Merge pull request #6065 from jreback/iloc_bug

BUG: suble iloc indexing bug with single block and multi-axis indexing (surfaced in GH6059)

Author: jreback

doc/source/release.rst

@@ -141,6 +141,7 @@ Bug Fixes
   - Bug in setting using fancy indexing a single element with a non-scalar (e.g. a list),
     (:issue:`6043`)
   - Regression in ``.get(None)`` indexing from 0.12 (:issue:`5652`)
+  - Subtle ``iloc`` indexing bug, surfaced in (:issue:`6059`)
 
 pandas 0.13.0
 -------------

pandas/core/internals.py

@@ -2596,11 +2596,27 @@ def get_slice(self, slobj, axis=0, raise_on_error=False):
 
         if axis == 0:
             new_items = new_axes[0]
+
+            # we want to preserver the view of a single-block
             if len(self.blocks) == 1:
+
                 blk = self.blocks[0]
+
+                # see GH 6059
+                ref_locs = blk._ref_locs
+                if ref_locs is not None:
+
+                    # need to preserve the ref_locs and just shift them
+                    indexer = np.ones(len(ref_locs),dtype=bool)
+                    indexer[slobj] = False
+                    indexer = indexer.astype(int).cumsum()[slobj]
+                    ref_locs = ref_locs[slobj]
+                    ref_locs -= indexer
+
                 newb = make_block(blk._slice(slobj), new_items, new_items,
                                   klass=blk.__class__, fastpath=True,
-                                  placement=blk._ref_locs)
+                                  placement=ref_locs)
+
                 new_blocks = [newb]
             else:
                 return self.reindex_items(

pandas/tests/test_indexing.py

@@ -720,6 +720,49 @@ def test_iloc_getitem_frame(self):
         # trying to use a label
         self.assertRaises(ValueError, df.iloc.__getitem__, tuple(['j','D']))
 
+
+    def test_iloc_getitem_doc_issue(self):
+
+        # multi axis slicing issue with single block
+        # surfaced in GH 6059
+
+        arr = np.random.randn(6,4)
+        index = date_range('20130101',periods=6)
+        columns = list('ABCD')
+        df = DataFrame(arr,index=index,columns=columns)
+
+        # defines ref_locs
+        df.describe()
+
+        result = df.iloc[3:5,0:2]
+        str(result)
+        result.dtypes
+
+        expected = DataFrame(arr[3:5,0:2],index=index[3:5],columns=columns[0:2])
+        assert_frame_equal(result,expected)
+
+        # for dups
+        df.columns = list('aaaa')
+        result = df.iloc[3:5,0:2]
+        str(result)
+        result.dtypes
+
+        expected = DataFrame(arr[3:5,0:2],index=index[3:5],columns=list('aa'))
+        assert_frame_equal(result,expected)
+
+        # related
+        arr = np.random.randn(6,4)
+        index = list(range(0,12,2))
+        columns = list(range(0,8,2))
+        df = DataFrame(arr,index=index,columns=columns)
+
+        df._data.blocks[0].ref_locs
+        result = df.iloc[1:5,2:4]
+        str(result)
+        result.dtypes
+        expected = DataFrame(arr[1:5,2:4],index=index[1:5],columns=columns[2:4])
+        assert_frame_equal(result,expected)
+
     def test_setitem_ndarray_1d(self):
         # GH5508