apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-15 06:52:39 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Changes in kernel parameters definition

Browse source
This commit is contained in:
Ricardo 2014-03-17 10:27:10 +00:00
parent f88b4c92e8
commit 7ac0689156
1 changed files with 6 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

10
GPy/util/multioutput.py
View file

@ -35,7 +35,8 @@ def build_likelihood(Y_list,noise_index,likelihoods_list=None):
likelihoods_list = [GPy.likelihoods.Gaussian(name="Gaussian_noise_%s" %j) for y,j in zip(Y_list,range(Ny))] likelihoods_list = [GPy.likelihoods.Gaussian(name="Gaussian_noise_%s" %j) for y,j in zip(Y_list,range(Ny))]
else: else:
assert len(likelihoods_list) == Ny assert len(likelihoods_list) == Ny
likelihood = GPy.likelihoods.mixed_noise.MixedNoise(likelihoods_list=likelihoods_list, noise_index=noise_index) #likelihood = GPy.likelihoods.mixed_noise.MixedNoise(likelihoods_list=likelihoods_list, noise_index=noise_index)
likelihood = GPy.likelihoods.mixed_noise.MixedNoise(likelihoods_list=likelihoods_list)
return likelihood return likelihood
@ -43,7 +44,7 @@ def ICM(input_dim, num_outputs, kernel, W_rank=1,W=None,kappa=None,name='X'):
""" """
Builds a kernel for an Intrinsic Coregionalization Model Builds a kernel for an Intrinsic Coregionalization Model
:input_dim: Input dimensionality :input_dim: Input dimensionality (does not include dimension of indices)
:num_outputs: Number of outputs :num_outputs: Number of outputs
:param kernel: kernel that will be multiplied by the coregionalize kernel (matrix B). :param kernel: kernel that will be multiplied by the coregionalize kernel (matrix B).
:type kernel: a GPy kernel :type kernel: a GPy kernel
@ -54,7 +55,8 @@ def ICM(input_dim, num_outputs, kernel, W_rank=1,W=None,kappa=None,name='X'):
kernel.input_dim = input_dim kernel.input_dim = input_dim
warnings.warn("kernel's input dimension overwritten to fit input_dim parameter.") warnings.warn("kernel's input dimension overwritten to fit input_dim parameter.")
K = kernel.prod(GPy.kern.Coregionalize([input_dim], num_outputs,W_rank,W,kappa,name='B'),name=name) K = kernel.prod(GPy.kern.Coregionalize(1, num_outputs, active_dims=[input_dim], rank=W_rank,W=W,kappa=kappa,name='B'),name=name)
#K = kernel * GPy.kern.Coregionalize(1, num_outputs, active_dims=[input_dim], rank=W_rank,W=W,kappa=kappa,name='B')
#K = kernel ** GPy.kern.Coregionalize(input_dim, num_outputs,W_rank,W,kappa, name= 'B') #K = kernel ** GPy.kern.Coregionalize(input_dim, num_outputs,W_rank,W,kappa, name= 'B')
K['.*variance'] = 1. K['.*variance'] = 1.
K['.*variance'].fix() K['.*variance'].fix()
@ -65,7 +67,7 @@ def LCM(input_dim, num_outputs, kernels_list, W_rank=1,name='X'):
""" """
Builds a kernel for an Linear Coregionalization Model Builds a kernel for an Linear Coregionalization Model
:input_dim: Input dimensionality :input_dim: Input dimensionality (does not include dimension of indices)
:num_outputs: Number of outputs :num_outputs: Number of outputs
:param kernel: kernel that will be multiplied by the coregionalize kernel (matrix B). :param kernel: kernel that will be multiplied by the coregionalize kernel (matrix B).
:type kernel: a GPy kernel :type kernel: a GPy kernel