Skip to content

BUG: Multiple unstack using row index level labels and multi level columns DataFrame #32990

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 7 commits into from
Mar 26, 2020
Merged

BUG: Multiple unstack using row index level labels and multi level columns DataFrame #32990

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
aa981dd
BUG: Fix bug for unstack with a lot of indices (#32624)
Mar 24, 2020
fbaa9cd
CLN: Fix equals empty list with bool expression
Mar 24, 2020
700d905
DOC: Fix Typo parced
Mar 24, 2020
482f379
CLN: Add black pandas and flak8 issues
Mar 24, 2020
d617caa
Add unittest for #28306 and #24729 and revert typo. Add whats new
phofl Mar 25, 2020
4028cca
Revert "DOC: Fix Typo parced"
phofl Mar 25, 2020
008aebb
Delete print statement
phofl Mar 25, 2020
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
4 changes: 2 additions & 2 deletions pandas/core/reshape/reshape.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -338,7 +338,7 @@ def _unstack_multiple(data, clocs, fill_value=None):
comp_ids, obs_ids = compress_group_index(group_index, sort=False)
recons_codes = decons_obs_group_ids(comp_ids, obs_ids, shape, ccodes, xnull=False)

if rlocs == []:
if not rlocs:
# Everything is in clocs, so the dummy df has a regular index
dummy_index = Index(obs_ids, name="__placeholder__")
else:
Expand All @@ -363,7 +363,7 @@ def _unstack_multiple(data, clocs, fill_value=None):
for i in range(len(clocs)):
val = clocs[i]
result = result.unstack(val, fill_value=fill_value)
clocs = [v if i > v else v - 1 for v in clocs]
clocs = [v if v < val else v - 1 for v in clocs]

return result

Expand Down
2 changes: 1 addition & 1 deletion pandas/core/tools/datetimes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -260,7 +260,7 @@ def _convert_listlike_datetimes(
Parameters
----------
arg : list, tuple, ndarray, Series, Index
date to be parced
date to be parsed
name : object
None or string for the Index name
tz : object
Expand Down
22 changes: 22 additions & 0 deletions pandas/tests/frame/test_reshape.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -765,6 +765,28 @@ def test_unstack_unused_level(self, cols):
expected.index = expected.index.droplevel("C")
tm.assert_frame_equal(result, expected)

def test_unstack_long_index(self):
# PH 32624: Error when using a lot of indices to unstack.
# The error occurred only, if a lot of indices are used.
df = pd.DataFrame(
[[1]],
columns=pd.MultiIndex.from_tuples([[0]], names=["c1"]),
index=pd.MultiIndex.from_tuples(
[[0, 0, 1, 0, 0, 0, 1]],
names=["i1", "i2", "i3", "i4", "i5", "i6", "i7"],
),
)
result = df.unstack(["i2", "i3", "i4", "i5", "i6", "i7"])
expected = pd.DataFrame(
[[1]],
columns=pd.MultiIndex.from_tuples(
[[0, 0, 1, 0, 0, 0, 1]],
names=["c1", "i2", "i3", "i4", "i5", "i6", "i7"],
),
index=pd.Index([0], name="i1"),
)
tm.assert_frame_equal(result, expected)

def test_unstack_nan_index(self): # GH7466
def cast(val):
val_str = "" if val != val else val
Expand Down