juaml/junifer
Watch
3
0
Fork
You've already forked junifer
 0
Code Issues 14 Pull requests 2 Packages Activity Actions

Use hexsha to verify junifer-data integrity #434

Merged
fraimondo merged 3 commits from enh/junifer_data_hexsha into main 2025-03-06 11:17:12 +00:00
Conversation 1 Commits 3 Files changed 7 +39 -28
7 changed files with 39 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

1
docs/changes/newsfragments/434.enh Normal file
View file

@ -0,0 +1 @@
Add commit SHA check for ``junifer_data`` to simplify data fetching by `Fede Raimondo`_

4
junifer/data/coordinates/_coordinates.py
View file

@ -15,7 +15,7 @@ from numpy.typing import ArrayLike
from ...utils import logger, raise_error from ...utils import logger, raise_error
from ...utils.singleton import Singleton from ...utils.singleton import Singleton
from ..pipeline_data_registry_base import BasePipelineDataRegistry from ..pipeline_data_registry_base import BasePipelineDataRegistry
from ..utils import JUNIFER_DATA_VERSION, get_dataset_path, get_native_warper from ..utils import JUNIFER_DATA_PARAMS, get_dataset_path, get_native_warper
from ._ants_coordinates_warper import ANTsCoordinatesWarper from ._ants_coordinates_warper import ANTsCoordinatesWarper
from ._fsl_coordinates_warper import FSLCoordinatesWarper from ._fsl_coordinates_warper import FSLCoordinatesWarper
@ -287,7 +287,7 @@ class CoordinatesRegistry(BasePipelineDataRegistry, metaclass=Singleton):
get( get(
file_path=coords_file_path, file_path=coords_file_path,
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
), ),
sep="\t", sep="\t",
header=None, header=None,

6
junifer/data/masks/_masks.py
View file

@ -28,7 +28,7 @@ from ...utils.singleton import Singleton
from ..pipeline_data_registry_base import BasePipelineDataRegistry from ..pipeline_data_registry_base import BasePipelineDataRegistry
from ..template_spaces import get_template from ..template_spaces import get_template
from ..utils import ( from ..utils import (
JUNIFER_DATA_VERSION, JUNIFER_DATA_PARAMS,
closest_resolution, closest_resolution,
get_dataset_path, get_dataset_path,
get_native_warper, get_native_warper,
@ -745,7 +745,7 @@ def _load_vickery_patil_mask(
return get( return get(
file_path=Path(f"masks/Vickery-Patil/{mask_fname}"), file_path=Path(f"masks/Vickery-Patil/{mask_fname}"),
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
@ -778,7 +778,7 @@ def _load_ukb_mask(name: str) -> Path:
return get( return get(
file_path=Path(f"masks/UKB/{mask_fname}"), file_path=Path(f"masks/UKB/{mask_fname}"),
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )

