Skip to content

REGR: Groupby first/last/nth treats None as an observation #38330

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 4 commits into from
Dec 6, 2020
Merged

REGR: Groupby first/last/nth treats None as an observation #38330

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
46a80a7
BUG: Groupby first/last/nth treats None as an observation
rhshadrach Dec 6, 2020
f93a8bd
Reverted test changes, whatsnew
rhshadrach Dec 6, 2020
7753f39
Reverted test changes, whatsnew
rhshadrach Dec 6, 2020
54c1a0b
Remove nth from whatsnew
rhshadrach Dec 6, 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
12 changes: 4 additions & 8 deletions pandas/_libs/groupby.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -928,9 +928,7 @@ def group_last(rank_t[:, :] out,
for j in range(K):
val = values[i, j]

# None should not be treated like other NA-like
# so that it won't be converted to nan
if not checknull(val) or val is None:
if not checknull(val):
# NB: use _treat_as_na here once
# conditional-nogil is available.
nobs[lab, j] += 1
Expand All @@ -939,7 +937,7 @@ def group_last(rank_t[:, :] out,
for i in range(ncounts):
for j in range(K):
if nobs[i, j] < min_count:
out[i, j] = NAN
out[i, j] = None
else:
out[i, j] = resx[i, j]
else:
Expand Down Expand Up @@ -1023,9 +1021,7 @@ def group_nth(rank_t[:, :] out,
for j in range(K):
val = values[i, j]

# None should not be treated like other NA-like
# so that it won't be converted to nan
if not checknull(val) or val is None:
if not checknull(val):
# NB: use _treat_as_na here once
# conditional-nogil is available.
nobs[lab, j] += 1
Expand All @@ -1035,7 +1031,7 @@ def group_nth(rank_t[:, :] out,
for i in range(ncounts):
for j in range(K):
if nobs[i, j] < min_count:
out[i, j] = NAN
out[i, j] = None
else:
out[i, j] = resx[i, j]

Expand Down
29 changes: 21 additions & 8 deletions pandas/tests/groupby/test_nth.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,14 +91,27 @@ def test_nth_with_na_object(index, nulls_fixture):


@pytest.mark.parametrize("method", ["first", "last"])
def test_first_last_with_None(method):
# https://github.com/pandas-dev/pandas/issues/32800
# None should be preserved as object dtype
df = DataFrame.from_dict({"id": ["a"], "value": [None]})
groups = df.groupby("id", as_index=False)
result = getattr(groups, method)()

tm.assert_frame_equal(result, df)
@pytest.mark.parametrize(
"df, expected",
[
(
DataFrame({"id": ["a"], "value": [None]}),
DataFrame({"value": [None]}, index=Index(["a"], name="id")),
),
(
DataFrame({"id": "a", "value": [None, "foo", np.nan]}),
DataFrame({"value": ["foo"]}, index=Index(["a"], name="id")),
),
(
DataFrame({"id": "a", "value": [np.nan]}, dtype=object),
DataFrame({"value": [None]}, index=Index(["a"], name="id")),
),
],
)
def test_first_last_with_none(method, df, expected):
# GH 32800, 38286
result = getattr(df.groupby("id"), method)()
tm.assert_frame_equal(result, expected)


def test_first_last_nth_dtypes(df_mixed_floats):
Expand Down