Thanks to visit codestin.com
Credit goes to github.com

Skip to content

BUG/API Raise ValueError for non-unique stack by name #6738

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

Closed
TomAugspurger wants to merge 1 commit into from
Closed

BUG/API Raise ValueError for non-unique stack by name #6738

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 7 additions & 0 deletions pandas/core/index.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2317,6 +2317,13 @@ def _set_names(self, values, validate=True):
names = property(
fset=_set_names, fget=_get_names, doc="Names of levels in MultiIndex")

def _reference_duplicate_name(self, name):
"""
Returns True if the name refered to in self.names is duplicated.
"""
# count the times name equals an element in self.names.
return np.sum(name == np.asarray(self.names)) > 1

def _format_native_types(self, **kwargs):
return self.tolist()

Expand Down
12 changes: 12 additions & 0 deletions pandas/core/reshape.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,6 +69,12 @@ def __init__(self, values, index, level=-1, value_columns=None):
raise ValueError('must pass column labels for multi-column data')

self.index = index
if isinstance(self.index, MultiIndex):
if index._reference_duplicate_name(level):
msg = ("Ambiguous reference to {0}. The index "
"names are not unique.".format(level))
raise ValueError(msg)

self.level = self.index._get_level_number(level)

levels = index.levels
Expand Down Expand Up @@ -497,6 +503,12 @@ def stack(frame, level=-1, dropna=True):
stacked : Series
"""
N, K = frame.shape
if isinstance(frame.columns, MultiIndex):
if frame.columns._reference_duplicate_name(level):
msg = ("Ambiguous reference to {0}. The column "
"names are not unique.".format(level))
raise ValueError(msg)

if isinstance(level, int) and level < 0:
level += frame.columns.nlevels

Expand Down
10 changes: 10 additions & 0 deletions pandas/tests/test_frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11387,6 +11387,16 @@ def test_unstack_dtypes(self):
expected = Series({'float64' : 2, 'object' : 2})
assert_series_equal(result, expected)

def test_unstack_non_unique_index_names(self):
idx = MultiIndex.from_tuples([('a', 'b'), ('c', 'd')],
names=['c1', 'c1'])
df = DataFrame([1, 2], index=idx)
with tm.assertRaises(ValueError):
df.unstack('c1')

with tm.assertRaises(ValueError):
df.T.stack('c1')

def test_reset_index(self):
stacked = self.frame.stack()[::2]
stacked = DataFrame({'foo': stacked, 'bar': stacked})
Expand Down
7 changes: 7 additions & 0 deletions pandas/tests/test_index.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1534,6 +1534,13 @@ def test_names(self):
level_names = [level.name for level in index.levels]
self.assertEqual(ind_names, level_names)

def test_reference_duplicate_name(self):
idx = MultiIndex.from_tuples([('a', 'b'), ('c', 'd')], names=['x', 'x'])
self.assertTrue(idx._reference_duplicate_name('x'))

idx = MultiIndex.from_tuples([('a', 'b'), ('c', 'd')], names=['x', 'y'])
self.assertFalse(idx._reference_duplicate_name('x'))

def test_astype(self):
expected = self.index.copy()
actual = self.index.astype('O')
Expand Down