BUG: Categorical.isin raising for overlapping intervals (pandas-dev#5…

…4951) fix Categorical.isin raising for overlapping intervals
phofl · Sep 2, 2023 · c866a4a · c866a4a
1 parent 1605bdf
commit c866a4a
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 2 deletions.
diff --git a/doc/source/whatsnew/v2.2.0.rst b/doc/source/whatsnew/v2.2.0.rst
@@ -171,7 +171,7 @@ Bug fixes
 
 Categorical
 ^^^^^^^^^^^
--
+- :meth:`Categorical.isin` raising ``InvalidIndexError`` for categorical containing overlapping :class:`Interval` values (:issue:`34974`)
 -
 
 Datetimelike

diff --git a/pandas/core/arrays/categorical.py b/pandas/core/arrays/categorical.py
@@ -2597,7 +2597,7 @@ def isin(self, values) -> npt.NDArray[np.bool_]:
             )
         values = sanitize_array(values, None, None)
         null_mask = np.asarray(isna(values))
-        code_values = self.categories.get_indexer(values)
+        code_values = self.categories.get_indexer_for(values)
         code_values = code_values[null_mask | (code_values >= 0)]
         return algorithms.isin(self.codes, code_values)
 

diff --git a/pandas/tests/indexes/categorical/test_category.py b/pandas/tests/indexes/categorical/test_category.py
@@ -228,6 +228,13 @@ def test_isin(self):
         expected = np.array([False] * 5 + [True])
         tm.assert_numpy_array_equal(result, expected)
 
+    def test_isin_overlapping_intervals(self):
+        # GH 34974
+        idx = pd.IntervalIndex([pd.Interval(0, 2), pd.Interval(0, 1)])
+        result = CategoricalIndex(idx).isin(idx)
+        expected = np.array([True, True])
+        tm.assert_numpy_array_equal(result, expected)
+
     def test_identical(self):
         ci1 = CategoricalIndex(["a", "b"], categories=["a", "b"], ordered=True)
         ci2 = CategoricalIndex(["a", "b"], categories=["a", "b", "c"], ordered=True)