Skip to content

BUG: Segfault with string Index when using Rolling after Groupby #36753

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 5 commits into from
Oct 6, 2020
Merged

BUG: Segfault with string Index when using Rolling after Groupby #36753

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
bca4433
Fix bugs in rolling sefault
phofl Sep 30, 2020
da13ded
Change test to test for all issues
phofl Sep 30, 2020
72e5e1c
Merge branch 'master' of https://github.com/pandas-dev/pandas
phofl Sep 30, 2020
440368c
Run black pandas
phofl Sep 30, 2020
cc30cbe
Delete sort_index
phofl Oct 1, 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/window/rolling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -397,7 +397,7 @@ def _insert_on_column(self, result: "DataFrame", obj: "DataFrame"):

if self.on is not None and not self._on.equals(obj.index):
name = self._on.name
extra_col = Series(self._on, index=obj.index, name=name)
extra_col = Series(self._on, index=self.obj.index, name=name).sort_index()
if name in result.columns:
# TODO: sure we want to overwrite results?
result[name] = extra_col
Expand Down Expand Up @@ -2268,7 +2268,7 @@ def _get_window_indexer(self, window: int) -> GroupbyRollingIndexer:
"""
rolling_indexer: Type[BaseIndexer]
indexer_kwargs: Optional[Dict] = None
index_array = self.obj.index.asi8
index_array = self._on.asi8
if isinstance(self.window, BaseIndexer):
rolling_indexer = type(self.window)
indexer_kwargs = self.window.__dict__
Expand Down
29 changes: 29 additions & 0 deletions pandas/tests/window/test_grouper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -416,3 +416,32 @@ def test_groupby_rolling_empty_frame(self):
result = expected.groupby(["s1", "s2"]).rolling(window=1).sum()
expected.index = pd.MultiIndex.from_tuples([], names=["s1", "s2", None])
tm.assert_frame_equal(result, expected)

def test_groupby_rolling_string_index(self):
# GH: 36727
df = pd.DataFrame(
[
["A", "group_1", pd.Timestamp(2019, 1, 1, 9)],
["B", "group_1", pd.Timestamp(2019, 1, 2, 9)],
["Z", "group_2", pd.Timestamp(2019, 1, 3, 9)],
["H", "group_1", pd.Timestamp(2019, 1, 6, 9)],
["E", "group_2", pd.Timestamp(2019, 1, 20, 9)],
],
columns=["index", "group", "eventTime"],
).set_index("index")

groups = df.groupby("group")
df["count_to_date"] = groups.cumcount()
rolling_groups = groups.rolling("10d", on="eventTime")
result = rolling_groups.apply(lambda df: df.shape[0])
expected = pd.DataFrame(
[
["A", "group_1", pd.Timestamp(2019, 1, 1, 9), 1.0],
["B", "group_1", pd.Timestamp(2019, 1, 2, 9), 2.0],
["H", "group_1", pd.Timestamp(2019, 1, 6, 9), 3.0],
["Z", "group_2", pd.Timestamp(2019, 1, 3, 9), 1.0],
["E", "group_2", pd.Timestamp(2019, 1, 20, 9), 1.0],
],
columns=["index", "group", "eventTime", "count_to_date"],
).set_index(["group", "index"])
tm.assert_frame_equal(result, expected)