40
junifer/data/parcellations/_parcellations.py
View file

@ -19,7 +19,7 @@ from ...utils import logger, raise_error, warn_with_log
from ...utils.singleton import Singleton from ...utils.singleton import Singleton
from ..pipeline_data_registry_base import BasePipelineDataRegistry from ..pipeline_data_registry_base import BasePipelineDataRegistry
from ..utils import ( from ..utils import (
JUNIFER_DATA_VERSION, JUNIFER_DATA_PARAMS,
closest_resolution, closest_resolution,
get_dataset_path, get_dataset_path,
get_native_warper, get_native_warper,
@ -639,13 +639,13 @@ def _retrieve_schaefer(
file_path=path_prefix / f"Schaefer2018_{n_rois}Parcels_{yeo_networks}" file_path=path_prefix / f"Schaefer2018_{n_rois}Parcels_{yeo_networks}"
f"Networks_order_FSLMNI152_{resolution}mm.nii.gz", f"Networks_order_FSLMNI152_{resolution}mm.nii.gz",
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
parcellation_label_path = get( parcellation_label_path = get(
file_path=path_prefix file_path=path_prefix
/ f"Schaefer2018_{n_rois}Parcels_{yeo_networks}Networks_order.txt", / f"Schaefer2018_{n_rois}Parcels_{yeo_networks}Networks_order.txt",
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
# Load labels # Load labels
@ -764,13 +764,13 @@ def _retrieve_tian(
parcellation_img_path = get( parcellation_img_path = get(
file_path=parcellation_fname, file_path=parcellation_fname,
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
parcellation_label_path = get( parcellation_label_path = get(
file_path=parcellation_fname_base_3T file_path=parcellation_fname_base_3T
/ f"Tian_Subcortex_S{scale}_3T_label.txt", / f"Tian_Subcortex_S{scale}_3T_label.txt",
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
# Load labels # Load labels
labels = pd.read_csv(parcellation_label_path, sep=" ", header=None)[ labels = pd.read_csv(parcellation_label_path, sep=" ", header=None)[
@ -783,7 +783,7 @@ def _retrieve_tian(
f"Tian_Subcortex_S{scale}_{magneticfield}.nii.gz" f"Tian_Subcortex_S{scale}_{magneticfield}.nii.gz"
), ),
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
# define 7T labels (b/c currently no labels file available for 7T) # define 7T labels (b/c currently no labels file available for 7T)
scale7Trois = {1: 16, 2: 34, 3: 54, 4: 62} scale7Trois = {1: 16, 2: 34, 3: 54, 4: 62}
@ -855,12 +855,12 @@ def _retrieve_suit(
parcellation_img_path = get( parcellation_img_path = get(
file_path=path_prefix / f"SUIT_{space}Space_{resolution}mm.nii", file_path=path_prefix / f"SUIT_{space}Space_{resolution}mm.nii",
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
parcellation_label_path = get( parcellation_label_path = get(
file_path=path_prefix / f"SUIT_{space}Space_{resolution}mm.tsv", file_path=path_prefix / f"SUIT_{space}Space_{resolution}mm.tsv",
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
# Load labels # Load labels
@ -938,20 +938,20 @@ def _retrieve_aicha(
parcellation_img_path = get( parcellation_img_path = get(
file_path=path_prefix / "AICHA.nii", file_path=path_prefix / "AICHA.nii",
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
# Conditional label file fetch # Conditional label file fetch
if version == 1: if version == 1:
parcellation_label_path = get( parcellation_label_path = get(
file_path=path_prefix / "AICHA_vol1.txt", file_path=path_prefix / "AICHA_vol1.txt",
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
elif version == 2: elif version == 2:
parcellation_label_path = get( parcellation_label_path = get(
file_path=path_prefix / "AICHA_vol3.txt", file_path=path_prefix / "AICHA_vol3.txt",
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
# Load labels # Load labels
@ -1055,12 +1055,12 @@ def _retrieve_shen(
parcellation_img_path = get( parcellation_img_path = get(
file_path=path_prefix / f"fconn_atlas_{n_rois}_{resolution}mm.nii", file_path=path_prefix / f"fconn_atlas_{n_rois}_{resolution}mm.nii",
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
parcellation_label_path = get( parcellation_label_path = get(
file_path=path_prefix / f"Group_seg{n_rois}_BAindexing_setA.txt", file_path=path_prefix / f"Group_seg{n_rois}_BAindexing_setA.txt",
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
labels = ( labels = (
pd.read_csv( pd.read_csv(
@ -1077,14 +1077,14 @@ def _retrieve_shen(
file_path=path_prefix file_path=path_prefix
/ f"shen_{resolution}mm_268_parcellation.nii.gz", / f"shen_{resolution}mm_268_parcellation.nii.gz",
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
labels = list(range(1, 269)) labels = list(range(1, 269))
elif year == 2019: elif year == 2019:
parcellation_img_path = get( parcellation_img_path = get(
file_path=path_prefix / "Shen_1mm_368_parcellation.nii.gz", file_path=path_prefix / "Shen_1mm_368_parcellation.nii.gz",
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
labels = list(range(1, 369)) labels = list(range(1, 369))
@ -1174,13 +1174,13 @@ def _retrieve_yan(
f"{resolution}mm.nii.gz" f"{resolution}mm.nii.gz"
), ),
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
parcellation_label_path = get( parcellation_label_path = get(
file_path=path_prefix file_path=path_prefix
/ f"{n_rois}Parcels_Yeo2011_{yeo_networks}Networks_LUT.txt", / f"{n_rois}Parcels_Yeo2011_{yeo_networks}Networks_LUT.txt",
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
elif kong_networks: elif kong_networks:
# Check kong_networks value # Check kong_networks value
@ -1199,13 +1199,13 @@ def _retrieve_yan(
f"{resolution}mm.nii.gz" f"{resolution}mm.nii.gz"
), ),
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
parcellation_label_path = get( parcellation_label_path = get(
file_path=path_prefix file_path=path_prefix
/ f"{n_rois}Parcels_Kong2022_{kong_networks}Networks_LUT.txt", / f"{n_rois}Parcels_Kong2022_{kong_networks}Networks_LUT.txt",
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
# Load label file # Load label file
@ -1272,7 +1272,7 @@ def _retrieve_brainnetome(
f"BNA-maxprob-thr{threshold}-{resolution}mm.nii.gz" f"BNA-maxprob-thr{threshold}-{resolution}mm.nii.gz"
), ),
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )
# Load labels # Load labels

