From 683f45366b451298e03e1cb839ff50fd1312bdd0 Mon Sep 17 00:00:00 2001 From: James Hensman Date: Thu, 24 Oct 2013 21:58:51 +0100 Subject: [PATCH] some tidying in gp.py --- GPy/core/gp.py | 21 +++--- GPy/core/sparse_gp.py | 168 ++++-------------------------------------- 2 files changed, 22 insertions(+), 167 deletions(-) diff --git a/GPy/core/gp.py b/GPy/core/gp.py index 67eb7c69..2ea09117 100644 --- a/GPy/core/gp.py +++ b/GPy/core/gp.py @@ -27,12 +27,6 @@ class GP(GPBase): GPBase.__init__(self, X, likelihood, kernel, normalize_X=normalize_X) self._set_params(self._get_params()) - def getstate(self): - return GPBase.getstate(self) - - def setstate(self, state): - GPBase.setstate(self, state) - self._set_params(self._get_params()) def _set_params(self, p): self.kern._set_params_transformed(p[:self.kern.num_params_transformed()]) @@ -101,12 +95,7 @@ class GP(GPBase): Note, we use the chain rule: dL_dtheta = dL_dK * d_K_dtheta """ - #return np.hstack((self.kern.dK_dtheta(dL_dK=self.dL_dK, X=self.X), self.likelihood._gradients(partial=np.diag(self.dL_dK)))) - if not isinstance(self.likelihood,EP): - tmp = np.hstack((self.kern.dK_dtheta(dL_dK=self.dL_dK, X=self.X), self.likelihood._gradients(partial=np.diag(self.dL_dK)))) - else: - tmp = np.hstack((self.kern.dK_dtheta(dL_dK=self.dL_dK, X=self.X), self.likelihood._gradients(partial=np.diag(self.dL_dK)))) - return tmp + return np.hstack((self.kern.dK_dtheta(dL_dK=self.dL_dK, X=self.X), self.likelihood._gradients(partial=np.diag(self.dL_dK)))) def _raw_predict(self, _Xnew, which_parts='all', full_cov=False, stop=False): """ @@ -193,3 +182,11 @@ class GP(GPBase): """ Xnew = self._add_output_index(Xnew, output) return self.predict(Xnew, which_parts=which_parts, full_cov=full_cov, likelihood_args=likelihood_args) + + def getstate(self): + return GPBase.getstate(self) + + def setstate(self, state): + GPBase.setstate(self, state) + self._set_params(self._get_params()) + diff --git a/GPy/core/sparse_gp.py b/GPy/core/sparse_gp.py index 9251fcd6..8c8df30c 100644 --- a/GPy/core/sparse_gp.py +++ b/GPy/core/sparse_gp.py @@ -52,23 +52,6 @@ class SparseGP(GPBase): self._const_jitter = None - def getstate(self): - """ - Get the current state of the class, - here just all the indices, rest can get recomputed - """ - return GPBase.getstate(self) + [self.Z, - self.num_inducing, - self.has_uncertain_inputs, - self.X_variance] - - def setstate(self, state): - self.X_variance = state.pop() - self.has_uncertain_inputs = state.pop() - self.num_inducing = state.pop() - self.Z = state.pop() - GPBase.setstate(self, state) - def _compute_kernel_matrices(self): # kernel computations, using BGPLVM notation self.Kmm = self.kern.K(self.Z) @@ -87,7 +70,6 @@ class SparseGP(GPBase): # factor Kmm self._Lm = jitchol(self.Kmm + self._const_jitter) - # TODO: no white kernel needed anymore, all noise in likelihood -------- # The rather complex computations of self._A if self.has_uncertain_inputs: @@ -421,145 +403,21 @@ class SparseGP(GPBase): else: raise NotImplementedError, "Cannot define a frame with more than two input dimensions" - def predict_single_output(self, Xnew, output=0, which_parts='all', full_cov=False): + def getstate(self): """ - For a specific output, predict the function at the new point(s) Xnew. - - :param Xnew: The points at which to make a prediction - :type Xnew: np.ndarray, Nnew x self.input_dim - :param output: output to predict - :type output: integer in {0,..., num_outputs-1} - :param which_parts: specifies which outputs kernel(s) to use in prediction - :type which_parts: ('all', list of bools) - :param full_cov: whether to return the full covariance matrix, or just the diagonal - :type full_cov: bool - :rtype: posterior mean, a Numpy array, Nnew x self.input_dim - :rtype: posterior variance, a Numpy array, Nnew x 1 if full_cov=False, Nnew x Nnew otherwise - :rtype: lower and upper boundaries of the 95% confidence intervals, Numpy arrays, Nnew x self.input_dim - - .. Note:: For multiple output models only + Get the current state of the class, + here just all the indices, rest can get recomputed """ + return GPBase.getstate(self) + [self.Z, + self.num_inducing, + self.has_uncertain_inputs, + self.X_variance] - assert hasattr(self,'multioutput') - index = np.ones_like(Xnew)*output - Xnew = np.hstack((Xnew,index)) - - # normalize X values - Xnew = (Xnew.copy() - self._Xoffset) / self._Xscale - mu, var = self._raw_predict(Xnew, full_cov=full_cov, which_parts=which_parts) - - # now push through likelihood - mean, var, _025pm, _975pm = self.likelihood.predictive_values(mu, var, full_cov, noise_model = output) - return mean, var, _025pm, _975pm - - def _raw_predict_single_output(self, _Xnew, output=0, X_variance_new=None, which_parts='all', full_cov=False,stop=False): - """ - Internal helper function for making predictions for a specific output, - does not account for normalization or likelihood - --------- - - :param Xnew: The points at which to make a prediction - :type Xnew: np.ndarray, Nnew x self.input_dim - :param output: output to predict - :type output: integer in {0,..., num_outputs-1} - :param which_parts: specifies which outputs kernel(s) to use in prediction - :type which_parts: ('all', list of bools) - :param full_cov: whether to return the full covariance matrix, or just the diagonal - - .. Note:: For multiple output models only - """ - Bi, _ = dpotri(self.LB, lower=0) # WTH? this lower switch should be 1, but that doesn't work! - symmetrify(Bi) - Kmmi_LmiBLmi = backsub_both_sides(self._Lm, np.eye(self.num_inducing) - Bi) - - if self.Cpsi1V is None: - psi1V = np.dot(self.psi1.T,self.likelihood.V) - tmp, _ = dtrtrs(self._Lm, np.asfortranarray(psi1V), lower=1, trans=0) - tmp, _ = dpotrs(self.LB, tmp, lower=1) - self.Cpsi1V, _ = dtrtrs(self._Lm, tmp, lower=1, trans=1) - - assert hasattr(self,'multioutput') - index = np.ones_like(_Xnew)*output - _Xnew = np.hstack((_Xnew,index)) - - if X_variance_new is None: - Kx = self.kern.K(self.Z, _Xnew, which_parts=which_parts) - mu = np.dot(Kx.T, self.Cpsi1V) - if full_cov: - Kxx = self.kern.K(_Xnew, which_parts=which_parts) - var = Kxx - mdot(Kx.T, Kmmi_LmiBLmi, Kx) # NOTE this won't work for plotting - else: - Kxx = self.kern.Kdiag(_Xnew, which_parts=which_parts) - var = Kxx - np.sum(Kx * np.dot(Kmmi_LmiBLmi, Kx), 0) - else: - Kx = self.kern.psi1(self.Z, _Xnew, X_variance_new) - mu = np.dot(Kx, self.Cpsi1V) - if full_cov: - raise NotImplementedError, "TODO" - else: - Kxx = self.kern.psi0(self.Z, _Xnew, X_variance_new) - psi2 = self.kern.psi2(self.Z, _Xnew, X_variance_new) - var = Kxx - np.sum(np.sum(psi2 * Kmmi_LmiBLmi[None, :, :], 1), 1) - - return mu, var[:, None] + def setstate(self, state): + self.X_variance = state.pop() + self.has_uncertain_inputs = state.pop() + self.num_inducing = state.pop() + self.Z = state.pop() + GPBase.setstate(self, state) - def plot_single_output_f(self, output=None, samples=0, plot_limits=None, which_data='all', which_parts='all', resolution=None, full_cov=False, fignum=None, ax=None): - - if ax is None: - fig = pb.figure(num=fignum) - ax = fig.add_subplot(111) - if fignum is None and ax is None: - fignum = fig.num - if which_data is 'all': - which_data = slice(None) - - GPBase.plot_single_output_f(self, output=output, samples=samples, plot_limits=plot_limits, which_data='all', which_parts='all', resolution=resolution, full_cov=full_cov, fignum=fignum, ax=ax) - - if self.X.shape[1] == 2: - if self.has_uncertain_inputs: - Xu = self.X * self._Xscale + self._Xoffset # NOTE self.X are the normalized values now - ax.errorbar(Xu[which_data, 0], self.likelihood.data[which_data, 0], - xerr=2 * np.sqrt(self.X_variance[which_data, 0]), - ecolor='k', fmt=None, elinewidth=.5, alpha=.5) - Zu = self.Z * self._Xscale + self._Xoffset - Zu = Zu[Zu[:,1]==output,0:1] - ax.plot(Zu[:,0], np.zeros_like(Zu[:,0]) + ax.get_ylim()[0], 'r|', mew=1.5, markersize=12) - - elif self.X.shape[1] == 2: - Zu = self.Z * self._Xscale + self._Xoffset - Zu = Zu[Zu[:,1]==output,0:2] - ax.plot(Zu[:, 0], Zu[:, 1], 'wo') - - - else: - raise NotImplementedError, "Cannot define a frame with more than two input dimensions" - - def plot_single_output(self, output=None, samples=0, plot_limits=None, which_data='all', which_parts='all', resolution=None, levels=20, fignum=None, ax=None): - if ax is None: - fig = pb.figure(num=fignum) - ax = fig.add_subplot(111) - if fignum is None and ax is None: - fignum = fig.num - if which_data is 'all': - which_data = slice(None) - - GPBase.plot_single_output(self, samples=samples, plot_limits=plot_limits, which_data='all', which_parts='all', resolution=resolution, levels=20, fignum=fignum, ax=ax, output=output) - - if self.X.shape[1] == 2: - if self.has_uncertain_inputs: - Xu = self.X * self._Xscale + self._Xoffset # NOTE self.X are the normalized values now - ax.errorbar(Xu[which_data, 0], self.likelihood.data[which_data, 0], - xerr=2 * np.sqrt(self.X_variance[which_data, 0]), - ecolor='k', fmt=None, elinewidth=.5, alpha=.5) - Zu = self.Z * self._Xscale + self._Xoffset - Zu = Zu[Zu[:,1]==output,0:1] - ax.plot(Zu, np.zeros_like(Zu) + ax.get_ylim()[0], 'r|', mew=1.5, markersize=12) - - elif self.X.shape[1] == 3: - Zu = self.Z * self._Xscale + self._Xoffset - Zu = Zu[Zu[:,1]==output,0:1] - ax.plot(Zu[:, 0], Zu[:, 1], 'wo') - - else: - raise NotImplementedError, "Cannot define a frame with more than two input dimensions"