fixing rebasing issues

Author: topper-123

pandas/core/indexes/base.py

@@ -1521,27 +1521,27 @@ def droplevel(self, level=0):
         # The two checks above guarantee that here self is a MultiIndex
 
         new_levels = list(self.levels)
-        new_labels = list(self.labels)
+        new_codes = list(self.codes)
         new_names = list(self.names)
 
         for i in levnums:
             new_levels.pop(i)
-            new_labels.pop(i)
+            new_codes.pop(i)
             new_names.pop(i)
 
         if len(new_levels) == 1:
 
             # set nan if needed
-            mask = new_labels[0] == -1
-            result = new_levels[0].take(new_labels[0])
+            mask = new_codes[0] == -1
+            result = new_levels[0].take(new_codes[0])
             if mask.any():
                 result = result.putmask(mask, np.nan)
 
             result.name = new_names[0]
             return result
         else:
             from .multi import MultiIndex
-            return MultiIndex(levels=new_levels, labels=new_labels,
+            return MultiIndex(levels=new_levels, codes=new_codes,
                               names=new_names, verify_integrity=False)
 
     _index_shared_docs['_get_grouper_for_level'] = """
@@ -3299,14 +3299,14 @@ def _join_multi(self, other, how, return_indexers=True):
             # common levels, ldrop_names, rdrop_names
             dropped_names = ldrop_names + rdrop_names
 
-            levels, labels, names = (
+            levels, codes, names = (
                 _restore_dropped_levels_multijoin(self, other,
                                                   dropped_names,
                                                   join_idx,
                                                   lidx, ridx))
 
             # Re-create the multi-index
-            multi_join_idx = MultiIndex(levels=levels, labels=labels,
+            multi_join_idx = MultiIndex(levels=levels, codes=codes,
                                         names=names, verify_integrity=False)
 
             multi_join_idx = multi_join_idx.remove_unused_levels()
@@ -3417,63 +3417,63 @@ def _get_leaf_sorter(labels):
                 left_indexer = None
                 join_index = left
             else:  # sort the leaves
-                left_indexer = _get_leaf_sorter(left.labels[:level + 1])
+                left_indexer = _get_leaf_sorter(left.codes[:level + 1])
                 join_index = left[left_indexer]
 
         else:
             left_lev_indexer = ensure_int64(left_lev_indexer)
             rev_indexer = lib.get_reverse_indexer(left_lev_indexer,
                                                   len(old_level))
 
-            new_lev_labels = algos.take_nd(rev_indexer, left.labels[level],
-                                           allow_fill=False)
+            new_lev_codes = algos.take_nd(rev_indexer, left.codes[level],
+                                          allow_fill=False)
 
-            new_labels = list(left.labels)
-            new_labels[level] = new_lev_labels
+            new_codes = list(left.codes)
+            new_codes[level] = new_lev_codes
 
             new_levels = list(left.levels)
             new_levels[level] = new_level
 
             if keep_order:  # just drop missing values. o.w. keep order
                 left_indexer = np.arange(len(left), dtype=np.intp)
-                mask = new_lev_labels != -1
+                mask = new_lev_codes != -1
                 if not mask.all():
-                    new_labels = [lab[mask] for lab in new_labels]
+                    new_codes = [lab[mask] for lab in new_codes]
                     left_indexer = left_indexer[mask]
 
             else:  # tie out the order with other
                 if level == 0:  # outer most level, take the fast route
-                    ngroups = 1 + new_lev_labels.max()
+                    ngroups = 1 + new_lev_codes.max()
                     left_indexer, counts = libalgos.groupsort_indexer(
-                        new_lev_labels, ngroups)
+                        new_lev_codes, ngroups)
 
                     # missing values are placed first; drop them!
                     left_indexer = left_indexer[counts[0]:]
-                    new_labels = [lab[left_indexer] for lab in new_labels]
+                    new_codes = [lab[left_indexer] for lab in new_codes]
 
                 else:  # sort the leaves
-                    mask = new_lev_labels != -1
+                    mask = new_lev_codes != -1
                     mask_all = mask.all()
                     if not mask_all:
-                        new_labels = [lab[mask] for lab in new_labels]
+                        new_codes = [lab[mask] for lab in new_codes]
 
-                    left_indexer = _get_leaf_sorter(new_labels[:level + 1])
-                    new_labels = [lab[left_indexer] for lab in new_labels]
+                    left_indexer = _get_leaf_sorter(new_codes[:level + 1])
+                    new_codes = [lab[left_indexer] for lab in new_codes]
 
                     # left_indexers are w.r.t masked frame.
                     # reverse to original frame!
                     if not mask_all:
                         left_indexer = mask.nonzero()[0][left_indexer]
 
