Backport PR pandas-dev#47771 on branch 1.4.x (REGR: fix pd.cut with datetime IntervalIndex as bins) (pandas-dev#48166)

Backport PR pandas-dev#47771: REGR: fix pd.cut with datetime IntervalIndex as bins

Co-authored-by: Joris Van den Bossche <[email protected]>

Author: meeseeksmachine

doc/source/whatsnew/v1.4.4.rst

@@ -16,6 +16,7 @@ Fixed regressions
 ~~~~~~~~~~~~~~~~~
 - Fixed regression in taking NULL :class:`objects` from a :class:`DataFrame` causing a segmentation violation. These NULL values are created by :meth:`numpy.empty_like` (:issue:`46848`)
 - Fixed regression in :func:`concat` materializing :class:`Index` during sorting even if :class:`Index` was already sorted (:issue:`47501`)
+- Fixed regression in :func:`cut` using a ``datetime64`` IntervalIndex as bins (:issue:`46218`)
 - Fixed regression in :meth:`DataFrame.loc` not updating the cache correctly after values were set (:issue:`47867`)
 - Fixed regression in :meth:`DataFrame.loc` not aligning index in some cases when setting a :class:`DataFrame` (:issue:`47578`)
 - Fixed regression in :meth:`DataFrame.loc` setting a length-1 array like value to a single value in the DataFrame (:issue:`46268`)

pandas/core/indexes/base.py

@@ -3816,8 +3816,14 @@ def _should_partial_index(self, target: Index) -> bool:
         Should we attempt partial-matching indexing?
         """
         if is_interval_dtype(self.dtype):
+            if is_interval_dtype(target.dtype):
+                return False
+            # See https://github.com/pandas-dev/pandas/issues/47772 the commented
+            # out code can be restored (instead of hardcoding `return True`)
+            # once that issue if fixed
             # "Index" has no attribute "left"
-            return self.left._should_compare(target)  # type: ignore[attr-defined]
+            # return self.left._should_compare(target)  # type: ignore[attr-defined]
+            return True
         return False
 
     @final

pandas/tests/indexes/interval/test_indexing.py

@@ -8,6 +8,7 @@
 from pandas import (
     NA,
     CategoricalIndex,
+    DatetimeIndex,
     Index,
     Interval,
     IntervalIndex,
@@ -298,6 +299,20 @@ def test_get_indexer_categorical_with_nans(self):
         expected = np.array([0, 1, 2, 3, 4, 0, 1, 2, 3, 4], dtype=np.intp)
         tm.assert_numpy_array_equal(result, expected)
 
+    def test_get_indexer_datetime(self):
+        ii = IntervalIndex.from_breaks(date_range("2018-01-01", periods=4))
+        result = ii.get_indexer(DatetimeIndex(["2018-01-02"]))
+        expected = np.array([0], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = ii.get_indexer(DatetimeIndex(["2018-01-02"]).astype(str))
+        tm.assert_numpy_array_equal(result, expected)
+
+        # TODO this should probably be deprecated?
+        # https://github.com/pandas-dev/pandas/issues/47772
+        result = ii.get_indexer(DatetimeIndex(["2018-01-02"]).asi8)
+        tm.assert_numpy_array_equal(result, expected)
+
     @pytest.mark.parametrize(
         "tuples, closed",
         [

pandas/tests/reshape/test_cut.py

@@ -14,6 +14,7 @@
     Timestamp,
     cut,
     date_range,
+    interval_range,
     isna,
     qcut,
     timedelta_range,
@@ -734,3 +735,12 @@ def test_cut_with_timestamp_tuple_labels():
 
     expected = Categorical.from_codes([0, 1, 2], labels, ordered=True)
     tm.assert_categorical_equal(result, expected)
+
+
+def test_cut_bins_datetime_intervalindex():
+    # https://github.com/pandas-dev/pandas/issues/46218
+    bins = interval_range(Timestamp("2022-02-25"), Timestamp("2022-02-27"), freq="1D")
+    # passing Series instead of list is important to trigger bug
+    result = cut(Series([Timestamp("2022-02-26")]), bins=bins)
+    expected = Categorical.from_codes([0], bins, ordered=True)
+    tm.assert_categorical_equal(result.array, expected)