prepare.py

import pickle
import datasets
import os
import pandas as pd

if __name__ == "__main__":
    cache_file = "dataset_cache.parquet"
    if os.path.exists(cache_file):
        # Load dataset from cache
        df = pd.read_parquet(cache_file)
        print("Dataset loaded from cache.")
    else:
        # Load dataset using datasets.load_dataset()
        dataset = datasets.load_dataset("renumics/cifar100-enriched", split="train")
        print("Dataset loaded using datasets.load_dataset().")
        
        df = dataset.to_pandas()  

        # Save dataset to cache
        df.to_parquet(cache_file)

        print("Dataset saved to cache.")