Merge pull request #6375 from jreback/take_dup

BUG: Bug in take with duplicate columns not consolidated (GH6240)

Author: jreback

doc/source/release.rst

@@ -118,6 +118,7 @@ Bug Fixes
 - Disabled clipboard tests until release time (run locally with ``nosetests -A disabled`` (:issue:`6048`).
 - Bug in ``DataFrame.replace()`` when passing a nested ``dict`` that contained
   keys not in the values to be replaced (:issue:`6342`)
+- Bug in take with duplicate columns not consolidated (:issue:`6240`)
 
 pandas 0.13.1
 -------------

pandas/core/internals.py

@@ -3399,6 +3399,11 @@ def reindex_items(self, new_items, indexer=None, copy=True,
                 new_blocks.append(na_block)
                 new_blocks = _consolidate(new_blocks, new_items)
 
+            # consolidate
+            # import for non-unique which creates a block for each item
+            # and they must be consolidated before passing on
+            new_blocks = _consolidate(new_blocks, new_items)
+
         return self.__class__(new_blocks, new_axes)
 
     def _make_na_block(self, items, ref_items, placement=None,

pandas/tests/test_frame.py

@@ -3243,6 +3243,19 @@ def check(result, expected=None):
         df['that'] = 1
         check(df, expected)
 
+    def test_column_dups2(self):
+
+        # drop buggy GH 6240
+        df = DataFrame({'A' : np.random.randn(5),
+                        'B' : np.random.randn(5),
+                        'C' : np.random.randn(5),
+                        'D' : ['a','b','c','d','e'] })
+
+        expected = df.take([0,1,1], axis=1)
+        df2 = df.take([2,0,1,2,1], axis=1)
+        result = df2.drop('C',axis=1)
+        assert_frame_equal(result, expected)
+
     def test_column_dups_indexing(self):
 
         def check(result, expected=None):