BUG: BooleanArray match non-masked behavior div/pow/mod (pandas-dev#46063)

jbrockmendel · yehoshuadimarsky · commit 5f5c36560161 · 2022-07-13T10:17:55.000-04:00
diff --git a/doc/source/whatsnew/v1.5.0.rst b/doc/source/whatsnew/v1.5.0.rst
@@ -328,6 +328,7 @@ Time Zones
 Numeric
 ^^^^^^^
 - Bug in operations with array-likes with ``dtype="boolean"`` and :attr:`NA` incorrectly altering the array in-place (:issue:`45421`)
+- Bug in division, ``pow`` and ``mod`` operations on array-likes with ``dtype="boolean"`` not being like their ``np.bool_`` counterparts (:issue:`46063`)
 - Bug in multiplying a :class:`Series` with ``IntegerDtype`` or ``FloatingDtype`` by an array-like with ``timedelta64[ns]`` dtype incorrectly raising (:issue:`45622`)
 -
 
diff --git a/pandas/core/arrays/masked.py b/pandas/core/arrays/masked.py
@@ -626,10 +626,21 @@ def _arith_method(self, other, op):
         if other is libmissing.NA:
             result = np.ones_like(self._data)
             if self.dtype.kind == "b":
-                if op_name in {"floordiv", "rfloordiv", "mod", "rmod", "pow", "rpow"}:
+                if op_name in {
+                    "floordiv",
+                    "rfloordiv",
+                    "pow",
+                    "rpow",
+                    "truediv",
+                    "rtruediv",
+                }:
+                    # GH#41165 Try to match non-masked Series behavior
+                    #  This is still imperfect GH#46043
+                    raise NotImplementedError(
+                        f"operator '{op_name}' not implemented for bool dtypes"
+                    )
+                elif op_name in {"mod", "rmod"}:
                     dtype = "int8"
-                elif op_name in {"truediv", "rtruediv"}:
-                    dtype = "float64"
                 else:
                     dtype = "bool"
                 result = result.astype(dtype)
@@ -646,12 +657,6 @@ def _arith_method(self, other, op):
                 #  types with respect to floordiv-by-zero
                 pd_op = op
 
-            elif self.dtype.kind == "b" and (
-                "div" in op_name or "pow" in op_name or "mod" in op_name
-            ):
-                # TODO(GH#41165): should these be disallowed?
-                pd_op = op
-
             with np.errstate(all="ignore"):
                 result = pd_op(self._data, other)
 
diff --git a/pandas/tests/arrays/boolean/test_arithmetic.py b/pandas/tests/arrays/boolean/test_arithmetic.py
@@ -5,7 +5,6 @@
 
 import pandas as pd
 import pandas._testing as tm
-from pandas.arrays import FloatingArray
 
 
 @pytest.fixture
@@ -55,15 +54,13 @@ def test_sub(left_array, right_array):
 
 
 def test_div(left_array, right_array):
-    result = left_array / right_array
-    expected = FloatingArray(
-        np.array(
-            [1.0, np.inf, np.nan, 0.0, np.nan, np.nan, np.nan, np.nan, np.nan],
-            dtype="float64",
-        ),
-        np.array([False, False, True, False, False, True, True, True, True]),
-    )
-    tm.assert_extension_array_equal(result, expected)
+    msg = "operator '.*' not implemented for bool dtypes"
+    with pytest.raises(NotImplementedError, match=msg):
+        # check that we are matching the non-masked Series behavior
+        pd.Series(left_array._data) / pd.Series(right_array._data)
+
+    with pytest.raises(NotImplementedError, match=msg):
+        left_array / right_array
 
 
 @pytest.mark.parametrize(
@@ -76,6 +73,11 @@ def test_div(left_array, right_array):
 )
 def test_op_int8(left_array, right_array, opname):
     op = getattr(operator, opname)
+    if opname != "mod":
+        msg = "operator '.*' not implemented for bool dtypes"
+        with pytest.raises(NotImplementedError, match=msg):
+            result = op(left_array, right_array)
+        return
     result = op(left_array, right_array)
     expected = op(left_array.astype("Int8"), right_array.astype("Int8"))
     tm.assert_extension_array_equal(result, expected)
diff --git a/pandas/tests/arrays/masked/test_arithmetic.py b/pandas/tests/arrays/masked/test_arithmetic.py
@@ -29,6 +29,15 @@ def check_skip(data, op_name):
         pytest.skip("subtract not implemented for boolean")
 
