DEPR: MultiIndex.to_hierarchical, labels (#29766)

Author: jbrockmendel

ci/deps/azure-macos-36.yaml

@@ -20,9 +20,9 @@ dependencies:
   - matplotlib=2.2.3
   - nomkl
   - numexpr
-  - numpy=1.13.3
+  - numpy=1.14
   - openpyxl
-  - pyarrow
+  - pyarrow>=0.12.0
   - pytables
   - python-dateutil==2.6.1
   - pytz

ci/deps/azure-windows-36.yaml

@@ -20,7 +20,7 @@ dependencies:
   - numexpr
   - numpy=1.15.*
   - openpyxl
-  - pyarrow
+  - pyarrow>=0.12.0
   - pytables
   - python-dateutil
   - pytz

doc/redirects.csv

@@ -828,7 +828,6 @@ generated/pandas.MultiIndex.sortlevel,../reference/api/pandas.MultiIndex.sortlev
 generated/pandas.MultiIndex.swaplevel,../reference/api/pandas.MultiIndex.swaplevel
 generated/pandas.MultiIndex.to_flat_index,../reference/api/pandas.MultiIndex.to_flat_index
 generated/pandas.MultiIndex.to_frame,../reference/api/pandas.MultiIndex.to_frame
-generated/pandas.MultiIndex.to_hierarchical,../reference/api/pandas.MultiIndex.to_hierarchical
 generated/pandas.notna,../reference/api/pandas.notna
 generated/pandas.notnull,../reference/api/pandas.notnull
 generated/pandas.option_context,../reference/api/pandas.option_context

doc/source/getting_started/install.rst

@@ -258,7 +258,7 @@ matplotlib                2.2.2              Visualization
 openpyxl                  2.4.8              Reading / writing for xlsx files
 pandas-gbq                0.8.0              Google Big Query access
 psycopg2                                     PostgreSQL engine for sqlalchemy
-pyarrow                   0.9.0              Parquet and feather reading / writing
+pyarrow                   0.12.0             Parquet and feather reading / writing
 pymysql                   0.7.11             MySQL engine for sqlalchemy
 pyreadstat                                   SPSS files (.sav) reading
 pytables                  3.4.2              HDF5 reading / writing

doc/source/reference/indexing.rst

@@ -305,7 +305,6 @@ MultiIndex components
 
    MultiIndex.set_levels
    MultiIndex.set_codes
-   MultiIndex.to_hierarchical
    MultiIndex.to_flat_index
    MultiIndex.to_frame
    MultiIndex.is_lexsorted

doc/source/whatsnew/v1.0.0.rst

@@ -265,62 +265,62 @@ The following methods now also correctly output values for unobserved categories
 Increased minimum versions for dependencies
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-Some minimum supported versions of dependencies were updated (:issue:`29723`).
+Some minimum supported versions of dependencies were updated (:issue:`29766`, :issue:`29723`).
 If installed, we now require:
 
-+-----------------+-----------------+----------+
-| Package         | Minimum Version | Required |
-+=================+=================+==========+
-| numpy           | 1.13.3          |    X     |
-+-----------------+-----------------+----------+
-| pytz            | 2015.4          |    X     |
-+-----------------+-----------------+----------+
-| python-dateutil | 2.6.1           |    X     |
-+-----------------+-----------------+----------+
-| bottleneck      | 1.2.1           |          |
-+-----------------+-----------------+----------+
-| numexpr         | 2.6.2           |          |
-+-----------------+-----------------+----------+
-| pytest (dev)    | 4.0.2           |          |
-+-----------------+-----------------+----------+
++-----------------+-----------------+----------+---------+
+| Package         | Minimum Version | Required | Changed |
++=================+=================+==========+=========+
+| numpy           | 1.13.3          |    X     |         |
++-----------------+-----------------+----------+---------+
+| pytz            | 2015.4          |    X     |         |
++-----------------+-----------------+----------+---------+
+| python-dateutil | 2.6.1           |    X     |         |
++-----------------+-----------------+----------+---------+
+| bottleneck      | 1.2.1           |          |         |
++-----------------+-----------------+----------+---------+
+| numexpr         | 2.6.2           |          |         |
++-----------------+-----------------+----------+---------+
+| pytest (dev)    | 4.0.2           |          |         |
++-----------------+-----------------+----------+---------+
 
 For `optional libraries <https://dev.pandas.io/docs/install.html#dependencies>`_ the general recommendation is to use the latest version.
 The following table lists the lowest version per library that is currently being tested throughout the development of pandas.
 Optional libraries below the lowest tested version may still work, but are not considered supported.
 
