manual merging

GPy/examples/dimensionality_reduction.py

@@ -187,10 +187,10 @@ def _simulate_sincos(D1, D2, D3, N, num_inducing, Q, plot_sim=False):
     _np.random.seed(1234)
     
     x = _np.linspace(0, 4 * _np.pi, N)[:, None]
-    s1 = _np.vectorize(lambda x: -_np.sin(_np.exp(x)))
+    s1 = _np.vectorize(lambda x: _np.sin(x))
     s2 = _np.vectorize(lambda x: _np.cos(x)**2)
     s3 = _np.vectorize(lambda x:-_np.exp(-_np.cos(2 * x)))
-    sS = _np.vectorize(lambda x: x*_np.sin(x))
+    sS = _np.vectorize(lambda x: _np.cos(x))
 
     s1 = s1(x)
     s2 = s2(x)
@@ -202,7 +202,7 @@ def _simulate_sincos(D1, D2, D3, N, num_inducing, Q, plot_sim=False):
     s3 -= s3.mean(); s3 /= s3.std(0)
     sS -= sS.mean(); sS /= sS.std(0)
 
-    S1 = _np.hstack([s1, s2, sS])
+    S1 = _np.hstack([s1, sS])
     S2 = _np.hstack([s2, s3, sS])
     S3 = _np.hstack([s3, sS])
 
@@ -270,7 +270,7 @@ def bgplvm_simulation(optimize=True, verbose=1,
     from GPy import kern
     from GPy.models import BayesianGPLVM
 
-    D1, D2, D3, N, num_inducing, Q = 13, 5, 8, 45, 5, 9
+    D1, D2, D3, N, num_inducing, Q = 13, 5, 8, 45, 3, 9
     _, _, Ylist = _simulate_sincos(D1, D2, D3, N, num_inducing, Q, plot_sim)
     Y = Ylist[0]
     k = kern.Linear(Q, ARD=True)# + kern.white(Q, _np.exp(-2)) # + kern.bias(Q)
@@ -294,7 +294,7 @@ def bgplvm_simulation_missing_data(optimize=True, verbose=1,
     from GPy.models import BayesianGPLVM
     from GPy.inference.latent_function_inference.var_dtc import VarDTCMissingData
 
-    D1, D2, D3, N, num_inducing, Q = 13, 5, 8, 45, 5, 9
+    D1, D2, D3, N, num_inducing, Q = 13, 5, 8, 45, 7, 9
     _, _, Ylist = _simulate_sincos(D1, D2, D3, N, num_inducing, Q, plot_sim)
     Y = Ylist[0]
     k = kern.Linear(Q, ARD=True)# + kern.white(Q, _np.exp(-2)) # + kern.bias(Q)
@@ -515,3 +515,28 @@ def cmu_mocap(subject='35', motion=['01'], in_place=True, optimize=True, verbose
         lvm_visualizer.close()
 
     return m
+
+def ssgplvm_simulation_linear():
+    import numpy as np
+    import GPy
+    N, D, Q = 1000, 20, 5
+    pi = 0.2
+    
+    def sample_X(Q, pi):
+        x = np.empty(Q)
+        dies = np.random.rand(Q)
+        for q in xrange(Q):
+            if dies[q]<pi:
+                x[q] = np.random.randn()
+            else:
+                x[q] = 0.
+        return x
+    
+    Y = np.empty((N,D))
+    X = np.empty((N,Q))
+    # Generate data from random sampled weight matrices
+    for n in xrange(N):
+        X[n] = sample_X(Q,pi)
+        w = np.random.randn(D,Q)
+        Y[n] = np.dot(w,X[n])
+    

GPy/examples/non_gaussian.py

@@ -30,7 +30,7 @@ def student_t_approx(optimize=True, plot=True):
     #Yc = Yc/Yc.max()
 
     #Add student t random noise to datapoints
-    deg_free = 5
+    deg_free = 1
     print "Real noise: ", real_std
     initial_var_guess = 0.5
     edited_real_sd = initial_var_guess
@@ -47,9 +47,9 @@ def student_t_approx(optimize=True, plot=True):
     m1['.*white'].constrain_fixed(1e-5)
     m1.randomize()
 
-    ##Gaussian GP model on corrupt data
+    #Gaussian GP model on corrupt data
     m2 = GPy.models.GPRegression(X, Yc.copy(), kernel=kernel2)
-    m1['.*white'].constrain_fixed(1e-5)
+    m2['.*white'].constrain_fixed(1e-5)
     m2.randomize()
 
     #Student t GP model on clean data
@@ -59,10 +59,6 @@ def student_t_approx(optimize=True, plot=True):
     m3['.*t_noise'].constrain_bounded(1e-6, 10.)
     m3['.*white'].constrain_fixed(1e-5)
     m3.randomize()
-    debug = True
-
-    #TODO: remove
-    return m3
 
     #Student t GP model on corrupt data
     t_distribution = GPy.likelihoods.StudentT(deg_free=deg_free, sigma2=edited_real_sd)
@@ -71,6 +67,16 @@ def student_t_approx(optimize=True, plot=True):
     m4['.*t_noise'].constrain_bounded(1e-6, 10.)
     m4['.*white'].constrain_fixed(1e-5)
     m4.randomize()
+    print m4
+    debug=True
+    if debug:
+        m4.optimize(messages=1)
+        import pylab as pb
+        pb.plot(m4.X, m4.inference_method.f_hat)
+        pb.plot(m4.X, m4.Y, 'rx')
+        m4.plot()
+        print m4
+        return m4
 
     if optimize:
         optimizer='scg'

GPy/examples/regression.py

@@ -284,7 +284,7 @@ def toy_poisson_rbf_1d_laplace(optimize=True, plot=True):
 
     kern = GPy.kern.RBF(1)
     poisson_lik = GPy.likelihoods.Poisson()
-    laplace_inf = GPy.inference.latent_function_inference.LaplaceInference()
+    laplace_inf = GPy.inference.latent_function_inference.Laplace()
 
     # create simple GP Model
     m = GPy.core.GP(X, Y, kernel=kern, likelihood=poisson_lik, inference_method=laplace_inf)