Merge pull request #6730 from jreback/numeric

BUG: bug in BlockManager._get_numeric_data, with invalid combine

Author: jreback

pandas/core/internals.py

@@ -1907,7 +1907,7 @@ def fillna(self, value, limit=None, inplace=False, downcast=None):
         values = self.values if inplace else self.values.copy()
         return [self.make_block(values.get_values(value), fill_value=value)]
 
-        
+
     def shift(self, periods, axis=0):
         """ shift the block by periods """
         N = len(self.values.T)
@@ -2674,18 +2674,17 @@ def get_data(self, copy=False, columns=None, **kwargs):
         if len(blocks) == 0:
             return self.make_empty()
 
-        return self.combine(blocks)
+        return self.combine(blocks, copy=copy)
 
-    def combine(self, blocks):
+    def combine(self, blocks, copy=True):
         """ return a new manager with the blocks """
         indexer = np.sort(np.concatenate([b.ref_locs for b in blocks]))
         new_items = self.items.take(indexer)
 
         new_blocks = []
         for b in blocks:
-            b = b.copy(deep=False)
-            b.ref_items = new_items
-            new_blocks.append(b)
+            b = b.reindex_items_from(new_items, copy=copy)
+            new_blocks.extend(_valid_blocks(b))
         new_axes = list(self.axes)
         new_axes[0] = new_items
         return self.__class__(new_blocks, new_axes, do_integrity_check=False)

pandas/tests/test_frame.py

@@ -10424,6 +10424,16 @@ def test_get_numeric_data(self):
         expected = df.ix[:, []]
         assert_frame_equal(result, expected)
 
+        df = DataFrame.from_dict({'a':[1,2], 'b':['foo','bar'],'c':[np.pi,np.e]})
+        result = df._get_numeric_data()
+        expected = DataFrame.from_dict({'a':[1,2], 'c':[np.pi,np.e]})
+        assert_frame_equal(result, expected)
+
+        df = result.copy()
+        result = df._get_numeric_data()
+        expected = df
+        assert_frame_equal(result, expected)
+
     def test_bool_describe_in_mixed_frame(self):
         df = DataFrame({
             'string_data': ['a', 'b', 'c', 'd', 'e'],
@@ -10937,7 +10947,7 @@ def test_rank2(self):
         expected = DataFrame([[1.0, 3.0, 2.0], [1, 2, 3]]) / 3.0
         result = df.rank(1, pct=True)
         assert_frame_equal(result, expected)
-        
+
         df = DataFrame([[1, 3, 2], [1, 2, 3]])
         expected = df.rank(0) / 2.0
         result = df.rank(0, pct=True)
@@ -10950,7 +10960,7 @@ def test_rank2(self):
         result = df.rank(1, numeric_only=False)
         assert_frame_equal(result, expected)
 
-        
+
         expected = DataFrame([[2.0, 1.5, 1.0], [1, 1.5, 2]])
         result = df.rank(0, numeric_only=False)
         assert_frame_equal(result, expected)