Merge branch 'linK_functions2' into devel

Conflicts:
	GPy/core/gp.py
	GPy/core/gp_base.py
	GPy/core/sparse_gp.py
	GPy/examples/regression.py
	GPy/kern/constructors.py
	GPy/kern/parts/coregionalise.py
	GPy/models/__init__.py
	GPy/models/sparse_gp_classification.py
	GPy/util/__init__.py

GPy/models/__init__.py

@@ -14,3 +14,5 @@ from warped_gp import WarpedGP
 from bayesian_gplvm import BayesianGPLVM
 from mrd import MRD
 from gradient_checker import GradientChecker
+from gp_multioutput_regression import GPMultioutputRegression
+from sparse_gp_multioutput_regression import SparseGPMultioutputRegression

GPy/models/fitc_classification.py

@@ -31,8 +31,8 @@ class FITCClassification(FITC):
             kernel = kern.rbf(X.shape[1]) + kern.white(X.shape[1],1e-3)
 
         if likelihood is None:
-            distribution = likelihoods.likelihood_functions.Binomial()
-            likelihood = likelihoods.EP(Y, distribution)
+            noise_model = likelihoods.binomial()
+            likelihood = likelihoods.EP(Y, noise_model)
         elif Y is not None:
             if not all(Y.flatten() == likelihood.data.flatten()):
                 raise Warning, 'likelihood.data and Y are different.'

GPy/models/gp_classification.py

@@ -31,8 +31,8 @@ class GPClassification(GP):
             kernel = kern.rbf(X.shape[1])
 
         if likelihood is None:
-            distribution = likelihoods.likelihood_functions.Binomial()
-            likelihood = likelihoods.EP(Y, distribution)
+            noise_model = likelihoods.binomial()
+            likelihood = likelihoods.EP(Y, noise_model)
         elif Y is not None:
             if not all(Y.flatten() == likelihood.data.flatten()):
                 raise Warning, 'likelihood.data and Y are different.'

GPy/models/gp_multioutput_regression.py

@@ -0,0 +1,59 @@
+# Copyright (c) 2013, Ricardo Andrade
+# Licensed under the BSD 3-clause license (see LICENSE.txt)
+
+
+import numpy as np
+from ..core import GP
+from .. import likelihoods
+from .. import kern
+from ..util import multioutput
+
+class GPMultioutputRegression(GP):
+    """
+    Multiple output Gaussian process with Gaussian noise
+
+    This is a wrapper around the models.GP class, with a set of sensible defaults
+
+    :param X_list: input observations
+    :type X_list: list of numpy arrays (num_data_output_i x input_dim), one array per output
+    :param Y_list: observed values
+    :type Y_list: list of numpy arrays (num_data_output_i x 1), one array per output
+    :param kernel_list: GPy kernels, defaults to rbf
+    :type kernel_list: list of GPy kernels
+    :param noise_variance_list: noise parameters per output, defaults to 1.0 for every output
+    :type noise_variance_list: list of floats
+    :param normalize_X:  whether to normalize the input data before computing (predictions will be in original scales)
+    :type normalize_X: False|True
+    :param normalize_Y:  whether to normalize the input data before computing (predictions will be in original scales)
+    :type normalize_Y: False|True
+    :param W_columns: number tuples of the corregionalization parameters 'coregion_W' (see coregionalize kernel documentation)
+    :type W_columns: integer
+    """
+
+    def __init__(self,X_list,Y_list,kernel_list=None,noise_variance_list=None,normalize_X=False,normalize_Y=False,W_columns=1):
+
+        self.num_outputs = len(Y_list)
+        assert len(X_list) == self.num_outputs, 'Number of outputs do not match length of inputs list.'
+
+        #Inputs indexing
+        i = 0
+        index = []
+        for x,y in zip(X_list,Y_list):
+            assert x.shape[0] == y.shape[0]
+            index.append(np.repeat(i,x.size)[:,None])
+            i += 1
+        index = np.vstack(index)
+        X = np.hstack([np.vstack(X_list),index])
+        original_dim = X.shape[1] - 1
+
+        #Mixed noise likelihood definition
+        likelihood = likelihoods.Gaussian_Mixed_Noise(Y_list,noise_params=noise_variance_list,normalize=normalize_Y)
+
+        #Coregionalization kernel definition
+        if kernel_list is None:
+            kernel_list = [[kern.rbf(original_dim)],[]]
+        mkernel = multioutput.build_lcm(input_dim=original_dim, num_outputs=self.num_outputs, CK = kernel_list[0], NC = kernel_list[1], W_columns=W_columns)
+
+        self.multioutput = True
+        GP.__init__(self, X, likelihood, mkernel, normalize_X=normalize_X)
+        self.ensure_default_constraints()

GPy/models/sparse_gp_classification.py

@@ -28,11 +28,11 @@ class SparseGPClassification(SparseGP):
 
     def __init__(self, X, Y=None, likelihood=None, kernel=None, normalize_X=False, normalize_Y=False, Z=None, num_inducing=10):
         if kernel is None:
-            kernel = kern.rbf(X.shape[1]) + kern.white(X.shape[1], 1e-3)
+            kernel = kern.rbf(X.shape[1])# + kern.white(X.shape[1],1e-3)
 
         if likelihood is None:
-            distribution = likelihoods.likelihood_functions.Binomial()
-            likelihood = likelihoods.EP(Y, distribution)
+            noise_model = likelihoods.binomial()
+            likelihood = likelihoods.EP(Y, noise_model)
         elif Y is not None:
             if not all(Y.flatten() == likelihood.data.flatten()):
                 raise Warning, 'likelihood.data and Y are different.'

