mirror of
https://github.com/SheffieldML/GPy.git
synced 2026-05-24 14:15:14 +02:00
Merged and fixed conflicts, names still need changing accordingly
This commit is contained in:
Ricardo
commit
b3eeacd956
55 changed files with 912 additions and 927 deletions
|
|
@ -5,9 +5,9 @@ import numpy as np
|
|||
from matplotlib import pyplot as plt
|
||||
|
||||
import GPy
|
||||
from GPy.models.Bayesian_GPLVM import Bayesian_GPLVM
|
||||
from GPy.util.datasets import swiss_roll_generated
|
||||
from GPy.core.transformations import logexp
|
||||
from GPy.models.bayesian_gplvm import BayesianGPLVM
|
||||
|
||||
default_seed = np.random.seed(123344)
|
||||
|
||||
|
|
@ -20,14 +20,14 @@ def BGPLVM(seed=default_seed):
|
|||
X = np.random.rand(N, Q)
|
||||
k = GPy.kern.rbf(Q) + GPy.kern.white(Q, 0.00001)
|
||||
K = k.K(X)
|
||||
Y = np.random.multivariate_normal(np.zeros(N), K, D).T
|
||||
Y = np.random.multivariate_normal(np.zeros(N), K, Q).T
|
||||
|
||||
k = GPy.kern.rbf(Q, ARD=True) + GPy.kern.linear(Q, ARD=True) + GPy.kern.rbf(Q, ARD=True) + GPy.kern.white(Q)
|
||||
# k = GPy.kern.rbf(Q) + GPy.kern.rbf(Q) + GPy.kern.white(Q)
|
||||
# k = GPy.kern.rbf(Q) + GPy.kern.bias(Q) + GPy.kern.white(Q, 0.00001)
|
||||
# k = GPy.kern.rbf(Q, ARD = False) + GPy.kern.white(Q, 0.00001)
|
||||
|
||||
m = GPy.models.Bayesian_GPLVM(Y, Q, kernel=k, M=M)
|
||||
m = GPy.models.BayesianGPLVM(Y, Q, kernel=k, M=M)
|
||||
m.constrain_positive('(rbf|bias|noise|white|S)')
|
||||
# m.constrain_fixed('S', 1)
|
||||
|
||||
|
|
@ -105,7 +105,7 @@ def swiss_roll(optimize=True, N=1000, M=15, Q=4, sigma=.2, plot=False):
|
|||
|
||||
kernel = GPy.kern.rbf(Q, ARD=True) + GPy.kern.bias(Q, np.exp(-2)) + GPy.kern.white(Q, np.exp(-2))
|
||||
|
||||
m = Bayesian_GPLVM(Y, Q, X=X, X_variance=S, M=M, Z=Z, kernel=kernel)
|
||||
m = BayesianGPLVM(Y, Q, X=X, X_variance=S, M=M, Z=Z, kernel=kernel)
|
||||
m.data_colors = c
|
||||
m.data_t = t
|
||||
|
||||
|
|
@ -129,7 +129,7 @@ def BGPLVM_oil(optimize=True, N=100, Q=5, M=25, max_f_eval=4e3, plot=False, **k)
|
|||
Yn = Y - Y.mean(0)
|
||||
Yn /= Yn.std(0)
|
||||
|
||||
m = GPy.models.Bayesian_GPLVM(Yn, Q, kernel=kernel, M=M, **k)
|
||||
m = GPy.models.BayesianGPLVM(Yn, Q, kernel=kernel, M=M, **k)
|
||||
m.data_labels = data['Y'][:N].argmax(axis=1)
|
||||
|
||||
# m.constrain('variance|leng', logexp_clipped())
|
||||
|
|
@ -234,7 +234,7 @@ def bgplvm_simulation_matlab_compare():
|
|||
from GPy import kern
|
||||
reload(mrd); reload(kern)
|
||||
k = kern.linear(Q, ARD=True) + kern.bias(Q, np.exp(-2)) + kern.white(Q, np.exp(-2))
|
||||
m = Bayesian_GPLVM(Y, Q, init="PCA", M=M, kernel=k,
|
||||
m = BayesianGPLVM(Y, Q, init="PCA", M=M, kernel=k,
|
||||
# X=mu,
|
||||
# X_variance=S,
|
||||
_debug=False)
|
||||
|
|
@ -259,7 +259,7 @@ def bgplvm_simulation(optimize='scg',
|
|||
Y = Ylist[0]
|
||||
|
||||
k = kern.linear(Q, ARD=True) + kern.bias(Q, np.exp(-2)) + kern.white(Q, np.exp(-2)) # + kern.bias(Q)
|
||||
m = Bayesian_GPLVM(Y, Q, init="PCA", M=M, kernel=k, _debug=True)
|
||||
m = BayesianGPLVM(Y, Q, init="PCA", M=M, kernel=k, _debug=True)
|
||||
# m.constrain('variance|noise', logexp_clipped())
|
||||
m.ensure_default_constraints()
|
||||
m['noise'] = Y.var() / 100.
