src/huggingface/get_files.py

from pathlib import Path
from huggingface_hub import hf_hub_download  # type: ignore[import]
import yaml  # type: ignore[import]
from src.constants import MODEL_REPO, MODEL_REPO_TYPE

def get_mp4_paths(environments: list[str]) -> dict[str, Path]:
    mp4_paths: dict[str, Path] = {}
    for env in environments:
        mp4_paths[env] = get_best(env, filename="demo.mp4")
    return mp4_paths


def get_best(env: str, filename: str = "demo.mp4") -> Path:
    hf_env_results_path = f"models/{env}/results.yaml"
    local_env_results_path = hf_hub_download(repo_id=MODEL_REPO, repo_type=MODEL_REPO_TYPE, filename=hf_env_results_path)
    with open(local_env_results_path, "r") as f:
        env_results = yaml.load(f, Loader=yaml.FullLoader)
    best_model_type = max(env_results, key=lambda model: env_results[model])
    model_results_path = f"models/{env}/{best_model_type}/results.yaml"
    local_model_results_path = hf_hub_download(repo_id=MODEL_REPO, repo_type=MODEL_REPO_TYPE, filename=model_results_path)
    with open(local_model_results_path, "r") as f:
        model_results = yaml.load(f, Loader=yaml.FullLoader)

    best_model = max(model_results, key=lambda model: model_results[model])
    hf_gif_path = f"models/{env}/{best_model_type}/{best_model}/{filename}"
    return Path(hf_hub_download(repo_id=MODEL_REPO, repo_type=MODEL_REPO_TYPE, filename=hf_gif_path))