Batch delete parquet files on root level on huggingface dataset (when accidentally pushed), leave anything else intact

delete.py

from huggingface_hub import HfApi, CommitOperationDelete, RepoFile

# Configure your repo details
repo_id = "user/repo"
token = "your token" # Ensure your token has 'write' permissions

api = HfApi(token=token)

# 1. List files in the repo (non-recursive)
files = api.list_repo_tree(repo_id, repo_type="dataset")

# 2. Filter for: 
#    - Is a RepoFile (not a folder)
#    - No "/" in the path (ensures it's root level)
#    - Ends with .parquet
to_delete = [
    CommitOperationDelete(path_in_repo=f.path) 
    for f in files 
    if isinstance(f, RepoFile) 
    and "/" not in f.path 
    and f.path.endswith(".parquet")
]

# 3. Execution logic
if to_delete:
    print(f"Found {len(to_delete)} parquet files to delete from root:")
    for op in to_delete:
        print(f" - {op.path_in_repo}")
    
    confirm = input("\nConfirm deletion? (y/n): ")
    if confirm.lower() == 'y':
        api.create_commit(
            repo_id=repo_id,
            operations=to_delete,
            commit_message="Cleanup: remove root-level parquet files",
            repo_type="dataset"
        )
        print("Deletion complete.")
    else:
        print("Aborted.")
else:
    print("No root-level .parquet files found.")