apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-30 14:35:15 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'params' of github.com:SheffieldML/GPy into params

Browse source
This commit is contained in:
Ricardo 2014-03-12 19:22:59 +00:00
commit 35fb0451e7
3 changed files with 16 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

6
GPy/core/parameterization/parameter_core.py
View file

@ -16,7 +16,7 @@ Observable Pattern for patameterization
from transformations import Transformation, Logexp, NegativeLogexp, Logistic, __fixed__, FIXED, UNFIXED from transformations import Transformation, Logexp, NegativeLogexp, Logistic, __fixed__, FIXED, UNFIXED
import numpy as np import numpy as np
__updated__ = '2014-03-11' __updated__ = '2014-03-12'
class HierarchyError(Exception): class HierarchyError(Exception):
""" """
@ -831,16 +831,13 @@ class Parameterizable(OptimizationHandlable):
self._gradient_array_ = np.empty(self.size, dtype=np.float64) self._gradient_array_ = np.empty(self.size, dtype=np.float64)
self._param_slices_ = [] self._param_slices_ = []
for i, p in enumerate(self._parameters_): for i, p in enumerate(self._parameters_):
p._parent_ = self p._parent_ = self
p._parent_index_ = i p._parent_index_ = i
pslice = slice(old_size, old_size+p.size) pslice = slice(old_size, old_size+p.size)
# first connect all children # first connect all children
p._propagate_param_grad(self._param_array_[pslice], self._gradient_array_[pslice]) p._propagate_param_grad(self._param_array_[pslice], self._gradient_array_[pslice])
# then connect children to self # then connect children to self
self._param_array_[pslice] = p._param_array_.ravel()#, requirements=['C', 'W']).ravel(order='C') self._param_array_[pslice] = p._param_array_.ravel()#, requirements=['C', 'W']).ravel(order='C')
self._gradient_array_[pslice] = p._gradient_array_.ravel()#, requirements=['C', 'W']).ravel(order='C') self._gradient_array_[pslice] = p._gradient_array_.ravel()#, requirements=['C', 'W']).ravel(order='C')
@ -868,6 +865,7 @@ class Parameterizable(OptimizationHandlable):
#=========================================================================== #===========================================================================
def copy(self): def copy(self):
"""Returns a (deep) copy of the current model""" """Returns a (deep) copy of the current model"""
raise NotImplementedError, "Copy is not yet implemented, TODO: Observable hierarchy"
import copy import copy
from .index_operations import ParameterIndexOperations, ParameterIndexOperationsView from .index_operations import ParameterIndexOperations, ParameterIndexOperationsView
from .lists_and_dicts import ArrayList from .lists_and_dicts import ArrayList

6
GPy/inference/latent_function_inference/dtc.py
View file

@ -19,7 +19,7 @@ class DTC(object):
def __init__(self): def __init__(self):
self.const_jitter = 1e-6 self.const_jitter = 1e-6
def inference(self, kern, X, X_variance, Z, likelihood, Y): def inference(self, kern, X, Z, likelihood, Y):
assert X_variance is None, "cannot use X_variance with DTC. Try varDTC." assert X_variance is None, "cannot use X_variance with DTC. Try varDTC."
#TODO: MAX! fix this! #TODO: MAX! fix this!
@ -80,10 +80,6 @@ class DTC(object):
grad_dict = {'dL_dKmm': dL_dK, 'dL_dKdiag':np.zeros_like(Knn), 'dL_dKnm':dL_dU.T} grad_dict = {'dL_dKmm': dL_dK, 'dL_dKdiag':np.zeros_like(Knn), 'dL_dKnm':dL_dU.T}
#update gradients
kern.update_gradients_sparse(X=X, Z=Z, **grad_dict)
likelihood.update_gradients(dL_dR)
#construct a posterior object #construct a posterior object
post = Posterior(woodbury_inv=Kmmi-P, woodbury_vector=v, K=Kmm, mean=None, cov=None, K_chol=L) post = Posterior(woodbury_inv=Kmmi-P, woodbury_vector=v, K=Kmm, mean=None, cov=None, K_chol=L)

9
GPy/inference/latent_function_inference/fitc.py
View file

@ -17,8 +17,7 @@ class FITC(object):
def __init__(self): def __init__(self):
self.const_jitter = 1e-6 self.const_jitter = 1e-6
def inference(self, kern, X, X_variance, Z, likelihood, Y): def inference(self, kern, X, Z, likelihood, Y):
assert X_variance is None, "cannot use X_variance with FITC. Try varDTC."
#TODO: MAX! fix this! #TODO: MAX! fix this!
from ...util.misc import param_to_array from ...util.misc import param_to_array
@ -81,11 +80,7 @@ class FITC(object):
dL_dU *= beta_star dL_dU *= beta_star
dL_dU -= 2.*KiU*dL_dR dL_dU -= 2.*KiU*dL_dR
grad_dict = {'dL_dKmm': dL_dK, 'dL_dKdiag':dL_dR, 'dL_dKnm':dL_dU.T} grad_dict = {'dL_dKmm': dL_dK, 'dL_dKdiag':dL_dR, 'dL_dKnm':dL_dU.T, 'partial_for_likelihood':dL_dR}
#update gradients
kern.update_gradients_sparse(X=X, Z=Z, **grad_dict)
likelihood.update_gradients(dL_dR)
#construct a posterior object #construct a posterior object
post = Posterior(woodbury_inv=Kmmi-P, woodbury_vector=v, K=Kmm, mean=None, cov=None, K_chol=L) post = Posterior(woodbury_inv=Kmmi-P, woodbury_vector=v, K=Kmm, mean=None, cov=None, K_chol=L)