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

Added cache dirs to load and file_utils #7499

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+7 −0
Open

Added cache dirs to load and file_utils #7499

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
6 changes: 6 additions & 0 deletions src/datasets/load.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -941,6 +941,7 @@ def __init__(
download_config: Optional[DownloadConfig] = None,
download_mode: Optional[Union[DownloadMode, str]] = None,
use_exported_dataset_infos: bool = False,
cache_dir: Optional[str] = None,
):
self.name = name
self.commit_hash = commit_hash
Expand All @@ -949,6 +950,7 @@ def __init__(
self.download_config = download_config or DownloadConfig()
self.download_mode = download_mode
self.use_exported_dataset_infos = use_exported_dataset_infos
self.cache_dir = cache_dir
increase_load_count(name)

def get_module(self) -> DatasetModule:
Expand All @@ -967,6 +969,7 @@ def get_module(self) -> DatasetModule:
repo_type="dataset",
revision=self.commit_hash,
proxies=self.download_config.proxies,
cache_dir=self.cache_dir
)
dataset_card_data = DatasetCard.load(dataset_readme_path).data
except EntryNotFoundError:
Expand Down Expand Up @@ -1537,6 +1540,7 @@ def dataset_module_factory(
repo_type="dataset",
revision=revision,
proxies=download_config.proxies,
cache_dir=cache_dir
)
commit_hash = os.path.basename(os.path.dirname(dataset_readme_path))
except LocalEntryNotFoundError as e:
Expand Down Expand Up @@ -1583,6 +1587,7 @@ def dataset_module_factory(
repo_type="dataset",
revision=commit_hash,
proxies=download_config.proxies,
cache_dir=cache_dir
)
if _require_custom_configs or (revision and revision != "main"):
can_load_config_from_parquet_export = False
Expand Down Expand Up @@ -1626,6 +1631,7 @@ def dataset_module_factory(
download_config=download_config,
download_mode=download_mode,
use_exported_dataset_infos=use_exported_dataset_infos,
cache_dir=cache_dir
).get_module()
except GatedRepoError as e:
message = f"Dataset '{path}' is a gated dataset on the Hub."
Expand Down
1 change: 1 addition & 0 deletions src/datasets/utils/file_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -193,6 +193,7 @@ def cached_path(
filename=resolved_path.path_in_repo,
force_download=download_config.force_download,
proxies=download_config.proxies,
cache_dir=cache_dir
)
except (
huggingface_hub.utils.RepositoryNotFoundError,
Expand Down