#import pandas as pd
#import pyarrow
#import fastparquet
from datasets import load_dataset_builder
from datasets import load_dataset
#dataset = load_dataset("competitions/aiornot")
base_url = "https://huggingface.co/datasets/competitions/aiornot/blob/main/data/"
data_files = {"train": base_url + "test-00002-of-00004-5b72d3007707ce77.parquet"}
wiki = load_dataset("parquet", data_files=data_files, split="train")
def read_par(file):
    parquet_file = "data.parquet"
    df = pd.read_parquet(parquet_file, engine='pyarrow')