Backport PR pandas-dev#51239 on branch 2.0.x (API / CoW: constructing DataFrame from DataFrame/BlockManager creates lazy copy) (pandas-dev#51650)

Backport PR pandas-dev#51239: API / CoW: constructing DataFrame from DataFrame/BlockManager creates lazy copy

Co-authored-by: Patrick Hoefler <[email protected]>

Author: meeseeksmachine

doc/source/whatsnew/v2.0.0.rst

@@ -246,6 +246,10 @@ Copy-on-Write improvements
   a modification to the data happens) when constructing a Series from an existing
   Series with the default of ``copy=False`` (:issue:`50471`)
 
+- The :class:`DataFrame` constructor will now create a lazy copy (deferring the copy until
+  a modification to the data happens) when constructing from an existing
+  :class:`DataFrame` with the default of ``copy=False`` (:issue:`51239`)
+
 - The :class:`DataFrame` constructor, when constructing a DataFrame from a dictionary
   of Series objects and specifying ``copy=False``, will now use a lazy copy
   of those Series objects for the columns of the DataFrame (:issue:`50777`)

pandas/core/frame.py

@@ -656,6 +656,8 @@ def __init__(
                 data = data.copy(deep=False)
 
         if isinstance(data, (BlockManager, ArrayManager)):
+            if using_copy_on_write():
+                data = data.copy(deep=False)
             # first check if a Manager is passed without any other arguments
             # -> use fastpath (without checking Manager type)
             if index is None and columns is None and dtype is None and not copy:

pandas/tests/copy_view/test_constructors.py

@@ -82,6 +82,25 @@ def test_series_from_series_with_reindex(using_copy_on_write):
         assert not result._mgr.blocks[0].refs.has_reference()
 
 
+@pytest.mark.parametrize("func", [lambda x: x, lambda x: x._mgr])
+@pytest.mark.parametrize("columns", [None, ["a"]])
+def test_dataframe_constructor_mgr_or_df(using_copy_on_write, columns, func):
+    df = DataFrame({"a": [1, 2, 3]})
+    df_orig = df.copy()
+
+    new_df = DataFrame(func(df))
+
+    assert np.shares_memory(get_array(df, "a"), get_array(new_df, "a"))
+    new_df.iloc[0] = 100
+
+    if using_copy_on_write:
+        assert not np.shares_memory(get_array(df, "a"), get_array(new_df, "a"))
+        tm.assert_frame_equal(df, df_orig)
+    else:
+        assert np.shares_memory(get_array(df, "a"), get_array(new_df, "a"))
+        tm.assert_frame_equal(df, new_df)
+
+
 @pytest.mark.parametrize("dtype", [None, "int64", "Int64"])
 @pytest.mark.parametrize("index", [None, [0, 1, 2]])
 @pytest.mark.parametrize("columns", [None, ["a", "b"], ["a", "b", "c"]])