junifer 0.0.5.dev242__py3-none-any.whl → 0.0.6__py3-none-any.whl

junifer/datagrabber/tests/test_multiple.py

@@ -29,7 +29,7 @@ def test_MultipleDataGrabber() -> None:
     dg1 = PatternDataladDataGrabber(
         rootdir=rootdir,
         uri=repo_uri,
-        types=["T1w"],
+        types=["T1w", "Warp"],
         patterns={
             "T1w": {
                 "pattern": (
@@ -44,6 +44,28 @@ def test_MultipleDataGrabber() -> None:
                     "space": "native",
                 },
             },
+            "Warp": [
+                {
+                    "pattern": (
+                        "{subject}/{session}/anat/"
+                        "{subject}_{session}_from-MNI152NLin2009cAsym_to-T1w_"
+                        "xfm.h5"
+                    ),
+                    "src": "MNI152NLin2009cAsym",
+                    "dst": "native",
+                    "warper": "ants",
+                },
+                {
+                    "pattern": (
+                        "{subject}/{session}/anat/"
+                        "{subject}_{session}_from-T1w_to-MNI152NLin2009cAsym_"
+                        "xfm.h5"
+                    ),
+                    "src": "native",
+                    "dst": "MNI152NLin2009cAsym",
+                    "warper": "ants",
+                },
+            ],
         },
         replacements=replacements,
     )
@@ -75,6 +97,7 @@ def test_MultipleDataGrabber() -> None:
 
     types = dg.get_types()
     assert "T1w" in types
+    assert "Warp" in types
     assert "BOLD" in types
 
     expected_subs = [
@@ -90,6 +113,7 @@ def test_MultipleDataGrabber() -> None:
         elem = dg[("sub-01", "ses-01")]
         # Check data types
         assert "T1w" in elem
+        assert "Warp" in elem
         assert "BOLD" in elem
         # Check meta
         assert "meta" in elem["BOLD"]
@@ -111,7 +135,7 @@ def test_MultipleDataGrabber_no_intersection() -> None:
     dg1 = PatternDataladDataGrabber(
         rootdir=rootdir,
         uri=_testing_dataset["example_bids"]["uri"],
-        types=["T1w"],
+        types=["T1w", "Warp"],
         patterns={
             "T1w": {
                 "pattern": (
@@ -119,6 +143,28 @@ def test_MultipleDataGrabber_no_intersection() -> None:
                 ),
                 "space": "native",
             },
+            "Warp": [
+                {
+                    "pattern": (
+                        "{subject}/{session}/anat/"
+                        "{subject}_{session}_from-MNI152NLin2009cAsym_to-T1w_"
+                        "xfm.h5"
+                    ),
+                    "src": "MNI152NLin2009cAsym",
+                    "dst": "native",
+                    "warper": "ants",
+                },
+                {
+                    "pattern": (
+                        "{subject}/{session}/anat/"
+                        "{subject}_{session}_from-T1w_to-MNI152NLin2009cAsym_"
+                        "xfm.h5"
+                    ),
+                    "src": "native",
+                    "dst": "MNI152NLin2009cAsym",
+                    "warper": "ants",
+                },
+            ],
         },
         replacements=replacements,
     )

junifer/datagrabber/tests/test_pattern_datalad.py

@@ -15,7 +15,7 @@ from junifer.datagrabber import PatternDataladDataGrabber
 _testing_dataset = {
     "example_bids": {
         "uri": "https://gin.g-node.org/juaml/datalad-example-bids",
-        "commit": "b87897cbe51bf0ee5514becaa5c7dd76491db5ad",
+        "commit": "3f288c8725207ae0c9b3616e093e78cda192b570",
         "id": "8fddff30-6993-420a-9d1e-b5b028c59468",
     },
     "example_bids_ses": {

junifer/datagrabber/tests/test_pattern_validation_mixin.py

@@ -4,8 +4,8 @@
 #          Synchon Mandal <s.mandal@fz-juelich.de>
 # License: AGPL
 