|
||||
|
|
@ -285,7 +285,7 @@ def mrd_simulation(optimize=True, plot=True, plot_sim=True, **kw):
|
|||
reload(mrd); reload(kern)
|
||||
|
||||
k = kern.linear(Q, [.05] * Q, ARD=True) + kern.bias(Q, np.exp(-2)) + kern.white(Q, np.exp(-2))
|
||||
m = mrd.MRD(Ylist, Q=Q, M=M, kernels=k, initx="", initz='permute', **kw)
|
||||
m = mrd.MRD(Ylist, input_dim=Q, M=M, kernels=k, initx="", initz='permute', **kw)
|
||||
|
||||
for i, Y in enumerate(Ylist):
|
||||
m['{}_noise'.format(i + 1)] = Y.var() / 100.
|
||||
|
|
@ -297,7 +297,7 @@ def mrd_simulation(optimize=True, plot=True, plot_sim=True, **kw):
|
|||
|
||||
if optimize:
|
||||
print "Optimizing Model:"
|
||||
m.optimize('scg', messages=1, max_iters=5e4, max_f_eval=5e4)
|
||||
m.optimize('scg', messages=1, max_iters=5e4, max_f_eval=5e4, gtol=.05)
|
||||
if plot:
|
||||
m.plot_X_1d("MRD Latent Space 1D")
|
||||
m.plot_scales("MRD Scales")
|
||||
|
|
@ -313,7 +313,7 @@ def brendan_faces():
|
|||
Yn /= Yn.std()
|
||||
|
||||
m = GPy.models.GPLVM(Yn, Q)
|
||||
# m = GPy.models.Bayesian_GPLVM(Yn, Q, M=100)
|
||||
# m = GPy.models.BayesianGPLVM(Yn, Q, M=100)
|
||||
|
||||
# optimize
|
||||
m.constrain('rbf|noise|white', GPy.core.transformations.logexp_clipped())
|
||||
|
|
@ -380,7 +380,7 @@ def cmu_mocap(subject='35', motion=['01'], in_place=True):
|
|||
# M = 30
|
||||
#
|
||||
# kernel = GPy.kern.rbf(Q, ARD=True) + GPy.kern.bias(Q) + GPy.kern.white(Q)
|
||||
# m = GPy.models.Bayesian_GPLVM(X, Q, kernel=kernel, M=M)
|
||||
# m = GPy.models.BayesianGPLVM(X, Q, kernel=kernel, M=M)
|
||||
# # m.scale_factor = 100.0
|
||||
# m.constrain_positive('(white|noise|bias|X_variance|rbf_variance|rbf_length)')
|
||||
# from sklearn import cluster
|
||||
|
|
|
|||
|
|
@ -10,16 +10,16 @@ import numpy as np
|
|||
import GPy
|
||||
|
||||
|
||||
def toy_rbf_1d(optim_iters=100):
|
||||
def toy_rbf_1d(max_nb_eval_optim=100):
|
||||
"""Run a simple demonstration of a standard Gaussian process fitting it to data sampled from an RBF covariance."""
