apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-09 12:02:38 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Minor changes.

Browse source
This commit is contained in:
Ricardo Andrade 2013-01-29 16:45:31 +00:00
parent ec89c4efc3
commit 0a88df62c3
1 changed files with 9 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

11
GPy/models/sparse_GP.py
View file

@ -35,9 +35,13 @@ class sparse_GP(GP):
:type beta: float :type beta: float
:param normalize_(X|Y) : whether to normalize the data before computing (predictions will be in original scales) :param normalize_(X|Y) : whether to normalize the data before computing (predictions will be in original scales)
:type normalize_(X|Y): bool :type normalize_(X|Y): bool
:parm likelihood: a GPy likelihood, defaults to gaussian
:param epsilon_ep: convergence criterion for the Expectation Propagation algorithm, defaults to 0.1
:param powerep: power-EP parameters [$\eta$,$\delta$], defaults to [1.,1.]
:type powerep: list
""" """
def __init__(self,X,Y=None,kernel=None, X_uncertainty=None, beta=100., Z=None,Zslices=None,M=10,normalize_X=False,normalize_Y=False,likelihood=None,method_ep='DTC',epsilon_ep=1e-3,epsilon_em=.1,power_ep=[1.,1.]): def __init__(self,X,Y=None,kernel=None,X_uncertainty=None,beta=100.,Z=None,Zslices=None,M=10,normalize_X=False,normalize_Y=False,likelihood=None,method_ep='DTC',epsilon_ep=1e-3,power_ep=[1.,1.]):
if Z is None: if Z is None:
self.Z = np.random.permutation(X.copy())[:M] self.Z = np.random.permutation(X.copy())[:M]
@ -53,7 +57,7 @@ class sparse_GP(GP):
self.has_uncertain_inputs=True self.has_uncertain_inputs=True
self.X_uncertainty = X_uncertainty self.X_uncertainty = X_uncertainty
GP.__init__(self, X=X, Y=Y, kernel=kernel, normalize_X=normalize_X, normalize_Y=normalize_Y,likelihood=likelihood,epsilon_ep=epsilon_ep,epsilon_em=epsilon_em,power_ep=power_ep) GP.__init__(self, X=X, Y=Y, kernel=kernel, normalize_X=normalize_X, normalize_Y=normalize_Y,likelihood=likelihood,epsilon_ep=epsilon_ep,power_ep=power_ep)
self.trYYT = np.sum(np.square(self.Y)) if not self.EP else None self.trYYT = np.sum(np.square(self.Y)) if not self.EP else None
@ -91,6 +95,9 @@ class sparse_GP(GP):
else: else:
if self.hetero_noise: if self.hetero_noise:
print "rick's stuff here" print "rick's stuff here"
else: else:
self.psi0 = self.kern.Kdiag(self.X,slices=self.Xslices).sum() self.psi0 = self.kern.Kdiag(self.X,slices=self.Xslices).sum()
self.psi1 = self.kern.K(self.Z,self.X) self.psi1 = self.kern.K(self.Z,self.X)