Backport PR pandas-dev#27712: BUG: partial string indexing with scalar (pandas-dev#27742)

Author: meeseeksmachine

doc/source/whatsnew/v0.25.1.rst

@@ -82,7 +82,7 @@ Interval
 Indexing
 ^^^^^^^^
 
--
+- Bug in partial-string indexing returning a NumPy array rather than a ``Series`` when indexing with a scalar like ``.loc['2015']`` (:issue:`27516`)
 -
 -
 

pandas/core/indexes/base.py

@@ -263,6 +263,9 @@ def _outer_indexer(self, left, right):
     _infer_as_myclass = False
 
     _engine_type = libindex.ObjectEngine
+    # whether we support partial string indexing. Overridden
+    # in DatetimeIndex and PeriodIndex
+    _supports_partial_string_indexing = False
 
     _accessors = {"str"}
 

pandas/core/indexes/datetimes.py

@@ -238,6 +238,7 @@ def _join_i8_wrapper(joinf, **kwargs):
     )
 
     _engine_type = libindex.DatetimeEngine
+    _supports_partial_string_indexing = True
 
     _tz = None
     _freq = None

pandas/core/indexes/period.py

@@ -173,6 +173,7 @@ class PeriodIndex(DatetimeIndexOpsMixin, Int64Index, PeriodDelegateMixin):
     _data = None
 
     _engine_type = libindex.PeriodEngine
+    _supports_partial_string_indexing = True
 
     # ------------------------------------------------------------------------
     # Index Constructors

pandas/core/indexing.py

@@ -1726,6 +1726,11 @@ def _is_scalar_access(self, key: Tuple):
             if isinstance(ax, MultiIndex):
                 return False
 
+            if isinstance(k, str) and ax._supports_partial_string_indexing:
+                # partial string indexing, df.loc['2000', 'A']
+                # should not be considered scalar
+                return False
+
             if not ax.is_unique:
                 return False
 
@@ -1741,7 +1746,10 @@ def _get_partial_string_timestamp_match_key(self, key, labels):
         """Translate any partial string timestamp matches in key, returning the
         new key (GH 10331)"""
         if isinstance(labels, MultiIndex):
-            if isinstance(key, str) and labels.levels[0].is_all_dates:
+            if (
+                isinstance(key, str)
+                and labels.levels[0]._supports_partial_string_indexing
+            ):
                 # Convert key '2016-01-01' to
                 # ('2016-01-01'[, slice(None, None, None)]+)
                 key = tuple([key] + [slice(None)] * (len(labels.levels) - 1))
@@ -1751,7 +1759,10 @@ def _get_partial_string_timestamp_match_key(self, key, labels):
                 # (..., slice('2016-01-01', '2016-01-01', None), ...)
                 new_key = []
                 for i, component in enumerate(key):
-                    if isinstance(component, str) and labels.levels[i].is_all_dates:
+                    if (
+                        isinstance(component, str)
+                        and labels.levels[i]._supports_partial_string_indexing
+                    ):
                         new_key.append(slice(component, component, None))
                     else:
                         new_key.append(component)
@@ -2340,7 +2351,7 @@ def convert_to_index_sliceable(obj, key):
 
         # We might have a datetimelike string that we can translate to a
         # slice here via partial string indexing
-        if idx.is_all_dates:
+        if idx._supports_partial_string_indexing:
             try:
                 return idx._get_string_slice(key)
             except (KeyError, ValueError, NotImplementedError):

pandas/tests/indexes/datetimes/test_partial_slicing.py

@@ -468,3 +468,14 @@ def test_getitem_with_datestring_with_UTC_offset(self, start, end):
         with pytest.raises(ValueError, match="The index must be timezone"):
             df = df.tz_localize(None)
             df[start:end]
+
+    def test_slice_reduce_to_series(self):
+        # GH 27516
+        df = pd.DataFrame(
+            {"A": range(24)}, index=pd.date_range("2000", periods=24, freq="M")
+        )
+        expected = pd.Series(
+            range(12), index=pd.date_range("2000", periods=12, freq="M"), name="A"
+        )
+        result = df.loc["2000", "A"]
+        tm.assert_series_equal(result, expected)