|
||||
data = GPy.util.datasets.toy_rbf_1d()
|
||||
|
||||
# create simple GP model
|
||||
m = GPy.models.GP_regression(data['X'],data['Y'])
|
||||
m = GPy.models.GPRegression(data['X'],data['Y'])
|
||||
|
||||
# optimize
|
||||
m.ensure_default_constraints()
|
||||
m.optimize(max_f_eval=optim_iters)
|
||||
m.optimize(max_f_eval=max_nb_eval_optim)
|
||||
# plot
|
||||
m.plot()
|
||||
print(m)
|
||||
|
|
@ -30,7 +30,7 @@ def rogers_girolami_olympics(optim_iters=100):
|
|||
data = GPy.util.datasets.rogers_girolami_olympics()
|
||||
|
||||
# create simple GP model
|
||||
m = GPy.models.GP_regression(data['X'],data['Y'])
|
||||
m = GPy.models.GPRegression(data['X'],data['Y'])
|
||||
|
||||
#set the lengthscale to be something sensible (defaults to 1)
|
||||
m['rbf_lengthscale'] = 10
|
||||
|
|
@ -49,7 +49,7 @@ def toy_rbf_1d_50(optim_iters=100):
|
|||
data = GPy.util.datasets.toy_rbf_1d_50()
|
||||
|
||||
# create simple GP model
|
||||
m = GPy.models.GP_regression(data['X'],data['Y'])
|
||||
m = GPy.models.GPRegression(data['X'],data['Y'])
|
||||
|
||||
# optimize
|
||||
m.ensure_default_constraints()
|
||||
|
|
@ -65,7 +65,7 @@ def silhouette(optim_iters=100):
|
|||
data = GPy.util.datasets.silhouette()
|
||||
|
||||
# create simple GP model
|
||||
m = GPy.models.GP_regression(data['X'],data['Y'])
|
||||
m = GPy.models.GPRegression(data['X'],data['Y'])
|
||||
|
||||
# optimize
|
||||
m.ensure_default_constraints()
|
||||
|
|
@ -87,9 +87,9 @@ def coregionalisation_toy2(optim_iters=100):
|
|||
Y = np.vstack((Y1,Y2))
|
||||
|
||||
k1 = GPy.kern.rbf(1) + GPy.kern.bias(1)
|
||||
k2 = GPy.kern.coregionalise(2,1)
|
||||
k2 = GPy.kern.Coregionalise(2,1)
|
||||
k = k1.prod(k2,tensor=True)
|
||||
m = GPy.models.GP_regression(X,Y,kernel=k)
|
||||
m = GPy.models.GPRegression(X,Y,kernel=k)
|
||||
m.constrain_fixed('.*rbf_var',1.)
|
||||
#m.constrain_positive('.*kappa')
|
||||
m.ensure_default_constraints()
|
||||
|
|
@ -119,9 +119,9 @@ def coregionalisation_toy(optim_iters=100):
|
|||
Y = np.vstack((Y1,Y2))
|
||||
|
||||
k1 = GPy.kern.rbf(1)
|
||||
k2 = GPy.kern.coregionalise(2,2)
|
||||
k2 = GPy.kern.Coregionalise(2,2)
|
||||
k = k1.prod(k2,tensor=True)
|
||||
m = GPy.models.GP_regression(X,Y,kernel=k)
|
||||
m = GPy.models.GPRegression(X,Y,kernel=k)
|
||||
m.constrain_fixed('.*rbf_var',1.)
