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

[REVIEW] Fix some warnings in test_parquet.py #10416

Merged
merged 5 commits into from
Mar 11, 2022
Merged

[REVIEW] Fix some warnings in test_parquet.py #10416

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
cfc49b1
fix some warnings
galipremsagar Mar 11, 2022
61dcac6
Add space to warning message.
bdice Mar 11, 2022
9c863ad
Apply suggestions from code review
galipremsagar Mar 11, 2022
12594da
address review
galipremsagar Mar 11, 2022
2019bad
Merge branch 'test_parquet' of https://github.com/galipremsagar/cudf …
galipremsagar Mar 11, 2022
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
2 changes: 1 addition & 1 deletion python/cudf/cudf/io/parquet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -415,7 +415,7 @@ def read_parquet(
# (There is a good chance this was not the intention)
if engine != "cudf":
warnings.warn(
"Using CPU via PyArrow to read Parquet dataset."
"Using CPU via PyArrow to read Parquet dataset. "
"This option is both inefficient and unstable!"
)
if filters is not None:
Expand Down
31 changes: 25 additions & 6 deletions python/cudf/cudf/tests/test_parquet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -891,7 +891,7 @@ def test_parquet_reader_list_table(tmpdir):
expect.to_parquet(fname)
assert os.path.exists(fname)
got = cudf.read_parquet(fname)
assert_eq(expect, got, check_dtype=False)
assert pa.Table.from_pandas(expect).equals(got.to_arrow())


def int_gen(first_val, i):
Expand Down Expand Up @@ -1051,7 +1051,7 @@ def test_parquet_reader_list_large_mixed(tmpdir):
expect.to_parquet(fname)
assert os.path.exists(fname)
got = cudf.read_parquet(fname)
assert_eq(expect, got, check_dtype=False)
assert pa.Table.from_pandas(expect).equals(got.to_arrow())


def test_parquet_reader_list_large_multi_rowgroup(tmpdir):
Expand Down Expand Up @@ -1121,7 +1121,10 @@ def test_parquet_reader_list_skiprows(skip, tmpdir):

expect = src.iloc[skip:]
got = cudf.read_parquet(fname, skiprows=skip)
assert_eq(expect, got, check_dtype=False)
if expect.empty:
assert_eq(expect, got)
else:
assert pa.Table.from_pandas(expect).equals(got.to_arrow())


@pytest.mark.parametrize("skip", [0, 1, 5, 10])
Expand All @@ -1145,7 +1148,7 @@ def test_parquet_reader_list_num_rows(skip, tmpdir):
rows_to_read = min(3, (num_rows - skip) - 5)
expect = src.iloc[skip:].head(rows_to_read)
got = cudf.read_parquet(fname, skiprows=skip, num_rows=rows_to_read)
assert_eq(expect, got, check_dtype=False)
assert pa.Table.from_pandas(expect).equals(got.to_arrow())


def struct_gen(gen, skip_rows, num_rows, include_validity=False):
Expand Down Expand Up @@ -2005,7 +2008,15 @@ def test_parquet_nullable_boolean(tmpdir, engine):
expected_gdf = cudf.DataFrame({"a": [True, False, None, True, False]})

pdf.to_parquet(pandas_path)
actual_gdf = cudf.read_parquet(pandas_path, engine=engine)
if engine == "pyarrow":
with pytest.warns(
UserWarning,
match="Using CPU via PyArrow to read Parquet dataset. This option "
"is both inefficient and unstable!",
):
actual_gdf = cudf.read_parquet(pandas_path, engine=engine)
else:
actual_gdf = cudf.read_parquet(pandas_path, engine=engine)
galipremsagar marked this conversation as resolved.
Show resolved Hide resolved

assert_eq(actual_gdf, expected_gdf)

Expand Down Expand Up @@ -2079,7 +2090,15 @@ def test_parquet_allnull_str(tmpdir, engine):
)

pdf.to_parquet(pandas_path)
actual_gdf = cudf.read_parquet(pandas_path, engine=engine)
if engine == "pyarrow":
with pytest.warns(
UserWarning,
match="Using CPU via PyArrow to read Parquet dataset. This option "
"is both inefficient and unstable!",
):
actual_gdf = cudf.read_parquet(pandas_path, engine=engine)
else:
actual_gdf = cudf.read_parquet(pandas_path, engine=engine)
galipremsagar marked this conversation as resolved.
Show resolved Hide resolved

assert_eq(actual_gdf, expected_gdf)

Expand Down