ENH: Accept CategoricalDtype in astype and Series

Author: TomAugspurger

pandas/core/internals.py

@@ -487,6 +487,16 @@ def _astype(self, dtype, copy=False, errors='raise', values=None,
         # may need to convert to categorical
         # this is only called for non-categoricals
         if self.is_categorical_astype(dtype):
+            if (('categories' in kwargs or 'ordered' in kwargs) and
+                    isinstance(dtype, CategoricalDtype)):
+                raise TypeError("Cannot specify a CategoricalDtype and also "
+                                "`categories` or `ordered`")
+            kwargs = kwargs.copy()
+            categories = getattr(dtype, 'categories', None)
+            ordered = getattr(dtype, 'ordered', False)
+
+            kwargs.setdefault('categories', categories)
+            kwargs.setdefault('ordered', ordered)
             return self.make_block(Categorical(self.values, **kwargs))
 
         # astype processing

pandas/core/series.py

@@ -2908,7 +2908,8 @@ def _try_cast(arr, take_fast_path):
                 subarr = np.array(subarr, dtype=dtype, copy=copy)
         except (ValueError, TypeError):
             if is_categorical_dtype(dtype):
-                subarr = Categorical(arr)
+                subarr = Categorical(arr, dtype.categories,
+                                     ordered=dtype.ordered)
             elif dtype is not None and raise_cast_failure:
                 raise
             else:

pandas/tests/series/test_constructors.py

@@ -3,6 +3,7 @@
 
 from datetime import datetime, timedelta
 
+import pytest
 from numpy import nan
 import numpy as np
 import numpy.ma as ma
@@ -148,6 +149,30 @@ def test_constructor_categorical(self):
         self.assertTrue(is_categorical_dtype(s))
         self.assertTrue(is_categorical_dtype(s.dtype))
 
+    def test_constructor_categorical_dtype(self):
+        result = pd.Series(['a', 'b'],
+                           dtype=pd.CategoricalDtype(['a', 'b', 'c'],
+                                                     ordered=True))
+        assert is_categorical_dtype(result) is True
+        tm.assert_index_equal(result.cat.categories, pd.Index(['a', 'b', 'c']))
+        assert result.cat.ordered
+
+        result = pd.Series(['a', 'b'], dtype=pd.CategoricalDtype(['b', 'a']))
+        assert is_categorical_dtype(result)
+        tm.assert_index_equal(result.cat.categories, pd.Index(['b', 'a']))
+        assert result.cat.ordered is False
+
+    @pytest.mark.xfail
+    def test_unordered_compare_equal(self):
+        result = pd.Series(['a', 'b', 'c'],
+                           dtype=pd.CategoricalDtype(['a', 'b']))
+        # TODO: is this a bug? Shouldn't unorderd categories not care about
+        # order in the comparison?
+        # https://github.com/pandas-dev/pandas/issues/16014
+        expected = pd.Series(pd.Categorical(['a', 'b', np.nan],
+                                            categories=['a', 'b']))
+        tm.assert_series_equal(result, expected)
+
     def test_constructor_maskedarray(self):
         data = ma.masked_all((3, ), dtype=float)
         result = Series(data)

pandas/tests/series/test_dtypes.py

@@ -12,7 +12,10 @@
 from numpy import nan
 import numpy as np
 
-from pandas import Series, Timestamp, Timedelta, DataFrame, date_range
+from pandas import (
+    Series, Timestamp, Timedelta, DataFrame, date_range,
+    Categorical, CategoricalDtype, Index
+)
 
 from pandas.compat import lrange, range, u
 from pandas import compat
@@ -171,6 +174,34 @@ def test_astype_dict(self):
         with pytest.raises(KeyError):
             s.astype({0: str})
 
+    def test_astype_categoricaldtype(self):
+        s = Series(['a', 'b', 'a'])
+        result = s.astype(CategoricalDtype(['a', 'b'], ordered=True))
+        expected = Series(Categorical(['a', 'b', 'a'], ordered=True))
+        tm.assert_series_equal(result, expected)
+
+        result = s.astype(CategoricalDtype(['a', 'b'], ordered=False))
+        expected = Series(Categorical(['a', 'b', 'a'], ordered=False))
+        tm.assert_series_equal(result, expected)
+
+        result = s.astype(CategoricalDtype(['a', 'b', 'c'], ordered=False))
+        expected = Series(Categorical(['a', 'b', 'a'],
+                                      categories=['a', 'b', 'c'],
+                                      ordered=False))
+        tm.assert_series_equal(result, expected)
+        tm.assert_index_equal(result.cat.categories, Index(['a', 'b', 'c']))
+
+    def test_astype_categoricaldtype_with_args(self):
+        s = Series(['a', 'b'])
+        type_ = CategoricalDtype(['a', 'b'])
+
+        with pytest.raises(TypeError):
+            s.astype(type_, ordered=True)
+        with pytest.raises(TypeError):
+            s.astype(type_, categories=['a', 'b'])
+        with pytest.raises(TypeError):
+            s.astype(type_, categories=['a', 'b'], ordered=False)
+
     def test_astype_generic_timestamp_deprecated(self):
         # see gh-15524
         data = [1]