Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
4 changes: 4 additions & 0 deletions changelog_entry.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
- bump: patch
changes:
fixed:
- Upload datasets to public HuggingFace repo (policyengine/policyengine-uk-data) in addition to private repo, so policyengine-uk gets the latest data.
16 changes: 15 additions & 1 deletion policyengine_uk_data/storage/upload_completed_datasets.py
Original file line number Diff line number Diff line change
@@ -1,5 +1,10 @@
from importlib import metadata

from policyengine_uk_data.storage import STORAGE_FOLDER
from policyengine_uk_data.utils.data_upload import upload_data_files
from policyengine_uk_data.utils.data_upload import (
upload_data_files,
upload_files_to_hf,
)


def upload_datasets():
Expand All @@ -14,13 +19,22 @@ def upload_datasets():
if not file_path.exists():
raise ValueError(f"File {file_path} does not exist.")

version = metadata.version("policyengine-uk-data")

upload_data_files(
files=dataset_files,
hf_repo_name="policyengine/policyengine-uk-data-private",
hf_repo_type="model",
gcs_bucket_name="policyengine-uk-data-private",
)

# Also upload to the public repo consumed by policyengine-uk
upload_files_to_hf(
files=dataset_files,
version=version,
hf_repo_name="policyengine/policyengine-uk-data",
)


if __name__ == "__main__":
upload_datasets()