fix(nifti): enable lazy loading for Nifti1ImageWrapper

- Change dataobj initialization from get_fdata() to .dataobj
- Preserves nibabel's ArrayProxy for lazy loading
- Prevents OOM errors on large 4D fMRI files
- Defers I/O errors to usage time for better error handling

Resolves #1

Author: The-Obstacle-Is-The-Way

src/datasets/features/nifti.py

@@ -27,7 +27,7 @@ class Nifti1ImageWrapper(nib.nifti1.Nifti1Image):
 
         def __init__(self, nifti_image: nib.nifti1.Nifti1Image):
             super().__init__(
-                dataobj=nifti_image.get_fdata(),
+                dataobj=nifti_image.dataobj,
                 affine=nifti_image.affine,
                 header=nifti_image.header,
                 extra=nifti_image.extra,

tests/features/test_nifti.py

@@ -128,3 +128,22 @@ def test_load_zipped_file_locally(shared_datadir):
 
     ds = load_dataset("niftifolder", data_files=nifti_path)
     assert isinstance(ds["train"][0]["nifti"], nib.nifti1.Nifti1Image)
+
+
+@require_nibabel
+def test_nifti_lazy_loading(shared_datadir):
+    import nibabel as nib
+    import numpy as np
+
+    nifti_path = str(shared_datadir / "test_nifti.nii.gz")
+    nifti = Nifti()
+    encoded_example = nifti.encode_example(nifti_path)
+    decoded_example = nifti.decode_example(encoded_example)
+
+    # Verify that the data object is an ArrayProxy (lazy) and not a numpy array (dense)
+    assert nib.is_proxy(decoded_example.dataobj)
+    assert not isinstance(decoded_example.dataobj, np.ndarray)
+
+    # Verify that we can still access the data
+    data = decoded_example.get_fdata()
+    assert data.shape == (80, 80, 10)