very weird merge conflict, including in files that I did not change

GPy/examples/classification.py

@@ -89,7 +89,7 @@ def toy_linear_1d_classification_laplace(seed=default_seed, optimize=True, plot=
 
     likelihood = GPy.likelihoods.Bernoulli()
     laplace_inf = GPy.inference.latent_function_inference.Laplace()
-    kernel = GPy.kern.rbf(1)
+    kernel = GPy.kern.RBF(1)
 
     # Model definition
     m = GPy.core.GP(data['X'], Y, kernel=kernel, likelihood=likelihood, inference_method=laplace_inf)

GPy/examples/coreg_example.py

@@ -0,0 +1,80 @@
+import numpy as np
+import pylab as pb
+import GPy
+pb.ion()
+pb.close('all')
+
+X1 = np.arange(3)[:,None]
+X2 = np.arange(4)[:,None]
+I1 = np.zeros_like(X1)
+I2 = np.ones_like(X2)
+
+_X = np.vstack([ X1, X2 ])
+_I = np.vstack([ I1, I2 ])
+
+X = np.hstack([ _X, _I ])
+
+Y1 = np.sin(X1/8.)
+Y2 = np.cos(X2/8.)
+
+Bias = GPy.kern.Bias(1,active_dims=[0])
+Coreg = GPy.kern.Coregionalize(1,2,active_dims=[1])
+K = Bias.prod(Coreg,name='X')
+
+#K.coregion.W = 0
+#print K.coregion.W
+
+#print Bias.K(_X,_X)
+#print K.K(X,X)
+
+#pb.matshow(K.K(X,X))
+
+
+Mlist = [GPy.kern.Matern32(1,lengthscale=20.,name="Mat")]
+kern = GPy.util.multioutput.LCM(input_dim=1,num_outputs=2,kernels_list=Mlist,name='H')
+kern.B.W = 0
+kern.B.kappa = 1.
+#kern.B.W.fix()
+#kern.B.kappa.fix()
+#m = GPy.models.GPCoregionalizedRegression(X_list=[X1,X2], Y_list=[Y1,Y2], kernel=kern)
+m = GPy.models.SparseGPCoregionalizedRegression(X_list=[X1], Y_list=[Y1], kernel=kern)
+#m.optimize()
+m.checkgrad(verbose=1)
+
+fig = pb.figure()
+ax0 = fig.add_subplot(211)
+ax1 = fig.add_subplot(212)
+slices = GPy.util.multioutput.get_slices([Y1,Y2])
+m.plot(fixed_inputs=[(1,0)],which_data_rows=slices[0],ax=ax0)
+#m.plot(fixed_inputs=[(1,1)],which_data_rows=slices[1],ax=ax1)
+
+
+
+"""
+
+X1 = 100 * np.random.rand(100)[:,None]
+X2 = 100 * np.random.rand(100)[:,None]
+#X1.sort()
+#X2.sort()
+
+Y1 = np.sin(X1/10.) + np.random.rand(100)[:,None]
+Y2 = np.cos(X2/10.) + np.random.rand(100)[:,None]
+
+
+
+
+Mlist = [GPy.kern.Matern32(1,lengthscale=20.,name="Mat")]
+kern = GPy.util.multioutput.LCM(input_dim=1,num_outputs=12,kernels_list=Mlist,name='H')
+
+
+m = GPy.models.GPCoregionalizedRegression(X_list=[X1,X2], Y_list=[Y1,Y2], kernel=kern)
+m.optimize()
+
+fig = pb.figure()
+ax0 = fig.add_subplot(211)
+ax1 = fig.add_subplot(212)
+slices = GPy.util.multioutput.get_slices([Y1,Y2])
+m.plot(fixed_inputs=[(1,0)],which_data_rows=slices[0],ax=ax0)
+m.plot(fixed_inputs=[(1,1)],which_data_rows=slices[1],ax=ax1)
+
+"""

GPy/examples/dimensionality_reduction.py

@@ -324,14 +324,14 @@ def mrd_simulation(optimize=True, verbose=True, plot=True, plot_sim=True, **kw):
 
     D1, D2, D3, N, num_inducing, Q = 60, 20, 36, 60, 6, 5
     _, _, Ylist = _simulate_sincos(D1, D2, D3, N, num_inducing, Q, plot_sim)
-    likelihood_list = [Gaussian(x, normalize=True) for x in Ylist]
-
-    k = kern.Linear(Q, ARD=True) + kern.Bias(Q, _np.exp(-2)) + kern.White(Q, _np.exp(-2))
-    m = MRD(likelihood_list, input_dim=Q, num_inducing=num_inducing, kernels=k, initx="", initz='permute', **kw)
-    m.ensure_default_constraints()
-
-    for i, bgplvm in enumerate(m.bgplvms):
-        m['{}_noise'.format(i)] = bgplvm.likelihood.Y.var() / 500.
+    
+    #Ylist = [Ylist[0]]
+    k = [kern.Linear(Q, ARD=True) + kern.White(Q, 1e-4) for _ in range(len(Ylist))]
+    m = MRD(Ylist, input_dim=Q, num_inducing=num_inducing, kernel=k, initx="", initz='permute', **kw)
+    
+    m['.*noise'] = [Y.var()/500. for Y in Ylist]
+    #for i, Y in enumerate(Ylist):
+    #    m['.*Y_{}.*Gaussian.*noise'.format(i)] = Y.var(1) / 500.
 
     if optimize:
         print "Optimizing Model:"

GPy/examples/regression.py

@@ -318,7 +318,7 @@ def toy_ARD(max_iters=1000, kernel_type='linear', num_samples=300, D=4, optimize
     Y /= Y.std()
 
     if kernel_type == 'linear':
-        kernel = GPy.kern.linear(X.shape[1], ARD=1)
+        kernel = GPy.kern.Linear(X.shape[1], ARD=1)
     elif kernel_type == 'rbf_inv':
         kernel = GPy.kern.RBF_inv(X.shape[1], ARD=1)
     else:
@@ -357,7 +357,7 @@ def toy_ARD_sparse(max_iters=1000, kernel_type='linear', num_samples=300, D=4, o
     Y /= Y.std()
 
     if kernel_type == 'linear':
-        kernel = GPy.kern.linear(X.shape[1], ARD=1)
+        kernel = GPy.kern.Linear(X.shape[1], ARD=1)
     elif kernel_type == 'rbf_inv':
         kernel = GPy.kern.RBF_inv(X.shape[1], ARD=1)
     else:
@@ -468,7 +468,7 @@ def sparse_GP_regression_2D(num_samples=400, num_inducing=50, max_iters=100, opt
 
 def uncertain_inputs_sparse_regression(max_iters=200, optimize=True, plot=True):
     """Run a 1D example of a sparse GP regression with uncertain inputs."""
-    fig, axes = pb.subplots(1, 2, figsize=(12, 5))
+    fig, axes = pb.subplots(1, 2, figsize=(12, 5), sharex=True, sharey=True)
 
     # sample inputs and outputs
     S = np.ones((20, 1))