apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-06-29 15:59:41 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

minor pep8 stuff

Browse source
This commit is contained in:
Max Zwiessele 2013-07-17 15:01:00 +01:00
parent a8ae457e6b
commit c44bda766c
2 changed files with 5 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

3
GPy/core/gp.py
View file

@ -96,7 +96,8 @@ class GP(GPBase):
model for a new variable Y* = v_tilde/tau_tilde, with a covariance model for a new variable Y* = v_tilde/tau_tilde, with a covariance
matrix K* = K + diag(1./tau_tilde) plus a normalization term. matrix K* = K + diag(1./tau_tilde) plus a normalization term.
""" """
return - 0.5 * self.num_data * self.output_dim * np.log(2.*np.pi) - 0.5 * self.output_dim * self.K_logdet + self._model_fit_term() + self.likelihood.Z return (-0.5 * self.num_data * self.output_dim * np.log(2.*np.pi) -
0.5 * self.output_dim * self.K_logdet + self._model_fit_term() + self.likelihood.Z)
def _log_likelihood_gradients(self): def _log_likelihood_gradients(self):

6
GPy/core/sparse_gp.py
View file

@ -108,7 +108,7 @@ class SparseGP(GPBase):
self.B = np.eye(self.num_inducing) + self.A self.B = np.eye(self.num_inducing) + self.A
self.LB = jitchol(self.B) self.LB = jitchol(self.B)
#VVT_factor is a matrix such that tdot(VVT_factor) = VVT...this is for efficiency! # VVT_factor is a matrix such that tdot(VVT_factor) = VVT...this is for efficiency!
self.psi1Vf = np.dot(self.psi1.T, self.likelihood.VVT_factor) self.psi1Vf = np.dot(self.psi1.T, self.likelihood.VVT_factor)
# back substutue C into psi1Vf # back substutue C into psi1Vf
@ -163,7 +163,7 @@ class SparseGP(GPBase):
def log_likelihood(self): def log_likelihood(self):
""" Compute the (lower bound on the) log marginal likelihood """ """ Compute the (lower bound on the) log marginal likelihood """
if self.likelihood.is_heteroscedastic: if self.likelihood.is_heteroscedastic:
A = -0.5 * self.num_data * self.output_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) A = -0.5 * self.num_data * self.output_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.output_dim * (np.sum(self.likelihood.precision.flatten() * self.psi0) - np.trace(self.A)) B = -0.5 * self.output_dim * (np.sum(self.likelihood.precision.flatten() * self.psi0) - np.trace(self.A))
else: else:
A = -0.5 * self.num_data * self.output_dim * (np.log(2.*np.pi) - np.log(self.likelihood.precision)) - 0.5 * self.likelihood.precision * self.likelihood.trYYT A = -0.5 * self.num_data * self.output_dim * (np.log(2.*np.pi) - np.log(self.likelihood.precision)) - 0.5 * self.likelihood.precision * self.likelihood.trYYT
@ -246,7 +246,7 @@ class SparseGP(GPBase):
Kmmi_LmiBLmi = backsub_both_sides(self.Lm, np.eye(self.num_inducing) - Bi) Kmmi_LmiBLmi = backsub_both_sides(self.Lm, np.eye(self.num_inducing) - Bi)
if self.Cpsi1V is None: if self.Cpsi1V is None:
psi1V = np.dot(self.psi1.T,self.likelihood.V) psi1V = np.dot(self.psi1.T, self.likelihood.V)
tmp, _ = dtrtrs(self.Lm, np.asfortranarray(psi1V), lower=1, trans=0) tmp, _ = dtrtrs(self.Lm, np.asfortranarray(psi1V), lower=1, trans=0)
tmp, _ = dpotrs(self.LB, tmp, lower=1) tmp, _ = dpotrs(self.LB, tmp, lower=1)
self.Cpsi1V, _ = dtrtrs(self.Lm, tmp, lower=1, trans=1) self.Cpsi1V, _ = dtrtrs(self.Lm, tmp, lower=1, trans=1)