apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-18 13:55:14 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

merged conflicts after merging in master to newGP branch

Browse source
This commit is contained in:
James Hensman 2013-01-31 09:24:00 +00:00
commit 791d240d96
45 changed files with 13510 additions and 138 deletions
Download patch file Download diff file Expand all files Collapse all files

20
GPy/core/model.py
View file

@ -303,7 +303,7 @@ class model(parameterised):
return '\n'.join(s)
def checkgrad(self, verbose=False, include_priors=False, step=1e-6, tolerance = 1e-3, *args):
def checkgrad(self, verbose=False, include_priors=False, step=1e-6, tolerance = 1e-3, return_ratio=False, *args):
"""
Check the gradient of the model by comparing to a numerical estimate.
If the overall gradient fails, invividual components are tested.
@ -323,12 +323,12 @@ class model(parameterised):
gradient = self._log_likelihood_gradients_transformed()
numerical_gradient = (f1-f2)/(2*dx)
ratio = (f1-f2)/(2*np.dot(dx,gradient))
global_ratio = (f1-f2)/(2*np.dot(dx,gradient))
if verbose:
print "Gradient ratio = ", ratio, '\n'
print "Gradient ratio = ", global_ratio, '\n'
sys.stdout.flush()
if (np.abs(1.-ratio)<tolerance) and not np.isnan(ratio):
if (np.abs(1.-global_ratio)<tolerance) and not np.isnan(global_ratio):
if verbose:
print 'Gradcheck passed'
else:
@ -379,13 +379,17 @@ class model(parameterised):
ng = '%.6f' % float(numerical_gradient)
grad_string = "{0:^{c0}}|{1:^{c1}}|{2:^{c2}}|{3:^{c3}}|{4:^{c4}}".format(formatted_name,r,d,g, ng, c0 = cols[0]+9, c1 = cols[1], c2 = cols[2], c3 = cols[3], c4 = cols[4])
print grad_string
if verbose:
print ''
print ''
return False
return True
if return_ratio:
return global_ratio
else:
return False
def EM(self,epsilon=.1,**kwargs):
def EPEM(self,epsilon=.1,**kwargs):
"""
TODO: Should this not bein the GP class?
Expectation maximization for Expectation Propagation.
kwargs are passed to the optimize function. They can be: