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

manual merging

Browse source
This commit is contained in:
James Hensman 2015-04-09 15:46:40 +01:00
commit ea787fd376
130 changed files with 982 additions and 787 deletions
Download patch file Download diff file Expand all files Collapse all files

6
GPy/inference/__init__.py
View file

@ -1,3 +1,3 @@
import latent_function_inference
import optimization
import mcmc
from . import latent_function_inference
from . import optimization
from . import mcmc

16
GPy/inference/latent_function_inference/__init__.py
View file

@ -61,15 +61,15 @@ class InferenceMethodList(LatentFunctionInference, list):
for inf in state:
self.append(inf)
from exact_gaussian_inference import ExactGaussianInference
from laplace import Laplace, LaplaceBlock
from .exact_gaussian_inference import ExactGaussianInference
from .laplace import Laplace,LaplaceBlock
from GPy.inference.latent_function_inference.var_dtc import VarDTC
from expectation_propagation import EP
from expectation_propagation_dtc import EPDTC
from dtc import DTC
from fitc import FITC
from var_dtc_parallel import VarDTC_minibatch
from svgp import SVGP
from .expectation_propagation import EP
from .expectation_propagation_dtc import EPDTC
from .dtc import DTC
from .fitc import FITC
from .var_dtc_parallel import VarDTC_minibatch
from .svgp import SVGP
# class FullLatentFunctionData(object):
#

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

@ -1,7 +1,7 @@
# Copyright (c) 2012-2014, James Hensman
# Licensed under the BSD 3-clause license (see LICENSE.txt)
from posterior import Posterior
from .posterior import Posterior
from ...util.linalg import jitchol, tdot, dtrtrs, dpotri, pdinv
import numpy as np
from . import LatentFunctionInference
@ -30,7 +30,7 @@ class DTC(LatentFunctionInference):
#make sure the noise is not hetero
beta = 1./likelihood.gaussian_variance(Y_metadata)
if beta.size > 1:
raise NotImplementedError, "no hetero noise with this implementation of DTC"
raise NotImplementedError("no hetero noise with this implementation of DTC")
Kmm = kern.K(Z)
Knn = kern.Kdiag(X)
@ -99,7 +99,7 @@ class vDTC(object):
#make sure the noise is not hetero
beta = 1./likelihood.gaussian_variance(Y_metadata)
if beta.size > 1:
raise NotImplementedError, "no hetero noise with this implementation of DTC"
raise NotImplementedError("no hetero noise with this implementation of DTC")
Kmm = kern.K(Z)
Knn = kern.Kdiag(X)

2
GPy/inference/latent_function_inference/exact_gaussian_inference.py
View file

@ -1,7 +1,7 @@
# Copyright (c) 2012-2014, GPy authors (see AUTHORS.txt).
# Licensed under the BSD 3-clause license (see LICENSE.txt)
from posterior import Posterior
from .posterior import Posterior
from ...util.linalg import pdinv, dpotrs, tdot
from ...util import diag
import numpy as np

2
GPy/inference/latent_function_inference/expectation_propagation.py
View file

@ -2,7 +2,7 @@
# Licensed under the BSD 3-clause license (see LICENSE.txt)
import numpy as np
from ...util.linalg import pdinv,jitchol,DSYR,tdot,dtrtrs, dpotrs
from posterior import Posterior
from .posterior import Posterior
from . import LatentFunctionInference
log_2_pi = np.log(2*np.pi)