-            join_index = MultiIndex(levels=new_levels, labels=new_labels,
+            join_index = MultiIndex(levels=new_levels, codes=new_codes,
                                     names=left.names, verify_integrity=False)
 
         if right_lev_indexer is not None:
             right_indexer = algos.take_nd(right_lev_indexer,
-                                          join_index.labels[level],
+                                          join_index.codes[level],
                                           allow_fill=False)
         else:
-            right_indexer = join_index.labels[level]
+            right_indexer = join_index.codes[level]
 
         if flip_order:
             left_indexer, right_indexer = right_indexer, left_indexer
@@ -4103,24 +4103,12 @@ def asof_locs(self, where, mask):
 
         return result
 
-<<<<<<< HEAD
     def sort_values(self, return_indexer=False, ascending=True):
         """
         Return a sorted copy of the index.
 
         Return a sorted copy of the index, and optionally return the indices
         that sorted the index itself.
-=======
-            levels, codes, names = (
-                _restore_dropped_levels_multijoin(self, other,
-                                                  dropped_names,
-                                                  join_idx,
-                                                  lidx, ridx))
-
-            # Re-create the multi-index
-            multi_join_idx = MultiIndex(levels=levels, codes=codes,
-                                        names=names, verify_integrity=False)
->>>>>>> various changes
 
         Parameters
         ----------
@@ -4478,24 +4466,15 @@ def isin(self, values, level=None):
         passed set of values. The length of the returned boolean array matches
         the length of the index.
 
-<<<<<<< HEAD
         Parameters
         ----------
         values : set or list-like
             Sought values.
 
             .. versionadded:: 0.18.1
-=======
-            new_level_codes = algos.take_nd(rev_indexer, left.codes[level],
-                                            allow_fill=False)
-
-            new_codes = list(left.codes)
-            new_codes[level] = new_level_codes
->>>>>>> various changes
 
                Support for values as a set.
 
-<<<<<<< HEAD
         level : str or int, optional
             Name or position of the index level to use (if the index is a
             `MultiIndex`).
@@ -4504,40 +4483,18 @@ def isin(self, values, level=None):
         -------
         is_contained : ndarray
             NumPy array of boolean values.
-=======
-            if keep_order:  # just drop missing values. o.w. keep order
-                left_indexer = np.arange(len(left), dtype=np.intp)
-                mask = new_level_codes != -1
-                if not mask.all():
-                    new_codes = [codes_[mask] for codes_ in new_codes]
-                    left_indexer = left_indexer[mask]
-
-            else:  # tie out the order with other
-                if level == 0:  # outer most level, take the fast route
-                    ngroups = 1 + new_level_codes.max()
-                    left_indexer, counts = libalgos.groupsort_indexer(
-                        new_level_codes, ngroups)
->>>>>>> various changes
 
         See Also
         --------
         Series.isin : Same for Series.
         DataFrame.isin : Same method for DataFrames.
 
-<<<<<<< HEAD
         Notes
         -----
         In the case of `MultiIndex` you must either specify `values` as a
         list-like object containing tuples that are the same length as the
         number of levels, or specify `level`. Otherwise it will raise a
         ``ValueError``.
-=======
-                else:  # sort the leaves
-                    mask = new_level_codes != -1
-                    mask_all = mask.all()
-                    if not mask_all:
-                        new_codes = [lab[mask] for lab in new_codes]
->>>>>>> various changes
 
         If `level` is specified:
 

pandas/core/indexes/multi.py

@@ -327,11 +327,11 @@ def from_arrays(cls, arrays, sortorder=None, names=None):
 
         from pandas.core.arrays.categorical import _factorize_from_iterables
 
-        labels, levels = _factorize_from_iterables(arrays)
+        codes, levels = _factorize_from_iterables(arrays)
         if names is None:
             names = [getattr(arr, "name", None) for arr in arrays]
 
-        return MultiIndex(levels=levels, labels=labels, sortorder=sortorder,
+        return MultiIndex(levels=levels, codes=codes, sortorder=sortorder,
                           names=names, verify_integrity=False)
 
     @classmethod
@@ -427,9 +427,9 @@ def from_product(cls, iterables, sortorder=None, names=None):
         elif is_iterator(iterables):
             iterables = list(iterables)
 
-        labels, levels = _factorize_from_iterables(iterables)
-        labels = cartesian_product(labels)
-        return MultiIndex(levels, labels, sortorder=sortorder, names=names)
+        codes, levels = _factorize_from_iterables(iterables)
+        codes = cartesian_product(codes)
+        return MultiIndex(levels, codes, sortorder=sortorder, names=names)
 