-from contextlib import nullcontext
-from typing import ContextManager, Dict, List, Union
+from contextlib import AbstractContextManager, nullcontext
+from typing import Union
 
 import pytest
 
@@ -186,10 +186,10 @@ from junifer.datagrabber.pattern_validation_mixin import PatternValidationMixin
     ],
 )
 def test_PatternValidationMixin(
-    types: Union[str, List[str], List[int]],
-    replacements: Union[str, List[str], List[int]],
-    patterns: Union[str, Dict[str, Dict[str, str]]],
-    expect: ContextManager,
+    types: Union[str, list[str], list[int]],
+    replacements: Union[str, list[str], list[int]],
+    patterns: Union[str, dict[str, dict[str, str]]],
+    expect: AbstractContextManager,
 ) -> None:
     """Test validation.
 

junifer/datareader/__init__.py

@@ -5,7 +5,7 @@
 #          Synchon Mandal <s.mandal@fz-juelich.de>
 # License: AGPL
 
-from .default import DefaultDataReader
+import lazy_loader as lazy
 
 
-__all__ = ["DefaultDataReader"]
+__getattr__, __dir__, __all__ = lazy.attach_stub(__name__, __file__)

junifer/datareader/__init__.pyi

@@ -0,0 +1,3 @@
+__all__ = ["DefaultDataReader"]
+
+from .default import DefaultDataReader

junifer/datareader/default.py

@@ -5,7 +5,7 @@
 # License: AGPL
 
 from pathlib import Path
-from typing import Dict, List, Optional, Union
+from typing import Optional, Union
 
 import nibabel as nib
 import pandas as pd
@@ -37,7 +37,7 @@ _readers["TSV"] = {"func": pd.read_csv, "params": {"sep": "\t"}}
 class DefaultDataReader(PipelineStepMixin, UpdateMetaMixin):
     """Concrete implementation for common data reading."""
 
-    def validate_input(self, input: List[str]) -> List[str]:
+    def validate_input(self, input: list[str]) -> list[str]:
         """Validate input.
 
         Parameters
@@ -75,9 +75,9 @@ class DefaultDataReader(PipelineStepMixin, UpdateMetaMixin):
 
     def _fit_transform(
         self,
-        input: Dict[str, Dict],
-        params: Optional[Dict] = None,
-    ) -> Dict:
+        input: dict[str, dict],
+        params: Optional[dict] = None,
+    ) -> dict:
         """Fit and transform.
 
         Parameters
@@ -165,7 +165,7 @@ class DefaultDataReader(PipelineStepMixin, UpdateMetaMixin):
 
 
 def _read_data(
-    data_type: str, path: Path, read_params: Dict
+    data_type: str, path: Path, read_params: dict
 ) -> Union[nib.Nifti1Image, pd.DataFrame, None]:
     """Read data for data type.
 

junifer/external/nilearn/__init__.py

@@ -3,8 +3,7 @@
 # Authors: Synchon Mandal <s.mandal@fz-juelich.de>
 # License: AGPL
 
-from .junifer_nifti_spheres_masker import JuniferNiftiSpheresMasker
-from .junifer_connectivity_measure import JuniferConnectivityMeasure
+import lazy_loader as lazy
 
 
-__all__ = ["JuniferNiftiSpheresMasker", "JuniferConnectivityMeasure"]
+__getattr__, __dir__, __all__ = lazy.attach_stub(__name__, __file__)

junifer/external/nilearn/__init__.pyi

@@ -0,0 +1,4 @@
+__all__ = ["JuniferNiftiSpheresMasker", "JuniferConnectivityMeasure"]
+
+from .junifer_nifti_spheres_masker import JuniferNiftiSpheresMasker
+from .junifer_connectivity_measure import JuniferConnectivityMeasure

junifer/external/nilearn/junifer_connectivity_measure.py

@@ -3,7 +3,7 @@
 # Authors: Synchon Mandal <s.mandal@fz-juelich.de>
 # License: AGPL
 
-from typing import Callable, List, Optional
+from typing import Callable, Optional
 
 import numpy as np
 from nilearn import signal
@@ -13,7 +13,7 @@ from nilearn.connectome import (
     prec_to_partial,
     sym_matrix_to_vec,
 )
-from scipy import linalg
+from scipy import linalg, stats
 from sklearn.base import clone
 from sklearn.covariance import EmpiricalCovariance
 
