Skip to content

Clean up DataFrame.setitem behavior for duplicate columns #39403

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.

Sign up for GitHub

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 9 commits into from
Jan 29, 2021
Merged

Clean up DataFrame.setitem behavior for duplicate columns #39403

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
9ce8713
Clean up DataFrame.setitem behavior for duplicate columns
phofl Jan 25, 2021
d9c8026
Add gh reference
phofl Jan 25, 2021
4d57974
Move function
phofl Jan 26, 2021
d0bdc78
Remove type
phofl Jan 26, 2021
6f5f419
Add note
phofl Jan 27, 2021
e0c047e
Adjust test
phofl Jan 27, 2021
9a82e6c
Add spaces
phofl Jan 28, 2021
2dad847
Add raises section
phofl Jan 28, 2021
ee4a849
Add types
phofl Jan 28, 2021
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
13 changes: 10 additions & 3 deletions pandas/core/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3211,6 +3211,14 @@ def _setitem_slice(self, key: slice, value):
self._check_setitem_copy()
self.iloc[key] = value

def _check_key_length(self, key, value: DataFrame):
if self.columns.is_unique:
if len(value.columns) != len(key):
raise ValueError("Columns must be same length as key")
else:
if len(self.columns.get_indexer_non_unique(key)[0]) != len(value.columns):
raise ValueError("Columns must be same length as key")

def _setitem_array(self, key, value):
# also raises Exception if object array with NA values
if com.is_bool_indexer(key):
Expand All @@ -3223,9 +3231,8 @@ def _setitem_array(self, key, value):
self._check_setitem_copy()
self.iloc[indexer] = value
else:
if isinstance(value, DataFrame) and self.columns.is_unique:
if len(value.columns) != len(key):
raise ValueError("Columns must be same length as key")
if isinstance(value, DataFrame):
self._check_key_length(key, value)
for k1, k2 in zip(key, value.columns):
self[k1] = value[k2]
else:
Expand Down
10 changes: 9 additions & 1 deletion pandas/tests/frame/indexing/test_setitem.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -378,11 +378,19 @@ def test_setitem_df_wrong_column_number(self, cols):
def test_setitem_listlike_indexer_duplicate_columns(self):
# GH#38604
df = DataFrame([[1, 2, 3]], columns=["a", "b", "b"])
rhs = DataFrame([[10, 11, 12]], columns=["d", "e", "c"])
rhs = DataFrame([[10, 11, 12]], columns=["a", "b", "b"])
df[["a", "b"]] = rhs
expected = DataFrame([[10, 11, 12]], columns=["a", "b", "b"])
tm.assert_frame_equal(df, expected)

def test_setitem_listlike_indexer_duplicate_columns_not_equal_length(self):
# GH#39403
df = DataFrame([[1, 2, 3]], columns=["a", "b", "b"])
rhs = DataFrame([[10, 11]], columns=["a", "b"])
msg = "Columns must be same length as key"
with pytest.raises(ValueError, match=msg):
df[["a", "b"]] = rhs


class TestDataFrameSetItemWithExpansion:
def test_setitem_listlike_views(self):
Expand Down