-+-----------------+-----------------+
-| Package         | Minimum Version |
-+=================+=================+
-| beautifulsoup4  | 4.6.0           |
-+-----------------+-----------------+
-| fastparquet     | 0.3.2           |
-+-----------------+-----------------+
-| gcsfs           | 0.2.2           |
-+-----------------+-----------------+
-| lxml            | 3.8.0           |
-+-----------------+-----------------+
-| matplotlib      | 2.2.2           |
-+-----------------+-----------------+
-| openpyxl        | 2.4.8           |
-+-----------------+-----------------+
-| pyarrow         | 0.9.0           |
-+-----------------+-----------------+
-| pymysql         | 0.7.1           |
-+-----------------+-----------------+
-| pytables        | 3.4.2           |
-+-----------------+-----------------+
-| scipy           | 0.19.0          |
-+-----------------+-----------------+
-| sqlalchemy      | 1.1.4           |
-+-----------------+-----------------+
-| xarray          | 0.8.2           |
-+-----------------+-----------------+
-| xlrd            | 1.1.0           |
-+-----------------+-----------------+
-| xlsxwriter      | 0.9.8           |
-+-----------------+-----------------+
-| xlwt            | 1.2.0           |
-+-----------------+-----------------+
++-----------------+-----------------+---------+
+| Package         | Minimum Version | Changed |
++=================+=================+=========+
+| beautifulsoup4  | 4.6.0           |         |
++-----------------+-----------------+---------+
+| fastparquet     | 0.3.2           |    X    |
++-----------------+-----------------+---------+
+| gcsfs           | 0.2.2           |         |
++-----------------+-----------------+---------+
+| lxml            | 3.8.0           |         |
++-----------------+-----------------+---------+
+| matplotlib      | 2.2.2           |         |
++-----------------+-----------------+---------+
+| openpyxl        | 2.4.8           |         |
++-----------------+-----------------+---------+
+| pyarrow         | 0.12.0          |    X    |
++-----------------+-----------------+---------+
+| pymysql         | 0.7.1           |         |
++-----------------+-----------------+---------+
+| pytables        | 3.4.2           |         |
++-----------------+-----------------+---------+
+| scipy           | 0.19.0          |         |
++-----------------+-----------------+---------+
+| sqlalchemy      | 1.1.4           |         |
++-----------------+-----------------+---------+
+| xarray          | 0.8.2           |         |
++-----------------+-----------------+---------+
+| xlrd            | 1.1.0           |         |
++-----------------+-----------------+---------+
+| xlsxwriter      | 0.9.8           |         |
++-----------------+-----------------+---------+
+| xlwt            | 1.2.0           |         |
++-----------------+-----------------+---------+
 
 See :ref:`install.dependencies` and :ref:`install.optional_dependencies` for more.
 
@@ -415,6 +415,11 @@ or ``matplotlib.Axes.plot``. See :ref:`plotting.formatters` for more.
 - :func:`core.internals.blocks.make_block` no longer accepts the "fastpath" keyword(:issue:`19265`)
 - :meth:`Block.make_block_same_class` no longer accepts the "dtype" keyword(:issue:`19434`)
 - Removed the previously deprecated :meth:`ExtensionArray._formatting_values`. Use :attr:`ExtensionArray._formatter` instead. (:issue:`23601`)
+- Removed the previously deprecated :meth:`MultiIndex.to_hierarchical` (:issue:`21613`)
+- Removed the previously deprecated :attr:`MultiIndex.labels`, use :attr:`MultiIndex.codes` instead (:issue:`23752`)
+- Removed the previously deprecated "labels" keyword from the :class:`MultiIndex` constructor, use "codes" instead (:issue:`23752`)
+- Removed the previously deprecated :meth:`MultiIndex.set_labels`, use :meth:`MultiIndex.set_codes` instead (:issue:`23752`)
+- Removed the previously deprecated "labels" keyword from :meth:`MultiIndex.set_codes`, :meth:`MultiIndex.copy`, :meth:`MultiIndex.drop`, use "codes" instead (:issue:`23752`)
 - Removed support for legacy HDF5 formats (:issue:`29787`)
 - :func:`read_excel` removed support for "skip_footer" argument, use "skipfooter" instead (:issue:`18836`)
 - :func:`read_excel` no longer allows an integer value for the parameter ``usecols``, instead pass a list of integers from 0 to ``usecols`` inclusive (:issue:`23635`)

