Skip to content
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

Correct dtype of count aggregations on empty dataframes #14473

Merged
merged 2 commits into from
Nov 22, 2023
Merged

Correct dtype of count aggregations on empty dataframes #14473

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2ce8c87
Add test of #14200
wence- Nov 22, 2023
fb3a0ba
Correct dtype of count aggregations on empty dataframes
wence- Nov 22, 2023
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
6 changes: 3 additions & 3 deletions python/cudf/cudf/core/groupby/groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -592,7 +592,9 @@ def agg(self, func):
# Structs lose their labels which we reconstruct here
col = col._with_type_metadata(cudf.ListDtype(orig_dtype))

if (
if agg_kind in {"COUNT", "SIZE"}:
data[key] = col.astype("int64")
elif (
self.obj.empty
and (
isinstance(agg_name, str)
Expand All @@ -609,8 +611,6 @@ def agg(self, func):
)
):
data[key] = col.astype(orig_dtype)
elif agg_kind in {"COUNT", "SIZE"}:
data[key] = col.astype("int64")
else:
data[key] = col
data = ColumnAccessor(data, multiindex=multilevel)
Expand Down
18 changes: 18 additions & 0 deletions python/cudf/cudf/tests/groupby/test_agg.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
# Copyright (c) 2023, NVIDIA CORPORATION.
import numpy as np
import pytest

import cudf


@pytest.mark.parametrize(
"empty",
[True, False],
ids=["empty", "nonempty"],
)
def test_agg_count_dtype(empty):
df = cudf.DataFrame({"a": [1, 2, 1], "c": ["a", "b", "c"]})
if empty:
df = df.iloc[:0]
result = df.groupby("a").agg({"c": "count"})
assert result["c"].dtype == np.dtype("int64")