def _get_df()

in libs/libcommon/src/libcommon/simple_cache.py [0:0]

• 20 lines of code
• 8 McCabe index (conditional complexity)

def _get_df(entries: list[CacheEntryFullMetadata]) -> pd.DataFrame:
    return pd.DataFrame(
        {
            "kind": pd.Series([entry["kind"] for entry in entries], dtype="category"),
            "dataset": pd.Series([entry["dataset"] for entry in entries], dtype="str"),
            "config": pd.Series([entry["config"] for entry in entries], dtype="str"),
            "split": pd.Series([entry["split"] for entry in entries], dtype="str"),
            "http_status": pd.Series(
                [entry["http_status"] for entry in entries], dtype="category"
            ),  # check if it's working as expected
            "error_code": pd.Series([entry["error_code"] for entry in entries], dtype="category"),
            "dataset_git_revision": pd.Series([entry["dataset_git_revision"] for entry in entries], dtype="str"),
            "job_runner_version": pd.Series([entry["job_runner_version"] for entry in entries], dtype=pd.Int16Dtype()),
            "progress": pd.Series([entry["progress"] for entry in entries], dtype="float"),
            "updated_at": pd.Series(
                [entry["updated_at"] for entry in entries], dtype="datetime64[ns]"
            ),  # check if it's working as expected
            "failed_runs": pd.Series([entry["failed_runs"] for entry in entries], dtype=pd.Int16Dtype()),
        }
    )