scripts/explore_dataset.py

from datasets import load_dataset

def explore_dataset():
    # Load the dataset
    dataset = load_dataset("arbml/Tunisian_Dialect_Corpus", split="train")
    
    # Print dataset info
    print("\nDataset Info:")
    print(dataset.info)
    
    # Print first example
    print("\nFirst Example:")
    print(dataset[0])
    
    # Print all column names
    print("\nColumn Names:")
    print(dataset.column_names)
    
    # Print first few rows
    print("\nFirst few rows:")
    print(dataset[:3])

if __name__ == "__main__":
    explore_dataset()