Separate MultiIndex names from levels

Author: topper-123

doc/source/whatsnew/v0.25.0.rst

@@ -250,6 +250,18 @@ is respected in indexing. (:issue:`24076`, :issue:`16785`)
     df['2019-01-01 12:00:00+04:00':'2019-01-01 13:00:00+04:00']
 
 
+.. _whatsnew_0250.api_breaking.MultiIndex._names:
+
+
+``MultiIndex.levels`` do not hold level names any longer
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+A :class:`MultiIndex` previously stored the level names as attributes of each of its
+:attr:`MultiIndex.levels`. From Pandas 0.25, the names are only accessed through
+:attr:`MultiIndex.names` (which was also possible previously). This is done in order to
+make :attr:`MultiIndex.levels` more similar to :attr:`CategoricalIndex.categories`.
+
+
 .. _whatsnew_0250.api_breaking.multi_indexing:
 
 

pandas/core/frame.py

@@ -7797,7 +7797,8 @@ def _count_level(self, level, axis=0, numeric_only=False):
         if isinstance(level, str):
             level = count_axis._get_level_number(level)
 
-        level_index = count_axis.levels[level]
+        level_name = count_axis._names[level]
+        level_index = count_axis.levels[level]._shallow_copy(name=level_name)
         level_codes = ensure_int64(count_axis.codes[level])
         counts = lib.count_level_2d(mask, level_codes, len(level_index), axis=0)
 

pandas/core/indexes/multi.py

@@ -259,6 +259,7 @@ def __new__(
         result._set_levels(levels, copy=copy, validate=False)
         result._set_codes(codes, copy=copy, validate=False)
 
+        result._names = [None for _ in levels]
         if names is not None:
             # handles name validation
             result._set_names(names)
@@ -1176,7 +1177,7 @@ def __len__(self):
         return len(self.codes[0])
 
     def _get_names(self):
-        return FrozenList(level.name for level in self.levels)
+        return FrozenList(self._names)
 
     def _set_names(self, names, level=None, validate=True):
         """
@@ -1222,7 +1223,7 @@ def _set_names(self, names, level=None, validate=True):
             level = [self._get_level_number(l) for l in level]
 
         # set the name
-        for l, name in zip(level, names):
+        for lev, name in zip(level, names):
             if name is not None:
                 # GH 20527
                 # All items in 'names' need to be hashable:
@@ -1232,7 +1233,7 @@ def _set_names(self, names, level=None, validate=True):
                             self.__class__.__name__
                         )
                     )
-            self.levels[l].rename(name, inplace=True)
+            self._names[lev] = name
 
     names = property(
         fset=_set_names, fget=_get_names, doc="""\nNames of levels in MultiIndex\n"""
@@ -1546,13 +1547,13 @@ def _get_level_values(self, level, unique=False):
         values : ndarray
         """
 
-        values = self.levels[level]
+        lev = self.levels[level]
         level_codes = self.codes[level]
+        name = self._names[level]
         if unique:
             level_codes = algos.unique(level_codes)
-        filled = algos.take_1d(values._values, level_codes, fill_value=values._na_value)
-        values = values._shallow_copy(filled)
-        return values
+        filled = algos.take_1d(lev._values, level_codes, fill_value=lev._na_value)
+        return lev._shallow_copy(filled, name=name)
 
     def get_level_values(self, level):
         """

pandas/core/reshape/reshape.py

@@ -260,10 +260,13 @@ def get_new_values(self):
     def get_new_columns(self):
         if self.value_columns is None:
             if self.lift == 0:
-                return self.removed_level
+                lev = self.removed_level._shallow_copy()
+                lev.name = self.removed_name
+                return lev
 
-            lev = self.removed_level
-            return lev.insert(0, lev._na_value)
+            lev = self.removed_level.insert(0, item=self.removed_level._na_value)
+            lev.name = self.removed_name
+            return lev
 
         stride = len(self.removed_level) + self.lift
         width = len(self.value_columns)
@@ -302,7 +305,9 @@ def get_new_index(self):
             lev, lab = self.new_index_levels[0], result_codes[0]
             if (lab == -1).any():
                 lev = lev.insert(len(lev), lev._na_value)
-            return lev.take(lab)
+            new_index = lev.take(lab)
+            new_index.name = self.new_index_names[0]
+            return new_index
 
         return MultiIndex(
             levels=self.new_index_levels,
@@ -658,7 +663,9 @@ def _convert_level_number(level_num, columns):
         new_names = this.columns.names[:-1]
         new_columns = MultiIndex.from_tuples(unique_groups, names=new_names)
     else:
-        new_columns = unique_groups = this.columns.levels[0]
+        new_columns = this.columns.levels[0]._shallow_copy()
+        new_columns.name = this.columns.names[0]
+        unique_groups = new_columns
 