@@ -186,7 +186,7 @@ def _map_eigenvalues(
 
 
 def _geometric_mean(
-    matrices: List[np.ndarray],
+    matrices: list[np.ndarray],
     init: Optional[np.ndarray] = None,
     max_iter: int = 10,
     tol: Optional[float] = 1e-7,
@@ -314,15 +314,18 @@ class JuniferConnectivityMeasure(ConnectivityMeasure):
     * default ``cov_estimator`` is
       :class:`sklearn.covariance.EmpiricalCovariance`
     * default ``kind`` is ``"correlation"``
+    * supports Spearman's correlation via ``kind="spearman correlation"``
 
     Parameters
     ----------
     cov_estimator : estimator object, optional
         The covariance estimator
         (default ``EmpiricalCovariance(store_precision=False)``).
-    kind : {"covariance", "correlation", "partial correlation", \
-            "tangent", "precision"}, optional
-        The matrix kind. For the use of ``"tangent"`` see [1]_
+    kind : {"covariance", "correlation", "spearman correlation", \
+            "partial correlation", "tangent", "precision"}, optional
+        The matrix kind. The default value uses Pearson's correlation.
+        If ``"spearman correlation"`` is used, the data will be ranked before
+        estimating the covariance. For the use of ``"tangent"`` see [1]_
         (default "correlation").
     vectorize : bool, optional
         If True, connectivity matrices are reshaped into 1D arrays and only
@@ -400,17 +403,22 @@ class JuniferConnectivityMeasure(ConnectivityMeasure):
             self.cov_estimator_ = clone(self.cov_estimator)
 
         # Compute all the matrices, stored in "connectivities"
-        if self.kind == "correlation":
-            covariances_std = [
-                self.cov_estimator_.fit(
-                    signal.standardize_signal(
-                        x,
-                        detrend=False,
-                        standardize=self.standardize,
-                    )
-                ).covariance_
-                for x in X
-            ]
+        if self.kind in ["correlation", "spearman correlation"]:
+            covariances_std = []
+            for x in X:
+                x = signal.standardize_signal(
+                    x,
+                    detrend=False,
+                    standardize=self.standardize,
+                )
+
+                # rank data if spearman correlation
+                # before calculating covariance
+                if self.kind == "spearman correlation":
+                    x = stats.rankdata(x, axis=0)
+
+                covariances_std.append(self.cov_estimator_.fit(x).covariance_)
+
             connectivities = [cov_to_corr(cov) for cov in covariances_std]
         else:
             covariances = [self.cov_estimator_.fit(x).covariance_ for x in X]

junifer/external/nilearn/junifer_nifti_spheres_masker.py

@@ -3,7 +3,7 @@
 # Authors: Synchon Mandal <s.mandal@fz-juelich.de>
 # License: AGPL
 
-from typing import TYPE_CHECKING, Callable, List, Optional, Tuple, Union
+from typing import TYPE_CHECKING, Callable, Optional, Union
 
 import numpy as np
 from nilearn import image, masking
@@ -271,7 +271,7 @@ class _JuniferExtractionFunctor:
     def __call__(
         self,
         imgs: Union["Nifti1Image", "Nifti2Image"],
-    ) -> Tuple["ArrayLike", None]:
+    ) -> tuple["ArrayLike", None]:
         """Implement function call overloading.
 
         Parameters
@@ -372,9 +372,9 @@ class JuniferNiftiSpheresMasker(NiftiSpheresMasker):
         self,
         imgs: Union["Nifti1Image", "Nifti2Image"],
         confounds: Union[
-            str, "Path", "ArrayLike", "DataFrame", List, None
+            str, "Path", "ArrayLike", "DataFrame", list, None
         ] = None,
-        sample_mask: Union["ArrayLike", List, Tuple, None] = None,
+        sample_mask: Union["ArrayLike", list, tuple, None] = None,
     ) -> "ArrayLike":
         """Extract signals from a single 4D niimg.
 

