Merge pull request #4833 from jreback/series_loc

BUG: Fixed an issue with a duplicate index and duplicate selector with loc (GH4825)

Author: jreback

doc/source/release.rst

@@ -411,6 +411,7 @@ Bug Fixes
   - Fixed an issue related to ticklocs/ticklabels with log scale bar plots
     across different versions of matplotlib (:issue:`4789`)
   - Suppressed DeprecationWarning associated with internal calls issued by repr() (:issue:`4391`)
+  - Fixed an issue with a duplicate index and duplicate selector with ``.loc`` (:issue:`4825`)
 
 pandas 0.12.0
 -------------

pandas/core/indexing.py

@@ -701,19 +701,27 @@ def _reindex(keys, level=None):
                     new_labels[cur_indexer]     = cur_labels
                     new_labels[missing_indexer] = missing_labels
 
+                    # reindex with the specified axis
+                    ndim = self.obj.ndim
+                    if axis+1 > ndim:
+                        raise AssertionError("invalid indexing error with non-unique index")
+
                     # a unique indexer
                     if keyarr_is_unique:
                         new_indexer = (Index(cur_indexer) + Index(missing_indexer)).values
                         new_indexer[missing_indexer] = -1
 
                     # we have a non_unique selector, need to use the original indexer here
                     else:
-                        new_indexer = indexer
 
-                    # reindex with the specified axis
-                    ndim = self.obj.ndim
-                    if axis+1 > ndim:
-                        raise AssertionError("invalid indexing error with non-unique index")
+                        # need to retake to have the same size as the indexer
+                        rindexer = indexer.values
+                        rindexer[~check] = 0
+                        result = self.obj.take(rindexer, axis=axis, convert=False)
+
+                        # reset the new indexer to account for the new size
+                        new_indexer = np.arange(len(result))
+                        new_indexer[~check] = -1
 
                     result = result._reindex_with_indexers({ axis : [ new_labels, new_indexer ] }, copy=True, allow_dups=True)
 

pandas/tests/test_indexing.py

@@ -1436,6 +1436,49 @@ def f():
         p.loc[:,:,'C'] = Series([30,32],index=p_orig.items)
         assert_panel_equal(p,expected)
 
+    def test_series_partial_set(self):
+        # partial set with new index
+        # Regression from GH4825
+        ser = Series([0.1, 0.2], index=[1, 2])
+
+        # loc
+        expected = Series([np.nan, 0.2, np.nan], index=[3, 2, 3])
+        result = ser.loc[[3, 2, 3]]
+        assert_series_equal(result, expected)
+
+        expected = Series([np.nan, np.nan, np.nan], index=[3, 3, 3])
+        result = ser.loc[[3, 3, 3]]
+        assert_series_equal(result, expected)
+
+        expected = Series([0.2, 0.2, np.nan], index=[2, 2, 3])
+        result = ser.loc[[2, 2, 3]]
+        assert_series_equal(result, expected)
+
+        expected = Series([0.3, np.nan, np.nan], index=[3, 4, 4])
+        result = Series([0.1, 0.2, 0.3], index=[1,2,3]).loc[[3,4,4]]
+        assert_series_equal(result, expected)
+
+        expected = Series([np.nan, 0.3, 0.3], index=[5, 3, 3])
+        result = Series([0.1, 0.2, 0.3, 0.4], index=[1,2,3,4]).loc[[5,3,3]]
+        assert_series_equal(result, expected)
+
+        expected = Series([np.nan, 0.4, 0.4], index=[5, 4, 4])
+        result = Series([0.1, 0.2, 0.3, 0.4], index=[1,2,3,4]).loc[[5,4,4]]
+        assert_series_equal(result, expected)
+
+        expected = Series([0.4, np.nan, np.nan], index=[7, 2, 2])
+        result = Series([0.1, 0.2, 0.3, 0.4], index=[4,5,6,7]).loc[[7,2,2]]
+        assert_series_equal(result, expected)
+
+        expected = Series([0.4, np.nan, np.nan], index=[4, 5, 5])
+        result = Series([0.1, 0.2, 0.3, 0.4], index=[1,2,3,4]).loc[[4,5,5]]
+        assert_series_equal(result, expected)
+
+        # iloc
+        expected = Series([0.2,0.2,0.1,0.1], index=[2,2,1,1])
+        result = ser.iloc[[1,1,0,0]]
+        assert_series_equal(result, expected)
+
 if __name__ == '__main__':
     import nose
     nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],