import os
#import pandas as pd
#import pyarrow
#import fastparquet
from datasets import load_dataset_builder
from datasets import load_dataset
access_token = os.environ.get('HFTOKEN') 
data_files = {'train': ['train.zip', 'train.csv'], 'test': 'test.zip'}
dataset = load_dataset('competitions/aiornot',
                       token=access_token,
                       data_files=data_files)
def read_par(file):
    parquet_file = "data.parquet"
    df = pd.read_parquet(parquet_file, engine='pyarrow')