junifer/external/nilearn/tests/test_junifer_connectivity_measure.py

@@ -6,7 +6,7 @@
 import copy
 import warnings
 from math import cosh, exp, log, sinh, sqrt
-from typing import TYPE_CHECKING, List, Optional, Tuple, Type, Union
+from typing import TYPE_CHECKING, Optional, Union
 
 import numpy as np
 import pytest
@@ -71,6 +71,7 @@ CONNECTIVITY_KINDS = (
     "tangent",
     "precision",
     "partial correlation",
+    "spearman correlation",
 )
 
 N_FEATURES = 49
@@ -148,7 +149,7 @@ def random_spd(
 
 def _signals(
     n_subjects: int = N_SUBJECTS,
-) -> Tuple[List[np.ndarray], np.ndarray]:
+) -> tuple[list[np.ndarray], np.ndarray]:
     """Generate signals and compute covariances while applying confounds.
 
     Parameters
@@ -177,15 +178,15 @@ def _signals(
 
 
 @pytest.fixture
-def signals() -> List[np.ndarray]:
+def signals() -> list[np.ndarray]:
     """Return signals as list of np.ndarray."""
     return _signals(N_SUBJECTS)[0]
 
 
 @pytest.fixture
 def signals_and_covariances(
-    cov_estimator: Union[LedoitWolf, EmpiricalCovariance]
-) -> Tuple[List[np.ndarray], List[float]]:
+    cov_estimator: Union[LedoitWolf, EmpiricalCovariance],
+) -> tuple[list[np.ndarray], list[float]]:
     """Return signals and covariances for a covariance estimator.
 
     Parameters
@@ -416,7 +417,7 @@ def grad_geometric_mean(
     init: Optional["ArrayLike"] = None,
     max_iter: int = 10,
     tol: float = 1e-7,
-) -> List[float]:
+) -> list[float]:
     """Compute gradient of geometric mean.
 
     Return the norm of the covariant derivative at each iteration step
@@ -614,8 +615,8 @@ def test_connectivity_measure_errors():
 @pytest.mark.parametrize("kind", CONNECTIVITY_KINDS)
 def test_connectivity_measure_generic(
     kind: str,
-    cov_estimator: Type["BaseEstimator"],
-    signals_and_covariances: Tuple[List[np.ndarray], List[float]],
+    cov_estimator: type["BaseEstimator"],
+    signals_and_covariances: tuple[list[np.ndarray], list[float]],
 ) -> None:
     """Test generic JuniferConnectivityMeasure.
 
@@ -777,8 +778,8 @@ def _assert_connectivity_partial_correlation(connectivities, covs) -> None:
 )
 def test_connectivity_measure_specific_for_each_kind(
     kind: str,
-    cov_estimator: Type["BaseEstimator"],
-    signals_and_covariances: Tuple[List[np.ndarray], List[float]],
+    cov_estimator: type["BaseEstimator"],
+    signals_and_covariances: tuple[list[np.ndarray], list[float]],
 ) -> None:
     """Test connectivity matrix for each kind.
 
@@ -811,7 +812,7 @@ def test_connectivity_measure_specific_for_each_kind(
 
 @pytest.mark.parametrize("kind", CONNECTIVITY_KINDS)
 def test_connectivity_measure_check_mean(
-    kind: str, signals: List[np.ndarray]
+    kind: str, signals: list[np.ndarray]
 ) -> None:
     """Test mean of connectivity matrix for each kind.
 
@@ -845,7 +846,7 @@ def test_connectivity_measure_check_mean(
 
 @pytest.mark.parametrize("kind", CONNECTIVITY_KINDS)
 def test_connectivity_measure_check_vectorization_option(
-    kind: str, signals: List[np.ndarray]
+    kind: str, signals: list[np.ndarray]
 ) -> None:
     """Test vectorization of connectivity matrix for each kind.
 
@@ -878,7 +879,7 @@ def test_connectivity_measure_check_vectorization_option(
     ["covariance", "correlation", "precision", "partial correlation"],
 )
 def test_connectivity_measure_check_inverse_transformation(
-    kind: str, signals: List[np.ndarray]
+    kind: str, signals: list[np.ndarray]
 ) -> None:
     """Test inverse transform.
 
