diff --git a/doc/source/whatsnew/v1.0.0.rst b/doc/source/whatsnew/v1.0.0.rst index 7c86ad0f029ed..7692651db840e 100644 --- a/doc/source/whatsnew/v1.0.0.rst +++ b/doc/source/whatsnew/v1.0.0.rst @@ -124,7 +124,37 @@ source, you should no longer need to install Cython into your build environment Backwards incompatible API changes ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -- :class:`pandas.core.groupby.GroupBy.transform` now raises on invalid operation names (:issue:`27489`). +.. _whatsnew_1000.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 1.0, 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` (:issue:`27242`:). + +*pandas 0.25.x* + +.. code-block:: ipython + + In [1]: mi = pd.MultiIndex.from_product([[1, 2], ['a', 'b']], names=['x', 'y']) + Out[2]: mi + MultiIndex([(1, 'a'), + (1, 'b'), + (2, 'a'), + (2, 'b')], + names=['x', 'y']) + Out[3]: mi.levels[0].name + 'x' + +*pandas 1.0.0* + +.. ipython:: python + + mi = pd.MultiIndex.from_product([[1, 2], ['a', 'b']], names=['x', 'y']) + mi.levels[0].name + - :class:`pandas.core.arrays.IntervalArray` adopts a new ``__repr__`` in accordance with other array classes (:issue:`25022`) *pandas 0.25.x* @@ -150,6 +180,7 @@ Backwards incompatible API changes Other API changes ^^^^^^^^^^^^^^^^^ +- :class:`pandas.core.groupby.GroupBy.transform` now raises on invalid operation names (:issue:`27489`) - :meth:`pandas.api.types.infer_dtype` will now return "integer-na" for integer and ``np.nan`` mix (:issue:`27283`) - :meth:`MultiIndex.from_arrays` will no longer infer names from arrays if ``names=None`` is explicitly provided (:issue:`27292`) - In order to improve tab-completion, Pandas does not include most deprecated attributes when introspecting a pandas object using ``dir`` (e.g. ``dir(df)``). diff --git a/pandas/core/frame.py b/pandas/core/frame.py index 64755b2390eaf..a3c839f6b13a1 100644 --- a/pandas/core/frame.py +++ b/pandas/core/frame.py @@ -7792,7 +7792,8 @@ 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) diff --git a/pandas/core/indexes/multi.py b/pandas/core/indexes/multi.py index 596eaf0c55dbd..b0a1ed0650f7c 100644 --- a/pandas/core/indexes/multi.py +++ b/pandas/core/indexes/multi.py @@ -274,6 +274,7 @@ def __new__( result._set_levels(levels, copy=copy, validate=False) result._set_codes(codes, copy=copy, validate=False) + result._names = [None] * len(levels) if names is not None: # handles name validation result._set_names(names) @@ -1216,7 +1217,7 @@ 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): """ @@ -1262,7 +1263,7 @@ 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: @@ -1272,7 +1273,7 @@ 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""" @@ -1582,13 +1583,13 @@ 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): """ diff --git a/pandas/core/reshape/reshape.py b/pandas/core/reshape/reshape.py index e654685d24d9d..340e964d7c14f 100644 --- a/pandas/core/reshape/reshape.py +++ b/pandas/core/reshape/reshape.py @@ -259,10 +259,10 @@ def get_new_values(self): def get_new_columns(self): if self.value_columns is None: if self.lift == 0: - return self.removed_level + return self.removed_level._shallow_copy(name=self.removed_name) - lev = self.removed_level - return lev.insert(0, lev._na_value) + lev = self.removed_level.insert(0, item=self.removed_level._na_value) + return lev.rename(self.removed_name) stride = len(self.removed_level) + self.lift width = len(self.value_columns) @@ -298,10 +298,10 @@ def get_new_index(self): # construct the new index if len(self.new_index_levels) == 1: - 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) + level, level_codes = self.new_index_levels[0], result_codes[0] + if (level_codes == -1).any(): + level = level.insert(len(level), level._na_value) + return level.take(level_codes).rename(self.new_index_names[0]) return MultiIndex( levels=self.new_index_levels, @@ -661,7 +661,8 @@ 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(name=this.columns.names[0]) + unique_groups = new_columns # time to ravel the values new_data = {} diff --git a/pandas/io/json/_table_schema.py b/pandas/io/json/_table_schema.py index 9016e8a98e5ba..1e27421a55499 100644 --- a/pandas/io/json/_table_schema.py +++ b/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)) diff --git a/pandas/tests/frame/test_alter_axes.py b/pandas/tests/frame/test_alter_axes.py index 017cbea7ec723..b310335be5f65 100644 --- a/pandas/tests/frame/test_alter_axes.py +++ b/pandas/tests/frame/test_alter_axes.py @@ -978,7 +978,7 @@ 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].rename(name=None))) stacked.index.names = [None, None] deleveled2 = stacked.reset_index() diff --git a/pandas/tests/indexes/multi/test_astype.py b/pandas/tests/indexes/multi/test_astype.py index 4adcdd0112b26..f320a89c471bf 100644 --- a/pandas/tests/indexes/multi/test_astype.py +++ b/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)) diff --git a/pandas/tests/indexes/multi/test_constructor.py b/pandas/tests/indexes/multi/test_constructor.py index 9472d539537ba..993979f31a35b 100644 --- a/pandas/tests/indexes/multi/test_constructor.py +++ b/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]: @@ -439,8 +440,9 @@ 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( diff --git a/pandas/tests/indexes/multi/test_names.py b/pandas/tests/indexes/multi/test_names.py index 5856cb56b307b..679e045a68f29 100644 --- a/pandas/tests/indexes/multi/test_names.py +++ b/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): @@ -82,9 +79,9 @@ def test_copy_names(): def test_names(idx, index_names): # names are assigned in setup - names = index_names + assert index_names == ["first", "second"] level_names = [level.name for level in idx.levels] - assert names == level_names + assert level_names == [None, None] # setting bad names on existing index = idx @@ -109,11 +106,10 @@ def test_names(idx, index_names): names=["first", "second", "third"], ) - # names are assigned + # names are assigned on index, but not transferred to the levels 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): diff --git a/pandas/tests/indexes/multi/test_reindex.py b/pandas/tests/indexes/multi/test_reindex.py index 88de4d1e80386..970288e5747c7 100644 --- a/pandas/tests/indexes/multi/test_reindex.py +++ b/pandas/tests/indexes/multi/test_reindex.py @@ -6,19 +6,17 @@ import pandas.util.testing as tm -def check_level_names(index, names): - assert [level.name for level in index.levels] == list(names) - - def test_reindex(idx): result, indexer = idx.reindex(list(idx[:4])) assert isinstance(result, MultiIndex) - check_level_names(result, idx[:4].names) + assert result.names == ["first", "second"] + assert [level.name for level in result.levels] == [None, None] result, indexer = idx.reindex(list(idx)) assert isinstance(result, MultiIndex) assert indexer is None - check_level_names(result, idx.names) + assert result.names == ["first", "second"] + assert [level.name for level in result.levels] == [None, None] def test_reindex_level(idx): diff --git a/pandas/tests/indexes/multi/test_reshape.py b/pandas/tests/indexes/multi/test_reshape.py index a30e6f33d1499..e79f212f30078 100644 --- a/pandas/tests/indexes/multi/test_reshape.py +++ b/pandas/tests/indexes/multi/test_reshape.py @@ -15,10 +15,11 @@ def test_insert(idx): # key not contained in all levels new_index = idx.insert(0, ("abc", "three")) - exp0 = Index(list(idx.levels[0]) + ["abc"], name="first") + exp0 = Index(list(idx.levels[0]) + ["abc"]) tm.assert_index_equal(new_index.levels[0], exp0) + assert new_index.names == ["first", "second"] - exp1 = Index(list(idx.levels[1]) + ["three"], name="second") + exp1 = Index(list(idx.levels[1]) + ["three"]) tm.assert_index_equal(new_index.levels[1], exp1) assert new_index[0] == ("abc", "three") diff --git a/pandas/tests/reshape/test_concat.py b/pandas/tests/reshape/test_concat.py index 13f0f14014a31..33cbaaed1848d 100644 --- a/pandas/tests/reshape/test_concat.py +++ b/pandas/tests/reshape/test_concat.py @@ -1219,8 +1219,10 @@ def test_concat_keys_specific_levels(self): names=["group_key"], ) - tm.assert_index_equal(result.columns.levels[0], Index(level, name="group_key")) - assert result.columns.names[0] == "group_key" + tm.assert_index_equal(result.columns.levels[0], Index(level)) + tm.assert_index_equal(result.columns.levels[1], Index([0, 1, 2, 3])) + + assert result.columns.names == ["group_key", None] def test_concat_dataframe_keys_bug(self, sort): t1 = DataFrame( @@ -1409,10 +1411,8 @@ def test_concat_keys_and_levels(self): keys=[("foo", "one"), ("foo", "two"), ("baz", "one"), ("baz", "two")], names=["first", "second"], ) - assert result.index.names == ("first", "second") + (None,) - tm.assert_index_equal( - result.index.levels[0], Index(["baz", "foo"], name="first") - ) + assert result.index.names == ("first", "second", None) + tm.assert_index_equal(result.index.levels[0], Index(["baz", "foo"])) def test_concat_keys_levels_no_overlap(self): # GH #1406 diff --git a/pandas/tests/reshape/test_reshape.py b/pandas/tests/reshape/test_reshape.py index e2c6f7d1c8feb..0b9392a0eeb5b 100644 --- a/pandas/tests/reshape/test_reshape.py +++ b/pandas/tests/reshape/test_reshape.py @@ -618,16 +618,15 @@ def test_reshaping_multi_index_categorical(self): df.index.names = ["major", "minor"] df["str"] = "foo" - dti = df.index.levels[0] - df["category"] = df["str"].astype("category") result = df["category"].unstack() + dti = df.index.levels[0] c = Categorical(["foo"] * len(dti)) expected = DataFrame( {"A": c.copy(), "B": c.copy(), "C": c.copy(), "D": c.copy()}, columns=Index(list("ABCD"), name="minor"), - index=dti, + index=dti.rename("major"), ) tm.assert_frame_equal(result, expected) diff --git a/pandas/tests/test_multilevel.py b/pandas/tests/test_multilevel.py index e641d6f842d87..76436f4480809 100644 --- a/pandas/tests/test_multilevel.py +++ b/pandas/tests/test_multilevel.py @@ -335,7 +335,7 @@ def test_count_level_corner(self): df = self.frame[:0] result = df.count(level=0) expected = ( - DataFrame(index=s.index.levels[0], columns=df.columns) + DataFrame(index=s.index.levels[0].set_names(["first"]), columns=df.columns) .fillna(0) .astype(np.int64) ) @@ -976,13 +976,11 @@ def test_count(self): result = series.count(level="b") expect = self.series.count(level=1) - tm.assert_series_equal(result, expect, check_names=False) - assert result.index.name == "b" + tm.assert_series_equal(result, expect) result = series.count(level="a") expect = self.series.count(level=0) - tm.assert_series_equal(result, expect, check_names=False) - assert result.index.name == "a" + tm.assert_series_equal(result, expect) msg = "Level x not found" with pytest.raises(KeyError, match=msg): @@ -1014,6 +1012,8 @@ def test_frame_group_ops(self, op, level, axis, skipna, sort): self.frame.iloc[1, [1, 2]] = np.nan self.frame.iloc[7, [0, 1]] = np.nan + level_name = self.frame.index.names[level] + if axis == 0: frame = self.frame else: @@ -1034,7 +1034,7 @@ def aggf(x): frame = frame.sort_index(level=level, axis=axis) # for good measure, groupby detail - level_index = frame._get_axis(axis).levels[level] + level_index = frame._get_axis(axis).levels[level].rename(level_name) tm.assert_index_equal(leftside._get_axis(axis), level_index) tm.assert_index_equal(rightside._get_axis(axis), level_index) @@ -1639,12 +1639,18 @@ def test_constructor_with_tz(self): ) result = MultiIndex.from_arrays([index, columns]) - tm.assert_index_equal(result.levels[0], index) - tm.assert_index_equal(result.levels[1], columns) + + assert result.names == ["dt1", "dt2"] + # levels don't have names set, so set name of index/columns to None in checks + tm.assert_index_equal(result.levels[0], index.rename(name=None)) + tm.assert_index_equal(result.levels[1], columns.rename(name=None)) result = MultiIndex.from_arrays([Series(index), Series(columns)]) - tm.assert_index_equal(result.levels[0], index) - tm.assert_index_equal(result.levels[1], columns) + + assert result.names == ["dt1", "dt2"] + # levels don't have names set, so set name of index/columns to None in checks + tm.assert_index_equal(result.levels[0], index.rename(name=None)) + tm.assert_index_equal(result.levels[1], columns.rename(name=None)) def test_set_index_datetime(self): # GH 3950 @@ -1666,18 +1672,19 @@ def test_set_index_datetime(self): df.index = df.index.tz_convert("US/Pacific") expected = pd.DatetimeIndex( - ["2011-07-19 07:00:00", "2011-07-19 08:00:00", "2011-07-19 09:00:00"], - name="datetime", + ["2011-07-19 07:00:00", "2011-07-19 08:00:00", "2011-07-19 09:00:00"] ) expected = expected.tz_localize("UTC").tz_convert("US/Pacific") df = df.set_index("label", append=True) tm.assert_index_equal(df.index.levels[0], expected) - tm.assert_index_equal(df.index.levels[1], Index(["a", "b"], name="label")) + tm.assert_index_equal(df.index.levels[1], Index(["a", "b"])) + assert df.index.names == ["datetime", "label"] df = df.swaplevel(0, 1) - tm.assert_index_equal(df.index.levels[0], Index(["a", "b"], name="label")) + tm.assert_index_equal(df.index.levels[0], Index(["a", "b"])) tm.assert_index_equal(df.index.levels[1], expected) + assert df.index.names == ["label", "datetime"] df = DataFrame(np.random.random(6)) idx1 = pd.DatetimeIndex(