pandas/compat/_optional.py

@@ -16,7 +16,7 @@
     "odfpy": "1.3.0",
     "openpyxl": "2.4.8",
     "pandas_gbq": "0.8.0",
-    "pyarrow": "0.9.0",
+    "pyarrow": "0.12.0",
     "pytables": "3.4.2",
     "pytest": "5.0.1",
     "s3fs": "0.3.0",

pandas/core/indexes/base.py

@@ -160,6 +160,12 @@ def _new_Index(cls, d):
         from pandas.core.indexes.period import _new_PeriodIndex
 
         return _new_PeriodIndex(cls, **d)
+
+    if issubclass(cls, ABCMultiIndex):
+        if "labels" in d and "codes" not in d:
+            # GH#23752 "labels" kwarg has been replaced with "codes"
+            d["codes"] = d.pop("labels")
+
     return cls.__new__(cls, **d)
 
 

pandas/core/indexes/multi.py

@@ -11,7 +11,7 @@
 from pandas._libs.hashtable import duplicated_int64
 from pandas.compat.numpy import function as nv
 from pandas.errors import PerformanceWarning, UnsortedIndexError
-from pandas.util._decorators import Appender, cache_readonly, deprecate_kwarg
+from pandas.util._decorators import Appender, cache_readonly
 
 from pandas.core.dtypes.common import (
     ensure_int64,
@@ -229,9 +229,7 @@ class MultiIndex(Index):
     of the mentioned helper methods.
     """
 
-    _deprecations = Index._deprecations | frozenset(
-        ["labels", "set_labels", "to_hierarchical"]
-    )
+    _deprecations = Index._deprecations | frozenset()
 
     # initialize to zero-length tuples to make everything work
     _typ = "multiindex"
@@ -244,7 +242,6 @@ class MultiIndex(Index):
     # --------------------------------------------------------------------
     # Constructors
 
-    @deprecate_kwarg(old_arg_name="labels", new_arg_name="codes")
     def __new__(
         cls,
         levels=None,
@@ -813,15 +810,6 @@ def set_levels(self, levels, level=None, inplace=False, verify_integrity=True):
     def codes(self):
         return self._codes
 
-    @property
-    def labels(self):
-        warnings.warn(
-            (".labels was deprecated in version 0.24.0. Use .codes instead."),
-            FutureWarning,
-            stacklevel=2,
-        )
-        return self.codes
-
     def _set_codes(
         self, codes, level=None, copy=False, validate=True, verify_integrity=False
     ):
@@ -854,23 +842,6 @@ def _set_codes(
         self._tuples = None
         self._reset_cache()
 
-    def set_labels(self, labels, level=None, inplace=False, verify_integrity=True):
-        warnings.warn(
-            (
-                ".set_labels was deprecated in version 0.24.0. "
-                "Use .set_codes instead."
-            ),
-            FutureWarning,
-            stacklevel=2,
-        )
-        return self.set_codes(
-            codes=labels,
-            level=level,
-            inplace=inplace,
-            verify_integrity=verify_integrity,
-        )
-
-    @deprecate_kwarg(old_arg_name="labels", new_arg_name="codes")
     def set_codes(self, codes, level=None, inplace=False, verify_integrity=True):
         """
         Set new codes on MultiIndex. Defaults to returning
@@ -947,7 +918,6 @@ def set_codes(self, codes, level=None, inplace=False, verify_integrity=True):
         if not inplace:
             return idx
 
-    @deprecate_kwarg(old_arg_name="labels", new_arg_name="codes")
     def copy(
         self,
         names=None,
@@ -981,7 +951,8 @@ def copy(
         """
         name = kwargs.get("name")
         names = self._validate_names(name=name, names=names, deep=deep)
-
+        if "labels" in kwargs:
+            raise TypeError("'labels' argument has been removed; use 'codes' instead")
         if deep:
             from copy import deepcopy
 
