Merge pull request #6022 from jreback/series_mi

BUG: regression in GH6018, indexing with a Series multi-index

Author: jreback

doc/source/release.rst

@@ -126,8 +126,10 @@ Bug Fixes
     of pandas in QTConsole, now fixed. If you're using an older version and
     need to supress the warnings, see (:issue:`5922`).
   - Bug in merging ``timedelta`` dtypes (:issue:`5695`)
-  - Bug in plotting.scatter_matrix function. Wrong alignment among diagonal 
+  - Bug in plotting.scatter_matrix function. Wrong alignment among diagonal
     and off-diagonal plots, see (:issue:`5497`).
+  - Regression in Series with a multi-index via ix (:issue:`6018`)
+  - Bug in Series.xs with a multi-index (:issue:`6018`)
 
 pandas 0.13.0
 -------------

pandas/core/frame.py

@@ -2037,145 +2037,6 @@ def _sanitize_column(self, key, value):
     def _series(self):
         return self._data.get_series_dict()
 
-    def xs(self, key, axis=0, level=None, copy=True, drop_level=True):
-        """
-        Returns a cross-section (row(s) or column(s)) from the DataFrame.
-        Defaults to cross-section on the rows (axis=0).
-
-        Parameters
-        ----------
-        key : object
-            Some label contained in the index, or partially in a MultiIndex
-        axis : int, default 0
-            Axis to retrieve cross-section on
-        level : object, defaults to first n levels (n=1 or len(key))
-            In case of a key partially contained in a MultiIndex, indicate
-            which levels are used. Levels can be referred by label or position.
-        copy : boolean, default True
-            Whether to make a copy of the data
-        drop_level : boolean, default True
-            If False, returns object with same levels as self.
-
-        Examples
-        --------
-        >>> df
-           A  B  C
-        a  4  5  2
-        b  4  0  9
-        c  9  7  3
-        >>> df.xs('a')
-        A    4
-        B    5
-        C    2
-        Name: a
-        >>> df.xs('C', axis=1)
-        a    2
-        b    9
-        c    3
-        Name: C
-        >>> s = df.xs('a', copy=False)
-        >>> s['A'] = 100
-        >>> df
-             A  B  C
-        a  100  5  2
-        b    4  0  9
-        c    9  7  3
-
-
-        >>> df
-                            A  B  C  D
-        first second third
-        bar   one    1      4  1  8  9
-              two    1      7  5  5  0
-        baz   one    1      6  6  8  0
-              three  2      5  3  5  3
-        >>> df.xs(('baz', 'three'))
-               A  B  C  D
-        third
-        2      5  3  5  3
-        >>> df.xs('one', level=1)
-                     A  B  C  D
-        first third
-        bar   1      4  1  8  9
-        baz   1      6  6  8  0
-        >>> df.xs(('baz', 2), level=[0, 'third'])
-                A  B  C  D
-        second
-        three   5  3  5  3
-
-        Returns
-        -------
-        xs : Series or DataFrame
-
-        """
-        axis = self._get_axis_number(axis)
-        labels = self._get_axis(axis)
-        if level is not None:
-            loc, new_ax = labels.get_loc_level(key, level=level,
-                                               drop_level=drop_level)
-
-            if not copy and not isinstance(loc, slice):
-                raise ValueError('Cannot retrieve view (copy=False)')
-
-            # level = 0
-            loc_is_slice = isinstance(loc, slice)
-            if not loc_is_slice:
-                indexer = [slice(None)] * 2
-                indexer[axis] = loc
-                indexer = tuple(indexer)
-            else:
-                indexer = loc
-                lev_num = labels._get_level_number(level)
-                if labels.levels[lev_num].inferred_type == 'integer':
-                    indexer = self.index[loc]
-
-            # select on the correct axis
-            if axis == 1 and loc_is_slice:
-                indexer = slice(None), indexer
-            result = self.ix[indexer]
-            setattr(result, result._get_axis_name(axis), new_ax)
-            return result
-
-        if axis == 1:
-            data = self[key]
-            if copy:
-                data = data.copy()
-            return data
-
-        self._consolidate_inplace()
-
-        index = self.index
-        if isinstance(index, MultiIndex):
-            loc, new_index = self.index.get_loc_level(key,
-                                                      drop_level=drop_level)
-        else:
-            loc = self.index.get_loc(key)
-
-            if isinstance(loc, np.ndarray):
-                if loc.dtype == np.bool_:
-                    inds, = loc.nonzero()
-                    return self.take(inds, axis=axis, convert=False)
-                else:
-                    return self.take(loc, axis=axis, convert=True)
-
-            if not np.isscalar(loc):
-                new_index = self.index[loc]
-
-        if np.isscalar(loc):
-
-            new_values, copy = self._data.fast_2d_xs(loc, copy=copy)
-            result = Series(new_values, index=self.columns,
-                            name=self.index[loc])
-            result.is_copy=True
-
-        else:
-            result = self[loc]
-            result.index = new_index
-
-        return result
-
-    _xs = xs
-
     def lookup(self, row_labels, col_labels):
         """Label-based "fancy indexing" function for DataFrame.
         Given equal-length arrays of row and column labels, return an

