ENH: allow as_blocks to take a copy argument (pandas-dev#9607)

tzinckgraf · jreback · commit 8eabc4edc6be · 2015-06-26T19:25:57.000-04:00
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
@@ -2359,14 +2359,18 @@ def ftypes(self):
         return Series(self._data.get_ftypes(), index=self._info_axis,
                       dtype=np.object_)
 
-    def as_blocks(self):
+    def as_blocks(self, copy=True):
         """
         Convert the frame to a dict of dtype -> Constructor Types that each has
         a homogeneous dtype.
 
         NOTE: the dtypes of the blocks WILL BE PRESERVED HERE (unlike in
               as_matrix)
 
+        Parameters
+        ----------
+        copy : boolean, default True
+
         Returns
         -------
         values : a dict of dtype -> Constructor Types
@@ -2381,7 +2385,7 @@ def as_blocks(self):
         for dtype, blocks in bd.items():
             # Must combine even after consolidation, because there may be
             # sparse items which are never consolidated into one block.
-            combined = self._data.combine(blocks, copy=True)
+            combined = self._data.combine(blocks, copy=copy)
             result[dtype] = self._constructor(combined).__finalize__(self)
 
         return result
diff --git a/pandas/tests/test_frame.py b/pandas/tests/test_frame.py
@@ -6149,6 +6149,34 @@ def test_equals_different_blocks(self):
         self.assertTrue(df0.equals(df1))
         self.assertTrue(df1.equals(df0))
 
+    def test_copy_blocks(self):
+        # API/ENH 9607
+        df = DataFrame(self.frame, copy=True)
+        column = df.columns[0]
+
+        # use the default copy=True, change a column
+        blocks = df.as_blocks()
+        for dtype, _df in blocks.items():
+            if column in _df:
+                _df.ix[:, column] = _df[column] + 1
+
+        # make sure we did not change the original DataFrame
+        self.assertFalse(_df[column].equals(df[column]))
+
+    def test_no_copy_blocks(self):
+        # API/ENH 9607
+        df = DataFrame(self.frame, copy=True)
+        column = df.columns[0]
+
+        # use the copy=False, change a column
+        blocks = df.as_blocks(copy=False)
+        for dtype, _df in blocks.items():
+            if column in _df:
+                _df.ix[:, column] = _df[column] + 1
+
+        # make sure we did change the original DataFrame
+        self.assertTrue(_df[column].equals(df[column]))
+
     def test_to_csv_from_csv(self):
 
         pname = '__tmp_to_csv_from_csv__'
