API: rename MultiIndex.labels to MultiIndex.codes (#23752)

Author: topper-123

asv_bench/benchmarks/groupby.py

@@ -473,8 +473,8 @@ def setup(self):
         n1 = 400
         n2 = 250
         index = MultiIndex(levels=[np.arange(n1), tm.makeStringIndex(n2)],
-                           labels=[np.repeat(range(n1), n2).tolist(),
-                                   list(range(n2)) * n1],
+                           codes=[np.repeat(range(n1), n2).tolist(),
+                                  list(range(n2)) * n1],
                            names=['lev1', 'lev2'])
         arr = np.random.randn(n1 * n2, 3)
         arr[::10000, 0] = np.nan

asv_bench/benchmarks/join_merge.py

@@ -115,16 +115,16 @@ class Join(object):
     def setup(self, sort):
         level1 = tm.makeStringIndex(10).values
         level2 = tm.makeStringIndex(1000).values
-        label1 = np.arange(10).repeat(1000)
-        label2 = np.tile(np.arange(1000), 10)
+        codes1 = np.arange(10).repeat(1000)
+        codes2 = np.tile(np.arange(1000), 10)
         index2 = MultiIndex(levels=[level1, level2],
-                            labels=[label1, label2])
+                            codes=[codes1, codes2])
         self.df_multi = DataFrame(np.random.randn(len(index2), 4),
                                   index=index2,
                                   columns=['A', 'B', 'C', 'D'])
 
-        self.key1 = np.tile(level1.take(label1), 10)
-        self.key2 = np.tile(level2.take(label2), 10)
+        self.key1 = np.tile(level1.take(codes1), 10)
+        self.key2 = np.tile(level2.take(codes2), 10)
         self.df = DataFrame({'data1': np.random.randn(100000),
                              'data2': np.random.randn(100000),
                              'key1': self.key1,

asv_bench/benchmarks/multiindex_object.py

@@ -79,8 +79,8 @@ def setup(self):
         levels = [np.arange(n),
                   tm.makeStringIndex(n).values,
                   1000 + np.arange(n)]
-        labels = [np.random.choice(n, (k * n)) for lev in levels]
-        self.mi = MultiIndex(levels=levels, labels=labels)
+        codes = [np.random.choice(n, (k * n)) for lev in levels]
+        self.mi = MultiIndex(levels=levels, codes=codes)
 
     def time_duplicated(self):
         self.mi.duplicated()

asv_bench/benchmarks/reindex.py

@@ -71,9 +71,9 @@ class LevelAlign(object):
     def setup(self):
         self.index = MultiIndex(
             levels=[np.arange(10), np.arange(100), np.arange(100)],
-            labels=[np.arange(10).repeat(10000),
-                    np.tile(np.arange(100).repeat(100), 10),
-                    np.tile(np.tile(np.arange(100), 100), 10)])
+            codes=[np.arange(10).repeat(10000),
+                   np.tile(np.arange(100).repeat(100), 10),
+                   np.tile(np.tile(np.arange(100), 100), 10)])
         self.df = DataFrame(np.random.randn(len(self.index), 4),
                             index=self.index)
         self.df_level = DataFrame(np.random.randn(100, 4),

asv_bench/benchmarks/stat_ops.py

@@ -31,10 +31,10 @@ class FrameMultiIndexOps(object):
 
     def setup(self, level, op):
         levels = [np.arange(10), np.arange(100), np.arange(100)]
-        labels = [np.arange(10).repeat(10000),
-                  np.tile(np.arange(100).repeat(100), 10),
-                  np.tile(np.tile(np.arange(100), 100), 10)]
-        index = pd.MultiIndex(levels=levels, labels=labels)
+        codes = [np.arange(10).repeat(10000),
+                 np.tile(np.arange(100).repeat(100), 10),
+                 np.tile(np.tile(np.arange(100), 100), 10)]
+        index = pd.MultiIndex(levels=levels, codes=codes)
         df = pd.DataFrame(np.random.randn(len(index), 4), index=index)
         self.df_func = getattr(df, op)
 