GPy/models/sparse_gp_multioutput_regression.py

@@ -0,0 +1,80 @@
+# Copyright (c) 2013, Ricardo Andrade
+# Licensed under the BSD 3-clause license (see LICENSE.txt)
+
+
+import numpy as np
+from ..core import SparseGP
+from .. import likelihoods
+from .. import kern
+from ..util import multioutput
+
+class SparseGPMultioutputRegression(SparseGP):
+    """
+    Sparse multiple output Gaussian process with Gaussian noise
+
+    This is a wrapper around the models.SparseGP class, with a set of sensible defaults
+
+    :param X_list: input observations
+    :type X_list: list of numpy arrays (num_data_output_i x input_dim), one array per output
+    :param Y_list: observed values
+    :type Y_list: list of numpy arrays (num_data_output_i x 1), one array per output
+    :param kernel_list: GPy kernels, defaults to rbf
+    :type kernel_list: list of GPy kernels
+    :param noise_variance_list: noise parameters per output, defaults to 1.0 for every output
+    :type noise_variance_list: list of floats
+    :param normalize_X:  whether to normalize the input data before computing (predictions will be in original scales)
+    :type normalize_X: False|True
+    :param normalize_Y:  whether to normalize the input data before computing (predictions will be in original scales)
+    :type normalize_Y: False|True
+    :param Z_list: inducing inputs (optional)
+    :type Z_list: list of numpy arrays (num_inducing_output_i x input_dim), one array per output | empty list
+    :param num_inducing: number of inducing inputs per output, defaults to 10 (ignored if Z_list is not empty)
+    :type num_inducing: integer
+    :param W_columns: number tuples of the corregionalization parameters 'coregion_W' (see coregionalize kernel documentation)
+    :type W_columns: integer
+    """
+    #NOTE not tested with uncertain inputs
+    def __init__(self,X_list,Y_list,kernel_list=None,noise_variance_list=None,normalize_X=False,normalize_Y=False,Z_list=[],num_inducing=10,W_columns=1):
+
+        self.num_outputs = len(Y_list)
+        assert len(X_list) == self.num_outputs, 'Number of outputs do not match length of inputs list.'
+
+        #Inducing inputs list
+        if len(Z_list):
+            assert len(Z_list) == self.num_outputs, 'Number of outputs do not match length of inducing inputs list.'
+        else:
+            if isinstance(num_inducing,np.int):
+                num_inducing = [num_inducing] * self.num_outputs
+            num_inducing = np.asarray(num_inducing)
+            assert num_inducing.size == self.num_outputs, 'Number of outputs do not match length of inducing inputs list.'
+            for ni,X in zip(num_inducing,X_list):
+                i = np.random.permutation(X.shape[0])[:ni]
+                Z_list.append(X[i].copy())
+
+        #Inputs and inducing inputs indexing
+        i = 0
+        index = []
+        index_z = []
+        for x,y,z in zip(X_list,Y_list,Z_list):
+            assert x.shape[0] == y.shape[0]
+            index.append(np.repeat(i,x.size)[:,None])
+            index_z.append(np.repeat(i,z.size)[:,None])
+            i += 1
+        index = np.vstack(index)
+        index_z = np.vstack(index_z)
+        X = np.hstack([np.vstack(X_list),index])
+        Z = np.hstack([np.vstack(Z_list),index_z])
+        original_dim = X.shape[1] - 1
+
+        #Mixed noise likelihood definition
+        likelihood = likelihoods.Gaussian_Mixed_Noise(Y_list,noise_params=noise_variance_list,normalize=normalize_Y)
+
+        #Coregionalization kernel definition
+        if kernel_list is None:
+            kernel_list = [[kern.rbf(original_dim)],[]]
+        mkernel = multioutput.build_lcm(input_dim=original_dim, num_outputs=self.num_outputs, CK = kernel_list[0], NC = kernel_list[1], W_columns=W_columns)
+
+        self.multioutput = True
+        SparseGP.__init__(self, X, likelihood, mkernel, Z=Z, normalize_X=normalize_X)
+        self.constrain_fixed('.*iip_\d+_1')
+        self.ensure_default_constraints()

GPy/models/sparse_gp_regression.py

@@ -20,7 +20,11 @@ class SparseGPRegression(SparseGP):
     :type normalize_X: False|True
     :param normalize_Y:  whether to normalize the input data before computing (predictions will be in original scales)
     :type normalize_Y: False|True
+    :param Z: inducing inputs (optional, see note)
+    :type Z: np.ndarray (num_inducing x input_dim) | None
     :rtype: model object
+    :param X_variance: The uncertainty in the measurements of X (Gaussian variance)
+    :type X_variance: np.ndarray (num_data x input_dim) | None
 
     .. Note:: Multiple independent outputs are allowed using columns of Y