Skip to content

Support file objects in Polars JSON and NDJSON readers and writers #1763

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
digit50 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Support file objects in Polars JSON and NDJSON readers and writers #1763

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
18 changes: 12 additions & 6 deletions hamilton/plugins/polars_post_1_0_0_extensions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -523,8 +523,9 @@ def _get_loading_kwargs(self):

def load_data(self, type_: type) -> tuple[DATAFRAME_TYPE, dict[str, Any]]:
df = pl.read_json(self.source, **self._get_loading_kwargs())
metadata = utils.get_file_metadata(self.source)
return df, metadata
if isinstance(self.source, (str, Path)):
return df, utils.get_file_metadata(self.source)
return df, utils.get_dataframe_metadata(df)

@classmethod
def name(cls) -> str:
Expand All @@ -549,7 +550,9 @@ def save_data(self, data: DATAFRAME_TYPE | pl.LazyFrame) -> dict[str, Any]:
data = data.collect()

data.write_json(self.file)
return utils.get_file_and_dataframe_metadata(self.file, data)
if isinstance(self.file, (str, Path)):
return utils.get_file_and_dataframe_metadata(self.file, data)
return utils.get_dataframe_metadata(data)

@classmethod
def name(cls) -> str:
Expand Down Expand Up @@ -581,8 +584,9 @@ def _get_loading_kwargs(self):

def load_data(self, type_: type) -> tuple[DATAFRAME_TYPE, dict[str, Any]]:
df = pl.read_ndjson(self.source, **self._get_loading_kwargs())
metadata = utils.get_file_metadata(self.source)
return df, metadata
if isinstance(self.source, (str, Path)):
return df, utils.get_file_metadata(self.source)
return df, utils.get_dataframe_metadata(df)

@classmethod
def name(cls) -> str:
Expand All @@ -607,7 +611,9 @@ def save_data(self, data: DATAFRAME_TYPE | pl.LazyFrame) -> dict[str, Any]:
data = data.collect()

data.write_ndjson(self.file)
return utils.get_file_and_dataframe_metadata(self.file, data)
if isinstance(self.file, (str, Path)):
return utils.get_file_and_dataframe_metadata(self.file, data)
return utils.get_dataframe_metadata(data)

@classmethod
def name(cls) -> str:
Expand Down
18 changes: 18 additions & 0 deletions tests/plugins/test_polars_extensions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -147,6 +147,24 @@ def test_polars_ndjson(df: pl.DataFrame, tmp_path: pathlib.Path) -> None:
polars.testing.assert_frame_equal(df, df2)


@pytest.mark.parametrize(
("writer_cls", "reader_cls"),
[(PolarsJSONWriter, PolarsJSONReader), (PolarsNDJSONWriter, PolarsNDJSONReader)],
)
def test_polars_json_file_objects(df: pl.DataFrame, writer_cls, reader_cls) -> None:
buffer = io.BytesIO()
write_metadata = writer_cls(file=buffer).save_data(df)

df2, read_metadata = reader_cls(source=io.BytesIO(buffer.getvalue())).load_data(pl.DataFrame)
_, bytes_metadata = reader_cls(source=buffer.getvalue()).load_data(pl.DataFrame)

polars.testing.assert_frame_equal(df, df2)
for metadata in (write_metadata, read_metadata, bytes_metadata):
assert "file_metadata" not in metadata
assert metadata["dataframe_metadata"]["rows"] == 2
assert metadata["dataframe_metadata"]["column_names"] == ["a", "b"]


def test_polars_avro(df: pl.DataFrame, tmp_path: pathlib.Path) -> None:
file = tmp_path / "test.avro"

Expand Down