Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
1 change: 0 additions & 1 deletion dask_sql/_compat.py
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@

INDEXER_WINDOW_STEP_IMPLEMENTED = _pandas_version >= parseVersion("1.5.0")
PANDAS_GT_200 = _pandas_version >= parseVersion("2.0.0")
PANDAS_GT_210 = _pandas_version >= parseVersion("2.1.0")

# TODO: remove if prompt-toolkit min version gets bumped
PIPE_INPUT_CONTEXT_MANAGER = _prompt_toolkit_version >= parseVersion("3.0.29")
Expand Down
2 changes: 1 addition & 1 deletion dask_sql/physical/utils/sort.py
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ def apply_sort(
by=sort_columns,
ascending=sort_ascending[0],
na_position="first" if sort_null_first[0] else "last",
ignore_index=True,
# ignore_index=True,
).persist()
except ValueError:
pass
Expand Down
5 changes: 1 addition & 4 deletions tests/integration/test_compatibility.py
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,6 @@
import pytest

from dask_sql import Context
from dask_sql._compat import PANDAS_GT_210
from dask_sql.utils import ParsingException
from tests.utils import assert_eq

Expand All @@ -29,10 +28,8 @@ def cast_datetime_to_string(df):
if not cols:
return df

strf = "%Y-%m-%dT%H:%M:%S" if PANDAS_GT_210 else "%Y-%m-%d %H:%M:%S"

for col in cols:
df[col] = df[col].dt.strftime(strf)
df[col] = df[col].dt.strftime("%Y-%m-%d %H:%M:%S")

return df

Expand Down
2 changes: 1 addition & 1 deletion tests/integration/test_groupby.py
Original file line number Diff line number Diff line change
Expand Up @@ -488,7 +488,7 @@ def test_covar_aggregation(c, timeseries_df):
pytest.param("gpu_user_table_1", marks=pytest.mark.gpu),
],
)
@pytest.mark.parametrize("split_out", [None, 2, 4])
@pytest.mark.parametrize("split_out", [1, 2, 4])
def test_groupby_split_out(c, input_table, split_out, request):
user_table = request.getfixturevalue(input_table)

Expand Down
8 changes: 6 additions & 2 deletions tests/integration/test_model.py
Original file line number Diff line number Diff line change
Expand Up @@ -88,11 +88,13 @@ def test_training_and_prediction(c, gpu_client):
check_trained_model(c, df_name=timeseries)


@pytest.mark.flaky(reruns=8, condition="sys.platform == 'darwin'")
@pytest.mark.xfail(
sys.platform == "win32",
reason="'xgboost.core.XGBoostError: Failed to poll' on Windows only",
)
@pytest.mark.xfail(
sys.platform == "darwin", reason="Intermittent socket errors on macOS", strict=False
)
@pytest.mark.parametrize(
"gpu_client", [False, pytest.param(True, marks=pytest.mark.gpu)], indirect=True
)
Expand Down Expand Up @@ -627,7 +629,9 @@ def test_mlflow_export(c, tmpdir):
)


@pytest.mark.flaky(reruns=8, condition="sys.platform == 'darwin'")
@pytest.mark.xfail(
sys.platform == "darwin", reason="Intermittent socket errors on macOS", strict=False
)
def test_mlflow_export_xgboost(c, client, tmpdir):
# Test only when mlflow & xgboost was installed
mlflow = pytest.importorskip("mlflow", reason="mlflow not installed")
Expand Down