prepare.py

import pickle
import datasets
import os
import pandas as pd
from cleanvision.imagelab import Imagelab

def cv_issues_cleanvision(df, image_name='image'):

    image_paths = df['image'].to_list()
    imagelab = Imagelab(filepaths=image_paths)
    imagelab.find_issues()

    df_cv=imagelab.issues.reset_index()

    return df_cv
    
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="test")
        print("Dataset loaded using datasets.load_dataset().")
        
        df = dataset.to_pandas()
        
        df=df.reset_index(drop=True)
        
        df_cv=cv_issues_cleanvision(df)
        df = pd.concat([df, df_cv], axis=1)    
       

        # Save dataset to cache
        #save df as parquet
        df.to_parquet(cache_file)

        print("Dataset saved to cache.")