Merge pull request pandas-dev#4779 from jreback/dups_ops

TST/BUG: duplicate indexing ops with a Series using where and inplace add buggy (GH4550/GH4548)

Author: jreback

doc/source/release.rst

@@ -368,6 +368,7 @@ Bug Fixes
   - Bug in concatenation with duplicate columns across dtypes not merging with axis=0 (:issue:`4771`)
   - Bug in ``iloc`` with a slice index failing (:issue:`4771`)
   - Incorrect error message with no colspecs or width in ``read_fwf``. (:issue:`4774`)
+  - Fix bugs in indexing in a Series with a duplicate index (:issue:`4548`, :issue:`4550`)
 
 pandas 0.12.0
 -------------

pandas/core/generic.py

@@ -7,7 +7,7 @@
 
 import pandas as pd
 from pandas.core.base import PandasObject
-from pandas.core.index import Index, MultiIndex, _ensure_index
+from pandas.core.index import Index, MultiIndex, _ensure_index, InvalidIndexError
 import pandas.core.indexing as indexing
 from pandas.core.indexing import _maybe_convert_indices
 from pandas.tseries.index import DatetimeIndex
@@ -2308,6 +2308,10 @@ def where(self, cond, other=np.nan, inplace=False, try_cast=False, raise_on_erro
 
                 _, other = self.align(other, join='left', fill_value=np.nan)
 
+                # if we are NOT aligned, raise as we cannot where index
+                if not all([ other._get_axis(i).equals(ax) for i, ax in enumerate(self.axes) ]):
+                    raise InvalidIndexError
+
             # slice me out of the other
             else:
                 raise NotImplemented

pandas/core/series.py

@@ -1037,9 +1037,13 @@ def __setitem__(self, key, value):
 
         if _is_bool_indexer(key):
             key = _check_bool_indexer(self.index, key)
-            self.where(~key, value, inplace=True)
-        else:
-            self._set_with(key, value)
+            try:
+                self.where(~key, value, inplace=True)
+                return
+            except (InvalidIndexError):
+                pass
+
+        self._set_with(key, value)
 
     def _set_with_engine(self, key, value):
         values = self.values

pandas/tests/test_series.py

@@ -1373,6 +1373,26 @@ def test_where_inplace(self):
         rs.where(cond, -s, inplace=True)
         assert_series_equal(rs, s.where(cond, -s))
 
+    def test_where_dups(self):
+        # GH 4550
+        # where crashes with dups in index
+        s1 = Series(list(range(3)))
+        s2 = Series(list(range(3)))
+        comb = pd.concat([s1,s2])
+        result = comb.where(comb < 2)
+        expected = Series([0,1,np.nan,0,1,np.nan],index=[0,1,2,0,1,2])
+        assert_series_equal(result, expected)
+
+        # GH 4548
+        # inplace updating not working with dups
+        comb[comb<1] = 5
+        expected = Series([5,1,2,5,1,2],index=[0,1,2,0,1,2])
+        assert_series_equal(comb, expected)
+
+        comb[comb<2] += 10
+        expected = Series([5,11,2,5,11,2],index=[0,1,2,0,1,2])
+        assert_series_equal(comb, expected)
+
     def test_mask(self):
         s = Series(np.random.randn(5))
         cond = s > 0