Backport PR #31651: PERF: Cache MultiIndex.levels

doc/source/whatsnew/v1.0.1.rst

@@ -27,6 +27,7 @@ Fixed regressions
 - Fixed regression in objTOJSON.c fix return-type warning (:issue:`31463`)
 - Fixed regression in :meth:`qcut` when passed a nullable integer. (:issue:`31389`)
 - Fixed regression in assigning to a :class:`Series` using a nullable integer dtype (:issue:`31446`)
+- Fixed performance regression when indexing a ``DataFrame`` or ``Series`` with a :class:`MultiIndex` for the index using a list of labels (:issue:`31648`)
 
 .. ---------------------------------------------------------------------------
 

pandas/core/indexes/multi.py

@@ -620,16 +620,6 @@ def from_frame(cls, df, sortorder=None, names=None):
 
     # --------------------------------------------------------------------
 
-    @property
-    def levels(self):
-        result = [
-            x._shallow_copy(name=name) for x, name in zip(self._levels, self._names)
-        ]
-        for level in result:
-            # disallow midx.levels[0].name = "foo"
-            level._no_setting_name = True
-        return FrozenList(result)
-
     @property
     def _values(self):
         # We override here, since our parent uses _data, which we don't use.
@@ -659,6 +649,22 @@ def array(self):
             "'MultiIndex.to_numpy()' to get a NumPy array of tuples."
         )
 
+    # --------------------------------------------------------------------
+    # Levels Methods
+
+    @cache_readonly
+    def levels(self):
+        # Use cache_readonly to ensure that self.get_locs doesn't repeatedly
+        # create new IndexEngine
+        # https://github.com/pandas-dev/pandas/issues/31648
+        result = [
+            x._shallow_copy(name=name) for x, name in zip(self._levels, self._names)
+        ]
+        for level in result:
+            # disallow midx.levels[0].name = "foo"
+            level._no_setting_name = True
+        return FrozenList(result)
+
     def _set_levels(
         self, levels, level=None, copy=False, validate=True, verify_integrity=False
     ):
@@ -1227,6 +1233,9 @@ def _set_names(self, names, level=None, validate=True):
                     )
             self._names[lev] = name
 
+        # If .levels has been accessed, the names in our cache will be stale.
+        self._reset_cache()
+
     names = property(
         fset=_set_names, fget=_get_names, doc="""\nNames of levels in MultiIndex.\n"""
     )

pandas/tests/indexes/multi/test_get_set.py

@@ -159,7 +159,7 @@ def test_set_levels_codes_directly(idx):
     minor_codes = [(x + 1) % 1 for x in minor_codes]
     new_codes = [major_codes, minor_codes]
 
-    msg = "can't set attribute"
+    msg = "[Cc]an't set attribute"
     with pytest.raises(AttributeError, match=msg):
         idx.levels = new_levels
     with pytest.raises(AttributeError, match=msg):