Skip to content

Fix metadata export when config rows are non-consecutive #8270

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
KirtiRamchandani wants to merge 1 commit into
base: main
Choose a base branch
from
+38 −2
Open

Fix metadata export when config rows are non-consecutive #8270

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
12 changes: 10 additions & 2 deletions src/datasets/utils/metadata.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,6 +106,10 @@ def _from_exported_parquet_files_and_dataset_infos(
exported_parquet_files: list[dict[str, Any]],
dataset_infos: DatasetInfosDict,
) -> "MetadataConfigs":
# groupby only merges consecutive keys; exported rows are not guaranteed sorted.
sorted_exported_parquet_files = sorted(
exported_parquet_files, key=lambda row: (row["config"], row["split"])
)
metadata_configs = {
config_name: {
"data_files": [
Expand All @@ -116,11 +120,15 @@ def _from_exported_parquet_files_and_dataset_infos(
for parquet_file in parquet_files_for_split
],
}
for split_name, parquet_files_for_split in groupby(parquet_files_for_config, itemgetter("split"))
for split_name, parquet_files_for_split in groupby(
parquet_files_for_config, itemgetter("split")
)
],
"version": str(dataset_infos.get(config_name, DatasetInfo()).version or "0.0.0"),
}
for config_name, parquet_files_for_config in groupby(exported_parquet_files, itemgetter("config"))
for config_name, parquet_files_for_config in groupby(
sorted_exported_parquet_files, itemgetter("config")
)
}
if dataset_infos:
# Preserve order of configs and splits
Expand Down
28 changes: 28 additions & 0 deletions tests/test_metadata_util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,6 +276,34 @@ def test_metadata_configs_incorrect_yaml():
_ = MetadataConfigs.from_dataset_card_data(dataset_card_data)


def test_non_consecutive_config_rows_are_merged_in_metadata_configs_from_exported_parquet_files():
exported_parquet_files = [
{
"config": "default",
"split": "train",
"url": "https://huggingface.co/datasets/org/name/resolve/refs%2Fconvert%2Fparquet/default/train/0000.parquet",
},
{
"config": "other",
"split": "train",
"url": "https://huggingface.co/datasets/org/name/resolve/refs%2Fconvert%2Fparquet/other/train/0000.parquet",
},
{
"config": "default",
"split": "train",
"url": "https://huggingface.co/datasets/org/name/resolve/refs%2Fconvert%2Fparquet/default/train/0001.parquet",
},
]
metadata_configs = MetadataConfigs._from_exported_parquet_files_and_dataset_infos(
"abc123", exported_parquet_files, {}
)
default_paths = metadata_configs["default"]["data_files"][0]["path"]
assert default_paths == [
"https://huggingface.co/datasets/org/name/resolve/abc123/default/train/0000.parquet",
"https://huggingface.co/datasets/org/name/resolve/abc123/default/train/0001.parquet",
]


def test_split_order_in_metadata_configs_from_exported_parquet_files_and_dataset_infos():
exported_parquet_files = [
{
Expand Down