@@ -67,10 +67,10 @@ class SeriesMultiIndexOps(object):
 
     def setup(self, level, op):
         levels = [np.arange(10), np.arange(100), np.arange(100)]
-        labels = [np.arange(10).repeat(10000),
-                  np.tile(np.arange(100).repeat(100), 10),
-                  np.tile(np.tile(np.arange(100), 100), 10)]
-        index = pd.MultiIndex(levels=levels, labels=labels)
+        codes = [np.arange(10).repeat(10000),
+                 np.tile(np.arange(100).repeat(100), 10),
+                 np.tile(np.tile(np.arange(100), 100), 10)]
+        index = pd.MultiIndex(levels=levels, codes=codes)
         s = pd.Series(np.random.randn(len(index)), index=index)
         self.s_func = getattr(s, op)
 

doc/source/advanced.rst

@@ -49,6 +49,11 @@ analysis.
 
 See the :ref:`cookbook<cookbook.multi_index>` for some advanced strategies.
 
+.. versionchanged:: 0.24.0
+
+   :attr:`MultiIndex.labels` has been renamed to :attr:`MultiIndex.codes`
+   and :attr:`MultiIndex.set_labels` to :attr:`MultiIndex.set_codes`.
+
 Creating a MultiIndex (hierarchical index) object
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -469,7 +474,7 @@ values across a level. For instance:
 .. ipython:: python
 
    midx = pd.MultiIndex(levels=[['zero', 'one'], ['x', 'y']],
-                        labels=[[1, 1, 0, 0], [1, 0, 1, 0]])
+                        codes=[[1, 1, 0, 0], [1, 0, 1, 0]])
    df = pd.DataFrame(np.random.randn(4, 2), index=midx)
    df
    df2 = df.mean(level=0)

doc/source/api.rst

@@ -1712,7 +1712,7 @@ MultiIndex Attributes
 
    MultiIndex.names
    MultiIndex.levels
-   MultiIndex.labels
+   MultiIndex.codes
    MultiIndex.nlevels
    MultiIndex.levshape
 
@@ -1723,7 +1723,7 @@ MultiIndex Components
    :toctree: generated/
 
    MultiIndex.set_levels
-   MultiIndex.set_labels
+   MultiIndex.set_codes
    MultiIndex.to_hierarchical
    MultiIndex.to_flat_index
    MultiIndex.to_frame

doc/source/dsintro.rst

@@ -961,7 +961,7 @@ From DataFrame using ``to_panel`` method
 .. ipython:: python
    :okwarning:
 
-   midx = pd.MultiIndex(levels=[['one', 'two'], ['x','y']], labels=[[1,1,0,0],[1,0,1,0]])
+   midx = pd.MultiIndex(levels=[['one', 'two'], ['x','y']], codes=[[1,1,0,0],[1,0,1,0]])
    df = pd.DataFrame({'A' : [1, 2, 3, 4], 'B': [5, 6, 7, 8]}, index=midx)
    df.to_panel()
 

doc/source/indexing.rst

@@ -1571,9 +1571,9 @@ Setting metadata
 
 Indexes are "mostly immutable", but it is possible to set and change their
 metadata, like the index ``name`` (or, for ``MultiIndex``, ``levels`` and
-``labels``).
+``codes``).
 
-You can use the ``rename``, ``set_names``, ``set_levels``, and ``set_labels``
+You can use the ``rename``, ``set_names``, ``set_levels``, and ``set_codes``
 to set these attributes directly. They default to returning a copy; however,
 you can specify ``inplace=True`` to have the data change in place.
 