@@ -1700,62 +1671,6 @@ def to_frame(self, index=True, name=None):
             result.index = self
         return result
 
-    def to_hierarchical(self, n_repeat, n_shuffle=1):
-        """
-        Return a MultiIndex reshaped to conform to the
-        shapes given by n_repeat and n_shuffle.
-
-        .. deprecated:: 0.24.0
-
-        Useful to replicate and rearrange a MultiIndex for combination
-        with another Index with n_repeat items.
-
-        Parameters
-        ----------
-        n_repeat : int
-            Number of times to repeat the labels on self.
-        n_shuffle : int
-            Controls the reordering of the labels. If the result is going
-            to be an inner level in a MultiIndex, n_shuffle will need to be
-            greater than one. The size of each label must divisible by
-            n_shuffle.
-
-        Returns
-        -------
-        MultiIndex
-
-        Examples
-        --------
-        >>> idx = pd.MultiIndex.from_tuples([(1, 'one'), (1, 'two'),
-                                            (2, 'one'), (2, 'two')])
-        >>> idx.to_hierarchical(3)
-        MultiIndex([(1, 'one'),
-                    (1, 'one'),
-                    (1, 'one'),
-                    (1, 'two'),
-                    (1, 'two'),
-                    (1, 'two'),
-                    (2, 'one'),
-                    (2, 'one'),
-                    (2, 'one'),
-                    (2, 'two'),
-                    (2, 'two'),
-                    (2, 'two')],
-                   )
-        """
-        levels = self.levels
-        codes = [np.repeat(level_codes, n_repeat) for level_codes in self.codes]
-        # Assumes that each level_codes is divisible by n_shuffle
-        codes = [x.reshape(n_shuffle, -1).ravel(order="F") for x in codes]
-        names = self.names
-        warnings.warn(
-            "Method .to_hierarchical is deprecated and will "
-            "be removed in a future version",
-            FutureWarning,
-            stacklevel=2,
-        )
-        return MultiIndex(levels=levels, codes=codes, names=names)
-
     def to_flat_index(self):
         """
         Convert a MultiIndex to an Index of Tuples containing the level values.
@@ -2148,7 +2063,6 @@ def repeat(self, repeats, axis=None):
     def where(self, cond, other=None):
         raise NotImplementedError(".where is not supported for MultiIndex operations")
 
-    @deprecate_kwarg(old_arg_name="labels", new_arg_name="codes")
     def drop(self, codes, level=None, errors="raise"):
         """
         Make new MultiIndex with passed list of codes deleted

pandas/io/feather_format.py

@@ -1,7 +1,5 @@
 """ feather-format compat """
 
-from distutils.version import LooseVersion
-
 from pandas.compat._optional import import_optional_dependency
 
 from pandas import DataFrame, Int64Index, RangeIndex
@@ -96,15 +94,9 @@ def read_feather(path, columns=None, use_threads=True):
     -------
     type of object stored in file
     """
-    pyarrow = import_optional_dependency("pyarrow")
+    import_optional_dependency("pyarrow")
     from pyarrow import feather
 
     path = _stringify_path(path)
 
-    if LooseVersion(pyarrow.__version__) < LooseVersion("0.11.0"):
-        int_use_threads = int(use_threads)
-        if int_use_threads < 1:
-            int_use_threads = 1
-        return feather.read_feather(path, columns=columns, nthreads=int_use_threads)
-
     return feather.read_feather(path, columns=columns, use_threads=bool(use_threads))

pandas/tests/extension/arrow/test_bool.py

@@ -5,7 +5,7 @@
 from pandas.tests.extension import base
 import pandas.util.testing as tm
 
-pytest.importorskip("pyarrow", minversion="0.10.0")
+pytest.importorskip("pyarrow", minversion="0.12.0")
 
 from .arrays import ArrowBoolArray, ArrowBoolDtype  # isort:skip
 

pandas/tests/extension/arrow/test_string.py

@@ -2,7 +2,7 @@
 
 import pandas as pd
 
-pytest.importorskip("pyarrow", minversion="0.10.0")
+pytest.importorskip("pyarrow", minversion="0.12.0")
 
 from .arrays import ArrowStringDtype  # isort:skip