API: Change str for CategoricalDtype to category (pandas-dev#17783)

Author: TomAugspurger

doc/source/whatsnew/v0.21.0.txt

@@ -157,11 +157,10 @@ The values have been correctly interpreted as integers.
 
 The ``.dtype`` property of a ``Categorical``, ``CategoricalIndex`` or a
 ``Series`` with categorical type will now return an instance of
-``CategoricalDtype``. For the most part, this is backwards compatible, though
-the string repr has changed. If you were previously using ``str(s.dtype) ==
-'category'`` to detect categorical data, switch to
-:func:`pandas.api.types.is_categorical_dtype`, which is compatible with the old
-and new ``CategoricalDtype``.
+``CategoricalDtype``. This change should be backwards compatible, though the
+repr has changed. ``str(CategoricalDtype())`` is still the string
+``'category'``, but the preferred way to detect categorical data is to use
+:func:`pandas.api.types.is_categorical_dtype`.
 
 See the :ref:`CategoricalDtype docs <categorical.categoricaldtype>` for more.
 

pandas/core/dtypes/dtypes.py

@@ -220,7 +220,7 @@ def __eq__(self, other):
             # both unordered; this could probably be optimized / cached
             return hash(self) == hash(other)
 
-    def __unicode__(self):
+    def __repr__(self):
         tpl = u'CategoricalDtype(categories={}ordered={})'
         if self.categories is None:
             data = u"None, "

pandas/tests/dtypes/test_dtypes.py

@@ -1,4 +1,5 @@
 # -*- coding: utf-8 -*-
+import re
 import pytest
 
 from itertools import product
@@ -649,3 +650,10 @@ def test_from_categorical_dtype_both(self):
         result = CategoricalDtype._from_categorical_dtype(
             c1, categories=[1, 2], ordered=False)
         assert result == CategoricalDtype([1, 2], ordered=False)
+
+    def test_str_vs_repr(self):
+        c1 = CategoricalDtype(['a', 'b'])
+        assert str(c1) == 'category'
+        # Py2 will have unicode prefixes
+        pat = r"CategoricalDtype\(categories=\[.*\], ordered=False\)"
+        assert re.match(pat, repr(c1))

pandas/tests/series/test_analytics.py

@@ -1784,7 +1784,8 @@ class TestNLargestNSmallest(object):
               # not supported on some archs
               # Series([3., 2, 1, 2, 5], dtype='complex256'),
               Series([3., 2, 1, 2, 5], dtype='complex128'),
-              Series(list('abcde'))])
+              Series(list('abcde')),
+              Series(list('abcde'), dtype='category')])
     def test_error(self, r):
         dt = r.dtype
         msg = ("Cannot use method 'n(larg|small)est' with "
@@ -1795,16 +1796,6 @@ def test_error(self, r):
             with tm.assert_raises_regex(TypeError, msg):
                 method(arg)
 
-    def test_error_categorical_dtype(self):
-        # same as test_error, but regex hard to escape properly
-        msg = ("Cannot use method 'n(larg|small)est' with dtype "
-               "CategoricalDtype.+")
-        with tm.assert_raises_regex(TypeError, msg):
-            Series(list('ab'), dtype='category').nlargest(2)
-
-        with tm.assert_raises_regex(TypeError, msg):
-            Series(list('ab'), dtype='category').nsmallest(2)
-
     @pytest.mark.parametrize(
         "s",
         [v for k, v in s_main_dtypes().iteritems()])