Update labels -> codes in various locations

Author: topper-123

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/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/whatsnew/v0.24.0.rst

@@ -1102,9 +1102,9 @@ Deprecations
 
 - :attr:`MultiIndex.labels` has been deprecated and replaced by :attr:`MultiIndex.codes`.
   The functionality is unchanged. This new name better reflects the natures of
-  these codes and makes the API more similar to the API for
+  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`` have also been deprecated in ``MultiIndex`` and replaced with ``codes``:
+  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``.
   - :meth:`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.

pandas/core/indexes/multi.py

@@ -11,7 +11,7 @@
 from pandas.compat import lrange, lzip, map, range, zip
 from pandas.compat.numpy import function as nv
 from pandas.errors import PerformanceWarning, UnsortedIndexError
-from pandas.util._decorators import Appender, cache_readonly
+from pandas.util._decorators import Appender, cache_readonly, deprecate_kwarg
 
 from pandas.core.dtypes.common import (
     ensure_int64, ensure_platform_int, is_categorical_dtype, is_hashable,
@@ -31,8 +31,6 @@
 
 from pandas.io.formats.printing import pprint_thing
 
-from pandas.util._decorators import deprecate_kwarg
-
 _index_doc_kwargs = dict(ibase._index_doc_kwargs)
 _index_doc_kwargs.update(
     dict(klass='MultiIndex',
@@ -655,19 +653,19 @@ def set_codes(self, codes, level=None, inplace=False,
         >>> idx = pd.MultiIndex.from_tuples([(1, u'one'), (1, u'two'),
                                             (2, u'one'), (2, u'two')],
                                             names=['foo', 'bar'])
-        >>> idx.set_labels([[1,0,1,0], [0,0,1,1]])
+        >>> idx.set_codes([[1,0,1,0], [0,0,1,1]])
         MultiIndex(levels=[[1, 2], [u'one', u'two']],
                    labels=[[1, 0, 1, 0], [0, 0, 1, 1]],
                    names=[u'foo', u'bar'])
-        >>> idx.set_labels([1,0,1,0], level=0)
+        >>> idx.set_codes([1,0,1,0], level=0)
         MultiIndex(levels=[[1, 2], [u'one', u'two']],
                    labels=[[1, 0, 1, 0], [0, 1, 0, 1]],
                    names=[u'foo', u'bar'])
-        >>> idx.set_labels([0,0,1,1], level='bar')
+        >>> idx.set_codes([0,0,1,1], level='bar')
         MultiIndex(levels=[[1, 2], [u'one', u'two']],
                    labels=[[0, 0, 1, 1], [0, 0, 1, 1]],
                    names=[u'foo', u'bar'])
-        >>> idx.set_labels([[1,0,1,0], [0,0,1,1]], level=[0,1])
+        >>> idx.set_codes([[1,0,1,0], [0,0,1,1]], level=[0,1])
         MultiIndex(levels=[[1, 2], [u'one', u'two']],
                    labels=[[1, 0, 1, 0], [0, 0, 1, 1]],
                    names=[u'foo', u'bar'])

pandas/tests/indexing/test_multiindex.py

@@ -24,8 +24,8 @@ def multiindex_dataframe_random_data():
     """DataFrame with 2 level MultiIndex with random data"""
     index = 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=['first', 'second'])
     return DataFrame(np.random.randn(10, 3), index=index,
                      columns=Index(['A', 'B', 'C'], name='exp'))
@@ -35,7 +35,7 @@ def multiindex_dataframe_random_data():
 def single_level_multiindex():
     """single level MultiIndex"""
     return MultiIndex(levels=[['foo', 'bar', 'baz', 'qux']],
-                      labels=[[0, 1, 2, 3]], names=['first'])
+                      codes=[[0, 1, 2, 3]], names=['first'])
 
 
 @pytest.fixture
@@ -900,8 +900,8 @@ def test_frame_getitem_setitem_slice(
 
     def test_frame_getitem_setitem_multislice(self):
         levels = [['t1', 't2'], ['a', 'b', 'c']]
-        labels = [[0, 0, 0, 1, 1], [0, 1, 2, 0, 1]]
-        midx = MultiIndex(labels=labels, levels=levels, names=[None, 'id'])
+        codes = [[0, 0, 0, 1, 1], [0, 1, 2, 0, 1]]
+        midx = MultiIndex(codes=codes, levels=levels, names=[None, 'id'])
         df = DataFrame({'value': [1, 2, 3, 7, 8]}, index=midx)
 
         result = df.loc[:, 'value']
@@ -1044,9 +1044,9 @@ def test_xs_partial(self, multiindex_dataframe_random_data,
 
         # ex from #1796
         index = MultiIndex(levels=[['foo', 'bar'], ['one', 'two'], [-1, 1]],
-                           labels=[[0, 0, 0, 0, 1, 1, 1, 1],
-                                   [0, 0, 1, 1, 0, 0, 1, 1], [0, 1, 0, 1, 0, 1,
-                                                              0, 1]])
+                           codes=[[0, 0, 0, 0, 1, 1, 1, 1],
+                                  [0, 0, 1, 1, 0, 0, 1, 1], [0, 1, 0, 1, 0, 1,
+                                                             0, 1]])
         df = DataFrame(np.random.randn(8, 4), index=index,
                        columns=list('abcd'))
 
