Small tidying up

GPy/likelihoods/bernoulli.py

@@ -248,41 +248,3 @@ class Bernoulli(Likelihood):
 
     def exact_inference_gradients(self, dL_dKdiag,Y_metadata=None):
         pass
-
-    def variational_expectations(self, Y, m, v, gh_points=None):
-        """
-        Probit specific numerical stable integrations
-        """
-        #Move to be faster
-        if self.gp_link:
-            pass
-        Yshape = Y.shape
-        mshape = m.shape
-        vshape = v.shape
-        Y = Y.flatten()
-        m = m.flatten()
-        v = v.flatten()
-
-        assert Yshape == mshape
-        assert mshape == vshape
-
-        Ysign = np.where(Y==1,1,-1).flatten()
-        gh_x, gh_w = np.polynomial.hermite.hermgauss(20)
-
-        #Shapes a bit weird
-        X = gh_x[None,:]*np.sqrt(2.*v[:, None]) + (m*Ysign)[:,None]
-        p = stats.norm.cdf(X)
-        p = np.clip(p, 1e-9, 1.-1e-9) # for numerical stability
-        N = stats.norm.pdf(X)
-        F = np.log(p).dot(gh_w)
-        NoverP = N/p
-        dF_dm = (NoverP*Ysign[:,None]).dot(gh_w)
-        dF_dv = -0.5*(NoverP**2 + NoverP*X).dot(gh_w)
-        if np.any(np.isnan(dF_dv)) or np.any(np.isinf(dF_dv)):
-            stop
-        if np.any(np.isnan(dF_dm)) or np.any(np.isinf(dF_dm)):
-            stop
-        #FIXME: Might be wrong reshaping
-        return F.reshape(Yshape), dF_dm.reshape(mshape), dF_dv.reshape(vshape), None
-
-

GPy/likelihoods/likelihood.py

@@ -325,7 +325,7 @@ class Likelihood(Parameterized):
     def logpdf_sum(self, f, y, Y_metadata=None):
         """
         Convenience function that can overridden for functions where this could
-        be computed more efficiently (Theano?)
+        be computed more efficiently
         """
         return np.sum(self.logpdf(f, y, Y_metadata=Y_metadata))