merge with current GPy devel

GPy/kern/src/ODE_UY.py

@@ -4,7 +4,7 @@
 from .kern import Kern
 from .independent_outputs import index_to_slices
 from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
+from paramz.transformations import Logexp
 import numpy as np
 
 class ODE_UY(Kern):

GPy/kern/src/ODE_UYC.py

@@ -3,7 +3,7 @@
 
 from .kern import Kern
 from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
+from paramz.transformations import Logexp
 import numpy as np
 from .independent_outputs import index_to_slices
 

GPy/kern/src/ODE_st.py

@@ -2,7 +2,7 @@
 # Licensed under the BSD 3-clause license (see LICENSE.txt)
 from .kern import Kern
 from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
+from paramz.transformations import Logexp
 import numpy as np
 from .independent_outputs import index_to_slices
 

GPy/kern/src/ODE_t.py

@@ -1,6 +1,6 @@
 from .kern import Kern
 from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
+from paramz.transformations import Logexp
 import numpy as np
 from .independent_outputs import index_to_slices
 

GPy/kern/src/add.py

@@ -3,7 +3,7 @@
 
 import numpy as np
 import itertools
-from ...util.caching import Cache_this
+from paramz.caching import Cache_this
 from .kern import CombinationKernel, Kern
 from functools import reduce
 

GPy/kern/src/basis_funcs.py

@@ -3,8 +3,8 @@
 import numpy as np
 from .kern import Kern
 from ...core.parameterization.param import Param
-from ...core.parameterization.transformations import Logexp
-from ...util.caching import Cache_this
+from paramz.transformations import Logexp
+from paramz.caching import Cache_this
 from ...util.linalg import tdot, mdot
 
 class BasisFuncKernel(Kern):

GPy/kern/src/brownian.py

@@ -3,7 +3,7 @@
 
 from .kern import Kern
 from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
+from paramz.transformations import Logexp
 import numpy as np
 
 class Brownian(Kern):

GPy/kern/src/coregionalize.py

@@ -4,7 +4,7 @@
 from .kern import Kern
 import numpy as np
 from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
+from paramz.transformations import Logexp
 from ...util.config import config # for assesing whether to use cython
 try:
     from . import coregionalize_cython

GPy/kern/src/eq_ode2.py

@@ -5,8 +5,8 @@ import numpy as np
 from scipy.special import wofz
 from .kern import Kern
 from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
-from ...util.caching import Cache_this
+from paramz.transformations import Logexp
+from paramz.caching import Cache_this
 
 class EQ_ODE2(Kern):
     """

GPy/kern/src/kern.py

@@ -3,8 +3,8 @@
 import sys
 import numpy as np
 from ...core.parameterization.parameterized import Parameterized
-from ...core.parameterization.observable_array import ObsAr
-from ...util.caching import Cache_this
+from paramz.core.observable_array import ObsAr
+from paramz.caching import Cache_this
 from .kernel_slice_operations import KernCallsViaSlicerMeta
 from functools import reduce
 import six
@@ -30,18 +30,16 @@ class Kern(Parameterized):
             tight dimensionality of inputs.
             You most likely want this to be the integer telling the number of
             input dimensions of the kernel.
-            If this is not an integer (!) we will work on the whole input matrix X,
-            and not check whether dimensions match or not (!).
 
-        _all_dims_active:
+        active_dims:
 
             is the active_dimensions of inputs X we will work on.
             All kernels will get sliced Xes as inputs, if _all_dims_active is not None
-            Only positive integers are allowed in _all_dims_active!
-            if _all_dims_active is None, slicing is switched off and all X will be passed through as given.
+            Only positive integers are allowed in active_dims!
+            if active_dims is None, slicing is switched off and all X will be passed through as given.
 
         :param int input_dim: the number of input dimensions to the function
-        :param array-like|None _all_dims_active: list of indices on which dimensions this kernel works on, or none if no slicing
+        :param array-like|None active_dims: list of indices on which dimensions this kernel works on, or none if no slicing
 
         Do not instantiate.
         """
@@ -60,7 +58,11 @@ class Kern(Parameterized):
         self.useGPU = self._support_GPU and useGPU
 
         from .psi_comp import PSICOMP_GH
-        self.psicomp = PSICOMP_GH()        
+        self.psicomp = PSICOMP_GH()
+
+    def __setstate__(self, state):
+        self._all_dims_active = range(0, max(state['active_dims'])+1)
+        super(Kern, self).__setstate__(state)
 