@@ -1189,7 +1189,7 @@ def test_getitem_toplevel(self, multiindex_dataframe_random_data):
 
     def test_getitem_setitem_slice_integers(self):
         index = MultiIndex(levels=[[0, 1, 2], [0, 2]],
-                           labels=[[0, 0, 1, 1, 2, 2], [0, 1, 0, 1, 0, 1]])
+                           codes=[[0, 0, 1, 1, 2, 2], [0, 1, 0, 1, 0, 1]])
 
         frame = DataFrame(np.random.randn(len(index), 4), index=index,
                           columns=['a', 'b', 'c', 'd'])
@@ -1211,8 +1211,8 @@ def test_getitem_setitem_slice_integers(self):
 
     def test_getitem_int(self, multiindex_dataframe_random_data):
         levels = [[0, 1], [0, 1, 2]]
-        labels = [[0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 1, 2]]
-        index = MultiIndex(levels=levels, labels=labels)
+        codes = [[0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 1, 2]]
+        index = MultiIndex(levels=levels, codes=codes)
 
         frame = DataFrame(np.random.randn(6, 2), index=index)
 
@@ -1236,7 +1236,7 @@ def test_getitem_partial(
         ymd = ymd.T
         result = ymd[2000, 2]
 
-        expected = ymd.reindex(columns=ymd.columns[ymd.columns.labels[1] == 1])
+        expected = ymd.reindex(columns=ymd.columns[ymd.columns.codes[1] == 1])
         expected.columns = expected.columns.droplevel(0).droplevel(0)
         tm.assert_frame_equal(result, expected)
 
@@ -1279,12 +1279,12 @@ def test_fancy_slice_partial(
 
         ymd = multiindex_year_month_day_dataframe_random_data
         result = ymd.loc[(2000, 2):(2000, 4)]
-        lev = ymd.index.labels[1]
+        lev = ymd.index.codes[1]
         expected = ymd[(lev >= 1) & (lev <= 3)]
         tm.assert_frame_equal(result, expected)
 
     def test_getitem_partial_column_select(self):
-        idx = MultiIndex(labels=[[0, 0, 0], [0, 1, 1], [1, 0, 1]],
+        idx = MultiIndex(codes=[[0, 0, 0], [0, 1, 1], [1, 0, 1]],
                          levels=[['a', 'b'], ['x', 'y'], ['p', 'q']])
         df = DataFrame(np.random.rand(3, 2), index=idx)
 
@@ -1582,7 +1582,7 @@ def test_frame_getitem_not_sorted2(self):
         df2_original = df2.copy()
 
         df2.index.set_levels(['b', 'd', 'a'], level='col1', inplace=True)
-        df2.index.set_labels([0, 1, 0, 2], level='col1', inplace=True)
+        df2.index.set_codes([0, 1, 0, 2], level='col1', inplace=True)
         assert not df2.index.is_lexsorted()
         assert not df2.index.is_monotonic
 

pandas/tests/io/parser/test_header.py

@@ -236,7 +236,7 @@ def test_header_multi_index_common_format_malformed1(all_parsers):
         columns=MultiIndex(levels=[[u("a"), u("b"), u("c")],
                                    [u("r"), u("s"), u("t"),
                                     u("u"), u("v")]],
-                           labels=[[0, 0, 1, 2, 2], [0, 1, 2, 3, 4]],
+                           codes=[[0, 0, 1, 2, 2], [0, 1, 2, 3, 4]],
                            names=[u("a"), u("q")]))
     data = """a,a,a,b,c,c
 q,r,s,t,u,v
@@ -255,7 +255,7 @@ def test_header_multi_index_common_format_malformed2(all_parsers):
         columns=MultiIndex(levels=[[u("a"), u("b"), u("c")],
                                    [u("r"), u("s"), u("t"),
                                     u("u"), u("v")]],
-                           labels=[[0, 0, 1, 2, 2], [0, 1, 2, 3, 4]],
+                           codes=[[0, 0, 1, 2, 2], [0, 1, 2, 3, 4]],
                            names=[None, u("q")]))
 
     data = """,a,a,b,c,c
@@ -272,10 +272,10 @@ def test_header_multi_index_common_format_malformed3(all_parsers):
     expected = DataFrame(np.array(
         [[3, 4, 5, 6], [9, 10, 11, 12]], dtype="int64"),
         index=MultiIndex(levels=[[1, 7], [2, 8]],
-                         labels=[[0, 1], [0, 1]]),
+                         codes=[[0, 1], [0, 1]]),
         columns=MultiIndex(levels=[[u("a"), u("b"), u("c")],
                                    [u("s"), u("t"), u("u"), u("v")]],
-                           labels=[[0, 1, 2, 2], [0, 1, 2, 3]],
+                           codes=[[0, 1, 2, 2], [0, 1, 2, 3]],
                            names=[None, u("q")]))
     data = """,a,a,b,c,c
 q,r,s,t,u,v

pandas/tests/io/parser/test_index_col.py

@@ -148,5 +148,5 @@ def test_multi_index_naming_not_all_at_beginning(all_parsers):
     expected = DataFrame({"Unnamed: 2": ["c", "d", "c", "d"]},
                          index=MultiIndex(
                              levels=[['a', 'b'], [1, 2, 3, 4]],
-                             labels=[[0, 0, 1, 1], [0, 1, 2, 3]]))
+                             codes=[[0, 0, 1, 1], [0, 1, 2, 3]]))
     tm.assert_frame_equal(result, expected)