ENH: Support Series[bool] as indexer for iloc.__getitem__ (#61162)

* updated indexing.py to allow iloc.__getitem__

* Updated test_iloc_mask test

* bugfix test_iloc_mask test

* bugfix test_iloc_mask

* whatsnew

* added test to test_iloc_mask

* formatting

* precommit

* added tests for series bool mask

* precommit

* reformatted tests

Author: arthurlw

Diff for: doc/source/whatsnew/v3.0.0.rst

@@ -68,6 +68,7 @@ Other enhancements
 - :func:`read_parquet` accepts ``to_pandas_kwargs`` which are forwarded to :meth:`pyarrow.Table.to_pandas` which enables passing additional keywords to customize the conversion to pandas, such as ``maps_as_pydicts`` to read the Parquet map data type as python dictionaries (:issue:`56842`)
 - :meth:`.DataFrameGroupBy.transform`, :meth:`.SeriesGroupBy.transform`, :meth:`.DataFrameGroupBy.agg`, :meth:`.SeriesGroupBy.agg`, :meth:`.SeriesGroupBy.apply`, :meth:`.DataFrameGroupBy.apply` now support ``kurt`` (:issue:`40139`)
 - :meth:`DataFrame.apply` supports using third-party execution engines like the Bodo.ai JIT compiler (:issue:`60668`)
+- :meth:`DataFrame.iloc` and :meth:`Series.iloc` now support boolean masks in ``__getitem__`` for more consistent indexing behavior (:issue:`60994`)
 - :meth:`DataFrameGroupBy.transform`, :meth:`SeriesGroupBy.transform`, :meth:`DataFrameGroupBy.agg`, :meth:`SeriesGroupBy.agg`, :meth:`RollingGroupby.apply`, :meth:`ExpandingGroupby.apply`, :meth:`Rolling.apply`, :meth:`Expanding.apply`, :meth:`DataFrame.apply` with ``engine="numba"`` now supports positional arguments passed as kwargs (:issue:`58995`)
 - :meth:`Rolling.agg`, :meth:`Expanding.agg` and :meth:`ExponentialMovingWindow.agg` now accept :class:`NamedAgg` aggregations through ``**kwargs`` (:issue:`28333`)
 - :meth:`Series.map` can now accept kwargs to pass on to func (:issue:`59814`)

Diff for: pandas/core/indexing.py

@@ -1582,11 +1582,7 @@ def _validate_key(self, key, axis: AxisInt) -> None:
         if com.is_bool_indexer(key):
             if hasattr(key, "index") and isinstance(key.index, Index):
                 if key.index.inferred_type == "integer":
-                    raise NotImplementedError(
-                        "iLocation based boolean "
-                        "indexing on an integer type "
-                        "is not available"
-                    )
+                    return
                 raise ValueError(
                     "iLocation based boolean indexing cannot use an indexable as a mask"
                 )

Diff for: pandas/tests/indexing/test_iloc.py

@@ -726,15 +726,16 @@ def test_iloc_setitem_with_scalar_index(self, indexer, value):
 
     @pytest.mark.filterwarnings("ignore::UserWarning")
     def test_iloc_mask(self):
-        # GH 3631, iloc with a mask (of a series) should raise
+        # GH 60994, iloc with a mask (of a series) should return accordingly
         df = DataFrame(list(range(5)), index=list("ABCDE"), columns=["a"])
         mask = df.a % 2 == 0
         msg = "iLocation based boolean indexing cannot use an indexable as a mask"
         with pytest.raises(ValueError, match=msg):
             df.iloc[mask]
+
         mask.index = range(len(mask))
-        msg = "iLocation based boolean indexing on an integer type is not available"
-        with pytest.raises(NotImplementedError, match=msg):
+        msg = "Unalignable boolean Series provided as indexer"
+        with pytest.raises(IndexingError, match=msg):
             df.iloc[mask]
 
         # ndarray ok
@@ -753,18 +754,13 @@ def test_iloc_mask(self):
             (None, ".iloc"): "0b1100",
             ("index", ""): "0b11",
             ("index", ".loc"): "0b11",
-            ("index", ".iloc"): (
-                "iLocation based boolean indexing cannot use an indexable as a mask"
-            ),
-            ("locs", ""): "Unalignable boolean Series provided as indexer "
-            "(index of the boolean Series and of the indexed "
-            "object do not match).",
-            ("locs", ".loc"): "Unalignable boolean Series provided as indexer "
-            "(index of the boolean Series and of the "
-            "indexed object do not match).",
-            ("locs", ".iloc"): (
-                "iLocation based boolean indexing on an integer type is not available"
-            ),
+            (
+                "index",
+                ".iloc",
+            ): "iLocation based boolean indexing cannot use an indexable as a mask",
+            ("locs", ""): "Unalignable boolean Series provided as indexer",
+            ("locs", ".loc"): "Unalignable boolean Series provided as indexer",
+            ("locs", ".iloc"): "Unalignable boolean Series provided as indexer",
         }
 
         # UserWarnings from reindex of a boolean mask
@@ -780,18 +776,52 @@ def test_iloc_mask(self):
                     else:
                         accessor = df
                     answer = str(bin(accessor[mask]["nums"].sum()))
-                except (ValueError, IndexingError, NotImplementedError) as err:
+                except (ValueError, IndexingError) as err:
                     answer = str(err)
 
                 key = (
                     idx,
                     method,
                 )
-                r = expected.get(key)
-                if r != answer:
-                    raise AssertionError(
-                        f"[{key}] does not match [{answer}], received [{r}]"
+                expected_result = expected.get(key)
+
+                # Fix the assertion to check for substring match
+                if (
+                    idx is None or (idx == "index" and method != ".iloc")
+                ) and "0b" in expected_result:
+                    # For successful numeric results, exact match is needed
+                    assert expected_result == answer, (
+                        f"[{key}] does not match [{answer}]"
                     )
+                else:
+                    # For error messages, substring match is sufficient
+                    assert expected_result in answer, f"[{key}] not found in [{answer}]"
+
+    def test_iloc_with_numpy_bool_array(self):
+        df = DataFrame(list(range(5)), index=list("ABCDE"), columns=["a"])
+        result = df.iloc[np.array([True, False, True, False, True], dtype=bool)]
+        expected = DataFrame({"a": [0, 2, 4]}, index=["A", "C", "E"])
+        tm.assert_frame_equal(result, expected)
+
+    def test_iloc_series_mask_with_index_mismatch_raises(self):
+        df = DataFrame(list(range(5)), index=list("ABCDE"), columns=["a"])
+        mask = df.a % 2 == 0
+        msg = "Unalignable boolean Series provided as indexer"
+        with pytest.raises(IndexingError, match=msg):
+            df.iloc[Series([True] * len(mask), dtype=bool)]
+
+    def test_iloc_series_mask_all_true(self):
+        df = DataFrame(list(range(5)), columns=["a"])
+        mask = Series([True] * len(df), dtype=bool)
+        result = df.iloc[mask]
+        tm.assert_frame_equal(result, df)
+
+    def test_iloc_series_mask_alternate_true(self):
+        df = DataFrame(list(range(5)), columns=["a"])
+        mask = Series([True, False, True, False, True], dtype=bool)
+        result = df.iloc[mask]
+        expected = DataFrame({"a": [0, 2, 4]}, index=[0, 2, 4])
+        tm.assert_frame_equal(result, expected)
 
     def test_iloc_non_unique_indexing(self):
         # GH 4017, non-unique indexing (on the axis)