merged and updated slicing operations

GPy/core/gp.py

@@ -216,15 +216,16 @@ class GP(Model):
 
         """
 
-        return Model._getstate(self) + [self.X,
-                self.num_data,
-                self.input_dim,
-                self.kern,
-                self.likelihood,
-                self.output_dim,
-                ]
+        return []#Model._getstate(self) + [self.X,
+#                 self.num_data,
+#                 self.input_dim,
+#                 self.kern,
+#                 self.likelihood,
+#                 self.output_dim,
+#                 ]
 
     def _setstate(self, state):
+        return 
         self.output_dim = state.pop()
         self.likelihood = state.pop()
         self.kern = state.pop()

GPy/core/parameterization/lists_and_dicts.py

@@ -28,4 +28,11 @@ class ArrayList(list):
                 return True
         return False
 
+    def index(self, item):
+        index = 0
+        for el in self:
+            if el is item:
+                return index
+            index += 1
+        raise ValueError, "{} is not in list".format(item)
     pass

GPy/core/parameterization/parameter_core.py

@@ -902,15 +902,19 @@ class Parameterizable(OptimizationHandlable):
     #===========================================================================
     def copy(self):
         """Returns a (deep) copy of the current model"""
-        raise NotImplementedError, "Copy is not yet implemented, TODO: Observable hierarchy"
+        #raise NotImplementedError, "Copy is not yet implemented, TODO: Observable hierarchy"
         import copy
         from .index_operations import ParameterIndexOperations, ParameterIndexOperationsView
         from .lists_and_dicts import ArrayList
         
+        param_mapping = [[] for _ in range(self.num_params)]
+
         dc = dict()
         for k, v in self.__dict__.iteritems():
             if k not in ['_parent_', '_parameters_', '_parent_index_', '_observer_callables_'] + self.parameter_names(recursive=False):
-                if isinstance(v, (Constrainable, ParameterIndexOperations, ParameterIndexOperationsView)):
+                if v in self._parameters_:
+                    param_mapping[self._parameters_.index(v)] += [k]
+                elif isinstance(v, (Constrainable, ParameterIndexOperations, ParameterIndexOperationsView)):
                     dc[k] = v.copy()
                 else:
                     dc[k] = copy.deepcopy(v)
@@ -928,9 +932,10 @@ class Parameterizable(OptimizationHandlable):
         s = self.__new__(self.__class__)
         s.__dict__ = dc
 
-        for p in params:
+        for p, mlist in zip(params, param_mapping):
             s.add_parameter(p, _ignore_added_names=True)
-
+            for m in mlist:
+                setattr(s, m, p)
         return s
 
     #===========================================================================

GPy/core/parameterization/parameterized.py

@@ -110,29 +110,15 @@ class Parameterized(Parameterizable, Pickleable):
         Allways append the state of the inherited object
         and call down to the inherited object in _setstate!!
         """
-        return [
-                self._fixes_,
-                self.priors,
-                self.constraints,
-                self._parameters_,
-                self._name,
-                self._added_names_,
-                ]
+        return []
 
     def _setstate(self, state):
-        self._added_names_ = state.pop()
-        self._name = state.pop()
-        self._parameters_ = state.pop()
-        self.constraints = state.pop()
-        self.priors = state.pop()
-        self._fixes_ = state.pop()
-        self._connect_parameters()
         self.parameters_changed()
     #===========================================================================
     # Override copy to handle programmatically added observers
     #===========================================================================
     def copy(self):
-        c = super(Pickleable, self).copy()
+        c = super(Parameterized, self).copy()
         c.add_observer(c, c._parameters_changed_notification, -100)
         return c
 

GPy/kern/__init__.py

@@ -1,6 +1,6 @@
 from _src.kern import Kern
 from _src.rbf import RBF
-from _src.linear import Linear
+from _src.linear import Linear, LinearFull
 from _src.static import Bias, White
 from _src.brownian import Brownian
 from _src.sympykern import Sympykern

GPy/kern/_src/kernel_slice_operations.py

@@ -5,29 +5,26 @@ Created on 11 Mar 2014
 '''
 from ...core.parameterization.parameterized import ParametersChangedMeta
 import numpy as np
-import functools
+
+def put_clean(dct, name, *args, **kw):
+    if name in dct:
+        dct['_clean_{}'.format(name)] = dct[name]
+        dct[name] = _slice_wrapper(None, dct[name], *args, **kw)
     