 
+def is_bool_not_implemented(data, op_name):
+    # match non-masked behavior
+    return data.dtype.kind == "b" and op_name.strip("_").lstrip("r") in [
+        "pow",
+        "truediv",
+        "floordiv",
+    ]
+
+
 # Test equivalence of scalars, numpy arrays with array ops
 # -----------------------------------------------------------------------------
 
@@ -42,9 +51,16 @@ def test_array_scalar_like_equivalence(data, all_arithmetic_operators):
 
     # TODO also add len-1 array (np.array([scalar], dtype=data.dtype.numpy_dtype))
     for scalar in [scalar, data.dtype.type(scalar)]:
-        result = op(data, scalar)
-        expected = op(data, scalar_array)
-        tm.assert_extension_array_equal(result, expected)
+        if is_bool_not_implemented(data, all_arithmetic_operators):
+            msg = "operator '.*' not implemented for bool dtypes"
+            with pytest.raises(NotImplementedError, match=msg):
+                op(data, scalar)
+            with pytest.raises(NotImplementedError, match=msg):
+                op(data, scalar_array)
+        else:
+            result = op(data, scalar)
+            expected = op(data, scalar_array)
+            tm.assert_extension_array_equal(result, expected)
 
 
 def test_array_NA(data, all_arithmetic_operators):
@@ -56,6 +72,15 @@ def test_array_NA(data, all_arithmetic_operators):
     scalar_array = pd.array([pd.NA] * len(data), dtype=data.dtype)
 
     mask = data._mask.copy()
+
+    if is_bool_not_implemented(data, all_arithmetic_operators):
+        msg = "operator '.*' not implemented for bool dtypes"
+        with pytest.raises(NotImplementedError, match=msg):
+            op(data, scalar)
+        # GH#45421 check op doesn't alter data._mask inplace
+        tm.assert_numpy_array_equal(mask, data._mask)
+        return
+
     result = op(data, scalar)
     # GH#45421 check op doesn't alter data._mask inplace
     tm.assert_numpy_array_equal(mask, data._mask)
@@ -74,6 +99,14 @@ def test_numpy_array_equivalence(data, all_arithmetic_operators):
     numpy_array = np.array([scalar] * len(data), dtype=data.dtype.numpy_dtype)
     pd_array = pd.array(numpy_array, dtype=data.dtype)
 
+    if is_bool_not_implemented(data, all_arithmetic_operators):
+        msg = "operator '.*' not implemented for bool dtypes"
+        with pytest.raises(NotImplementedError, match=msg):
+            op(data, numpy_array)
+        with pytest.raises(NotImplementedError, match=msg):
+            op(data, pd_array)
+        return
+
     result = op(data, numpy_array)
     expected = op(data, pd_array)
     tm.assert_extension_array_equal(result, expected)
@@ -91,6 +124,14 @@ def test_frame(data, all_arithmetic_operators):
     # DataFrame with scalar
     df = pd.DataFrame({"A": data})
 
+    if is_bool_not_implemented(data, all_arithmetic_operators):
+        msg = "operator '.*' not implemented for bool dtypes"
+        with pytest.raises(NotImplementedError, match=msg):
+            op(df, scalar)
+        with pytest.raises(NotImplementedError, match=msg):
+            op(data, scalar)
+        return
+
     result = op(df, scalar)
     expected = pd.DataFrame({"A": op(data, scalar)})
     tm.assert_frame_equal(result, expected)
@@ -101,30 +142,25 @@ def test_series(data, all_arithmetic_operators):
     op = tm.get_op_from_name(all_arithmetic_operators)
     check_skip(data, all_arithmetic_operators)
 
-    s = pd.Series(data)
+    ser = pd.Series(data)
 
-    # Series with scalar
-    result = op(s, scalar)
-    expected = pd.Series(op(data, scalar))
-    tm.assert_series_equal(result, expected)
+    others = [
+        scalar,
+        np.array([scalar] * len(data), dtype=data.dtype.numpy_dtype),
+        pd.array([scalar] * len(data), dtype=data.dtype),
+        pd.Series([scalar] * len(data), dtype=data.dtype),
+    ]
 