@@ -1588,7 +1588,7 @@ See :ref:`Advanced Indexing <advanced>` for usage of MultiIndexes.
   ind.name = "bob"
   ind
 
-``set_names``, ``set_levels``, and ``set_labels`` also take an optional
+``set_names``, ``set_levels``, and ``set_codes`` also take an optional
 `level`` argument
 
 .. ipython:: python

doc/source/internals.rst

@@ -74,23 +74,23 @@ MultiIndex
 ~~~~~~~~~~
 
 Internally, the ``MultiIndex`` consists of a few things: the **levels**, the
-integer **labels**, and the level **names**:
+integer **codes** (until version 0.24 named *labels*), and the level **names**:
 
 .. ipython:: python
 
    index = pd.MultiIndex.from_product([range(3), ['one', 'two']],
                                       names=['first', 'second'])
    index
    index.levels
-   index.labels
+   index.codes
    index.names
 
-You can probably guess that the labels determine which unique element is
+You can probably guess that the codes determine which unique element is
 identified with that location at each layer of the index. It's important to
-note that sortedness is determined **solely** from the integer labels and does
+note that sortedness is determined **solely** from the integer codes and does
 not check (or care) whether the levels themselves are sorted. Fortunately, the
 constructors ``from_tuples`` and ``from_arrays`` ensure that this is true, but
-if you compute the levels and labels yourself, please be careful.
+if you compute the levels and codes yourself, please be careful.
 
 Values
 ~~~~~~

doc/source/io.rst

@@ -3728,8 +3728,8 @@ storing/selecting from homogeneous index ``DataFrames``.
 
         index = pd.MultiIndex(levels=[['foo', 'bar', 'baz', 'qux'],
                                       ['one', 'two', 'three']],
-                              labels=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3],
-                                      [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
+                              codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3],
+                                     [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
                               names=['foo', 'bar'])
         df_mi = pd.DataFrame(np.random.randn(10, 3), index=index,
                              columns=['A', 'B', 'C'])

