BUG: pandas.cut should disallow overlapping IntervalIndex bins (#23999)

Author: charlesdong1991

doc/source/whatsnew/v0.24.0.rst

@@ -1530,6 +1530,7 @@ Reshaping
 - Bug in :func:`pandas.melt` when passing column names that are not present in ``DataFrame`` (:issue:`23575`)
 - Bug in :meth:`DataFrame.append` with a :class:`Series` with a dateutil timezone would raise a ``TypeError`` (:issue:`23682`)
 - Bug in ``Series`` construction when passing no data and ``dtype=str`` (:issue:`22477`)
+- Bug in :func:`cut` with ``bins`` as an overlapping ``IntervalIndex`` where multiple bins were returned per item instead of raising a ``ValueError`` (:issue:`23980`)
 
 .. _whatsnew_0240.bug_fixes.sparse:
 

pandas/core/reshape/tile.py

@@ -43,7 +43,8 @@ def cut(x, bins, right=True, labels=None, retbins=False, precision=3,
           and maximum values of `x`.
         * sequence of scalars : Defines the bin edges allowing for non-uniform
           width. No extension of the range of `x` is done.
-        * IntervalIndex : Defines the exact bins to be used.
+        * IntervalIndex : Defines the exact bins to be used. Note that
+          IntervalIndex for `bins` must be non-overlapping.
 
     right : bool, default True
         Indicates whether `bins` includes the rightmost edge or not. If
@@ -217,7 +218,9 @@ def cut(x, bins, right=True, labels=None, retbins=False, precision=3,
                 bins[-1] += adj
 
     elif isinstance(bins, IntervalIndex):
-        pass
+        if bins.is_overlapping:
+            raise ValueError('Overlapping IntervalIndex is not accepted.')
+
     else:
         bins = np.asarray(bins)
         bins = _convert_bin_to_numeric_type(bins, dtype)

pandas/tests/reshape/test_tile.py

@@ -91,6 +91,12 @@ def test_bins_from_intervalindex(self):
         tm.assert_numpy_array_equal(result.codes,
                                     np.array([1, 1, 2], dtype='int8'))
 
+    def test_bins_not_overlapping_from_intervalindex(self):
+        # verify if issue 23980 is properly solved.
+        ii = IntervalIndex.from_tuples([(0, 10), (2, 12), (4, 14)])
+        with pytest.raises(ValueError):
+            cut([5, 6], bins=ii)
+
     def test_bins_not_monotonic(self):
         data = [.2, 1.4, 2.5, 6.2, 9.7, 2.1]
         pytest.raises(ValueError, cut, data, [0.1, 1.5, 1, 10])