Merge pull request #5249 from jreback/drop_dup

BUG: fixed issue with drop on a non-unique index with Series (GH5248)

Author: jreback

doc/source/release.rst

@@ -621,6 +621,7 @@ Bug Fixes
     non-business date. (:issue:`5203`)
   - Fixed bug in Excel writers where frames with duplicate column names weren't
     written correctly. (:issue:`5235`)
+  - Fixed issue with ``drop`` and a non-unique index on Series (:issue:`5248`)
 
 pandas 0.12.0
 -------------

pandas/core/frame.py

@@ -672,9 +672,9 @@ def to_dict(self, outtype='dict'):
             raise ValueError("outtype %s not understood" % outtype)
 
     def to_gbq(self, destination_table, schema=None, col_order=None, if_exists='fail', **kwargs):
-        """Write a DataFrame to a Google BigQuery table. 
-        
-        If the table exists, the DataFrame will be appended. If not, a new table 
+        """Write a DataFrame to a Google BigQuery table.
+
+        If the table exists, the DataFrame will be appended. If not, a new table
         will be created, in which case the schema will have to be specified. By default,
         rows will be written in the order they appear in the DataFrame, though
         the user may specify an alternative order.
@@ -2233,33 +2233,6 @@ def rename(self, index=None, columns=None, **kwargs):
         return super(DataFrame, self).rename(index=index, columns=columns,
                                              **kwargs)
 
-    def reindex_like(self, other, method=None, copy=True, limit=None,
-                     fill_value=NA):
-        """
-        Reindex DataFrame to match indices of another DataFrame, optionally
-        with filling logic
-
-        Parameters
-        ----------
-        other : DataFrame
-        method : string or None
-        copy : boolean, default True
-        limit : int, default None
-            Maximum size gap to forward or backward fill
-
-        Notes
-        -----
-        Like calling s.reindex(index=other.index, columns=other.columns,
-                               method=...)
-
-        Returns
-        -------
-        reindexed : DataFrame
-        """
-        return self.reindex(index=other.index, columns=other.columns,
-                            method=method, copy=copy, limit=limit,
-                            fill_value=fill_value)
-
     def set_index(self, keys, drop=True, append=False, inplace=False,
                   verify_integrity=False):
         """

pandas/core/generic.py

@@ -1103,6 +1103,8 @@ def drop(self, labels, axis=0, level=None):
         """
         axis_name = self._get_axis_name(axis)
         axis, axis_ = self._get_axis(axis), axis
+        if not is_list_like(labels):
+            labels = [ labels ]
 
         if axis.is_unique:
             if level is not None:

pandas/core/indexing.py

@@ -581,9 +581,11 @@ def _multi_take_opportunity(self, tup):
             return False
 
         # just too complicated
-        for ax in self.obj._data.axes:
+        for indexer, ax in zip(tup,self.obj._data.axes):
             if isinstance(ax, MultiIndex):
                 return False
+            elif com._is_bool_indexer(indexer):
+                return False
 
         return True
 

pandas/tests/test_frame.py

@@ -3175,9 +3175,11 @@ def check(result, expected=None):
 
         # drop
         df = DataFrame([[1,5,7.],[1,5,7.],[1,5,7.]],columns=['bar','a','a'])
-        df = df.drop(['a'],axis=1)
+        result = df.drop(['a'],axis=1)
         expected = DataFrame([[1],[1],[1]],columns=['bar'])
-        check(df,expected)
+        check(result,expected)
+        result = df.drop('a',axis=1)
+        check(result,expected)
 
         # describe
         df = DataFrame([[1,1,1],[2,2,2],[3,3,3]],columns=['bar','a','a'],dtype='float64')

pandas/tests/test_series.py

@@ -1415,6 +1415,31 @@ def test_mask(self):
         rs = s.where(cond, np.nan)
         assert_series_equal(rs, s.mask(~cond))
 
+    def test_drop(self):
+
+        # unique
+        s = Series([1,2],index=['one','two'])
+        expected = Series([1],index=['one'])
+        result = s.drop(['two'])
+        assert_series_equal(result,expected)
+        result = s.drop('two')
+        assert_series_equal(result,expected)
+
+        # non-unique
+        # GH 5248
+        s = Series([1,1,2],index=['one','two','one'])
+        expected = Series([1,2],index=['one','one'])
+        result = s.drop(['two'])
+        assert_series_equal(result,expected)
+        result = s.drop('two')
+        assert_series_equal(result,expected)
+
+        expected = Series([1],index=['two'])
+        result = s.drop(['one'])
+        assert_series_equal(result,expected)
+        result = s.drop('one')
+        assert_series_equal(result,expected)
+
     def test_ix_setitem(self):
         inds = self.series.index[[3, 4, 7]]