     @property
     def _effective_input_dim(self):
@@ -211,15 +213,15 @@ class Kern(Parameterized):
     def get_most_significant_input_dimensions(self, which_indices=None):
         """
         Determine which dimensions should be plotted
-        
+
         Returns the top three most signification input dimensions
-        
+
         if less then three dimensions, the non existing dimensions are
         labeled as None, so for a 1 dimensional input this returns
         (0, None, None).
-        
-        :param which_indices: force the indices to be the given indices. 
-        :type which_indices: int or tuple(int,int) or tuple(int,int,int) 
+
+        :param which_indices: force the indices to be the given indices.
+        :type which_indices: int or tuple(int,int) or tuple(int,int,int)
         """
         if which_indices is None:
             which_indices = np.argsort(self.input_sensitivity())[::-1][:3]
@@ -235,7 +237,7 @@ class Kern(Parameterized):
                 input_1, input_2 = which_indices, None
             except ValueError:
                 # which_indices was a list or array like with only one int
-                input_1, input_2 = which_indices[0], None            
+                input_1, input_2 = which_indices[0], None
         return input_1, input_2, input_3
 
 

GPy/kern/src/kernel_slice_operations.py

@@ -7,9 +7,9 @@ This module provides a meta class for the kernels. The meta class is for
 slicing the inputs (X, X2) for the kernels, before K (or any other method involving X)
 gets calls. The `_all_dims_active` of a kernel decide which dimensions the kernel works on.
 '''
-from ...core.parameterization.parameterized import ParametersChangedMeta
 import numpy as np
 from functools import wraps
+from paramz.parameterized import ParametersChangedMeta
 
 def put_clean(dct, name, func):
     if name in dct:

GPy/kern/src/linear.py

@@ -6,8 +6,8 @@ import numpy as np
 from .kern import Kern
 from ...util.linalg import tdot
 from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
-from ...util.caching import Cache_this
+from paramz.transformations import Logexp
+from paramz.caching import Cache_this
 from .psi_comp import PSICOMP_Linear
 
 class Linear(Kern):

GPy/kern/src/mlp.py

@@ -3,9 +3,9 @@
 
 from .kern import Kern
 from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
+from paramz.transformations import Logexp
 import numpy as np
-from ...util.caching import Cache_this
+from paramz.caching import Cache_this
 four_over_tau = 2./np.pi
 
 class MLP(Kern):

GPy/kern/src/periodic.py

@@ -7,7 +7,7 @@ from .kern import Kern
 from ...util.linalg import mdot
 from ...util.decorators import silence_errors
 from ...core.parameterization.param import Param
-from ...core.parameterization.transformations import Logexp
+from paramz.transformations import Logexp
 
 class Periodic(Kern):
     def __init__(self, input_dim, variance, lengthscale, period, n_freq, lower, upper, active_dims, name):

GPy/kern/src/poly.py

@@ -4,7 +4,8 @@
 import numpy as np
 from .kern import Kern
 from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
+from paramz.transformations import Logexp
+
 class Poly(Kern):
     """
     Polynomial kernel

GPy/kern/src/prod.py

@@ -3,7 +3,7 @@
 
 import numpy as np
 from .kern import CombinationKernel
-from ...util.caching import Cache_this
+from paramz.caching import Cache_this
 import itertools
 from functools import reduce
 

GPy/kern/src/psi_comp/__init__.py

@@ -1,9 +1,9 @@
 # Copyright (c) 2012, GPy authors (see AUTHORS.txt).
 # Licensed under the BSD 3-clause license (see LICENSE.txt)
 
-from ....core.parameterization.parameter_core import Pickleable
-from ....util.caching import Cache_this
-from ....core.parameterization import variational
+from paramz.core.pickleable import Pickleable
+from paramz.caching import Cache_this
+from GPy.core.parameterization import variational
 #from linear_psi_comp import LINEAr
 
 class PSICOMP(Pickleable):

GPy/kern/src/psi_comp/gaussherm.py

@@ -8,7 +8,7 @@ An approximated psi-statistics implementation based on Gauss-Hermite Quadrature
 import numpy as np
 
 from ....core.parameterization import Param
-from ....util.caching import Cache_this
+from paramz.caching import Cache_this
 from ....util.linalg import tdot
 from . import PSICOMP
 
@@ -30,7 +30,7 @@ class PSICOMP_GH(PSICOMP):
     @Cache_this(limit=10, ignore_args=(0,))
     def comp_K(self, Z, qX):
         if self.Xs is None or self.Xs.shape != qX.mean.shape:
-            from ....core.parameterization import ObsAr
+            from paramz import ObsAr
             self.Xs = ObsAr(np.empty((self.degree,)+qX.mean.shape))
         mu, S = qX.mean.values, qX.variance.values
         S_sq = np.sqrt(S)