pandas/core/generic.py

@@ -1133,6 +1133,145 @@ def take(self, indices, axis=0, convert=True, is_copy=True):
 
         return result
 
+    def xs(self, key, axis=0, level=None, copy=True, drop_level=True):
+        """
+        Returns a cross-section (row(s) or column(s)) from the Series/DataFrame.
+        Defaults to cross-section on the rows (axis=0).
+
+        Parameters
+        ----------
+        key : object
+            Some label contained in the index, or partially in a MultiIndex
+        axis : int, default 0
+            Axis to retrieve cross-section on
+        level : object, defaults to first n levels (n=1 or len(key))
+            In case of a key partially contained in a MultiIndex, indicate
+            which levels are used. Levels can be referred by label or position.
+        copy : boolean, default True
+            Whether to make a copy of the data
+        drop_level : boolean, default True
+            If False, returns object with same levels as self.
+
+        Examples
+        --------
+        >>> df
+           A  B  C
+        a  4  5  2
+        b  4  0  9
+        c  9  7  3
+        >>> df.xs('a')
+        A    4
+        B    5
+        C    2
+        Name: a
+        >>> df.xs('C', axis=1)
+        a    2
+        b    9
+        c    3
+        Name: C
+        >>> s = df.xs('a', copy=False)
+        >>> s['A'] = 100
+        >>> df
+             A  B  C
+        a  100  5  2
+        b    4  0  9
+        c    9  7  3
+
+
+        >>> df
+                            A  B  C  D
+        first second third
+        bar   one    1      4  1  8  9
+              two    1      7  5  5  0
+        baz   one    1      6  6  8  0
+              three  2      5  3  5  3
+        >>> df.xs(('baz', 'three'))
+               A  B  C  D
+        third
+        2      5  3  5  3
+        >>> df.xs('one', level=1)
+                     A  B  C  D
+        first third
+        bar   1      4  1  8  9
+        baz   1      6  6  8  0
+        >>> df.xs(('baz', 2), level=[0, 'third'])
+                A  B  C  D
+        second
+        three   5  3  5  3
+
+        Returns
+        -------
+        xs : Series or DataFrame
+
+        """
+        axis = self._get_axis_number(axis)
+        labels = self._get_axis(axis)
+        if level is not None:
+            loc, new_ax = labels.get_loc_level(key, level=level,
+                                               drop_level=drop_level)
+
+            if not copy and not isinstance(loc, slice):
+                raise ValueError('Cannot retrieve view (copy=False)')
+
+            # level = 0
+            loc_is_slice = isinstance(loc, slice)
+            if not loc_is_slice:
+                indexer = [slice(None)] * self.ndim
+                indexer[axis] = loc
+                indexer = tuple(indexer)
+            else:
+                indexer = loc
+                lev_num = labels._get_level_number(level)
+                if labels.levels[lev_num].inferred_type == 'integer':
+                    indexer = self.index[loc]
+
+            # select on the correct axis
+            if axis == 1 and loc_is_slice:
+                indexer = slice(None), indexer
+            result = self.ix[indexer]
+            setattr(result, result._get_axis_name(axis), new_ax)
+            return result
+
+        if axis == 1:
+            data = self[key]
+            if copy:
+                data = data.copy()
+            return data
+
+        self._consolidate_inplace()
+
+        index = self.index
+        if isinstance(index, MultiIndex):
+            loc, new_index = self.index.get_loc_level(key,
+                                                      drop_level=drop_level)
+        else:
+            loc = self.index.get_loc(key)
+
+            if isinstance(loc, np.ndarray):
+                if loc.dtype == np.bool_:
+                    inds, = loc.nonzero()
+                    return self.take(inds, axis=axis, convert=False)
+                else:
+                    return self.take(loc, axis=axis, convert=True)
+
+            if not np.isscalar(loc):
+                new_index = self.index[loc]
+
+        if np.isscalar(loc):
+            from pandas import Series
+            new_values, copy = self._data.fast_2d_xs(loc, copy=copy)
+            result = Series(new_values, index=self.columns,
+                            name=self.index[loc])
+            result.is_copy=True
+
+        else:
+            result = self[loc]
+            result.index = new_index
+
+        return result
+
+    _xs = xs
+
     # TODO: Check if this was clearer in 0.12
     def select(self, crit, axis=0):
         """

