EA: support basic 2D operations

pandas/core/arrays/base.py

@@ -47,7 +47,7 @@ class ExtensionArray:
     * _from_sequence
     * _from_factorized
     * __getitem__
-    * __len__
+    * shape
     * dtype
     * nbytes
     * isna
@@ -272,7 +272,7 @@ def __len__(self) -> int:
         -------
         length : int
         """
-        raise AbstractMethodError(self)
+        return self.shape[0]
 
     def __iter__(self):
         """
@@ -300,14 +300,21 @@ def shape(self) -> Tuple[int, ...]:
         """
         Return a tuple of the array dimensions.
         """
-        return (len(self),)
+        raise AbstractMethodError(self)
 
     @property
     def ndim(self) -> int:
         """
         Extension Arrays are only allowed to be 1-dimensional.
         """
-        return 1
+        return len(self.shape)
+
+    @property
+    def size(self) -> int:
+        """
+        The number of elements in this array.
+        """
+        return np.prod(self.shape)
 
     @property
     def nbytes(self) -> int:

pandas/core/arrays/categorical.py

@@ -489,20 +489,6 @@ def astype(self, dtype, copy=True):
             return self._set_dtype(dtype)
         return np.array(self, dtype=dtype, copy=copy)
 
-    @cache_readonly
-    def ndim(self):
-        """
-        Number of dimensions of the Categorical
-        """
-        return self._codes.ndim
-
-    @cache_readonly
-    def size(self):
-        """
-        return the len of myself
-        """
-        return len(self)
-
     @cache_readonly
     def itemsize(self):
         """
@@ -1913,11 +1899,9 @@ def _slice(self, slicer):
         codes = self._codes[slicer]
         return self._constructor(values=codes, dtype=self.dtype, fastpath=True)
 
-    def __len__(self):
-        """
-        The length of this Categorical.
-        """
-        return len(self._codes)
+    @property
+    def shape(self):
+        return self._codes.shape
 
     def __iter__(self):
         """

pandas/core/arrays/datetimelike.py

@@ -402,12 +402,8 @@ def __array__(self, dtype=None):
         return self._data
 
     @property
-    def size(self) -> int:
-        """The number of elements in this array."""
-        return np.prod(self.shape)
-
-    def __len__(self):
-        return len(self._data)
+    def shape(self):
+        return self._data.shape
 
     def __getitem__(self, key):
         """

pandas/core/arrays/integer.py

@@ -393,8 +393,9 @@ def __setitem__(self, key, value):
         self._data[key] = value
         self._mask[key] = mask
 
-    def __len__(self):
-        return len(self._data)
+    @property
+    def shape(self):
+        return self._data.shape
 
     @property
     def nbytes(self):

pandas/core/arrays/interval.py

@@ -466,8 +466,9 @@ def _validate(self):
     def __iter__(self):
         return iter(np.asarray(self))
 
-    def __len__(self):
-        return len(self.left)
+    @property
+    def shape(self):
+        return self.left.shape
 
     def __getitem__(self, value):
         left = self.left[value]
@@ -701,11 +702,6 @@ def isna(self):
     def nbytes(self):
         return self.left.nbytes + self.right.nbytes
 
-    @property
-    def size(self):
-        # Avoid materializing self.values
-        return self.left.size
-
     @property
     def shape(self):
         return self.left.shape

pandas/core/arrays/numpy_.py

@@ -240,8 +240,9 @@ def __setitem__(self, key, value):
         else:
             self._ndarray[key] = value
 
-    def __len__(self):
-        return len(self._ndarray)
+    @property
+    def shape(self):
+        return self._ndarray.shape
 
     @property
     def nbytes(self):

pandas/core/arrays/sparse.py

@@ -849,8 +849,9 @@ def _valid_sp_values(self):
         mask = notna(sp_vals)
         return sp_vals[mask]
 
-    def __len__(self):
-        return self.sp_index.length
+    @property
+    def shape(self):
+        return (self.sp_index.length,)
 
     @property
     def _null_fill_value(self):

pandas/tests/extension/arrow/bool.py

@@ -73,8 +73,9 @@ def __getitem__(self, item):
             vals = self._data.to_pandas()[item]
             return type(self).from_scalars(vals)
 
-    def __len__(self):
-        return len(self._data)
+    @property
+    def shape(self):
+        return (len(self._data),)
 
     def astype(self, dtype, copy=True):
         # needed to fix this astype for the Series constructor.

pandas/tests/extension/arrow/test_bool.py

@@ -15,13 +15,17 @@ def dtype():
     return ArrowBoolDtype()
 
 
-@pytest.fixture
 def data():
     values = np.random.randint(0, 2, size=100, dtype=bool)
     values[1] = ~values[0]
     return ArrowBoolArray.from_scalars(values)
 
 
+@pytest.fixture(name="data")
+def data_fixture():
+    return data()
+
+
 @pytest.fixture
 def data_missing():
     return ArrowBoolArray.from_scalars([None, True])

pandas/tests/extension/decimal/array.py

@@ -118,8 +118,9 @@ def __setitem__(self, key, value):
             value = decimal.Decimal(value)
         self._data[key] = value
 
-    def __len__(self):
-        return len(self._data)
+    @property
+    def shape(self):
+        return self._data.shape
 
     @property
     def nbytes(self):

pandas/tests/extension/json/array.py

@@ -105,8 +105,9 @@ def __setitem__(self, key, value):
                     assert isinstance(v, self.dtype.type)
                     self.data[k] = v
 
-    def __len__(self):
-        return len(self.data)
+    @property
+    def shape(self):
+        return (len(self.data),)
 
     @property
     def nbytes(self):