GPy/kern/src/psi_comp/rbf_psi_comp.py

@@ -3,7 +3,7 @@ The module for psi-statistics for RBF kernel
 """
 
 import numpy as np
-from GPy.util.caching import Cacher
+from paramz.caching import Cacher
 
 def psicomputations(variance, lengthscale, Z, variational_posterior, return_psi2_n=False):
     # here are the "statistics" for psi0, psi1 and psi2

GPy/kern/src/psi_comp/rbf_psi_gpucomp.py

@@ -3,7 +3,7 @@ The module for psi-statistics for RBF kernel
 """
 
 import numpy as np
-from ....util.caching import Cache_this
+from paramz.caching import Cache_this
 from . import PSICOMP_RBF
 from ....util import gpu_init
 

GPy/kern/src/psi_comp/ssrbf_psi_gpucomp.py

@@ -4,7 +4,7 @@ The module for psi-statistics for RBF kernel for Spike-and-Slab GPLVM
 """
 
 import numpy as np
-from ....util.caching import Cache_this
+from paramz.caching import Cache_this
 from . import PSICOMP_RBF
 
 

GPy/kern/src/rbf.py

@@ -6,7 +6,7 @@ import numpy as np
 from .stationary import Stationary
 from .psi_comp import PSICOMP_RBF, PSICOMP_RBF_GPU
 from ...core import Param
-from ...core.parameterization.transformations import Logexp
+from paramz.transformations import Logexp
 
 class RBF(Stationary):
     """
@@ -47,12 +47,13 @@ class RBF(Stationary):
         return dc
 
     def __setstate__(self, state):
+        self.use_invLengthscale = False
         return super(RBF, self).__setstate__(state)
 
     def spectrum(self, omega):
         assert self.input_dim == 1 #TODO: higher dim spectra?
         return self.variance*np.sqrt(2*np.pi)*self.lengthscale*np.exp(-self.lengthscale*2*omega**2/2)
-    
+
     def parameters_changed(self):
         if self.use_invLengthscale: self.lengthscale[:] = 1./np.sqrt(self.inv_l+1e-200)
         super(RBF,self).parameters_changed()
@@ -85,7 +86,7 @@ class RBF(Stationary):
 
     def gradients_qX_expectations(self, dL_dpsi0, dL_dpsi1, dL_dpsi2, Z, variational_posterior):
         return self.psicomp.psiDerivativecomputations(self, dL_dpsi0, dL_dpsi1, dL_dpsi2, Z, variational_posterior)[3:]
-    
+
     def update_gradients_diag(self, dL_dKdiag, X):
         super(RBF,self).update_gradients_diag(dL_dKdiag, X)
         if self.use_invLengthscale: self.inv_l.gradient =self.lengthscale.gradient*(self.lengthscale**3/-2.)

GPy/kern/src/spline.py

@@ -4,7 +4,7 @@
 import numpy as np
 from .kern import Kern
 from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
+from paramz.transformations import Logexp
 
 class Spline(Kern):
     """

GPy/kern/src/standard_periodic.py

@@ -15,7 +15,7 @@ Neural Networks and Machine Learning, pages 133-165. Springer, 1998.
 
 from .kern import Kern
 from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
+from paramz.transformations import Logexp
 
 import numpy as np
 

GPy/kern/src/static.py

@@ -5,7 +5,7 @@
 from .kern import Kern
 import numpy as np
 from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
+from paramz.transformations import Logexp
 
 class Static(Kern):
     def __init__(self, input_dim, variance, active_dims, name):

GPy/kern/src/stationary.py

@@ -2,15 +2,15 @@
 # Licensed under the BSD 3-clause license (see LICENSE.txt)
 
 
-from .kern import Kern
-from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
-from ...util.linalg import tdot
-from ... import util
 import numpy as np
 from scipy import integrate
+from .kern import Kern
+from ...core.parameterization import Param
+from ...util.linalg import tdot
+from ... import util
 from ...util.config import config # for assesing whether to use cython
-from ...util.caching import Cache_this
+from paramz.caching import Cache_this
+from paramz.transformations import Logexp
 
 try:
     from . import stationary_cython

GPy/kern/src/trunclinear.py

@@ -5,8 +5,8 @@
 import numpy as np
 from .kern import Kern
 from ...core.parameterization import Param
-from ...core.parameterization.transformations import Logexp
-from ...util.caching import Cache_this
+from paramz.transformations import Logexp
+from paramz.caching import Cache_this
 
 class TruncLinear(Kern):
     """