Changed default value of config.cast_policy from 'custom' to 'numpy+floatX'

doc/library/config.txt

@@ -156,18 +156,19 @@ import theano and print the config variable, as in:
 
     String value: either 'numpy+floatX', 'numpy' or 'custom'
 
-    Default: 'custom'
+    Default: 'numpy+floatX'
 
     This specifies how data types are implicitly figured out in Theano, e.g. for
-    constants or in the results of arithmetic operations. The current default
-    value ('custom') corresponds to a set of custom rules originally used in
+    constants or in the results of arithmetic operations. The 'custom' value
+    corresponds to a set of custom rules originally used in
     Theano (which can be partially customized, see e.g. the in-code help of
-    ``tensor.NumpyAutocaster``). However the 'custom' option will be
-    deprecated in a future release of Theano. The 'numpy' setting attempts to
-    mimic the numpy casting rules. 'numpy+floatX' does the same, except that
+    ``tensor.NumpyAutocaster``), and is now deprecated.
+    The 'numpy' setting attempts to
+    mimic the numpy casting rules. The default value ('numpy+floatX') does
+    the same, except that
     it prefers to use float32 numbers instead of float64 when ``config.floatX``
-    is set to 'float32' (this will become the default value in a future
-    release of Theano). Note that both 'numpy' and 'numpy+floatX'
+    is set to 'float32'.
+    Note that both 'numpy' and 'numpy+floatX'
     behave differently from numpy on purpose in the following situations:
        * Depending on the value of ``config.int_division``, the resulting type
          of a division of integer types with the ``/`` operator may not match

theano/configdefaults.py

@@ -16,8 +16,8 @@ AddConfigVar('floatX',
         )
 
 AddConfigVar('cast_policy',
-        "Rules for implicit type casting (until further notice, do not modify within a script, and clear your Theano cache whenever it is modified)",
-        EnumStr('custom', 'numpy+floatX', 'numpy'),
+        "Rules for implicit type casting",
+        EnumStr('numpy+floatX', 'numpy', 'default'),
         )
 
 AddConfigVar('int_division',