BUG-19214 int categoricals are formatted as ints

doc/source/whatsnew/v0.24.0.rst

@@ -1321,6 +1321,7 @@ Categorical
 - Bug in many methods of the ``.str``-accessor, which always failed on calling the ``CategoricalIndex.str`` constructor (:issue:`23555`, :issue:`23556`)
 - Bug in :meth:`Series.where` losing the categorical dtype for categorical data (:issue:`24077`)
 - Bug in :meth:`Categorical.apply` where ``NaN`` values could be handled unpredictably. They now remain unchanged (:issue:`24241`)
+- Bug where an integer ``Categorical`` would be formatted as if it had floats if ``NaN`` values were present (:issue:`19214`)
 
 Datetimelike
 ^^^^^^^^^^^^

pandas/io/formats/format.py

@@ -134,8 +134,11 @@ def _get_footer(self):
         return compat.text_type(footer)
 
     def _get_formatted_values(self):
-        return format_array(self.categorical.get_values(), None,
-                            float_format=None, na_rep=self.na_rep)
+        results = format_array(self.categorical.get_values(), None,
+                               float_format=None, na_rep=self.na_rep)
+        if is_integer_dtype(self.categorical.dtype.categories):
+            return [result.replace(".0", "") for result in results]
+        return results
 
     def to_string(self):
         categorical = self.categorical
@@ -1176,6 +1179,11 @@ def _format_strings(self):
                                   na_rep=self.na_rep, digits=self.digits,
                                   space=self.space, justify=self.justify,
                                   leading_space=self.leading_space)
+
+        if (is_categorical_dtype(values.dtype) and
+                is_integer_dtype(values.dtype.categories)):
+            # integers were coerced to float for array with NaN (GH 19214)
+            return [value.replace(".0", "") for value in fmt_values]
         return fmt_values
 
 

pandas/tests/arrays/categorical/test_repr.py

@@ -240,6 +240,15 @@ def test_categorical_repr_datetime_ordered(self):
 
         assert repr(c) == exp
 
+    def test_categorical_repr_int_with_nan(self):
+        c = Categorical([1, 2, np.nan])
+        c_exp = """[1, 2, NaN]\nCategories (2, int64): [1, 2]"""
+        assert repr(c) == c_exp
+
+        s = Series([1, 2, np.nan], dtype="object").astype("category")
+        s_exp = """0      1\n1      2\n2    NaN\ndtype: category\nCategories (2, int64): [1, 2]"""  # noqa
+        assert repr(s) == s_exp
+
     def test_categorical_repr_period(self):
         idx = period_range('2011-01-01 09:00', freq='H', periods=5)
         c = Categorical(idx)