-    # Series with np.ndarray
-    other = np.array([scalar] * len(data), dtype=data.dtype.numpy_dtype)
-    result = op(s, other)
-    expected = pd.Series(op(data, other))
-    tm.assert_series_equal(result, expected)
+    for other in others:
+        if is_bool_not_implemented(data, all_arithmetic_operators):
+            msg = "operator '.*' not implemented for bool dtypes"
+            with pytest.raises(NotImplementedError, match=msg):
+                op(ser, other)
 
-    # Series with pd.array
-    other = pd.array([scalar] * len(data), dtype=data.dtype)
-    result = op(s, other)
-    expected = pd.Series(op(data, other))
-    tm.assert_series_equal(result, expected)
-
-    # Series with Series
-    other = pd.Series([scalar] * len(data), dtype=data.dtype)
-    result = op(s, other)
-    expected = pd.Series(op(data, other.array))
-    tm.assert_series_equal(result, expected)
+        else:
+            result = op(ser, other)
+            expected = pd.Series(op(data, other))
+            tm.assert_series_equal(result, expected)
 
 
 # Test generic characteristics / errors
@@ -169,6 +205,9 @@ def test_error_len_mismatch(data, all_arithmetic_operators):
             r"numpy boolean subtract, the `\-` operator, is not supported, use "
             r"the bitwise_xor, the `\^` operator, or the logical_xor function instead"
         )
+    elif is_bool_not_implemented(data, all_arithmetic_operators):
+        msg = "operator '.*' not implemented for bool dtypes"
+        err = NotImplementedError
 
     for other in [other, np.array(other)]:
         with pytest.raises(err, match=msg):
diff --git a/pandas/tests/extension/test_boolean.py b/pandas/tests/extension/test_boolean.py
@@ -108,7 +108,11 @@ class TestArithmeticOps(base.BaseArithmeticOpsTests):
 
     def check_opname(self, s, op_name, other, exc=None):
         # overwriting to indicate ops don't raise an error
-        super().check_opname(s, op_name, other, exc=None)
+        exc = None
+        if op_name.strip("_").lstrip("r") in ["pow", "truediv", "floordiv"]:
+            # match behavior with non-masked bool dtype
+            exc = NotImplementedError
+        super().check_opname(s, op_name, other, exc=exc)
 
     def _check_op(self, obj, op, other, op_name, exc=NotImplementedError):
         if exc is None:
@@ -144,9 +148,19 @@ def _check_op(self, obj, op, other, op_name, exc=NotImplementedError):
             with pytest.raises(exc):
                 op(obj, other)
 
-    def _check_divmod_op(self, s, op, other, exc=None):
-        # override to not raise an error
-        super()._check_divmod_op(s, op, other, None)
+    @pytest.mark.xfail(
+        reason="Inconsistency between floordiv and divmod; we raise for floordiv "
+        "but not for divmod. This matches what we do for non-masked bool dtype."
+    )
+    def test_divmod_series_array(self, data, data_for_twos):
+        super().test_divmod_series_array(data, data_for_twos)
+
+    @pytest.mark.xfail(
+        reason="Inconsistency between floordiv and divmod; we raise for floordiv "
+        "but not for divmod. This matches what we do for non-masked bool dtype."
+    )
+    def test_divmod(self, data):
+        super().test_divmod(data)
 
 
 class TestComparisonOps(base.BaseComparisonOpsTests):

Original file line number	Diff line number	Diff line change
`@@ -328,6 +328,7 @@ Time Zones`
`328`	`328`	`Numeric`
`329`	`329`	`^^^^^^^`
`330`	`330`	- Bug in operations with array-likes with ``dtype="boolean"`` and :attr:`NA` incorrectly altering the array in-place (:issue:`45421`)
	`331`	+- Bug in division, ``pow`` and ``mod`` operations on array-likes with ``dtype="boolean"`` not being like their ``np.bool_`` counterparts (:issue:`46063`)
`331`	`332`	- Bug in multiplying a :class:`Series` with ``IntegerDtype`` or ``FloatingDtype`` by an array-like with ``timedelta64[ns]`` dtype incorrectly raising (:issue:`45622`)
`332`	`333`	`-`
`333`	`334`