from pathlib import Path
import pandas as pd
import os

from .version import Version
from .base import BaseDataset
from .info import DatasetInfo
from . import constants as C


def get_dataset(split="train"):
    data_dir = Path(__file__).parent.parent.parent / "data"
    # here = os.path.dirname(__path__)
    # data_dir = here + '/../../data/'
    
    meta = pd.read_csv(data_dir / "non-empty-meta.csv")
    info = DatasetInfo.load(data_dir / "info.yaml")

    # meta['image_path'] = [f'data/image/{panoid}_{heading}.jpg' for panoid, heading in zip(meta['panoid'], meta['heading'])]

    ds = BaseDataset(info, meta)
    if split:
        return ds[split]
    else:
        return ds