Merge pull request #10308 from behzadnouri/block-type-loss

BUG: bug in setitem where type promotion is applied to entire block

Author: jreback

doc/source/whatsnew/v0.16.2.txt

@@ -140,6 +140,7 @@ Bug Fixes
 
 - Bug in getting timezone data with ``dateutil`` on various platforms ( :issue:`9059`, :issue:`8639`, :issue:`9663`, :issue:`10121`)
 - Bug in display datetimes with mixed frequencies uniformly; display 'ms' datetimes to the proper precision. (:issue:`10170`)
+- Bug in ``setitem`` where type pormotion is applied to entire block (:issue:`10280`)
 
 - Bug in ``Series`` arithmetic methods may incorrectly hold names (:issue:`10068`)
 

pandas/core/indexing.py

@@ -204,6 +204,15 @@ def _setitem_with_indexer(self, indexer, value):
 
         # maybe partial set
         take_split_path = self.obj._is_mixed_type
+
+        # if there is only one block/type, still have to take split path
+        # unless the block is one-dimensional or it can hold the value
+        if not take_split_path and self.obj._data.blocks:
+            blk, = self.obj._data.blocks
+            if 1 < blk.ndim:  # in case of dict, keys are indices
+                val = list(value.values()) if isinstance(value,dict) else value
+                take_split_path = not blk._can_hold_element(val)
+
         if isinstance(indexer, tuple):
             nindexer = []
             for i, idx in enumerate(indexer):

pandas/tests/test_indexing.py

@@ -2330,6 +2330,31 @@ def test_setitem_dtype_upcast(self):
         expected = DataFrame([{"a": 1, "c" : 'foo'}, {"a": 3, "b": 2, "c" : np.nan}])
         assert_frame_equal(df,expected)
 
+        # GH10280
+        df = DataFrame(np.arange(6).reshape(2, 3), index=list('ab'),
+                columns=['foo', 'bar', 'baz'])
+
+        for val in [3.14, 'wxyz']:
+            left = df.copy()
+            left.loc['a', 'bar'] = val
+            right = DataFrame([[0, val, 2], [3, 4, 5]], index=list('ab'),
+                    columns=['foo', 'bar', 'baz'])
+
+            assert_frame_equal(left, right)
+            self.assertTrue(com.is_integer_dtype(left['foo']))
+            self.assertTrue(com.is_integer_dtype(left['baz']))
+
+        left = DataFrame(np.arange(6).reshape(2, 3) / 10.0, index=list('ab'),
+                columns=['foo', 'bar', 'baz'])
+        left.loc['a', 'bar'] = 'wxyz'
+
+        right = DataFrame([[0, 'wxyz', .2], [.3, .4, .5]], index=list('ab'),
+                columns=['foo', 'bar', 'baz'])
+
+        assert_frame_equal(left, right)
+        self.assertTrue(com.is_float_dtype(left['foo']))
+        self.assertTrue(com.is_float_dtype(left['baz']))
+
     def test_setitem_iloc(self):