Merge pull request #4043 from jreback/GH4032

BUG: (GH4032) Fixed insertion issue into DataFrame, after rename

Author: jreback

doc/source/release.rst

@@ -253,8 +253,7 @@ pandas 0.11.1
   - Fix running of bs4 tests when it is not installed (:issue:`3605`)
   - Fix parsing of html table (:issue:`3606`)
   - ``read_html()`` now only allows a single backend: ``html5lib`` (:issue:`3616`)
-  - ``convert_objects`` with ``convert_dates='coerce'`` was parsing some single-letter strings
-     into today's date
+  - ``convert_objects`` with ``convert_dates='coerce'`` was parsing some single-letter strings into today's date
   - ``DataFrame.from_records`` did not accept empty recarrays (:issue:`3682`)
   - ``DataFrame.to_csv`` will succeed with the deprecated option ``nanRep``, @tdsmith
   - ``DataFrame.to_html`` and ``DataFrame.to_latex`` now accept a path for
@@ -277,10 +276,11 @@ pandas 0.11.1
   - Indexing with a string with seconds resolution not selecting from a time index (:issue:`3925`)
   - csv parsers would loop infinitely if ``iterator=True`` but no ``chunksize`` was 
     specified (:issue:`3967`), python parser failing with ``chunksize=1``
-	- Fix index name not propogating when using ``shift`` 
-	- Fixed dropna=False being ignored with multi-index stack (:issue:`3997`)
+  - Fix index name not propogating when using ``shift`` 
+  - Fixed dropna=False being ignored with multi-index stack (:issue:`3997`)
   - Fixed flattening of columns when renaming MultiIndex columns DataFrame (:issue:`4004`)
-	- Fix ``Series.clip`` for datetime series. NA/NaN threshold values will now throw ValueError (:issue:`3996`)
+  - Fix ``Series.clip`` for datetime series. NA/NaN threshold values will now throw ValueError (:issue:`3996`)
+  - Fixed insertion issue into DataFrame, after rename (:issue:`4032`)
 
 .. _Gh3616: https://github.com/pydata/pandas/issues/3616
 

pandas/core/internals.py

@@ -85,6 +85,8 @@ def set_ref_items(self, ref_items, maybe_rename=True):
         """
         if not isinstance(ref_items, Index):
             raise AssertionError('block ref_items must be an Index')
+        if maybe_rename == 'clear':
+            self._ref_locs = None
         if maybe_rename:
             self.items = ref_items.take(self.ref_locs)
         self.ref_items = ref_items
@@ -1798,12 +1800,18 @@ def insert(self, loc, item, value, allow_duplicates=False):
 
         if len(self.blocks) > 100:
             self._consolidate_inplace()
+        elif new_items.is_unique:
+            self.set_items_clear(new_items)
 
         self._known_consolidated = False
 
     def set_items_norename(self, value):
         self.set_axis(0, value, maybe_rename=False, check_axis=False)
 
+    def set_items_clear(self, value):
+        """ clear the ref_locs on all blocks """
+        self.set_axis(0, value, maybe_rename='clear', check_axis=False)
+
     def _delete_from_all_blocks(self, loc, item):
         """ delete from the items loc the item
             the item could be in multiple blocks which could
@@ -1914,7 +1922,7 @@ def _add_new_block(self, item, value, loc=None):
             # and reset
             self._reset_ref_locs()
             self._set_ref_locs(do_refs=True)
-            
+
     def _find_block(self, item):
         self._check_have(item)
         for i, block in enumerate(self.blocks):

pandas/tests/test_frame.py

@@ -10018,6 +10018,21 @@ def test_columns_with_dups(self):
         xp.columns = ['A', 'A', 'B']
         assert_frame_equal(rs, xp)
 
+    def test_insert_column_bug_4032(self):
+        # GH4032, inserting a column and renaming causing errors
+        df = DataFrame({'b': [1.1, 2.2]})
+        df = df.rename(columns={})
+        df.insert(0, 'a', [1, 2])
+
+        result = df.rename(columns={})
+        expected = DataFrame([[1,1.1],[2, 2.2]],columns=['a','b'])
+        assert_frame_equal(result,expected)
+        df.insert(0, 'c', [1.3, 2.3])
+
+        result = df.rename(columns={})
+        expected = DataFrame([[1.3,1,1.1],[2.3,2, 2.2]],columns=['c','a','b'])
+        assert_frame_equal(result,expected)
+
     def test_cast_internals(self):
         casted = DataFrame(self.frame._data, dtype=int)
         expected = DataFrame(self.frame._series, dtype=int)