visualize_squad.py

datasets = load_dataset("squad")
def visualize(datasets, datatype = 'train', n_questions=10):
    n = len(datasets[datatype])
    random_questions=random.choices(list(range(n)),k=n_questions)
    for i in random_questions:
        print(f"Context:{datasets[datatype][i]['context']}")
        print(f"Question:{datasets[datatype][i]['question']}")
        print(f"Answer:{datasets[datatype][i]['answers']['text']}")
        print(f"Answer Start in Text:{datasets[datatype][i]['answers']['answer_start']}")
        print("-"*100)
visualize(datasets)