from datasets import load_dataset
from datasets import Features, ClassLabel
from datasets.features import Dicom

features = Features({
    "dicom": Dicom(force=True),  # necessary to be able to load one corrupted file
    "label": ClassLabel(num_classes=2)
})

ds = load_dataset("TobiasPitters/dicom-sample-dataset",
                  features=features)

error_count = 0

for idx, item in enumerate(ds["test"]):
    dicom = item["dicom"]

    try:
        print(f"Type: {type(dicom)}")
        if hasattr(dicom, 'PatientID'):
            print(f"PatientID: {dicom.PatientID}")
        if hasattr(dicom, 'StudyInstanceUID'):
            print(f"StudyInstanceUID: {dicom.StudyInstanceUID}")
        if hasattr(dicom, 'Modality'):
            print(f"Modality: {dicom.Modality}")
    except Exception as e:
        error_count += 1
        print(e)

print(f"Finished processing with {error_count} errors.")