doc/source/whatsnew/v0.24.0.rst

@@ -1100,6 +1100,13 @@ Other API Changes
 Deprecations
 ~~~~~~~~~~~~
 
+- :attr:`MultiIndex.labels` has been deprecated and replaced by :attr:`MultiIndex.codes`.
+  The functionality is unchanged. The new name better reflects the natures of
+  these codes and makes the ``MultiIndex`` API more similar to the API for :class:`CategoricalIndex`(:issue:`13443`).
+  As a consequence, other uses of the name ``labels`` in ``MultiIndex`` have also been deprecated and replaced with ``codes``:
+  - You should initialize a ``MultiIndex`` instance using a parameter named ``codes`` rather than ``labels``.
+  - ``MultiIndex.set_labels`` has been deprecated in favor of :meth:`MultiIndex.set_codes`.
+  - For method :meth:`MultiIndex.copy`, the ``labels`` parameter has been deprecated and replaced by a ``codes`` parameter.
 - :meth:`DataFrame.to_stata`, :meth:`read_stata`, :class:`StataReader` and :class:`StataWriter` have deprecated the ``encoding`` argument. The encoding of a Stata dta file is determined by the file type and cannot be changed (:issue:`21244`)
 - :meth:`MultiIndex.to_hierarchical` is deprecated and will be removed in a future version (:issue:`21613`)
 - :meth:`Series.ptp` is deprecated. Use ``numpy.ptp`` instead (:issue:`21614`)

pandas/core/frame.py

@@ -1839,7 +1839,7 @@ def to_panel(self):
             selfsorted = self
 
         major_axis, minor_axis = selfsorted.index.levels
-        major_labels, minor_labels = selfsorted.index.labels
+        major_codes, minor_codes = selfsorted.index.codes
         shape = len(major_axis), len(minor_axis)
 
         # preserve names, if any
@@ -1854,8 +1854,8 @@ def to_panel(self):
 
         # create new manager
         new_mgr = selfsorted._data.reshape_nd(axes=new_axes,
-                                              labels=[major_labels,
-                                                      minor_labels],
+                                              labels=[major_codes,
+                                                      minor_codes],
                                               shape=shape,
                                               ref_items=selfsorted.columns)
 
@@ -3736,8 +3736,8 @@ def drop(self, labels=None, axis=0, index=None, columns=None,
 
         >>> midx = pd.MultiIndex(levels=[['lama', 'cow', 'falcon'],
         ...                              ['speed', 'weight', 'length']],
-        ...                      labels=[[0, 0, 0, 1, 1, 1, 2, 2, 2],
-        ...                              [0, 1, 2, 0, 1, 2, 0, 1, 2]])
+        ...                      codes=[[0, 0, 0, 1, 1, 1, 2, 2, 2],
+        ...                             [0, 1, 2, 0, 1, 2, 0, 1, 2]])
         >>> df = pd.DataFrame(index=midx, columns=['big', 'small'],
         ...                   data=[[45, 30], [200, 100], [1.5, 1], [30, 20],
         ...                         [250, 150], [1.5, 0.8], [320, 250],
@@ -4226,7 +4226,7 @@ def _maybe_casted_values(index, labels=None):
             if isinstance(self.index, MultiIndex):
                 names = [n if n is not None else ('level_%d' % i)
                          for (i, n) in enumerate(self.index.names)]
-                to_insert = lzip(self.index.levels, self.index.labels)
+                to_insert = lzip(self.index.levels, self.index.codes)
             else:
                 default = 'index' if 'index' not in self else 'level_0'
                 names = ([default] if self.index.name is None
@@ -4594,7 +4594,7 @@ def sort_index(self, axis=0, level=None, ascending=True, inplace=False,
         elif isinstance(labels, MultiIndex):
             from pandas.core.sorting import lexsort_indexer
 
-            indexer = lexsort_indexer(labels._get_labels_for_sorting(),
+            indexer = lexsort_indexer(labels._get_codes_for_sorting(),
                                       orders=ascending,
                                       na_position=na_position)
         else:
@@ -7147,8 +7147,9 @@ def _count_level(self, level, axis=0, numeric_only=False):
             level = count_axis._get_level_number(level)
 
         level_index = count_axis.levels[level]
-        labels = ensure_int64(count_axis.labels[level])
-        counts = lib.count_level_2d(mask, labels, len(level_index), axis=0)
+        level_codes = ensure_int64(count_axis.codes[level])
+        counts = lib.count_level_2d(mask, level_codes, len(level_index),
+                                    axis=0)
 
         result = DataFrame(counts, index=level_index, columns=agg_axis)
 

pandas/core/groupby/generic.py

@@ -1112,7 +1112,7 @@ def value_counts(self, normalize=False, sort=True, ascending=False,
             lab = cut(Series(val), bins, include_lowest=True)
             lev = lab.cat.categories
             lab = lev.take(lab.cat.codes)
-            llab = lambda lab, inc: lab[inc]._multiindex.labels[-1]
+            llab = lambda lab, inc: lab[inc]._multiindex.codes[-1]
 
         if is_interval_dtype(lab):
             # TODO: should we do this inside II?
@@ -1163,7 +1163,7 @@ def value_counts(self, normalize=False, sort=True, ascending=False,
             out, labels[-1] = out[sorter], labels[-1][sorter]
 
         if bins is None:
-            mi = MultiIndex(levels=levels, labels=labels, names=names,
+            mi = MultiIndex(levels=levels, codes=labels, names=names,
                             verify_integrity=False)
 
             if is_integer_dtype(out):
@@ -1191,10 +1191,10 @@ def value_counts(self, normalize=False, sort=True, ascending=False,
             out, left[-1] = out[sorter], left[-1][sorter]
 
         # build the multi-index w/ full levels
-        labels = list(map(lambda lab: np.repeat(lab[diff], nbin), labels[:-1]))
-        labels.append(left[-1])
+        codes = list(map(lambda lab: np.repeat(lab[diff], nbin), labels[:-1]))
+        codes.append(left[-1])
 
-        mi = MultiIndex(levels=levels, labels=labels, names=names,
+        mi = MultiIndex(levels=levels, codes=codes, names=names,
                         verify_integrity=False)
 
         if is_integer_dtype(out):

pandas/core/groupby/ops.py

@@ -290,10 +290,10 @@ def result_index(self):
         if not self.compressed and len(self.groupings) == 1:
             return self.groupings[0].result_index.rename(self.names[0])
 
-        labels = self.recons_labels
+        codes = self.recons_labels
         levels = [ping.result_index for ping in self.groupings]
         result = MultiIndex(levels=levels,
-                            labels=labels,
+                            codes=codes,
                             verify_integrity=False,
                             names=self.names)
         return result