scripts/explore_tsac.py

from datasets import load_dataset

def explore_tsac():
    # Load the TSAC dataset
    dataset = load_dataset("fbougares/tsac", split="train", trust_remote_code=True)
    
    # 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_tsac()