Skip to content

Fix local dataframe extension detection #779

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

Open
fallintoplace wants to merge 1 commit into
base: main
Choose a base branch
from
+21 −3
Open

Fix local dataframe extension detection #779

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 packages/data-designer-config/src/data_designer/config/utils/io_helpers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -196,7 +196,7 @@ def smart_load_dataframe(dataframe: str | Path | pd.DataFrame) -> pd.DataFrame:
ext = PurePosixPath(urlparse(dataframe).path).suffix.lstrip(".").lower()
else:
dataframe = Path(dataframe)
ext = dataframe.suffix.lower()
ext = dataframe.suffix.lstrip(".").lower()
if not dataframe.exists():
raise FileNotFoundError(f"File not found: {dataframe}")

Expand Down
22 changes: 20 additions & 2 deletions packages/data-designer-config/tests/config/utils/test_io_helpers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@ def test_smart_load_dataframe(mock_read_parquet, mock_read_json, mock_read_csv,

mock_path = MagicMock(autospec=Path)
mock_path.exists.return_value = True
mock_path.suffix.lower.return_value = "csv"
mock_path.suffix = ".csv"
mock_path_cls.return_value = mock_path

stub_base_path_str = "/some/path/to/data.{extension}"
Expand All @@ -73,13 +73,31 @@ def test_smart_load_dataframe(mock_read_parquet, mock_read_json, mock_read_csv,
mock_read_csv.assert_called_once_with(mock_path)

mock_path.reset_mock()
mock_path.suffix.lower.return_value = "json"
mock_path.suffix = ".json"
mock_path.exists.return_value = False
path_json = stub_base_path_str.format(extension="json")
with pytest.raises(FileNotFoundError):
_ = smart_load_dataframe(Path(path_json))


@pytest.mark.parametrize("extension", ["csv", "json", "parquet"])
@pytest.mark.parametrize("path_type", [Path, str], ids=["path", "string"])
def test_smart_load_dataframe_from_real_local_files(tmp_path: Path, extension: str, path_type) -> None:
expected = lazy.pd.DataFrame({"id": [1, 2], "value": ["alpha", "beta"]})
file_path = tmp_path / f"data.{extension}"

if extension == "csv":
expected.to_csv(file_path, index=False)
elif extension == "json":
expected.to_json(file_path, orient="records", lines=True)
else:
expected.to_parquet(file_path, index=False)

loaded = smart_load_dataframe(path_type(file_path))

lazy.pd.testing.assert_frame_equal(loaded, expected)


def test_smart_load_yaml():
stub_dict = {
"hello": "world",
Expand Down
Loading