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

@ -6,7 +6,7 @@ from ...util import diag
from ...util.linalg import mdot, jitchol, backsub_both_sides, tdot, dtrtrs, dtrtri, dpotri, dpotrs, symmetrify, DSYR
from ...core.parameterization.variational import VariationalPosterior
from . import LatentFunctionInference
from posterior import Posterior
from .posterior import Posterior
log_2_pi = np.log(2*np.pi)
class EPDTC(LatentFunctionInference):
@ -180,7 +180,7 @@ class EPDTC(LatentFunctionInference):
if VVT_factor.shape[1] == Y.shape[1]:
woodbury_vector = Cpsi1Vf # == Cpsi1V
else:
print 'foobar'
print('foobar')
psi1V = np.dot(mu_tilde[:,None].T*beta, psi1).T
tmp, _ = dtrtrs(Lm, psi1V, lower=1, trans=0)
tmp, _ = dpotrs(LB, tmp, lower=1)
@ -315,7 +315,7 @@ def _compute_dL_dR(likelihood, het_noise, uncertain_inputs, LB, _LBi_Lmi_psi1Vf,
dL_dR = None
elif het_noise:
if uncertain_inputs:
raise NotImplementedError, "heteroscedatic derivates with uncertain inputs not implemented"
raise NotImplementedError("heteroscedatic derivates with uncertain inputs not implemented")
else:
#from ...util.linalg import chol_inv
#LBi = chol_inv(LB)

4
GPy/inference/latent_function_inference/fitc.py
View file

@ -1,7 +1,7 @@
# Copyright (c) 2012, James Hensman
# Licensed under the BSD 3-clause license (see LICENSE.txt)
from posterior import Posterior
from .posterior import Posterior
from ...util.linalg import jitchol, tdot, dtrtrs, dpotri, pdinv
from ...util import diag
import numpy as np
@ -27,7 +27,7 @@ class FITC(LatentFunctionInference):
#make sure the noise is not hetero
sigma_n = likelihood.gaussian_variance(Y_metadata)
if sigma_n.size >1:
raise NotImplementedError, "no hetero noise with this implementation of FITC"
raise NotImplementedError("no hetero noise with this implementation of FITC")
Kmm = kern.K(Z)
Knn = kern.Kdiag(X)

2
GPy/inference/latent_function_inference/laplace.py
View file

@ -12,7 +12,7 @@
import numpy as np
from ...util.linalg import mdot, jitchol, dpotrs, dtrtrs, dpotri, symmetrify, pdinv
from posterior import Posterior
from .posterior import Posterior
import warnings
def warning_on_one_line(message, category, filename, lineno, file=None, line=None):
return ' %s:%s: %s:%s\n' % (filename, lineno, category.__name__, message)

12
GPy/inference/latent_function_inference/posterior.py
View file

@ -52,7 +52,7 @@ class Posterior(object):
or ((mean is not None) and (cov is not None)):
pass # we have sufficient to compute the posterior
else:
raise ValueError, "insufficient information to compute the posterior"
raise ValueError("insufficient information to compute the posterior")
self._K_chol = K_chol
self._K = K
@ -108,7 +108,7 @@ class Posterior(object):
if self._precision is None:
cov = np.atleast_3d(self.covariance)
self._precision = np.zeros(cov.shape) # if one covariance per dimension
for p in xrange(cov.shape[-1]):
for p in range(cov.shape[-1]):
self._precision[:,:,p] = pdinv(cov[:,:,p])[0]
return self._precision
@ -126,7 +126,7 @@ class Posterior(object):
if self._woodbury_inv is not None:
winv = np.atleast_3d(self._woodbury_inv)
self._woodbury_chol = np.zeros(winv.shape)
for p in xrange(winv.shape[-1]):
for p in range(winv.shape[-1]):
self._woodbury_chol[:,:,p] = pdinv(winv[:,:,p])[2]
#Li = jitchol(self._woodbury_inv)
#self._woodbury_chol, _ = dtrtri(Li)
@ -135,13 +135,13 @@ class Posterior(object):
#self._woodbury_chol = jitchol(W)
#try computing woodbury chol from cov
elif self._covariance is not None:
raise NotImplementedError, "TODO: check code here"
raise NotImplementedError("TODO: check code here")
B = self._K - self._covariance
tmp, _ = dpotrs(self.K_chol, B)
self._woodbury_inv, _ = dpotrs(self.K_chol, tmp.T)
_, _, self._woodbury_chol, _ = pdinv(self._woodbury_inv)
else:
raise ValueError, "insufficient information to compute posterior"
raise ValueError("insufficient information to compute posterior")
return self._woodbury_chol
@property
@ -161,7 +161,7 @@ class Posterior(object):
elif self._covariance is not None:
B = np.atleast_3d(self._K) - np.atleast_3d(self._covariance)
self._woodbury_inv = np.empty_like(B)
for i in xrange(B.shape[-1]):
for i in range(B.shape[-1]):
tmp, _ = dpotrs(self.K_chol, B[:,:,i])
self._woodbury_inv[:,:,i], _ = dpotrs(self.K_chol, tmp.T)
return self._woodbury_inv

