diff --git a/GPy/core/sparse_gp.py b/GPy/core/sparse_gp.py
index 120f0d94..e451b684 100644
--- a/GPy/core/sparse_gp.py
+++ b/GPy/core/sparse_gp.py
@@ -10,8 +10,8 @@ from parameterization.variational import VariationalPosterior
 
 import logging
 from GPy.inference.latent_function_inference.posterior import Posterior
-from GPy.inference.optimization.stochastics import SparseGPStochastics,\
-    SparseGPMissing
+#no stochastics.py file added! from GPy.inference.optimization.stochastics import SparseGPStochastics,\
+    #SparseGPMissing
 logger = logging.getLogger("sparse gp")
 
 class SparseGP(GP):
diff --git a/GPy/kern/_src/stationary.py b/GPy/kern/_src/stationary.py
index 1685e7c7..1558f0a5 100644
--- a/GPy/kern/_src/stationary.py
+++ b/GPy/kern/_src/stationary.py
@@ -8,9 +8,9 @@ from ...core.parameterization.transformations import Logexp
 from ...util.linalg import tdot
 from ... import util
 import numpy as np
-from scipy import integrate
-from ...util.caching import Cache_this
+from scipy import integrate, weave
 from ...util.config import config # for assesing whether to use weave
+from ...util.caching import Cache_this
 
 class Stationary(Kern):
     """
@@ -132,10 +132,22 @@ class Stationary(Kern):
         return ret
 
     def update_gradients_diag(self, dL_dKdiag, X):
+        """
+        Given the derivative of the objective with respect to the diagonal of
+        the covariance matrix, compute the derivative wrt the parameters of
+        this kernel and stor in the <parameter>.gradient field.
+
+        See also update_gradients_full
+        """
         self.variance.gradient = np.sum(dL_dKdiag)
         self.lengthscale.gradient = 0.
 
     def update_gradients_full(self, dL_dK, X, X2=None):
+        """
+        Given the derivative of the objective wrt the covariance matrix
+        (dL_dK), compute the gradient wrt the parameters of this kernel,
+        and store in the parameters object as e.g. self.variance.gradient
+        """
         self.variance.gradient = np.einsum('ij,ij,i', self.K(X, X2), dL_dK, 1./self.variance)
 
         #now the lengthscale gradient(s)
@@ -173,6 +185,7 @@ class Stationary(Kern):
         return 1./np.where(dist != 0., dist, np.inf)
 
     def weave_lengthscale_grads(self, tmp, X, X2):
+        """Use scipy.weave to compute derivatives wrt the lengthscales"""
         N,M = tmp.shape
         Q = X.shape[1]
         if hasattr(X, 'values'):X = X.values
@@ -190,7 +203,6 @@ class Stationary(Kern):
           grads[q] = gradq;
         }
         """
-        from scipy import weave
         weave.inline(code, ['tmp', 'X', 'X2', 'grads', 'N', 'M', 'Q'], type_converters=weave.converters.blitz, support_code="#include <math.h>")
         return -grads/self.lengthscale**3
 
diff --git a/GPy/likelihoods/sstudent_t.py b/GPy/likelihoods/sstudent_t.py
index e8fb03ce..790c1437 100644
--- a/GPy/likelihoods/sstudent_t.py
+++ b/GPy/likelihoods/sstudent_t.py
@@ -4,7 +4,7 @@
 
 import sympy as sym
 from sympy.utilities.lambdify import lambdify
-from GPy.util.symbolic import gammaln
+# does not exist! JH from GPy.util.symbolic import gammaln
 
 import numpy as np
 import link_functions