|
||||
#m.constrain_positive('kappa')
|
||||
m.ensure_default_constraints()
|
||||
|
|
@ -155,10 +155,10 @@ def coregionalisation_sparse(optim_iters=100):
|
|||
Z = np.hstack((np.random.rand(M,1)*8,np.random.randint(0,2,M)[:,None]))
|
||||
|
||||
k1 = GPy.kern.rbf(1)
|
||||
k2 = GPy.kern.coregionalise(2,2)
|
||||
k2 = GPy.kern.Coregionalise(2,2)
|
||||
k = k1.prod(k2,tensor=True) + GPy.kern.white(2,0.001)
|
||||
|
||||
m = GPy.models.sparse_GP_regression(X,Y,kernel=k,Z=Z)
|
||||
m = GPy.models.SparseGPRegression(X,Y,kernel=k,Z=Z)
|
||||
m.scale_factor = 10000.
|
||||
m.constrain_fixed('.*rbf_var',1.)
|
||||
#m.constrain_positive('kappa')
|
||||
|
|
@ -181,7 +181,7 @@ def coregionalisation_sparse(optim_iters=100):
|
|||
return m
|
||||
|
||||
|
||||
def multiple_optima(gene_number=937,resolution=80, model_restarts=10, seed=10000, optim_iters=100):
|
||||
def multiple_optima(gene_number=937,resolution=80, model_restarts=10, seed=10000, optim_iters=300):
|
||||
"""Show an example of a multimodal error surface for Gaussian process regression. Gene 939 has bimodal behaviour where the noisey mode is higher."""
|
||||
|
||||
# Contour over a range of length scales and signal/noise ratios.
|
||||
|
|
@ -197,7 +197,7 @@ def multiple_optima(gene_number=937,resolution=80, model_restarts=10, seed=10000
|
|||
data['Y'] = data['Y'] - np.mean(data['Y'])
|
||||
|
||||
lls = GPy.examples.regression._contour_data(data, length_scales, log_SNRs, GPy.kern.rbf)
|
||||
pb.contour(length_scales, log_SNRs, np.exp(lls), 20)
|
||||
pb.contour(length_scales, log_SNRs, np.exp(lls), 20, cmap=pb.cm.jet)
|
||||
ax = pb.gca()
|
||||
pb.xlabel('length scale')
|
||||
pb.ylabel('log_10 SNR')
|
||||
|
|
@ -211,18 +211,20 @@ def multiple_optima(gene_number=937,resolution=80, model_restarts=10, seed=10000
|
|||
optim_point_y = np.empty(2)
|
||||
np.random.seed(seed=seed)
|
||||
for i in range(0, model_restarts):
|
||||
kern = GPy.kern.rbf(1, variance=np.random.exponential(1.), lengthscale=np.random.exponential(50.)) + GPy.kern.white(1,variance=np.random.exponential(1.))
|
||||
#kern = GPy.kern.rbf(1, variance=np.random.exponential(1.), lengthscale=np.random.exponential(50.))
|
||||
kern = GPy.kern.rbf(1, variance=np.random.uniform(1e-3,1), lengthscale=np.random.uniform(5,50))
|
||||
|
||||
m = GPy.models.GP_regression(data['X'],data['Y'], kernel=kern)
|
||||
optim_point_x[0] = m.get('rbf_lengthscale')
|
||||
optim_point_y[0] = np.log10(m.get('rbf_variance')) - np.log10(m.get('white_variance'));
|
||||
m = GPy.models.GPRegression(data['X'],data['Y'], kernel=kern)
|
||||
m['noise_variance'] = np.random.uniform(1e-3,1)
|
||||
optim_point_x[0] = m['rbf_lengthscale']
|
||||
optim_point_y[0] = np.log10(m['rbf_variance']) - np.log10(m['noise_variance']);
|
||||
|
||||
# optimize
|
||||
m.ensure_default_constraints()
|
||||
m.optimize(xtol=1e-6, ftol=1e-6, max_f_eval=optim_iters)
|
||||
m.optimize('scg', xtol=1e-6, ftol=1e-6, max_f_eval=optim_iters)
|
||||
|
||||
optim_point_x[1] = m.get('rbf_lengthscale')
|
||||
optim_point_y[1] = np.log10(m.get('rbf_variance')) - np.log10(m.get('white_variance'));
|
||||
optim_point_x[1] = m['rbf_lengthscale']
|
||||
optim_point_y[1] = np.log10(m['rbf_variance']) - np.log10(m['noise_variance']);
|
||||
|
||||
pb.arrow(optim_point_x[0], optim_point_y[0], optim_point_x[1]-optim_point_x[0], optim_point_y[1]-optim_point_y[0], label=str(i), head_length=1, head_width=0.5, fc='k', ec='k')
|
||||
models.append(m)
|
||||
|
|
@ -231,39 +233,32 @@ def multiple_optima(gene_number=937,resolution=80, model_restarts=10, seed=10000
|
|||
ax.set_ylim(ylim)
|
||||
return (models, lls)
|
||||
|
||||
def _contour_data(data, length_scales, log_SNRs, signal_kernel_call=GPy.kern.rbf):
|
||||
def _contour_data(data, length_scales, log_SNRs, kernel_call=GPy.kern.rbf):
|
||||
"""Evaluate the GP objective function for a given data set for a range of signal to noise ratios and a range of lengthscales.
