diff --git a/GPy/testing/kernel_tests.py b/GPy/testing/kernel_tests.py
index c1bb9265..3b09d6e7 100644
--- a/GPy/testing/kernel_tests.py
+++ b/GPy/testing/kernel_tests.py
@@ -282,7 +282,7 @@ class KernelGradientTestsContinuous(unittest.TestCase):
         try:
             k.K(self.X)
         except AssertionError:
-            raise AssertionError, "k.K(X) should run on self.D-1 dimension"
+            raise AssertionError("k.K(X) should run on self.D-1 dimension")
 
     def test_Matern52(self):
         k = GPy.kern.Matern52(self.D)
diff --git a/GPy/util/caching.py b/GPy/util/caching.py
index 16adc320..b1419aec 100644
--- a/GPy/util/caching.py
+++ b/GPy/util/caching.py
@@ -148,10 +148,10 @@ class Cacher(object):
         return Cacher(self.operation, self.limit, self.ignore_args, self.force_kwargs)
 
     def __getstate__(self, memo=None):
-        raise NotImplementedError, "Trying to pickle Cacher object with function {}, pickling functions not possible.".format(str(self.operation))
+        raise NotImplementedError("Trying to pickle Cacher object with function {}, pickling functions not possible.".format(str(self.operation)))
 
     def __setstate__(self, memo=None):
-        raise NotImplementedError, "Trying to pickle Cacher object with function {}, pickling functions not possible.".format(str(self.operation))
+        raise NotImplementedError("Trying to pickle Cacher object with function {}, pickling functions not possible.".format(str(self.operation)))
 
     @property
     def __name__(self):
diff --git a/GPy/util/choleskies.py b/GPy/util/choleskies.py
index cc3a7f75..606229f7 100644
--- a/GPy/util/choleskies.py
+++ b/GPy/util/choleskies.py
@@ -10,7 +10,7 @@ def safe_root(N):
     i = np.sqrt(N)
     j = int(i)
     if i != j:
-        raise ValueError, "N is not square!"
+        raise ValueError("N is not square!")
     return j
 
 def flat_to_triang(flat):
diff --git a/GPy/util/config.py b/GPy/util/config.py
index 6dad46c8..8496fe36 100644
--- a/GPy/util/config.py
+++ b/GPy/util/config.py
@@ -20,4 +20,4 @@ user_file = os.path.join(home,'.gpy_user.cfg')
 config.readfp(open(default_file))
 config.read([local_file, user_file])
 if not config:
-    raise ValueError, "No configuration file found at either " + user_file + " or " + local_file + " or " + default_file + "."
+    raise ValueError("No configuration file found at either " + user_file + " or " + local_file + " or " + default_file + ".")
diff --git a/GPy/util/datasets.py b/GPy/util/datasets.py
index 3ba46f52..2648dd8d 100644
--- a/GPy/util/datasets.py
+++ b/GPy/util/datasets.py
@@ -785,7 +785,7 @@ def hapmap3(data_set='hapmap3'):
         from sys import stdout
         import bz2
     except ImportError as i:
-        raise i, "Need pandas for hapmap dataset, make sure to install pandas (http://pandas.pydata.org/) before loading the hapmap dataset"
+        raise i("Need pandas for hapmap dataset, make sure to install pandas (http://pandas.pydata.org/) before loading the hapmap dataset")
 
     dir_path = os.path.join(data_path,'hapmap3')
     hapmap_file_name = 'hapmap3_r2_b36_fwd.consensus.qc.poly'
diff --git a/GPy/util/linalg.py b/GPy/util/linalg.py
index d7ad5d61..04b341f3 100644
--- a/GPy/util/linalg.py
+++ b/GPy/util/linalg.py
@@ -91,7 +91,7 @@ def jitchol(A, maxtries=5):
     else:
         diagA = np.diag(A)
         if np.any(diagA <= 0.):
-            raise linalg.LinAlgError, "not pd: non-positive diagonal elements"
+            raise linalg.LinAlgError("not pd: non-positive diagonal elements")
         jitter = diagA.mean() * 1e-6
         num_tries = 1
         while num_tries <= maxtries and np.isfinite(jitter):
@@ -105,7 +105,7 @@ def jitchol(A, maxtries=5):
     import traceback
     logging.warning('\n'.join(['Added {} rounds of jitter, jitter of {:.10e}'.format(num_tries-1, jitter),
                                 '  in '+traceback.format_list(traceback.extract_stack(limit=2)[-2:-1])[0][2:]]))
-    raise linalg.LinAlgError, "not positive definite, even with jitter."
+    raise linalg.LinAlgError("not positive definite, even with jitter.")
 
 # def dtrtri(L, lower=1):
 #     """
diff --git a/GPy/util/ln_diff_erfs.py b/GPy/util/ln_diff_erfs.py
index 582a4585..c1137283 100644
--- a/GPy/util/ln_diff_erfs.py
+++ b/GPy/util/ln_diff_erfs.py
@@ -35,7 +35,7 @@ def ln_diff_erfs(x1, x2, return_sign=False):
         elif x2.size==1:
             v = np.zeros(x1.shape)
         else:
-            raise ValueError, "This function does not broadcast unless provided with a scalar."
+            raise ValueError("This function does not broadcast unless provided with a scalar.")
     
     if x1.size == 1:
         x1 = np.tile(x1, x2.shape)
diff --git a/GPy/util/mocap.py b/GPy/util/mocap.py
index 58662cf9..bcc3c029 100644
--- a/GPy/util/mocap.py
+++ b/GPy/util/mocap.py
@@ -174,7 +174,7 @@ class skeleton(tree):
         return connection
 
     def to_xyz(self, channels):
-        raise NotImplementedError, "this needs to be implemented to use the skeleton class"
+        raise NotImplementedError("this needs to be implemented to use the skeleton class")
 
 
     def finalize(self):