Skip to content

API / CoW: Respect CoW for DataFrame(Index) #52276

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Mar 29, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion doc/source/whatsnew/v2.0.0.rst
Original file line number Diff line number Diff line change
Expand Up @@ -191,7 +191,8 @@ Copy-on-Write improvements
of those Series objects for the columns of the DataFrame (:issue:`50777`)

- The :class:`DataFrame` constructor, when constructing a DataFrame from a
:class:`Series` and specifying ``copy=False``, will now respect Copy-on-Write.
:class:`Series` or :class:`Index` and specifying ``copy=False``, will
now respect Copy-on-Write.

- The :class:`DataFrame` constructor, when constructing from a NumPy array,
will now copy the array by default to avoid mutating the :class:`DataFrame`
Expand Down
4 changes: 2 additions & 2 deletions pandas/core/internals/construction.py
Original file line number Diff line number Diff line change
Expand Up @@ -292,7 +292,7 @@ def ndarray_to_mgr(
if values.ndim == 1:
values = values.reshape(-1, 1)

elif isinstance(values, ABCSeries):
elif isinstance(values, (ABCSeries, Index)):
if not copy_on_sanitize and (
dtype is None or astype_is_view(values.dtype, dtype)
):
Expand All @@ -305,7 +305,7 @@ def ndarray_to_mgr(

values = _ensure_2d(values)

elif isinstance(values, (np.ndarray, ExtensionArray, Index)):
elif isinstance(values, (np.ndarray, ExtensionArray)):
# drop subclass info
_copy = (
copy_on_sanitize
Expand Down
22 changes: 12 additions & 10 deletions pandas/tests/copy_view/test_constructors.py
Original file line number Diff line number Diff line change
Expand Up @@ -228,26 +228,28 @@ def test_dataframe_from_dict_of_series_with_reindex(dtype):
assert np.shares_memory(arr_before, arr_after)


@pytest.mark.parametrize("cons", [Series, Index])
@pytest.mark.parametrize(
"data, dtype", [([1, 2], None), ([1, 2], "int64"), (["a", "b"], None)]
)
def test_dataframe_from_series(using_copy_on_write, data, dtype):
ser = Series(data, dtype=dtype)
ser_orig = ser.copy()
df = DataFrame(ser, dtype=dtype)
assert np.shares_memory(get_array(ser), get_array(df, 0))
def test_dataframe_from_series_or_index(using_copy_on_write, data, dtype, cons):
obj = cons(data, dtype=dtype)
obj_orig = obj.copy()
df = DataFrame(obj, dtype=dtype)
assert np.shares_memory(get_array(obj), get_array(df, 0))
if using_copy_on_write:
assert not df._mgr._has_no_reference(0)

df.iloc[0, 0] = data[-1]
if using_copy_on_write:
tm.assert_series_equal(ser, ser_orig)
tm.assert_equal(obj, obj_orig)


def test_dataframe_from_series_different_dtype(using_copy_on_write):
ser = Series([1, 2], dtype="int64")
df = DataFrame(ser, dtype="int32")
assert not np.shares_memory(get_array(ser), get_array(df, 0))
@pytest.mark.parametrize("cons", [Series, Index])
def test_dataframe_from_series_or_index_different_dtype(using_copy_on_write, cons):
obj = cons([1, 2], dtype="int64")
df = DataFrame(obj, dtype="int32")
assert not np.shares_memory(get_array(obj), get_array(df, 0))
if using_copy_on_write:
assert df._mgr._has_no_reference(0)

Expand Down