fixup! ENH: Parametrized CategoricalDtype

Author: TomAugspurger

pandas/core/categorical.py

@@ -234,8 +234,11 @@ def __init__(self, values, categories=None, ordered=None, dtype=None,
                  fastpath=False):
 
         if dtype is not None:
-            if isinstance(dtype, compat.string_types) and dtype == 'category':
-                dtype = CategoricalDtype(categories, ordered)
+            if isinstance(dtype, compat.string_types):
+                if dtype == 'category':
+                    dtype = CategoricalDtype(categories, ordered)
+                else:
+                    raise ValueError("Unknown `dtype` {}".format(dtype))
             elif categories is not None or ordered is not None:
                 raise ValueError("Cannot specify both `dtype` and `categories`"
                                  " or `ordered`.")

pandas/core/dtypes/dtypes.py

@@ -215,9 +215,6 @@ def __unicode__(self):
             data = self.categories._format_data(name=self.__class__.__name__)
         return tpl.format(data, self.ordered)
 
-    def __repr__(self):
-        return str(self)
-
     @staticmethod
     def _hash_categories(categories, ordered=True):
         from pandas.core.util.hashing import (

pandas/core/indexes/category.py

@@ -180,7 +180,8 @@ def _shallow_copy(self, values=None, categories=None, ordered=None,
         # overridden.
         if dtype is not None and (categories is not None or
                                   ordered is not None):
-            raise TypeError
+            raise TypeError("Cannot specify both `dtype` and `categories` "
+                            "or `ordered`")
 
         if categories is None and ordered is None:
             dtype = self.dtype if dtype is None else dtype

pandas/tests/dtypes/test_common.py

@@ -550,6 +550,7 @@ def test_is_complex_dtype():
     (pd.CategoricalIndex(['a', 'b']).dtype, CategoricalDtype(['a', 'b'])),
     (pd.CategoricalIndex(['a', 'b']), CategoricalDtype(['a', 'b'])),
     (CategoricalDtype(), CategoricalDtype()),
+    (CategoricalDtype(['a', 'b']), CategoricalDtype()),
     (pd.DatetimeIndex([1, 2]), np.dtype('<M8[ns]')),
     (pd.DatetimeIndex([1, 2]).dtype, np.dtype('<M8[ns]')),
     ('<M8[ns]', np.dtype('<M8[ns]')),

pandas/tests/test_categorical.py

@@ -454,11 +454,21 @@ def test_constructor_dtype_and_others_raises(self):
         with tm.assert_raises_regex(ValueError, "Cannot"):
             Categorical(['a', 'b'], ordered=False, dtype=dtype)
 
-    def test_constructor_str_category(self):
-        result = Categorical(['a', 'b'], dtype='category')
-        expected = Categorical(['a', 'b'])
+    @pytest.mark.parametrize('categories', [
+        None, ['a', 'b'], ['a', 'c'],
+    ])
+    @pytest.mark.parametrize('ordered', [True, False])
+    def test_constructor_str_category(self, categories, ordered):
+        result = Categorical(['a', 'b'], categories=categories,
+                             ordered=ordered, dtype='category')
+        expected = Categorical(['a', 'b'], categories=categories,
+                               ordered=ordered)
         tm.assert_categorical_equal(result, expected)
 
+    def test_constructor_str_unknown(self):
+        with tm.assert_raises_regex(ValueError, "Unknown `dtype`"):
+            Categorical([1, 2], dtype="foo")
+
     def test_from_codes(self):
 
         # too few categories