update PR

Author: topper-123

asv_bench/benchmarks/groupby.py

@@ -471,8 +471,8 @@ 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

@@ -119,16 +119,16 @@ 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/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),

doc/source/whatsnew/v0.24.0.rst

@@ -1022,8 +1022,8 @@ Deprecations
   The functionality is unchanged. This new name better reflects the natures of
   these codes and makes the API more similar to the API for
   :class:`CategoricalIndex`(:issue:`13443`).
-  As a concequence, other uses of the name ``labels`` have also been deprecated in ``MultiIndex`` and replaced with ``codes``:
-  - You should initialize a MultiIndex instance using a parameter named ``codes`` rather than ``labels``.
+  As a consequence, other uses of the name ``labels`` have also been deprecated in ``MultiIndex`` 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.
 - :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`)

pandas/core/frame.py

@@ -3785,8 +3785,8 @@ 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],

pandas/core/indexes/multi.py

@@ -428,7 +428,7 @@ def codes(self):
 
     @property
     def labels(self):
-        warnings.warn(("labels was deprecated in version 0.24.0. "
+        warnings.warn((".labels was deprecated in version 0.24.0. "
                        "Use .codes instead."),
                       FutureWarning, stacklevel=2)
         return self.codes
@@ -463,7 +463,7 @@ def _set_codes(self, codes, level=None, copy=False, validate=True,
 
     def set_labels(self, labels, level=None, inplace=False,
                    verify_integrity=True):
-        warnings.warn(("set_labels was deprecated in version 0.24.0. "
+        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,
@@ -1494,7 +1494,7 @@ def _sort_levels_monotonic(self):
         --------
 
         >>> i = pd.MultiIndex(levels=[['a', 'b'], ['bb', 'aa']],
-                              labels=[[0, 0, 1, 1], [0, 1, 0, 1]])
+                              codes=[[0, 0, 1, 1], [0, 1, 0, 1]])
         >>> i
         MultiIndex(levels=[['a', 'b'], ['bb', 'aa']],
                    labels=[[0, 0, 1, 1], [0, 1, 0, 1]])
@@ -1869,7 +1869,7 @@ def swaplevel(self, i=-2, j=-1):
         Examples
         --------
         >>> mi = pd.MultiIndex(levels=[['a', 'b'], ['bb', 'aa']],
-        ...                    labels=[[0, 0, 1, 1], [0, 1, 0, 1]])
+        ...                    codes=[[0, 0, 1, 1], [0, 1, 0, 1]])
         >>> mi
         MultiIndex(levels=[['a', 'b'], ['bb', 'aa']],
            labels=[[0, 0, 1, 1], [0, 1, 0, 1]])

pandas/core/series.py

@@ -3560,8 +3560,8 @@ 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]])
         >>> s = pd.Series([45, 200, 1.2, 30, 250, 1.5, 320, 1, 0.3],
         ...               index=midx)
         >>> s

pandas/tests/indexes/multi/test_copy.py

@@ -43,6 +43,7 @@ def test_labels_deprecated(idx):
     with tm.assert_produces_warning(FutureWarning):
         idx.copy(labels=codes)
 
+
 def test_view(idx):
     i_view = idx.view()
     assert_multiindex_copied(i_view, idx)

pandas/tests/indexes/multi/test_get_set.py

@@ -348,7 +348,7 @@ def test_set_levels_codes_names_bad_input(idx):
     with pytest.raises(ValueError, match='Length of levels'):
         idx.set_levels([levels[0]])
 
-    with tm.assert_raises_regex(ValueError, 'Length of codes'):
+    with pytest.raises(ValueError, match='Length of codes'):
         idx.set_codes([codes[0]])
 
     with pytest.raises(ValueError, match='Length of names'):
@@ -359,7 +359,7 @@ def test_set_levels_codes_names_bad_input(idx):
         idx.set_levels(levels[0])
 
     # shouldn't scalar data error, instead should demand list-like
-    with tm.assert_raises_regex(TypeError, 'list of lists-like'):
+    with pytest.raises(TypeError, match='list of lists-like'):
         idx.set_codes(codes[0])
 
     # shouldn't scalar data error, instead should demand list-like

pandas/tests/io/test_feather.py

@@ -87,15 +87,19 @@ def test_rw_nthreads(self):
             "the 'nthreads' keyword is deprecated, "
             "use 'use_threads' instead"
         )
-        with tm.assert_produces_warning(FutureWarning) as w:
+        # TODO: make the warning work with check_stacklevel=True
+        with tm.assert_produces_warning(
+                FutureWarning, check_stacklevel=False) as w:
             self.check_round_trip(df, nthreads=2)
-        assert len(w) == 1
-        assert expected_warning in str(w[0])
+        # we have an extra FutureWarning because of #GH23752
+        assert any(expected_warning in str(x) for x in w)
 
-        with tm.assert_produces_warning(FutureWarning) as w:
+        # TODO: make the warning work with check_stacklevel=True
+        with tm.assert_produces_warning(
+                FutureWarning, check_stacklevel=False) as w:
             self.check_round_trip(df, nthreads=1)
-        assert len(w) == 1
-        assert expected_warning in str(w[0])
+        # we have an extra FutureWarnings because of #GH23752
+        assert any(expected_warning in str(x) for x in w)
 
     def test_rw_use_threads(self):
         df = pd.DataFrame({'A': np.arange(100000)})

pandas/tests/test_algos.py

@@ -1462,7 +1462,6 @@ def test_too_many_ndims(self):
         with pytest.raises(TypeError, match=msg):
             algos.rank(arr)
 
-    @pytest.mark.xfail(reason="MemoryError")
     @pytest.mark.parametrize('values', [
         np.arange(2**24 + 1),
         np.arange(2**25 + 2).reshape(2**24 + 1, 2)],