From 592414ce64bff32f567d04a262ab715411c5dcfc Mon Sep 17 00:00:00 2001
From: James Hensman <james.hensman@gmail.com>
Date: Wed, 1 Apr 2015 09:37:10 +0100
Subject: [PATCH] tests to probe the mean-function functionality

---
 GPy/testing/meanfunc_tests.py | 56 +++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)
 create mode 100644 GPy/testing/meanfunc_tests.py

diff --git a/GPy/testing/meanfunc_tests.py b/GPy/testing/meanfunc_tests.py
new file mode 100644
index 00000000..1d875377
--- /dev/null
+++ b/GPy/testing/meanfunc_tests.py
@@ -0,0 +1,56 @@
+# Copyright (c) 2015, James Hensman
+# Licensed under the BSD 3-clause license (see LICENSE.txt)
+
+import unittest
+import numpy as np
+import GPy
+
+class MFtests(unittest.TestCase):
+    def simple_mean_function():
+        """
+        The simplest possible mean function. No parameters, just a simple Sinusoid.
+        """
+        #create  simple mean function
+        mf = GPy.core.Mapping(1,1)
+        mf.f = np.sin
+        mf.update_gradients = lambda a,b: None
+
+        X = np.linspace(0,10,50).reshape(-1,1)
+        Y = np.sin(X) + 0.5*np.cos(3*X) + 0.1*np.random.randn(*X.shape)
+
+        k =GPy.kern.RBF(1)
+        lik = GPy.likelihoods.Gaussian()
+        m = GPy.core.GP(X, Y, kernel=k, likelihood=lik, mean_function=mf)
+        self.assertTrue(m.checkgrad())
+
+    def test_parametric_mean_function(self):
+        """
+        A linear mean function with parameters that we'll learn alongside the kernel
+        """
+
+        X = np.linspace(0,10,50).reshape(-1,1)
+        Y = np.sin(X) + 0.5*np.cos(3*X) + 0.1*np.random.randn(*X.shape) + 3*X
+
+        mf = GPy.mappings.Linear(1,1)
+
+        k =GPy.kern.RBF(1)
+        lik = GPy.likelihoods.Gaussian()
+        m = GPy.core.GP(X, Y, kernel=k, likelihood=lik, mean_function=mf)
+        self.assertTrue(m.checkgrad())
+
+    def test_svgp_mean_function(self):
+
+        # an instance of the SVIGOP with a men function
+        X = np.linspace(0,10,500).reshape(-1,1)
+        Y = np.sin(X) + 0.5*np.cos(3*X) + 0.1*np.random.randn(*X.shape)
+        Y = np.where(Y>0, 1,0) # make aclassificatino problem
+
+        mf = GPy.mappings.Linear(1,1)
+        Z = np.linspace(0,10,50).reshape(-1,1)
+        lik = GPy.likelihoods.Bernoulli()
+        k =GPy.kern.RBF(1) + GPy.kern.White(1, 1e-4)
+        m = GPy.core.SVGP(X, Y,Z=Z, kernel=k, likelihood=lik, mean_function=mf)
+        self.assertTrue(m.checkgrad())
+
+
+