run.py

import pickle
import datasets
from renumics import spotlight
import os
import pandas as pd

if __name__ == "__main__":
    cache_file = "dataset_cache.parquet"
    cache_file_enrichment="emodb_full_results.parquet"
    cache_file_issues="emodb_metadata_issues.pkl"
    
    if os.path.exists(cache_file):
        # Load dataset from cache
        df_db = pd.read_parquet(cache_file) 
        print("Dataset loaded from cache.")
    else:
        # Load dataset using datasets.load_dataset()
        dataset = datasets.load_dataset("renumics/emodb", split="all")
        print("Dataset loaded using datasets.load_dataset().")
        
        df_db = dataset.to_pandas()  

        # Save dataset to cache
        df_db.to_parquet(cache_file)

        print("Dataset saved to cache.")
    
    df=pd.read_parquet(cache_file_enrichment) 
    
    df['audio'] = df_db['audio']
     
    with open(cache_file_issues, "rb") as issue_file:
        issues = pickle.load(issue_file)


    while True:
        dtypes = dtype={"audio": spotlight.Audio, 
                'm1_embedding':spotlight.Embedding, 
                'm2_embedding':spotlight.Embedding, 
                'embedding_emotion':spotlight.Embedding}
        view = spotlight.show(df, issues=issues, port=7860, host="0.0.0.0", layout="layout-model-comparison.json",
                    dtype=dtypes, allow_filebrowsing=False)
        view.close()