2
GPy/inference/latent_function_inference/svgp.py
View file

@ -2,7 +2,7 @@ from . import LatentFunctionInference
from ...util import linalg
from ...util import choleskies
import numpy as np
from posterior import Posterior
from .posterior import Posterior
class SVGP(LatentFunctionInference):

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

@ -1,7 +1,7 @@
# Copyright (c) 2012, GPy authors (see AUTHORS.txt).
# Licensed under the BSD 3-clause license (see LICENSE.txt)
from posterior import Posterior
from .posterior import Posterior
from ...util.linalg import mdot, jitchol, backsub_both_sides, tdot, dtrtrs, dtrtri, dpotri, dpotrs, symmetrify
from ...util import diag
from ...core.parameterization.variational import VariationalPosterior
@ -170,7 +170,7 @@ class VarDTC(LatentFunctionInference):
if VVT_factor.shape[1] == Y.shape[1]:
woodbury_vector = Cpsi1Vf # == Cpsi1V
else:
print 'foobar'
print('foobar')
import ipdb; ipdb.set_trace()
psi1V = np.dot(Y.T*beta, psi1).T
tmp, _ = dtrtrs(Lm, psi1V, lower=1, trans=0)
@ -213,7 +213,7 @@ def _compute_dL_dR(likelihood, het_noise, uncertain_inputs, LB, _LBi_Lmi_psi1Vf,
dL_dR = None
elif het_noise:
if uncertain_inputs:
raise NotImplementedError, "heteroscedatic derivates with uncertain inputs not implemented"
raise NotImplementedError("heteroscedatic derivates with uncertain inputs not implemented")
else:
#from ...util.linalg import chol_inv
#LBi = chol_inv(LB)

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

@ -1,7 +1,7 @@
# Copyright (c) 2014, GPy authors (see AUTHORS.txt).
# Licensed under the BSD 3-clause license (see LICENSE.txt)
from posterior import Posterior
from .posterior import Posterior
from ...util.linalg import jitchol, backsub_both_sides, tdot, dtrtrs, dtrtri,pdinv
from ...util import diag
from ...core.parameterization.variational import VariationalPosterior
@ -92,7 +92,7 @@ class VarDTC_minibatch(LatentFunctionInference):
psi0_full = 0.
YRY_full = 0.
for n_start in xrange(0,num_data,batchsize):
for n_start in range(0,num_data,batchsize):
n_end = min(batchsize+n_start, num_data)
if batchsize==num_data:
Y_slice = Y
@ -170,7 +170,7 @@ class VarDTC_minibatch(LatentFunctionInference):
Kmm = kern.K(Z).copy()
diag.add(Kmm, self.const_jitter)
if not np.isfinite(Kmm).all():
print Kmm
print(Kmm)
Lm = jitchol(Kmm)
LmInvPsi2LmInvT = backsub_both_sides(Lm,psi2_full,transpose='right')