4
junifer/data/template_spaces.py
View file

@ -12,7 +12,7 @@ from junifer_data import get
from templateflow import api as tflow from templateflow import api as tflow
from ..utils import logger, raise_error from ..utils import logger, raise_error
from .utils import JUNIFER_DATA_VERSION, closest_resolution, get_dataset_path from .utils import JUNIFER_DATA_PARAMS, closest_resolution, get_dataset_path
__all__ = ["get_template", "get_xfm"] __all__ = ["get_template", "get_xfm"]
@ -40,7 +40,7 @@ def get_xfm(src: str, dst: str) -> Path: # pragma: no cover
return get( return get(
file_path=xfm_file_path, file_path=xfm_file_path,
dataset_path=get_dataset_path(), dataset_path=get_dataset_path(),
tag=JUNIFER_DATA_VERSION, **JUNIFER_DATA_PARAMS,
) )

10
junifer/data/utils.py
View file

@ -14,6 +14,8 @@ from ..utils import config, logger, raise_error
__all__ = [ __all__ = [
"JUNIFER_DATA_HEXSHA",
"JUNIFER_DATA_PARAMS",
"JUNIFER_DATA_VERSION", "JUNIFER_DATA_VERSION",
"closest_resolution", "closest_resolution",
"get_dataset_path", "get_dataset_path",
@ -24,6 +26,14 @@ __all__ = [
# junifer-data version constant # junifer-data version constant
JUNIFER_DATA_VERSION = "1" JUNIFER_DATA_VERSION = "1"
# junifer-data hexsha constant
JUNIFER_DATA_HEXSHA = "e9aecf7b5a2fff82de00d265e02afde42a448647"
JUNIFER_DATA_PARAMS = {
"tag": JUNIFER_DATA_VERSION,
"hexsha": JUNIFER_DATA_HEXSHA,
}
def closest_resolution( def closest_resolution(
resolution: Optional[Union[float, int]], resolution: Optional[Union[float, int]],

2
pyproject.toml
View file

@ -52,7 +52,7 @@ dependencies = [
"lazy_loader==0.4", "lazy_loader==0.4",
"importlib_metadata; python_version<'3.9'", "importlib_metadata; python_version<'3.9'",
"looseversion==1.3.0; python_version>='3.12'", "looseversion==1.3.0; python_version>='3.12'",
"junifer_data==1.1.0", "junifer_data==1.2.0",
] ]
dynamic = ["version"] dynamic = ["version"]