diff --git a/GPy/core/parameterization/priors.py b/GPy/core/parameterization/priors.py
index a4bbecb3..38cb0d19 100644
--- a/GPy/core/parameterization/priors.py
+++ b/GPy/core/parameterization/priors.py
@@ -414,7 +414,7 @@ class DGPLVM_KFDA(Prior):
     def compute_cls(self, x):
         cls = {}
         # Appending each data point to its proper class
-        for j in xrange(self.datanum):
+        for j in range(self.datanum):
             class_label = self.get_class_label(self.lbl[j])
             if class_label not in cls:
                 cls[class_label] = []
@@ -553,7 +553,7 @@ class DGPLVM(Prior):
     def compute_cls(self, x):
         cls = {}
         # Appending each data point to its proper class
-        for j in xrange(self.datanum):
+        for j in range(self.datanum):
             class_label = self.get_class_label(self.lbl[j])
             if class_label not in cls:
                 cls[class_label] = []
@@ -572,7 +572,7 @@ class DGPLVM(Prior):
     # Adding data points as tuple to the dictionary so that we can access indices
     def compute_indices(self, x):
         data_idx = {}
-        for j in xrange(self.datanum):
+        for j in range(self.datanum):
             class_label = self.get_class_label(self.lbl[j])
             if class_label not in data_idx:
                 data_idx[class_label] = []
@@ -591,7 +591,7 @@ class DGPLVM(Prior):
             else:
                 lst_idx = []
             # Here we put indices of each class in to the list called lst_idx_all
-            for m in xrange(len(data_idx[i])):
+            for m in range(len(data_idx[i])):
                 lst_idx.append(data_idx[i][m][0])
             lst_idx_all.append(lst_idx)
         return lst_idx_all
@@ -627,7 +627,7 @@ class DGPLVM(Prior):
             # pdb.set_trace()
             # Calculating Bi
             B_i[i] = (M_i[i] - M_0).reshape(1, self.dim)
-        for k in xrange(self.datanum):
+        for k in range(self.datanum):
             for i in data_idx:
                 N_i = float(len(data_idx[i]))
                 if k in lst_idx_all[i]:
@@ -772,7 +772,7 @@ class DGPLVM_T(Prior):
     def compute_cls(self, x):
         cls = {}
         # Appending each data point to its proper class
-        for j in xrange(self.datanum):
+        for j in range(self.datanum):
             class_label = self.get_class_label(self.lbl[j])
             if class_label not in cls:
                 cls[class_label] = []
@@ -791,7 +791,7 @@ class DGPLVM_T(Prior):
     # Adding data points as tuple to the dictionary so that we can access indices
     def compute_indices(self, x):
         data_idx = {}
-        for j in xrange(self.datanum):
+        for j in range(self.datanum):
             class_label = self.get_class_label(self.lbl[j])
             if class_label not in data_idx:
                 data_idx[class_label] = []
@@ -810,7 +810,7 @@ class DGPLVM_T(Prior):
             else:
                 lst_idx = []
             # Here we put indices of each class in to the list called lst_idx_all
-            for m in xrange(len(data_idx[i])):
+            for m in range(len(data_idx[i])):
                 lst_idx.append(data_idx[i][m][0])
             lst_idx_all.append(lst_idx)
         return lst_idx_all
@@ -846,7 +846,7 @@ class DGPLVM_T(Prior):
             # pdb.set_trace()
             # Calculating Bi
             B_i[i] = (M_i[i] - M_0).reshape(1, self.dim)
-        for k in xrange(self.datanum):
+        for k in range(self.datanum):
             for i in data_idx:
                 N_i = float(len(data_idx[i]))
                 if k in lst_idx_all[i]:
diff --git a/GPy/inference/optimization/stochastics.py b/GPy/inference/optimization/stochastics.py
index dc71d539..f1532bc5 100644
--- a/GPy/inference/optimization/stochastics.py
+++ b/GPy/inference/optimization/stochastics.py
@@ -30,7 +30,7 @@ class SparseGPMissing(StochasticStorage):
         Thus, we can just make sure the loop goes over self.d every
         time.
         """
-        self.d = xrange(model.Y_normalized.shape[1])
+        self.d = range(model.Y_normalized.shape[1])
 
 class SparseGPStochastics(StochasticStorage):
     """
diff --git a/GPy/kern/_src/add.py b/GPy/kern/_src/add.py
index 82c84c52..77f0d76e 100644
--- a/GPy/kern/_src/add.py
+++ b/GPy/kern/_src/add.py
@@ -165,7 +165,7 @@ class Add(CombinationKernel):
                 else:
                     eff_dL_dpsi1 += dL_dpsi2.sum(0) * p2.psi1(Z, variational_posterior) * 2.
             grads = p1.gradients_qX_expectations(dL_dpsi0, eff_dL_dpsi1, dL_dpsi2, Z, variational_posterior)
-            [np.add(target_grads[i],grads[i],target_grads[i]) for i in xrange(len(grads))]
+            [np.add(target_grads[i],grads[i],target_grads[i]) for i in range(len(grads))]
         return target_grads
 
     def add(self, other):
diff --git a/GPy/models/sparse_gp_minibatch.py b/GPy/models/sparse_gp_minibatch.py
index d3bbe5fe..10c54d49 100644
--- a/GPy/models/sparse_gp_minibatch.py
+++ b/GPy/models/sparse_gp_minibatch.py
@@ -82,7 +82,7 @@ class SparseGPMiniBatch(SparseGP):
             m_f = lambda i: "Precomputing Y for missing data: {: >7.2%}".format(float(i+1)/overall)
             message = m_f(-1)
             print(message, end=' ')
-            for d in xrange(overall):
+            for d in range(overall):
                 self.Ylist.append(self.Y_normalized[self.ninan[:, d], d][:, None])
                 print(' '*(len(message)+1) + '\r', end=' ')
                 message = m_f(d)
@@ -182,11 +182,11 @@ class SparseGPMiniBatch(SparseGP):
             full_values[key][value_indices[key]] += current_values[key]
         """
         for key in current_values.keys():
-            if value_indices is not None and value_indices.has_key(key):
+            if value_indices is not None and key in value_indices:
                 index = value_indices[key]
             else:
                 index = slice(None)
-            if full_values.has_key(key):
+            if key in full_values:
                 full_values[key][index] += current_values[key]
             else:
                 full_values[key] = current_values[key]