import pickle
import datasets
from renumics import spotlight
import os

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()
        dataset = datasets.load_dataset("renumics/cifar100-enriched", split="train")
        print("Dataset loaded using datasets.load_dataset().")

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


    df = dataset.to_pandas()
    df_show = df.drop(columns=['embedding', 'probabilities'])
    spotlight.show(df_show.sample(5000, random_state=1), port=7860, host="0.0.0.0", 
                dtype={"image": spotlight.Image, "embedding_reduced": spotlight.Embedding}, allow_filebrowsing=False)