2
GPy/inference/mcmc/__init__.py
View file

@ -1 +1 @@
from hmc import HMC
from .hmc import HMC

6
GPy/inference/mcmc/hmc.py
View file

@ -39,7 +39,7 @@ class HMC:
:rtype: numpy.ndarray
"""
params = np.empty((num_samples,self.p.size))
for i in xrange(num_samples):
for i in range(num_samples):
self.p[:] = np.random.multivariate_normal(np.zeros(self.p.size),self.M)
H_old = self._computeH()
theta_old = self.model.optimizer_array.copy()
@ -59,7 +59,7 @@ class HMC:
return params
def _update(self, hmc_iters):
for i in xrange(hmc_iters):
for i in range(hmc_iters):
self.p[:] += -self.stepsize/2.*self.model._transform_gradients(self.model.objective_function_gradients())
self.model.optimizer_array = self.model.optimizer_array + self.stepsize*np.dot(self.Minv, self.p)
self.p[:] += -self.stepsize/2.*self.model._transform_gradients(self.model.objective_function_gradients())
@ -82,7 +82,7 @@ class HMC_shortcut:
def sample(self, m_iters=1000, hmc_iters=20):
params = np.empty((m_iters,self.p.size))
for i in xrange(m_iters):
for i in range(m_iters):
# sample a stepsize from the uniform distribution
stepsize = np.exp(np.random.rand()*(self.stepsize_range[1]-self.stepsize_range[0])+self.stepsize_range[0])
self.p[:] = np.random.multivariate_normal(np.zeros(self.p.size),self.M)

10
GPy/inference/mcmc/samplers.py
View file

@ -9,7 +9,13 @@ import sys
import re
import numdifftools as ndt
import pdb
import cPickle
try:
#In Python 2, cPickle is faster. It does not exist in Python 3 but the underlying code is always used
#if available
import cPickle as pickle
except ImportError:
import pickle
class Metropolis_Hastings:
@ -40,7 +46,7 @@ class Metropolis_Hastings:
fcurrent = self.model.log_likelihood() + self.model.log_prior()
accepted = np.zeros(Ntotal,dtype=np.bool)
for it in range(Ntotal):
print "sample %d of %d\r"%(it,Ntotal),
print("sample %d of %d\r"%(it,Ntotal), end=' ')
sys.stdout.flush()
prop = np.random.multivariate_normal(current, self.cov*self.scale*self.scale)
self.model._set_params_transformed(prop)

4
GPy/inference/optimization/__init__.py
View file

@ -1,2 +1,2 @@
from scg import SCG
from optimization import *
from .scg import SCG
from .optimization import *

6
GPy/inference/optimization/conjugate_gradient_descent.py
View file

@ -1,7 +1,7 @@
# Copyright (c) 2012-2014, Max Zwiessele
# Licensed under the BSD 3-clause license (see LICENSE.txt)
from gradient_descent_update_rules import FletcherReeves, \
from .gradient_descent_update_rules import FletcherReeves, \
PolakRibiere
from Queue import Empty
from multiprocessing import Value
@ -74,7 +74,7 @@ class _Async_Optimization(Thread):
if self.outq is not None:
self.outq.put(self.SENTINEL)
if self.messages:
print ""
print("")
self.runsignal.clear()
def run(self, *args, **kwargs):
@ -213,7 +213,7 @@ class Async_Optimize(object):
# # print "^C"
# self.runsignal.clear()
# c.join()
print "WARNING: callback still running, optimisation done!"
print("WARNING: callback still running, optimisation done!")
return p.result
class CGD(Async_Optimize):

