feedback: docs, whatsnew, dataframe test, strict dtype test

Author: jorisvandenbossche

doc/source/whatsnew/v1.1.0.rst

@@ -150,6 +150,7 @@ Other enhancements
   such as ``dict`` and ``list``, mirroring the behavior of :meth:`DataFrame.update` (:issue:`33215`)
 - :meth:`~pandas.core.groupby.GroupBy.transform` and :meth:`~pandas.core.groupby.GroupBy.aggregate` has gained ``engine`` and ``engine_kwargs`` arguments that supports executing functions with ``Numba`` (:issue:`32854`, :issue:`33388`)
 - :meth:`~pandas.core.resample.Resampler.interpolate` now supports SciPy interpolation method :class:`scipy.interpolate.CubicSpline` as method ``cubicspline`` (:issue:`33670`)
+- The ``ExtensionArray`` class has now an ``equals`` method, similarly to ``Series.equals()`` (:issue:`27081`).
 -
 
 .. ---------------------------------------------------------------------------

pandas/_testing.py

@@ -1490,7 +1490,9 @@ def box_expected(expected, box_cls, transpose=True):
     -------
     subclass of box_cls
     """
-    if box_cls is pd.Index:
+    if box_cls is pd.array:
+        expected = pd.array(expected)
+    elif box_cls is pd.Index:
         expected = pd.Index(expected)
     elif box_cls is pd.Series:
         expected = pd.Series(expected)

pandas/core/arrays/base.py

@@ -335,13 +335,19 @@ def __iter__(self):
         for i in range(len(self)):
             yield self[i]
 
-    def __eq__(self, other: Any) -> Union[np.ndarray, "ExtensionArray"]:
+    def __eq__(self, other: Any) -> ArrayLike:
         """
         Return for `self == other` (element-wise equality).
         """
+        # Implementer note: this should return a boolean numpy ndarray or
+        # a boolean ExtensionArray.
+        # When `other` is one of Series, Index, or DataFrame, this method should
+        # return NotImplemented (to ensure that those objects are responsible for
+        # first unpacking the arrays, and then dispatch the operation to the
+        # underlying arrays)
         raise AbstractMethodError(self)
 
-    def __ne__(self, other: Any) -> Union[np.ndarray, "ExtensionArray"]:
+    def __ne__(self, other: Any) -> ArrayLike:
         """
         Return for `self != other` (element-wise in-equality).
         """
@@ -713,6 +719,8 @@ def equals(self, other: "ExtensionArray") -> bool:
         """
         if not type(self) == type(other):
             return False
+        elif not self.dtype == other.dtype:
+            return False
         elif not len(self) == len(other):
             return False
         else:

pandas/tests/arrays/integer/test_comparison.py

@@ -104,3 +104,13 @@ def test_compare_to_int(self, any_nullable_int_dtype, all_compare_operators):
         expected[s2.isna()] = pd.NA
 
         self.assert_series_equal(result, expected)
+
+
+def test_equals():
+    # GH-30652
+    # equals is generally tested in /tests/extension/base/methods, but this
+    # specifically tests that two arrays of the same class but different dtype
+    # do not evaluate equal
+    a1 = pd.array([1, 2, None], dtype="Int64")
+    a2 = pd.array([1, 2, None], dtype="Int32")
+    assert a1.equals(a2) is False

pandas/tests/extension/base/methods.py

@@ -422,14 +422,17 @@ def test_repeat_raises(self, data, repeats, kwargs, error, msg, use_numpy):
             else:
                 data.repeat(repeats, **kwargs)
 
-    def test_equals(self, data, na_value, as_series):
+    @pytest.mark.parametrize("box", [pd.array, pd.Series, pd.DataFrame])
+    def test_equals(self, data, na_value, as_series, box):
         data2 = type(data)._from_sequence([data[0]] * len(data), dtype=data.dtype)
         data_na = type(data)._from_sequence([na_value] * len(data), dtype=data.dtype)
 
-        if as_series:
-            data = pd.Series(data)
-            data2 = pd.Series(data2)
-            data_na = pd.Series(data_na)
+        data = tm.box_expected(data, box, transpose=False)
+        data2 = tm.box_expected(data2, box, transpose=False)
+        data_na = tm.box_expected(data_na, box, transpose=False)
+
+        # we are asserting with `is True/False` explicitly, to test that the
+        # result is an actual Python bool, and not something "truthy"
 
         assert data.equals(data) is True
         assert data.equals(data.copy()) is True

pandas/tests/extension/test_numpy.py

@@ -262,9 +262,10 @@ def test_diff(self, data, periods):
         return super().test_diff(data, periods)
 
     @skip_nested
-    def test_equals(self, data, na_value, as_series):
+    @pytest.mark.parametrize("box", [pd.array, pd.Series, pd.DataFrame])
+    def test_equals(self, data, na_value, as_series, box):
         # Fails creating with _from_sequence
-        super().test_equals(data, na_value, as_series)
+        super().test_equals(data, na_value, as_series, box)
 
 
 @skip_nested

pandas/tests/extension/test_sparse.py

@@ -316,9 +316,10 @@ def test_shift_0_periods(self, data):
         data._sparse_values[0] = data._sparse_values[1]
         assert result._sparse_values[0] != result._sparse_values[1]
 
-    def test_equals(self, data, na_value, as_series):
+    @pytest.mark.parametrize("box", [pd.array, pd.Series, pd.DataFrame])
+    def test_equals(self, data, na_value, as_series, box):
         self._check_unsupported(data)
-        super().test_equals(data, na_value, as_series)
+        super().test_equals(data, na_value, as_series, box)
 
 
 class TestCasting(BaseSparseTests, base.BaseCastingTests):