data-use-annotation / upload_to_hf.py
rafmacalaba's picture
feat: implement HF Datasets remote fetching and save
5b87eae
import os
from huggingface_hub import HfApi, create_repo
token = os.environ.get("HF_TOKEN")
if not token:
raise ValueError("HF_TOKEN not found in environment.")
api = HfApi(token=token)
repo_id = "rafmacalaba/wbg_annotation_data"
print(f"Creating dataset repository: {repo_id}")
try:
create_repo(repo_id=repo_id, repo_type="dataset", exist_ok=True, token=token)
print("Repository created or already exists.")
except Exception as e:
print(f"Error creating repo: {e}")
folder_path = "annotation_data"
print(f"Uploading {folder_path} to {repo_id}...")
api.upload_folder(
folder_path=folder_path,
repo_id=repo_id,
repo_type="dataset",
path_in_repo="annotation_data"
)
print("Upload complete! Data is now available at https://huggingface.co/datasets/" + repo_id)