16
GPy/inference/optimization/optimization.py
View file

@ -10,7 +10,7 @@ try:
rasm_available = True
except ImportError:
rasm_available = False
from scg import SCG
from .scg import SCG
class Optimizer():
"""
@ -54,7 +54,7 @@ class Optimizer():
self.time = str(end - start)
def opt(self, f_fp=None, f=None, fp=None):
raise NotImplementedError, "this needs to be implemented to use the optimizer class"
raise NotImplementedError("this needs to be implemented to use the optimizer class")
def plot(self):
"""
@ -125,9 +125,9 @@ class opt_lbfgsb(Optimizer):
opt_dict = {}
if self.xtol is not None:
print "WARNING: l-bfgs-b doesn't have an xtol arg, so I'm going to ignore it"
print("WARNING: l-bfgs-b doesn't have an xtol arg, so I'm going to ignore it")
if self.ftol is not None:
print "WARNING: l-bfgs-b doesn't have an ftol arg, so I'm going to ignore it"
print("WARNING: l-bfgs-b doesn't have an ftol arg, so I'm going to ignore it")
if self.gtol is not None:
opt_dict['pgtol'] = self.gtol
if self.bfgs_factor is not None:
@ -162,7 +162,7 @@ class opt_simplex(Optimizer):
if self.ftol is not None:
opt_dict['ftol'] = self.ftol
if self.gtol is not None:
print "WARNING: simplex doesn't have an gtol arg, so I'm going to ignore it"
print("WARNING: simplex doesn't have an gtol arg, so I'm going to ignore it")
opt_result = optimize.fmin(f, self.x_init, (), disp=self.messages,
maxfun=self.max_f_eval, full_output=True, **opt_dict)
@ -190,11 +190,11 @@ class opt_rasm(Optimizer):
opt_dict = {}
if self.xtol is not None:
print "WARNING: minimize doesn't have an xtol arg, so I'm going to ignore it"
print("WARNING: minimize doesn't have an xtol arg, so I'm going to ignore it")
if self.ftol is not None:
print "WARNING: minimize doesn't have an ftol arg, so I'm going to ignore it"
print("WARNING: minimize doesn't have an ftol arg, so I'm going to ignore it")
if self.gtol is not None:
print "WARNING: minimize doesn't have an gtol arg, so I'm going to ignore it"
print("WARNING: minimize doesn't have an gtol arg, so I'm going to ignore it")
opt_result = rasm.minimize(self.x_init, f_fp, (), messages=self.messages,
maxnumfuneval=self.max_f_eval)

15
GPy/inference/optimization/scg.py
View file

@ -21,14 +21,13 @@
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
from __future__ import print_function
import numpy as np
import sys
def print_out(len_maxiters, fnow, current_grad, beta, iteration):
print '\r',
print '{0:>0{mi}g} {1:> 12e} {2:< 12.6e} {3:> 12e}'.format(iteration, float(fnow), float(beta), float(current_grad), mi=len_maxiters), # print 'Iteration:', iteration, ' Objective:', fnow, ' Scale:', beta, '\r',
print('\r', end=' ')
print('{0:>0{mi}g} {1:> 12e} {2:< 12.6e} {3:> 12e}'.format(iteration, float(fnow), float(beta), float(current_grad), mi=len_maxiters), end=' ') # print 'Iteration:', iteration, ' Objective:', fnow, ' Scale:', beta, '\r',
sys.stdout.flush()
def exponents(fnow, current_grad):
@ -80,7 +79,7 @@ def SCG(f, gradf, x, optargs=(), maxiters=500, max_f_eval=np.inf, display=True,
len_maxiters = len(str(maxiters))
if display:
print ' {0:{mi}s} {1:11s} {2:11s} {3:11s}'.format("I", "F", "Scale", "|g|", mi=len_maxiters)
print(' {0:{mi}s} {1:11s} {2:11s} {3:11s}'.format("I", "F", "Scale", "|g|", mi=len_maxiters))
exps = exponents(fnow, current_grad)
p_iter = iteration
@ -140,7 +139,7 @@ def SCG(f, gradf, x, optargs=(), maxiters=500, max_f_eval=np.inf, display=True,
b = np.any(n_exps < exps)
if a or b:
p_iter = iteration
print ''
print('')
if b:
exps = n_exps
@ -189,6 +188,6 @@ def SCG(f, gradf, x, optargs=(), maxiters=500, max_f_eval=np.inf, display=True,
if display:
print_out(len_maxiters, fnow, current_grad, beta, iteration)
print ""
print status
print("")
print(status)
return x, flog, function_eval, status

2
GPy/inference/optimization/stochastics.py
View file

@ -30,7 +30,7 @@ class SparseGPMissing(StochasticStorage):
Thus, we can just make sure the loop goes over self.d every
time.
"""
self.d = xrange(model.Y_normalized.shape[1])
self.d = range(model.Y_normalized.shape[1])
class SparseGPStochastics(StochasticStorage):
"""