prepare.py

import pickle
import datasets
import os
import umap


if __name__ == "__main__":
    cache_file = "dataset_cache.pkl"
    if os.path.exists(cache_file):
        # Load dataset from cache
        with open(cache_file, "rb") as file:
            dataset = pickle.load(file)
        print("Dataset loaded from cache.")
    else:
        # Load dataset using datasets.load_dataset()
        ds = datasets.load_dataset("renumics/speech_commands_enriched", split="test")
        print("Dataset loaded using datasets.load_dataset().")

        df = ds.to_pandas()

        # Save dataset to cache
        with open(cache_file, "wb") as file:
            pickle.dump(df, file)

        print("Dataset saved to cache.")