|
||||
|
||||
:data_set: A data set from the utils.datasets director.
|
||||
:length_scales: a list of length scales to explore for the contour plot.
|
||||
:log_SNRs: a list of base 10 logarithm signal to noise ratios to explore for the contour plot.
|
||||
:signal_kernel: a kernel to use for the 'signal' portion of the data."""
|
||||
:kernel: a kernel to use for the 'signal' portion of the data."""
|
||||
|
||||
lls = []
|
||||
total_var = np.var(data['Y'])
|
||||
kernel = kernel_call(1, variance=1., lengthscale=1.)
|
||||
model = GPy.models.GPRegression(data['X'], data['Y'], kernel=kernel)
|
||||
for log_SNR in log_SNRs:
|
||||
SNR = 10**log_SNR
|
||||
SNR = 10.**log_SNR
|
||||
noise_var = total_var/(1.+SNR)
|
||||
signal_var = total_var - noise_var
|
||||
model.kern['.*variance'] = signal_var
|
||||
model['noise_variance'] = noise_var
|
||||
length_scale_lls = []
|
||||
|
||||
for length_scale in length_scales:
|
||||
noise_var = 1.
|
||||
signal_var = SNR
|
||||
noise_var = noise_var/(noise_var + signal_var)*total_var
|
||||
signal_var = signal_var/(noise_var + signal_var)*total_var
|
||||
|
||||
signal_kernel = signal_kernel_call(1, variance=signal_var, lengthscale=length_scale)
|
||||
noise_kernel = GPy.kern.white(1, variance=noise_var)
|
||||
kernel = signal_kernel + noise_kernel
|
||||
K = kernel.K(data['X'])
|
||||
total_var = (np.dot(np.dot(data['Y'].T,GPy.util.linalg.pdinv(K)[0]), data['Y'])/data['Y'].shape[0])[0,0]
|
||||
noise_var *= total_var
|
||||
signal_var *= total_var
|
||||
|
||||
kernel = signal_kernel_call(1, variance=signal_var, lengthscale=length_scale) + GPy.kern.white(1, variance=noise_var)
|
||||
|
||||
model = GPy.models.GP_regression(data['X'], data['Y'], kernel=kernel)
|
||||
model.constrain_positive('')
|
||||
model['.*lengthscale'] = length_scale
|
||||
length_scale_lls.append(model.log_likelihood())
|
||||
|
||||
lls.append(length_scale_lls)
|
||||
|
||||
return np.array(lls)
|
||||
|
||||
def sparse_GP_regression_1D(N = 400, M = 5, optim_iters=100):
|
||||
|
|
@ -276,7 +271,7 @@ def sparse_GP_regression_1D(N = 400, M = 5, optim_iters=100):
|
|||
noise = GPy.kern.white(1)
|
||||
kernel = rbf + noise
|
||||
# create simple GP model
|
||||
m = GPy.models.sparse_GP_regression(X, Y, kernel, M=M)
|
||||
m = GPy.models.SparseGPRegression(X, Y, kernel, M=M)
|
||||
|
||||
m.ensure_default_constraints()
|
||||
|
||||
|
|
@ -296,7 +291,7 @@ def sparse_GP_regression_2D(N = 400, M = 50, optim_iters=100):