     # --------------------------------------------------------------------
 
@@ -873,15 +873,15 @@ def format(self, space=2, sparsify=None, adjoin=True, names=False,
             return []
 
         stringified_levels = []
-        for lev, lab in zip(self.levels, self.labels):
+        for lev, level_codes in zip(self.levels, self.codes):
             na = na_rep if na_rep is not None else _get_na_rep(lev.dtype.type)
 
             if len(lev) > 0:
 
-                formatted = lev.take(lab).format(formatter=formatter)
+                formatted = lev.take(level_codes).format(formatter=formatter)
 
                 # we have some NA
-                mask = lab == -1
+                mask = level_codes == -1
                 if mask.any():
                     formatted = np.array(formatted, dtype=object)
                     formatted[mask] = na
@@ -891,7 +891,7 @@ def format(self, space=2, sparsify=None, adjoin=True, names=False,
                 # weird all NA case
                 formatted = [pprint_thing(na if isna(x) else x,
                                           escape_chars=('\t', '\r', '\n'))
-                             for x in algos.take_1d(lev._values, lab)]
+                             for x in algos.take_1d(lev._values, level_codes)]
             stringified_levels.append(formatted)
 
         result_levels = []

pandas/tests/indexes/multi/test_copy.py

@@ -39,9 +39,8 @@ def test_shallow_copy(idx):
 
 def test_labels_deprecated(idx):
     # GH23752
-    codes = idx.codes
     with tm.assert_produces_warning(FutureWarning):
-        idx.copy(labels=codes)
+        idx.copy(labels=idx.codes)
 
 
 def test_view(idx):

pandas/tests/indexing/multiindex/conftest.py

@@ -10,8 +10,8 @@ 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'))

pandas/tests/indexing/multiindex/test_getitem.py

@@ -64,8 +64,8 @@ def test_getitem_duplicates_multiindex(self):
 
         index = MultiIndex(levels=[['D', 'B', 'C'],
                                    [0, 26, 27, 37, 57, 67, 75, 82]],
-                           labels=[[0, 0, 0, 1, 2, 2, 2, 2, 2, 2],
-                                   [1, 3, 4, 6, 0, 2, 2, 3, 5, 7]],
+                           codes=[[0, 0, 0, 1, 2, 2, 2, 2, 2, 2],
+                                  [1, 3, 4, 6, 0, 2, 2, 3, 5, 7]],
                            names=['tag', 'day'])
         arr = np.random.randn(len(index), 1)
         df = DataFrame(arr, index=index, columns=['val'])
@@ -87,8 +87,8 @@ def f():
         # A is treated as a special Timestamp
         index = MultiIndex(levels=[['A', 'B', 'C'],
                                    [0, 26, 27, 37, 57, 67, 75, 82]],
-                           labels=[[0, 0, 0, 1, 2, 2, 2, 2, 2, 2],
-                                   [1, 3, 4, 6, 0, 2, 2, 3, 5, 7]],
+                           codes=[[0, 0, 0, 1, 2, 2, 2, 2, 2, 2],
+                                  [1, 3, 4, 6, 0, 2, 2, 3, 5, 7]],
                            names=['tag', 'day'])
         df = DataFrame(arr, index=index, columns=['val'])
         result = df.val['A']
@@ -264,8 +264,8 @@ def test_getitem_toplevel(self, multiindex_dataframe_random_data):
 
     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)
 

pandas/tests/indexing/multiindex/test_loc.py

@@ -11,7 +11,7 @@
 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.mark.filterwarnings("ignore:\\n.ix:DeprecationWarning")
@@ -40,7 +40,7 @@ def test_loc_getitem_series(self):
 
         empty = Series(data=[], dtype=np.float64)
         expected = Series([], index=MultiIndex(
-            levels=index.levels, labels=[[], []], dtype=np.float64))
+            levels=index.levels, codes=[[], []], dtype=np.float64))
         result = x.loc[empty]
         tm.assert_series_equal(result, expected)
 
@@ -60,7 +60,7 @@ def test_loc_getitem_array(self):
         # empty array:
         empty = np.array([])
         expected = Series([], index=MultiIndex(
-            levels=index.levels, labels=[[], []], dtype=np.float64))
+            levels=index.levels, codes=[[], []], dtype=np.float64))
         result = x.loc[empty]
         tm.assert_series_equal(result, expected)
 

pandas/tests/indexing/multiindex/test_partial.py

@@ -52,9 +52,9 @@ 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'))
 
@@ -68,7 +68,7 @@ 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)
 
@@ -82,12 +82,12 @@ 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)