From 45403105f9793a88f9e9003f1f953efff9eb10d0 Mon Sep 17 00:00:00 2001 From: James Hensman Date: Wed, 10 Apr 2013 09:34:15 +0100 Subject: [PATCH] changed X_uncertainty for X_variance (in the code) for consistency with actual naming (in the printing) --- GPy/models/Bayesian_GPLVM.py | 22 +++++++++++----------- GPy/models/GP.py | 2 +- GPy/models/generalized_FITC.py | 8 ++++---- GPy/models/sparse_GP.py | 30 +++++++++++++++--------------- 4 files changed, 31 insertions(+), 31 deletions(-) diff --git a/GPy/models/Bayesian_GPLVM.py b/GPy/models/Bayesian_GPLVM.py index 0f5758ba..f66fabde 100644 --- a/GPy/models/Bayesian_GPLVM.py +++ b/GPy/models/Bayesian_GPLVM.py @@ -22,12 +22,12 @@ class Bayesian_GPLVM(sparse_GP, GPLVM): :type init: 'PCA'|'random' """ - def __init__(self, Y, Q, X = None, X_uncertainty = None, init='PCA', M=10, Z=None, kernel=None, **kwargs): + def __init__(self, Y, Q, X = None, X_variance = None, init='PCA', M=10, Z=None, kernel=None, **kwargs): if X == None: X = self.initialise_latent(init, Q, Y) - if X_uncertainty is None: - X_uncertainty = np.ones_like(X) * 0.5 + if X_variance is None: + X_variance = np.ones_like(X) * 0.5 if Z is None: Z = np.random.permutation(X.copy())[:M] @@ -37,7 +37,7 @@ class Bayesian_GPLVM(sparse_GP, GPLVM): kernel = kern.rbf(Q) + kern.white(Q) - sparse_GP.__init__(self, X, Gaussian(Y), kernel, Z=Z, X_uncertainty=X_uncertainty, **kwargs) + sparse_GP.__init__(self, X, Gaussian(Y), kernel, Z=Z, X_variance=X_variance, **kwargs) def _get_param_names(self): X_names = sum([['X_%i_%i'%(n,q) for q in range(self.Q)] for n in range(self.N)],[]) @@ -54,28 +54,28 @@ class Bayesian_GPLVM(sparse_GP, GPLVM): =============================================================== """ - return np.hstack((self.X.flatten(), self.X_uncertainty.flatten(), sparse_GP._get_params(self))) + return np.hstack((self.X.flatten(), self.X_variance.flatten(), sparse_GP._get_params(self))) def _set_params(self,x): N, Q = self.N, self.Q self.X = x[:self.X.size].reshape(N,Q).copy() - self.X_uncertainty = x[(N*Q):(2*N*Q)].reshape(N,Q).copy() + self.X_variance = x[(N*Q):(2*N*Q)].reshape(N,Q).copy() sparse_GP._set_params(self, x[(2*N*Q):]) def dL_dmuS(self): - dL_dmu_psi0, dL_dS_psi0 = self.kern.dpsi1_dmuS(self.dL_dpsi1,self.Z,self.X,self.X_uncertainty) - dL_dmu_psi1, dL_dS_psi1 = self.kern.dpsi0_dmuS(self.dL_dpsi0,self.Z,self.X,self.X_uncertainty) - dL_dmu_psi2, dL_dS_psi2 = self.kern.dpsi2_dmuS(self.dL_dpsi2,self.Z,self.X,self.X_uncertainty) + dL_dmu_psi0, dL_dS_psi0 = self.kern.dpsi1_dmuS(self.dL_dpsi1,self.Z,self.X,self.X_variance) + dL_dmu_psi1, dL_dS_psi1 = self.kern.dpsi0_dmuS(self.dL_dpsi0,self.Z,self.X,self.X_variance) + dL_dmu_psi2, dL_dS_psi2 = self.kern.dpsi2_dmuS(self.dL_dpsi2,self.Z,self.X,self.X_variance) dL_dmu = dL_dmu_psi0 + dL_dmu_psi1 + dL_dmu_psi2 dL_dS = dL_dS_psi0 + dL_dS_psi1 + dL_dS_psi2 - dKL_dS = (1. - (1./self.X_uncertainty))*0.5 + dKL_dS = (1. - (1./self.X_variance))*0.5 dKL_dmu = self.X return np.hstack(((dL_dmu - dKL_dmu).flatten(), (dL_dS - dKL_dS).flatten())) def KL_divergence(self): var_mean = np.square(self.X).sum() - var_S = np.sum(self.X_uncertainty - np.log(self.X_uncertainty)) + var_S = np.sum(self.X_variance - np.log(self.X_variance)) return 0.5*(var_mean + var_S) - 0.5*self.Q*self.N def log_likelihood(self): diff --git a/GPy/models/GP.py b/GPy/models/GP.py index 53ba1183..cfda0cfe 100644 --- a/GPy/models/GP.py +++ b/GPy/models/GP.py @@ -269,7 +269,7 @@ class GP(model): Zu = self.Z*self._Xstd + self._Xmean pb.plot(Zu,Zu*0+pb.ylim()[0],'r|',mew=1.5,markersize=12) if self.has_uncertain_inputs: - pb.errorbar(self.X[:,0], pb.ylim()[0]+np.zeros(self.N), xerr=2*np.sqrt(self.X_uncertainty.flatten())) + pb.errorbar(self.X[:,0], pb.ylim()[0]+np.zeros(self.N), xerr=2*np.sqrt(self.X_variance.flatten())) elif self.X.shape[1]==2: #FIXME resolution = resolution or 50 diff --git a/GPy/models/generalized_FITC.py b/GPy/models/generalized_FITC.py index 8c983b05..26875f64 100644 --- a/GPy/models/generalized_FITC.py +++ b/GPy/models/generalized_FITC.py @@ -19,8 +19,8 @@ class generalized_FITC(sparse_GP): :type likelihood: GPy.likelihood.(Gaussian | EP) :param kernel : the kernel/covariance function. See link kernels :type kernel: a GPy kernel - :param X_uncertainty: The uncertainty in the measurements of X (Gaussian variance) - :type X_uncertainty: np.ndarray (N x Q) | None + :param X_variance: The variance in the measurements of X (Gaussian variance) + :type X_variance: np.ndarray (N x Q) | None :param Z: inducing inputs (optional, see note) :type Z: np.ndarray (M x Q) | None :param Zslices: slices for the inducing inputs (see slicing TODO: link) @@ -30,13 +30,13 @@ class generalized_FITC(sparse_GP): :type normalize_(X|Y): bool """ - def __init__(self, X, likelihood, kernel, Z, X_uncertainty=None, Xslices=None,Zslices=None, normalize_X=False): + def __init__(self, X, likelihood, kernel, Z, X_variance=None, Xslices=None,Zslices=None, normalize_X=False): self.Z = Z self.M = self.Z.shape[0] self._precision = likelihood.precision - sparse_GP.__init__(self, X, likelihood, kernel=kernel, Z=self.Z, X_uncertainty=None, Xslices=None,Zslices=None, normalize_X=False) + sparse_GP.__init__(self, X, likelihood, kernel=kernel, Z=self.Z, X_variance=None, Xslices=None,Zslices=None, normalize_X=False) def _set_params(self, p): self.Z = p[:self.M*self.Q].reshape(self.M, self.Q) diff --git a/GPy/models/sparse_GP.py b/GPy/models/sparse_GP.py index 3d44ad6b..e19945e2 100644 --- a/GPy/models/sparse_GP.py +++ b/GPy/models/sparse_GP.py @@ -22,8 +22,8 @@ class sparse_GP(GP): :type likelihood: GPy.likelihood.(Gaussian | EP) :param kernel : the kernel/covariance function. See link kernels :type kernel: a GPy kernel - :param X_uncertainty: The uncertainty in the measurements of X (Gaussian variance) - :type X_uncertainty: np.ndarray (N x Q) | None + :param X_variance: The uncertainty in the measurements of X (Gaussian variance) + :type X_variance: np.ndarray (N x Q) | None :param Z: inducing inputs (optional, see note) :type Z: np.ndarray (M x Q) | None :param Zslices: slices for the inducing inputs (see slicing TODO: link) @@ -33,7 +33,7 @@ class sparse_GP(GP): :type normalize_(X|Y): bool """ - def __init__(self, X, likelihood, kernel, Z, X_uncertainty=None, Xslices=None,Zslices=None, normalize_X=False): + def __init__(self, X, likelihood, kernel, Z, X_variance=None, Xslices=None,Zslices=None, normalize_X=False): self.scale_factor = 100.0# a scaling factor to help keep the algorithm stable self.Z = Z @@ -42,12 +42,12 @@ class sparse_GP(GP): self.M = Z.shape[0] self.likelihood = likelihood - if X_uncertainty is None: + if X_variance is None: self.has_uncertain_inputs=False else: - assert X_uncertainty.shape==X.shape + assert X_variance.shape==X.shape self.has_uncertain_inputs=True - self.X_uncertainty = X_uncertainty + self.X_variance = X_variance if not self.likelihood.is_heteroscedastic: self.likelihood.trYYT = np.trace(np.dot(self.likelihood.Y, self.likelihood.Y.T)) # TODO: something more elegant here? @@ -56,16 +56,16 @@ class sparse_GP(GP): #normalize X uncertainty also if self.has_uncertain_inputs: - self.X_uncertainty /= np.square(self._Xstd) + self.X_variance /= np.square(self._Xstd) def _compute_kernel_matrices(self): # kernel computations, using BGPLVM notation self.Kmm = self.kern.K(self.Z) if self.has_uncertain_inputs: - self.psi0 = self.kern.psi0(self.Z,self.X, self.X_uncertainty) - self.psi1 = self.kern.psi1(self.Z,self.X, self.X_uncertainty).T - self.psi2 = self.kern.psi2(self.Z,self.X, self.X_uncertainty) + self.psi0 = self.kern.psi0(self.Z,self.X, self.X_variance) + self.psi1 = self.kern.psi1(self.Z,self.X, self.X_variance).T + self.psi2 = self.kern.psi2(self.Z,self.X, self.X_variance) else: self.psi0 = self.kern.Kdiag(self.X,slices=self.Xslices) self.psi1 = self.kern.K(self.Z,self.X) @@ -210,9 +210,9 @@ class sparse_GP(GP): """ dL_dtheta = self.kern.dK_dtheta(self.dL_dKmm,self.Z) if self.has_uncertain_inputs: - dL_dtheta += self.kern.dpsi0_dtheta(self.dL_dpsi0, self.Z,self.X,self.X_uncertainty) - dL_dtheta += self.kern.dpsi1_dtheta(self.dL_dpsi1.T,self.Z,self.X, self.X_uncertainty) - dL_dtheta += self.kern.dpsi2_dtheta(self.dL_dpsi2, self.Z,self.X, self.X_uncertainty) + dL_dtheta += self.kern.dpsi0_dtheta(self.dL_dpsi0, self.Z,self.X,self.X_variance) + dL_dtheta += self.kern.dpsi1_dtheta(self.dL_dpsi1.T,self.Z,self.X, self.X_variance) + dL_dtheta += self.kern.dpsi2_dtheta(self.dL_dpsi2, self.Z,self.X, self.X_variance) else: dL_dtheta += self.kern.dK_dtheta(self.dL_dpsi1,self.Z,self.X) dL_dtheta += self.kern.dKdiag_dtheta(self.dL_dpsi0, self.X) @@ -225,8 +225,8 @@ class sparse_GP(GP): """ dL_dZ = 2.*self.kern.dK_dX(self.dL_dKmm,self.Z)#factor of two becase of vertical and horizontal 'stripes' in dKmm_dZ if self.has_uncertain_inputs: - dL_dZ += self.kern.dpsi1_dZ(self.dL_dpsi1,self.Z,self.X, self.X_uncertainty) - dL_dZ += 2.*self.kern.dpsi2_dZ(self.dL_dpsi2,self.Z,self.X, self.X_uncertainty) # 'stripes' + dL_dZ += self.kern.dpsi1_dZ(self.dL_dpsi1,self.Z,self.X, self.X_variance) + dL_dZ += 2.*self.kern.dpsi2_dZ(self.dL_dpsi2,self.Z,self.X, self.X_variance) # 'stripes' else: dL_dZ += self.kern.dK_dX(self.dL_dpsi1,self.Z,self.X) return dL_dZ