|
|||
kernel = rbf + noise
|
||||
|
||||
# create simple GP model
|
||||
m = GPy.models.sparse_GP_regression(X,Y,kernel, M = M)
|
||||
m = GPy.models.SparseGPRegression(X,Y,kernel, M = M)
|
||||
|
||||
# contrain all parameters to be positive (but not inducing inputs)
|
||||
m.ensure_default_constraints()
|
||||
|
|
@ -325,7 +320,7 @@ def uncertain_inputs_sparse_regression(optim_iters=100):
|
|||
k = GPy.kern.rbf(1) + GPy.kern.white(1)
|
||||
|
||||
# create simple GP model - no input uncertainty on this one
|
||||
m = GPy.models.sparse_GP_regression(X, Y, kernel=k, Z=Z)
|
||||
m = GPy.models.SparseGPRegression(X, Y, kernel=k, Z=Z)
|
||||
m.ensure_default_constraints()
|
||||
m.optimize('scg', messages=1, max_f_eval=optim_iters)
|
||||
m.plot(ax=axes[0])
|
||||
|
|
@ -333,7 +328,7 @@ def uncertain_inputs_sparse_regression(optim_iters=100):
|
|||
|
||||
|
||||
#the same model with uncertainty
|
||||
m = GPy.models.sparse_GP_regression(X, Y, kernel=k, Z=Z, X_variance=S)
|
||||
m = GPy.models.SparseGPRegression(X, Y, kernel=k, Z=Z, X_variance=S)
|
||||
m.ensure_default_constraints()
|
||||
m.optimize('scg', messages=1, max_f_eval=optim_iters)
|
||||
m.plot(ax=axes[1])
|
||||
|
|
|
|||
|
|
@ -19,7 +19,7 @@ def tuto_GP_regression():
|
|||
|
||||
kernel = GPy.kern.rbf(D=1, variance=1., lengthscale=1.)
|
||||
|
||||
m = GPy.models.GP_regression(X,Y,kernel)
|
||||
m = GPy.models.GPRegression(X, Y, kernel)
|
||||
|
||||
print m
|
||||
m.plot()
|
||||
|
|
@ -47,7 +47,7 @@ def tuto_GP_regression():
|
|||
ker = GPy.kern.Matern52(2,ARD=True) + GPy.kern.white(2)
|
||||
|
||||
# create simple GP model
|
||||
m = GPy.models.GP_regression(X,Y,ker)
|
||||
m = GPy.models.GPRegression(X, Y, ker)
|
||||
|
||||
# contrain all parameters to be positive
|
||||
m.constrain_positive('')
|
||||
|
|
@ -145,7 +145,7 @@ def tuto_kernel_overview():
|
|||
Y = 0.5*X[:,:1] + 0.5*X[:,1:] + 2*np.sin(X[:,:1]) * np.sin(X[:,1:])
|
||||
|
||||
# Create GP regression model
|
||||
m = GPy.models.GP_regression(X,Y,Kanova)
|
||||
m = GPy.models.GPRegression(X, Y, Kanova)
|
||||
pb.figure(figsize=(5,5))
|
||||
m.plot()
|
||||
|
||||
|
|
@ -196,5 +196,5 @@ def model_interaction():
|
|||
X = np.random.randn(20,1)
|
||||
Y = np.sin(X) + np.random.randn(*X.shape)*0.01 + 5.
|
||||
k = GPy.kern.rbf(1) + GPy.kern.bias(1)
|
||||
return GPy.models.GP_regression(X,Y,kernel=k)
|
||||
return GPy.models.GPRegression(X, Y, kernel=k)
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue