TST: ExtensionArrays disallow .values attribute (pandas-dev#20794)

Author: jorisvandenbossche

pandas/core/arrays/base.py

@@ -61,14 +61,19 @@ class ExtensionArray(object):
 
     ExtensionArrays are limited to 1 dimension.
 
-    They may be backed by none, one, or many NumPy ararys. For example,
+    They may be backed by none, one, or many NumPy arrays. For example,
     ``pandas.Categorical`` is an extension array backed by two arrays,
     one for codes and one for categories. An array of IPv6 address may
     be backed by a NumPy structured array with two fields, one for the
     lower 64 bits and one for the upper 64 bits. Or they may be backed
     by some other storage type, like Python lists. Pandas makes no
     assumptions on how the data are stored, just that it can be converted
     to a NumPy array.
+    The ExtensionArray interface does not impose any rules on how this data
+    is stored. However, currently, the backing data cannot be stored in
+    attributes called ``.values`` or ``._values`` to ensure full compatibility
+    with pandas internals. But other names as ``.data``, ``._data``,
+    ``._items``, ... can be freely used.
     """
     # '_typ' is for pandas.core.dtypes.generic.ABCExtensionArray.
     # Don't override this.

pandas/tests/extension/base/interface.py

@@ -50,3 +50,9 @@ def test_is_extension_array_dtype(self, data):
         assert is_extension_array_dtype(data.dtype)
         assert is_extension_array_dtype(pd.Series(data))
         assert isinstance(data.dtype, ExtensionDtype)
+
+    def test_no_values_attribute(self, data):
+        # GH-20735: EA's with .values attribute give problems with internal
+        # code, disallowing this for now until solved
+        assert not hasattr(data, 'values')
+        assert not hasattr(data, '_values')

pandas/tests/extension/decimal/array.py

@@ -30,10 +30,13 @@ class DecimalArray(ExtensionArray):
     def __init__(self, values):
         values = np.asarray(values, dtype=object)
 
-        self.values = values
+        self._data = values
         # Some aliases for common attribute names to ensure pandas supports
         # these
-        self._items = self._data = self.data = self.values
+        self._items = self.data = self._data
+        # those aliases are currently not working due to assumptions
+        # in internal code (GH-20735)
+        # self._values = self.values = self.data
 
     @classmethod
     def _from_sequence(cls, scalars):
@@ -45,27 +48,27 @@ def _from_factorized(cls, values, original):
 
     def __getitem__(self, item):
         if isinstance(item, numbers.Integral):
-            return self.values[item]
+            return self._data[item]
         else:
-            return type(self)(self.values[item])
+            return type(self)(self._data[item])
 
     def copy(self, deep=False):
         if deep:
-            return type(self)(self.values.copy())
+            return type(self)(self._data.copy())
         return type(self)(self)
 
     def __setitem__(self, key, value):
         if pd.api.types.is_list_like(value):
             value = [decimal.Decimal(v) for v in value]
         else:
             value = decimal.Decimal(value)
-        self.values[key] = value
+        self._data[key] = value
 
     def __len__(self):
-        return len(self.values)
+        return len(self._data)
 
     def __repr__(self):
-        return 'DecimalArray({!r})'.format(self.values)
+        return 'DecimalArray({!r})'.format(self._data)
 
     @property
     def nbytes(self):
@@ -75,7 +78,7 @@ def nbytes(self):
         return 0
 
     def isna(self):
-        return np.array([x.is_nan() for x in self.values])
+        return np.array([x.is_nan() for x in self._data])
 
     def take(self, indexer, allow_fill=True, fill_value=None):
         indexer = np.asarray(indexer)
@@ -86,7 +89,7 @@ def take(self, indexer, allow_fill=True, fill_value=None):
             return type(self)([self._na_value] * len(indexer))
 
         indexer = _ensure_platform_int(indexer)
-        out = self.values.take(indexer)
+        out = self._data.take(indexer)
         out[mask] = self._na_value
 
         return type(self)(out)
@@ -97,7 +100,7 @@ def _na_value(self):
 
     @classmethod
     def _concat_same_type(cls, to_concat):
-        return cls(np.concatenate([x.values for x in to_concat]))
+        return cls(np.concatenate([x._data for x in to_concat]))
 
 
 def make_data():

pandas/tests/extension/json/array.py

@@ -33,6 +33,13 @@ def __init__(self, values):
                 raise TypeError
         self.data = values
 
+        # Some aliases for common attribute names to ensure pandas supports
+        # these
+        self._items = self._data = self.data
+        # those aliases are currently not working due to assumptions
+        # in internal code (GH-20735)
+        # self._values = self.values = self.data
+
     @classmethod
     def _from_sequence(cls, scalars):
         return cls(scalars)