apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-10 20:42:39 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'devel' into devel

Browse source
This commit is contained in:
Neil Lawrence 2018-09-01 04:38:02 -07:00 • committed by GitHub
commit e623078954
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 14 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

37
GPy/core/gp.py
View file

@ -578,7 +578,7 @@ class GP(Model):
mag[n] = np.sqrt(np.linalg.det(G[n, :, :])) mag[n] = np.sqrt(np.linalg.det(G[n, :, :]))
return mag return mag
def posterior_samples_f(self,X, size=10, full_cov=True, **predict_kwargs): def posterior_samples_f(self,X, size=10, **predict_kwargs):
""" """
Samples the posterior GP at the points X. Samples the posterior GP at the points X.
@ -586,35 +586,28 @@ class GP(Model):
:type X: np.ndarray (Nnew x self.input_dim) :type X: np.ndarray (Nnew x self.input_dim)
:param size: the number of a posteriori samples. :param size: the number of a posteriori samples.
:type size: int. :type size: int.
:param full_cov: whether to return the full covariance matrix, or just the diagonal. :returns: set of simulations
:type full_cov: bool. :rtype: np.ndarray (Nnew x D x samples)
:returns: fsim: set of simulations
:rtype: np.ndarray (D x N x samples) (if D==1 we flatten out the first dimension)
""" """
m, v = self._raw_predict(X, full_cov=full_cov, **predict_kwargs) m, v = self._raw_predict(X, full_cov=True, **predict_kwargs)
if self.normalizer is not None: if self.normalizer is not None:
m, v = self.normalizer.inverse_mean(m), self.normalizer.inverse_variance(v) m, v = self.normalizer.inverse_mean(m), self.normalizer.inverse_variance(v)
def sim_one_dim(m, v): def sim_one_dim(m, v):
if not full_cov: return np.random.multivariate_normal(m, v, size).T
return np.random.multivariate_normal(m.flatten(), np.diag(v.flatten()), size).T
else:
return np.random.multivariate_normal(m.flatten(), v, size).T
if self.output_dim == 1: if self.output_dim == 1:
return sim_one_dim(m, v) return sim_one_dim(m.flatten(), v)[:, np.newaxis, :]
else: else:
fsim = np.empty((self.output_dim, X.shape[0], size)) fsim = np.empty((X.shape[0], self.output_dim, size))
for d in range(self.output_dim): for d in range(self.output_dim):
if full_cov and v.ndim == 3: if v.ndim == 3:
fsim[d] = sim_one_dim(m[:, d], v[:, :, d]) fsim[:, d, :] = sim_one_dim(m[:, d], v[:, :, d])
elif (not full_cov) and v.ndim == 2:
fsim[d] = sim_one_dim(m[:, d], v[:, d])
else: else:
fsim[d] = sim_one_dim(m[:, d], v) fsim[:, d, :] = sim_one_dim(m[:, d], v)
return fsim return fsim
def posterior_samples(self, X, size=10, full_cov=False, Y_metadata=None, likelihood=None, **predict_kwargs): def posterior_samples(self, X, size=10, Y_metadata=None, likelihood=None, **predict_kwargs):
""" """
Samples the posterior GP at the points X. Samples the posterior GP at the points X.
@ -622,19 +615,17 @@ class GP(Model):
:type X: np.ndarray (Nnew x self.input_dim.) :type X: np.ndarray (Nnew x self.input_dim.)
:param size: the number of a posteriori samples. :param size: the number of a posteriori samples.
:type size: int. :type size: int.
:param full_cov: whether to return the full covariance matrix, or just the diagonal.
:type full_cov: bool.
:param noise_model: for mixed noise likelihood, the noise model to use in the samples. :param noise_model: for mixed noise likelihood, the noise model to use in the samples.
:type noise_model: integer. :type noise_model: integer.
:returns: Ysim: set of simulations, :returns: Ysim: set of simulations,
:rtype: np.ndarray (D x N x samples) (if D==1 we flatten out the first dimension) :rtype: np.ndarray (D x N x samples) (if D==1 we flatten out the first dimension)
""" """
fsim = self.posterior_samples_f(X, size, full_cov=full_cov, **predict_kwargs) fsim = self.posterior_samples_f(X, size, **predict_kwargs)
if likelihood is None: if likelihood is None:
likelihood = self.likelihood likelihood = self.likelihood
if fsim.ndim == 3: if fsim.ndim == 3:
for d in range(fsim.shape[0]): for d in range(fsim.shape[1]):
fsim[d] = likelihood.samples(fsim[d], Y_metadata=Y_metadata) fsim[:, d] = likelihood.samples(fsim[:, d], Y_metadata=Y_metadata)
else: else:
fsim = likelihood.samples(fsim, Y_metadata=Y_metadata) fsim = likelihood.samples(fsim, Y_metadata=Y_metadata)
return fsim return fsim