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

Jump to bottom

Restore saved format state in load_from_disk #5073

Merged
merged 3 commits into from Oct 11, 2022
Merged

Restore saved format state in load_from_disk #5073

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5611581
Set saved format in load_from_disk dataset
asofiaoliveira Oct 5, 2022
46ddb30
Add test
asofiaoliveira Oct 8, 2022
43c1836
Use with_format
mariosasko Oct 10, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
12 changes: 11 additions & 1 deletion src/datasets/arrow_dataset.py
View file
Open in desktop
Expand Up @@ -1346,13 +1346,23 @@ def load_from_disk(dataset_path: str, fs=None, keep_in_memory: Optional[bool] =
split = state["_split"]
split = Split(split) if split is not None else split

return Dataset(
dataset = Dataset(
arrow_table=arrow_table,
info=dataset_info,
split=split,
fingerprint=state["_fingerprint"],
)

format = {
"type": state["_format_type"],
"format_kwargs": state["_format_kwargs"],
"columns": state["_format_columns"],
"output_all_columns": state["_output_all_columns"],
}
dataset = dataset.with_format(**format)

return dataset

@property
def data(self) -> Table:
"""The Apache Arrow table backing the dataset.
Expand Down
11 changes: 11 additions & 0 deletions tests/test_arrow_dataset.py
View file
Open in desktop
Expand Up @@ -318,6 +318,17 @@ def test_dummy_dataset_load_from_disk(self, in_memory):
self.assertEqual(dset[0]["filename"], "my_name-train_0")
self.assertEqual(dset["filename"][0], "my_name-train_0")

def test_restore_saved_format(self, in_memory):
with tempfile.TemporaryDirectory() as tmp_dir:

with self._create_dummy_dataset(in_memory, tmp_dir, multiple_columns=True) as dset:
dset.set_format(type="numpy", columns=["col_1"], output_all_columns=True)
dataset_path = os.path.join(tmp_dir, "my_dataset")
dset.save_to_disk(dataset_path)

with load_from_disk(dataset_path) as loaded_dset:
self.assertEqual(dset.format, loaded_dset.format)

def test_set_format_numpy_multiple_columns(self, in_memory):
with tempfile.TemporaryDirectory() as tmp_dir:
with self._create_dummy_dataset(in_memory, tmp_dir, multiple_columns=True) as dset:
Expand Down