pandas/core/indexing.py

@@ -57,7 +57,9 @@ def __getitem__(self, key):
 
     def _get_label(self, label, axis=0):
         # ueber-hack
-        if (isinstance(label, tuple) and
+        if self.ndim == 1:
+            return self.obj[label]
+        elif (isinstance(label, tuple) and
                 isinstance(label[axis], slice)):
 
             raise IndexingError('no slices here')
@@ -1364,46 +1366,6 @@ def _crit(v):
     return not both_none and (_crit(obj.start) and _crit(obj.stop))
 
 
-class _SeriesIndexer(_IXIndexer):
-
-    """
-    Class to support fancy indexing, potentially using labels
-
-    Notes
-    -----
-    Indexing based on labels is INCLUSIVE
-    Slicing uses PYTHON SEMANTICS (endpoint is excluded)
-
-    If Index contains int labels, these will be used rather than the locations,
-    so be very careful (ambiguous).
-
-    Examples
-    --------
-    >>> ts.ix[5:10] # equivalent to ts[5:10]
-    >>> ts.ix[[date1, date2, date3]]
-    >>> ts.ix[date1:date2] = 0
-    """
-
-    def _get_label(self, key, axis=0):
-        return self.obj[key]
-
-    def _get_loc(self, key, axis=0):
-        return self.obj.values[key]
-
-    def _slice(self, indexer, axis=0, typ=None):
-        return self.obj._get_values(indexer)
-
-    def _setitem_with_indexer(self, indexer, value):
-
-        # need to delegate to the super setter
-        if isinstance(indexer, dict):
-            return super(_SeriesIndexer, self)._setitem_with_indexer(indexer,
-                                                                     value)
-
-        # fast access
-        self.obj._set_values(indexer, value)
-
-
 def _check_bool_indexer(ax, key):
     # boolean indexing, need to check that the data are aligned, otherwise
     # disallowed

pandas/core/series.py

@@ -28,7 +28,7 @@
 from pandas.core.index import (Index, MultiIndex, InvalidIndexError,
                                _ensure_index, _handle_legacy_indexes)
 from pandas.core.indexing import (
-    _SeriesIndexer, _check_bool_indexer, _check_slice_bounds,
+    _check_bool_indexer, _check_slice_bounds,
     _is_index_slice, _maybe_convert_indices)
 from pandas.core import generic
 from pandas.core.internals import SingleBlockManager
@@ -445,11 +445,6 @@ def _maybe_box(self, values):
 
         return values
 
-    def _xs(self, key, axis=0, level=None, copy=True):
-        return self.__getitem__(key)
-
-    xs = _xs
-
     def _ixs(self, i, axis=0):
         """
         Return the i-th value or values in the Series by location
@@ -2473,10 +2468,6 @@ def to_period(self, freq=None, copy=True):
 Series._add_numeric_operations()
 _INDEX_TYPES = ndarray, Index, list, tuple
 
-# reinstall the SeriesIndexer
-# defined in indexing.py; pylint: disable=E0203
-Series._create_indexer('ix', _SeriesIndexer)
-
 #------------------------------------------------------------------------------
 # Supplementary functions