From 35a099f4edfa1605e2b02d943438dba1b6454413 Mon Sep 17 00:00:00 2001 From: Ricardo Andrade Date: Fri, 22 Mar 2013 19:03:46 +0000 Subject: [PATCH] minor changes --- GPy/examples/fitc_class_01.py | 4 ++-- GPy/examples/fitc_class_02.py | 15 ++++++++------- 2 files changed, 10 insertions(+), 9 deletions(-) diff --git a/GPy/examples/fitc_class_01.py b/GPy/examples/fitc_class_01.py index 413d0c14..06c948b5 100644 --- a/GPy/examples/fitc_class_01.py +++ b/GPy/examples/fitc_class_01.py @@ -42,8 +42,8 @@ m.ensure_default_constraints() m.update_likelihood_approximation() print m.checkgrad(verbose=1) # Parameters optimization: -m.optimize() -#m.EPEM() #FIXME +#m.optimize() +m.pseudo_EM() #FIXME # Plot pb.subplot(211) diff --git a/GPy/examples/fitc_class_02.py b/GPy/examples/fitc_class_02.py index cd8d6700..71e10081 100644 --- a/GPy/examples/fitc_class_02.py +++ b/GPy/examples/fitc_class_02.py @@ -25,15 +25,15 @@ likelihood = GPy.likelihoods.EP(data['Y'],distribution) sample = np.random.randint(0,data['X'].shape[0],10) Z = data['X'][sample,:] # create sparse GP EP model -#m = GPy.models.sparse_GP(data['X'],likelihood=likelihood,kernel=kernel,Z=Z) m = GPy.models.generalized_FITC(data['X'],likelihood=likelihood,kernel=kernel,Z=Z) m.ensure_default_constraints() m.set('len',10.) -m.update_likelihood_approximation() +#m.update_likelihood_approximation() # optimize -m.optimize() +#m.optimize() +m.pseudo_EM() print(m) # plot @@ -48,17 +48,18 @@ kernel = GPy.kern.rbf(data['X'].shape[1]) + GPy.kern.white(data['X'].shape[1]) distribution = GPy.likelihoods.likelihood_functions.probit() likelihood = GPy.likelihoods.EP(data['Y'],distribution) -sample = np.random.randint(0,data['X'].shape[0],10) -Z = data['X'][sample,:] +#sample = np.random.randint(0,data['X'].shape[0],10) +#Z = data['X'][sample,:] # create sparse GP EP model m = GPy.models.sparse_GP(data['X'],likelihood=likelihood,kernel=kernel,Z=Z) m.ensure_default_constraints() m.set('len',10.) -m.update_likelihood_approximation() +#m.update_likelihood_approximation() # optimize -m.optimize() +#m.optimize() +m.pseudo_EM() print(m) # plot