _get_params(self): def _get_params(self):
""" """
@ -40,13 +50,13 @@ class Bayesian_GPLVM(sparse_GP_regression, GPLVM):
=============================================================== ===============================================================
""" """
return np.hstack((self.X.flatten(), self.X_uncertainty.flatten(), sparse_GP_regression._get_params(self))) return np.hstack((self.X.flatten(), self.X_uncertainty.flatten(), sparse_GP._get_params(self)))
def _set_params(self,x): def _set_params(self,x):
N, Q = self.N, self.Q N, Q = self.N, self.Q
self.X = x[:self.X.size].reshape(N,Q).copy() self.X = x[:self.X.size].reshape(N,Q).copy()
self.X_uncertainty = x[(N*Q):(2*N*Q)].reshape(N,Q).copy() self.X_uncertainty = x[(N*Q):(2*N*Q)].reshape(N,Q).copy()
sparse_GP_regression._set_params(self, x[(2*N*Q):]) sparse_GP._set_params(self, x[(2*N*Q):])
def dL_dmuS(self): def dL_dmuS(self):
dL_dmu_psi0, dL_dS_psi0 = self.kern.dpsi1_dmuS(self.dL_dpsi1,self.Z,self.X,self.X_uncertainty) dL_dmu_psi0, dL_dS_psi0 = self.kern.dpsi1_dmuS(self.dL_dpsi1,self.Z,self.X,self.X_uncertainty)
@ -58,5 +68,5 @@ class Bayesian_GPLVM(sparse_GP_regression, GPLVM):
return np.hstack((dL_dmu.flatten(), dL_dS.flatten())) return np.hstack((dL_dmu.flatten(), dL_dS.flatten()))
def _log_likelihood_gradients(self): def _log_likelihood_gradients(self):
return np.hstack((self.dL_dmuS().flatten(), sparse_GP_regression._log_likelihood_gradients(self))) return np.hstack((self.dL_dmuS().flatten(), sparse_GP._log_likelihood_gradients(self)))

4
GPy/models/__init__.py
View file

@ -9,6 +9,6 @@ from sparse_GP_regression import sparse_GP_regression
from GPLVM import GPLVM from GPLVM import GPLVM
from warped_GP import warpedGP from warped_GP import warpedGP
# TODO: from generalized_FITC import generalized_FITC # TODO: from generalized_FITC import generalized_FITC
#from sparse_GPLVM import sparse_GPLVM from sparse_GPLVM import sparse_GPLVM
#from uncollapsed_sparse_GP import uncollapsed_sparse_GP #from uncollapsed_sparse_GP import uncollapsed_sparse_GP
#from BGPLVM import Bayesian_GPLVM from BGPLVM import Bayesian_GPLVM

2
GPy/models/sparse_GP.py
View file

@ -65,7 +65,7 @@ class sparse_GP(GP):
# kernel computations, using BGPLVM notation # kernel computations, using BGPLVM notation
self.Kmm = self.kern.K(self.Z) self.Kmm = self.kern.K(self.Z)
if self.has_uncertain_inputs: if self.has_uncertain_inputs:
self.psi0 = self.kern.psi0(self.Z,self.X, self.X_uncerTainty) self.psi0 = self.kern.psi0(self.Z,self.X, self.X_uncertainty)
self.psi1 = self.kern.psi1(self.Z,self.X, self.X_uncertainty).T self.psi1 = self.kern.psi1(self.Z,self.X, self.X_uncertainty).T
self.psi2 = self.kern.psi2(self.Z,self.X, self.X_uncertainty) self.psi2 = self.kern.psi2(self.Z,self.X, self.X_uncertainty)
if self.likelihood.is_heteroscedastic: if self.likelihood.is_heteroscedastic: