scripts/inspect_far_dataset.py

from __future__ import annotations
import pandas as pd
from huggingface_hub import hf_hub_download
from config import FAR_DATASET_FILE, FAR_DATASET_REPO, HF_TOKEN

path = hf_hub_download(
    repo_id=FAR_DATASET_REPO,
    filename=FAR_DATASET_FILE,
    repo_type="dataset",
    token=HF_TOKEN,
)
frame = pd.read_csv(path)
print(frame.info())
print(frame.head(5).to_string())