 class KernCallsViaSlicerMeta(ParametersChangedMeta):
-    def __call__(self, *args, **kw):
-        instance = super(ParametersChangedMeta, self).__call__(*args, **kw)
-        instance.K = _Slice_wrapper(instance, instance.K)
-        instance.Kdiag = _Slice_wrapper_diag(instance, instance.Kdiag)
-
-        instance.update_gradients_full = _Slice_wrapper_derivative(instance, instance.update_gradients_full)
-        instance.update_gradients_diag = _Slice_wrapper_diag_derivative(instance, instance.update_gradients_diag)
-
-        instance.gradients_X = _Slice_wrapper_grad_X(instance, instance.gradients_X)
-        instance.gradients_X_diag = _Slice_wrapper_grad_X_diag(instance, instance.gradients_X_diag)
-
-        instance.psi0 = _Slice_wrapper(instance, instance.psi0)
-        instance.psi1 = _Slice_wrapper(instance, instance.psi1)
-        instance.psi2 = _Slice_wrapper(instance, instance.psi2)
-
-        instance.update_gradients_expectations = _Slice_wrapper_psi_stat_derivative_no_ret(instance, instance.update_gradients_expectations)
-        instance.gradients_Z_expectations = _Slice_wrapper_psi_stat_derivative_Z(instance, instance.gradients_Z_expectations)
-        instance.gradients_qX_expectations = _Slice_wrapper_psi_stat_derivative(instance, instance.gradients_qX_expectations)
-        instance.parameters_changed()
-        return instance
+    def __new__(cls, name, bases, dct):
+        put_clean(dct, 'K')
+        put_clean(dct, 'Kdiag', diag=True)
+        put_clean(dct, 'update_gradients_full', diag=False, derivative=True)
+        put_clean(dct, 'gradients_X', diag=False, derivative=True, ret_X=True)
+        put_clean(dct, 'gradients_X_diag', diag=True, derivative=True, ret_X=True)
+        put_clean(dct, 'psi0', diag=False, derivative=False)
+        put_clean(dct, 'psi1', diag=False, derivative=False)
+        put_clean(dct, 'psi2', diag=False, derivative=False)
+        put_clean(dct, 'update_gradients_expectations', derivative=True, psi_stat=True)
+        put_clean(dct, 'gradients_Z_expectations', derivative=True, psi_stat_Z=True, ret_X=True)
+        put_clean(dct, 'gradients_qX_expectations', derivative=True, psi_stat=True, ret_X=True)
+        return super(KernCallsViaSlicerMeta, cls).__new__(cls, name, bases, dct)
     
 class _Slice_wrap(object):
     def __init__(self, instance, f):

GPy/kern/_src/linear.py

@@ -313,3 +313,47 @@ class Linear(Kern):
 
     def input_sensitivity(self):
         return np.ones(self.input_dim) * self.variances
+
+class LinearFull(Kern):
+    def __init__(self, input_dim, rank, W=None, kappa=None, active_dims=None, name='linear_full'):
+        super(LinearFull, self).__init__(input_dim, active_dims, name)
+        if W is None:
+            W = np.ones((input_dim, rank))
+        if kappa is None:
+            kappa = np.ones(input_dim)
+        assert W.shape == (input_dim, rank)
+        assert kappa.shape == (input_dim,)
+
+        self.W = Param('W', W)
+        self.kappa = Param('kappa', kappa, Logexp())
+        self.add_parameters(self.W, self.kappa)
+
+    def K(self, X, X2=None):
+        P = np.dot(self.W, self.W.T) + np.diag(self.kappa)
+        return np.einsum('ij,jk,lk->il', X, P, X if X2 is None else X2)
+
+    def update_gradients_full(self, dL_dK, X, X2=None):
+        self.kappa.gradient = np.einsum('ij,ik,kj->j', X, dL_dK, X if X2 is None else X2)
+        self.W.gradient = np.einsum('ij,kl,ik,lm->jm', X, X if X2 is None else X2, dL_dK, self.W)
+        self.W.gradient += np.einsum('ij,kl,ik,jm->lm', X, X if X2 is None else X2, dL_dK, self.W)
+
+    def Kdiag(self, X):
+        P = np.dot(self.W, self.W.T) + np.diag(self.kappa)
+        return np.einsum('ij,jk,ik->i', X, P, X)
+
+    def update_gradients_diag(self, dL_dKdiag, X):
+        self.kappa.gradient = np.einsum('ij,i->j', np.square(X), dL_dKdiag)
+        self.W.gradient = 2.*np.einsum('ij,ik,jl,i->kl', X, X, self.W, dL_dKdiag)
+
+    def gradients_X(self, dL_dK, X, X2=None):
+        P = np.dot(self.W, self.W.T) + np.diag(self.kappa)
+        if X2 is None:
+            return 2.*np.einsum('ij,jk,kl->il', dL_dK, X, P)
+        else:
+            return np.einsum('ij,jk,kl->il', dL_dK, X2, P)
+
+    def gradients_X_diag(self, dL_dKdiag, X):
+        P = np.dot(self.W, self.W.T) + np.diag(self.kappa)
+        return 2.*np.einsum('jk,i,ij->ik', P, dL_dKdiag, X)
+
+

GPy/testing/kernel_tests.py

@@ -288,6 +288,11 @@ class KernelGradientTestsContinuous(unittest.TestCase):
         k.randomize()
         self.assertTrue(check_kernel_gradient_functions(k, X=self.X, X2=self.X2, verbose=verbose))
 
+    def test_LinearFull(self):
+        k = GPy.kern.LinearFull(self.D, self.D-1)
+        k.randomize()
+        self.assertTrue(check_kernel_gradient_functions(k, X=self.X, X2=self.X2, verbose=verbose))
+
 #TODO: turn off grad checkingwrt X for indexed kernels like coregionalize
 # class KernelGradientTestsContinuous1D(unittest.TestCase):
 #     def setUp(self):

GPy/util/caching.py

@@ -48,7 +48,7 @@ class Cacher(object):
                 if k in kw and kw[k] is not None:
                     return self.operation(*args, **kw)
         # TODO: WARNING !!! Cache OFFSWITCH !!! WARNING
-        #return self.operation(*args)
+        # return self.operation(*args, **kw)
 
         #if the result is cached, return the cached computation
         state = [all(a is b for a, b in itertools.izip_longest(args, cached_i)) for cached_i in self.cached_inputs]