CLN: CategoricalDtype repr now yields category

DISPLAY: show dtype when displaying Categorical series (for consistency)

Author: jreback

pandas/core/common.py

@@ -128,6 +128,38 @@ class CategoricalDtype(object):
     def __unicode__(self):
         return self.name
 
+    def __str__(self):
+        """
+        Return a string representation for a particular Object
+
+        Invoked by str(df) in both py2/py3.
+        Yields Bytestring in Py2, Unicode String in py3.
+        """
+
+        if compat.PY3:
+            return self.__unicode__()
+        return self.__bytes__()
+
+    def __bytes__(self):
+        """
+        Return a string representation for a particular object.
+
+        Invoked by bytes(obj) in py3 only.
+        Yields a bytestring in both py2/py3.
+        """
+        from pandas.core.config import get_option
+
+        encoding = get_option("display.encoding")
+        return self.__unicode__().encode(encoding, 'replace')
+
+    def __repr__(self):
+        """
+        Return a string representation for a particular object.
+
+        Yields Bytestring in Py2, Unicode String in py3.
+        """
+        return str(self)
+
     def __hash__(self):
         # make myself hashable
         return hash(str(self))

pandas/core/format.py

@@ -167,8 +167,7 @@ def _get_footer(self):
             footer += 'Length: %d' % len(self.series)
 
         # TODO: in tidy_repr, with freq index, no dtype is shown -> also include a guard here?
-        # tidy_repr does not show a dtype for categorical, so do the same here
-        if self.dtype and not com.is_categorical_dtype(self.series.dtype):
+        if self.dtype:
             name = getattr(self.series.dtype, 'name', None)
             if name:
                 if footer:

pandas/core/series.py

@@ -897,7 +897,10 @@ def _repr_footer(self):
         # Categorical
         if com.is_categorical_dtype(self.dtype):
             level_info = self.cat._repr_level_info()
-            return u('%sLength: %d\n%s') % (namestr, len(self),level_info)
+            return u('%sLength: %d, dtype: %s\n%s') % (namestr,
+                                                       len(self),
+                                                       str(self.dtype.name),
+                                                       level_info)
 
         # reg series
         return u('%sLength: %d, dtype: %s') % (namestr,

pandas/tests/test_categorical.py

@@ -778,21 +778,21 @@ def test_describe(self):
     def test_repr(self):
         a = pd.Series(pd.Categorical([1,2,3,4], name="a"))
         exp = u("0    1\n1    2\n2    3\n3    4\n" +
-              "Name: a\nLevels (4, int64): [1 < 2 < 3 < 4]")
+              "Name: a, dtype: category\nLevels (4, int64): [1 < 2 < 3 < 4]")
 
         self.assertEqual(exp, a.__unicode__())
 
         a = pd.Series(pd.Categorical(["a","b"] *25, name="a"))
         exp = u("".join(["%s    a\n%s    b\n"%(i,i+1) for i in range(0,10,2)]) + "...\n" +
                 "".join(["%s    a\n%s    b\n"%(i,i+1) for i in range(40,50,2)]) +
-                "Name: a, Length: 50\n" +
+                "Name: a, Length: 50, dtype: category\n" +
                 "Levels (2, object): [a < b]")
         self.assertEqual(exp,a._tidy_repr())
 
         levs = list("abcdefghijklmnopqrstuvwxyz")
         a = pd.Series(pd.Categorical(["a","b"], name="a", levels=levs))
         exp = u("0    a\n1    b\n" +
-                "Name: a\n"
+                "Name: a, dtype: category\n"
                 "Levels (26, object): [a < b < c < d ... w < x < y < z]")
         self.assertEqual(exp,a.__unicode__())