     # time to ravel the values
     new_data = {}

pandas/io/json/_table_schema.py

@@ -243,8 +243,10 @@ def build_table_schema(data, index=True, primary_key=None, version=True):
 
     if index:
         if data.index.nlevels > 1:
-            for level in data.index.levels:
-                fields.append(convert_pandas_type_to_json_field(level))
+            for level, name in zip(data.index.levels, data.index.names):
+                new_field = convert_pandas_type_to_json_field(level)
+                new_field["name"] = name
+                fields.append(new_field)
         else:
             fields.append(convert_pandas_type_to_json_field(data.index))
 

pandas/tests/frame/test_alter_axes.py

@@ -979,7 +979,7 @@ def test_reset_index(self, float_frame):
         ):
             values = lev.take(level_codes)
             name = names[i]
-            tm.assert_index_equal(values, Index(deleveled[name]))
+            tm.assert_index_equal(values, Index(deleveled[name]), check_names=False)
 
         stacked.index.names = [None, None]
         deleveled2 = stacked.reset_index()

pandas/tests/indexes/multi/test_astype.py

@@ -11,7 +11,7 @@ def test_astype(idx):
     actual = idx.astype("O")
     assert_copy(actual.levels, expected.levels)
     assert_copy(actual.codes, expected.codes)
-    assert [level.name for level in actual.levels] == list(expected.names)
+    assert actual.names == list(expected.names)
 
     with pytest.raises(TypeError, match="^Setting.*dtype.*object"):
         idx.astype(np.dtype(int))

pandas/tests/indexes/multi/test_constructor.py

@@ -17,7 +17,7 @@ def test_constructor_single_level():
         levels=[["foo", "bar", "baz", "qux"]], codes=[[0, 1, 2, 3]], names=["first"]
     )
     assert isinstance(result, MultiIndex)
-    expected = Index(["foo", "bar", "baz", "qux"], name="first")
+    expected = Index(["foo", "bar", "baz", "qux"])
     tm.assert_index_equal(result.levels[0], expected)
     assert result.names == ["first"]
 
@@ -292,8 +292,9 @@ def test_from_arrays_empty():
     # 1 level
     result = MultiIndex.from_arrays(arrays=[[]], names=["A"])
     assert isinstance(result, MultiIndex)
-    expected = Index([], name="A")
+    expected = Index([])
     tm.assert_index_equal(result.levels[0], expected)
+    assert result.names == ["A"]
 
     # N levels
     for N in [2, 3]:
@@ -426,8 +427,9 @@ def test_from_product_empty_zero_levels():
 
 def test_from_product_empty_one_level():
     result = MultiIndex.from_product([[]], names=["A"])
-    expected = pd.Index([], name="A")
+    expected = pd.Index([])
     tm.assert_index_equal(result.levels[0], expected)
+    assert result.names == ["A"]
 
 
 @pytest.mark.parametrize(

pandas/tests/indexes/multi/test_names.py

@@ -27,28 +27,25 @@ def test_index_name_retained():
 
 
 def test_changing_names(idx):
-
-    # names should be applied to levels
-    level_names = [level.name for level in idx.levels]
-    check_level_names(idx, idx.names)
+    assert [level.name for level in idx.levels] == [None, None]
 
     view = idx.view()
     copy = idx.copy()
     shallow_copy = idx._shallow_copy()
 
-    # changing names should change level names on object
+    # changing names should not change level names on object
     new_names = [name + "a" for name in idx.names]
     idx.names = new_names
-    check_level_names(idx, new_names)
+    check_level_names(idx, [None, None])
 
-    # but not on copies
-    check_level_names(view, level_names)
-    check_level_names(copy, level_names)
-    check_level_names(shallow_copy, level_names)
+    # and not on copies
+    check_level_names(view, [None, None])
+    check_level_names(copy, [None, None])
+    check_level_names(shallow_copy, [None, None])
 
     # and copies shouldn't change original
     shallow_copy.names = [name + "c" for name in shallow_copy.names]
-    check_level_names(idx, new_names)
+    check_level_names(idx, [None, None])
 
 
 def test_take_preserve_name(idx):
@@ -84,7 +81,8 @@ def test_names(idx, index_names):
     # names are assigned in setup
     names = index_names
     level_names = [level.name for level in idx.levels]
-    assert names == level_names
+    assert names == ["first", "second"]
+    assert level_names == [None, None]
 
     # setting bad names on existing
     index = idx
@@ -111,9 +109,8 @@ def test_names(idx, index_names):
 
     # names are assigned
     index.names = ["a", "b"]
-    ind_names = list(index.names)
     level_names = [level.name for level in index.levels]
-    assert ind_names == level_names
+    assert level_names == [None, None]
 
 
 def test_duplicate_level_names_access_raises(idx):

pandas/tests/indexes/multi/test_reindex.py

@@ -13,12 +13,12 @@ def check_level_names(index, names):
 def test_reindex(idx):
     result, indexer = idx.reindex(list(idx[:4]))
     assert isinstance(result, MultiIndex)
-    check_level_names(result, idx[:4].names)
+    check_level_names(result, [None, None])
 
     result, indexer = idx.reindex(list(idx))
     assert isinstance(result, MultiIndex)
     assert indexer is None
-    check_level_names(result, idx.names)
+    check_level_names(result, [None, None])
 
 
 def test_reindex_level(idx):