@@ -914,7 +915,7 @@ def test_connectivity_measure_check_inverse_transformation(
     ["covariance", "correlation", "precision", "partial correlation"],
 )
 def test_connectivity_measure_check_inverse_transformation_discard_diag(
-    kind: str, signals: List[np.ndarray]
+    kind: str, signals: list[np.ndarray]
 ) -> None:
     """Test diagonal for inverse transform.
 
@@ -956,7 +957,7 @@ def test_connectivity_measure_check_inverse_transformation_discard_diag(
 
 
 def test_connectivity_measure_inverse_transform_tangent(
-    signals: List[np.ndarray],
+    signals: list[np.ndarray],
 ) -> None:
     """Test that for 'tangent' kind, covariance matrices are reconstructed.
 
@@ -1066,7 +1067,7 @@ def test_confounds_connectivity_measure_errors() -> None:
 
 
 def test_connectivity_measure_standardize(
-    signals: List[np.ndarray],
+    signals: list[np.ndarray],
 ) -> None:
     """Check warning is raised and then suppressed with setting standardize.
 

junifer/external/nilearn/tests/test_junifer_nifti_spheres_masker.py

@@ -4,7 +4,6 @@
 # License: AGPL
 
 import warnings
-from typing import List, Tuple
 
 import nibabel
 import numpy as np
@@ -361,10 +360,10 @@ def test_nifti_spheres_masker_io_shapes() -> None:
     ],
 )
 def test_junifer_and_nilearn_mean_agg_are_equal(
-    shape: Tuple[int, ...],
+    shape: tuple[int, ...],
     radius: float,
     allow_overlap: bool,
-    coords: List[Tuple[int, int, int]],
+    coords: list[tuple[int, int, int]],
 ) -> None:
     """Test junifer's masker behaves same as nilearn's when agg is mean.
 

junifer/markers/__init__.py

@@ -5,43 +5,7 @@
 #          Synchon Mandal <s.mandal@fz-juelich.de>
 # License: AGPL
 
-from .base import BaseMarker
-from .collection import MarkerCollection
-from .ets_rss import RSSETSMarker
-from .parcel_aggregation import ParcelAggregation
-from .sphere_aggregation import SphereAggregation
-from .functional_connectivity import (
-    FunctionalConnectivityParcels,
-    FunctionalConnectivitySpheres,
-    CrossParcellationFC,
-    EdgeCentricFCParcels,
-    EdgeCentricFCSpheres,
-)
-from .reho import ReHoParcels, ReHoSpheres
-from .falff import ALFFParcels, ALFFSpheres
-from .temporal_snr import (
-    TemporalSNRParcels,
-    TemporalSNRSpheres,
-)
-from .brainprint import BrainPrint
+import lazy_loader as lazy
 
 
-__all__ = [
-    "BaseMarker",
-    "MarkerCollection",
-    "RSSETSMarker",
-    "ParcelAggregation",
-    "SphereAggregation",
-    "FunctionalConnectivityParcels",
-    "FunctionalConnectivitySpheres",
-    "CrossParcellationFC",
-    "EdgeCentricFCParcels",
-    "EdgeCentricFCSpheres",
-    "ReHoParcels",
-    "ReHoSpheres",
-    "ALFFParcels",
-    "ALFFSpheres",
-    "TemporalSNRParcels",
-    "TemporalSNRSpheres",
-    "BrainPrint",
-]
+__getattr__, __dir__, __all__ = lazy.attach_stub(__name__, __file__)

junifer/markers/__init__.pyi

@@ -0,0 +1,37 @@
+__all__ = [
+    "BaseMarker",
+    "RSSETSMarker",
+    "ParcelAggregation",
+    "SphereAggregation",
+    "FunctionalConnectivityParcels",
+    "FunctionalConnectivitySpheres",
+    "CrossParcellationFC",
+    "EdgeCentricFCParcels",
+    "EdgeCentricFCSpheres",
+    "ReHoParcels",
+    "ReHoSpheres",
+    "ALFFParcels",
+    "ALFFSpheres",
+    "TemporalSNRParcels",
+    "TemporalSNRSpheres",
+    "BrainPrint",
+]
+
+from .base import BaseMarker
+from .ets_rss import RSSETSMarker
+from .parcel_aggregation import ParcelAggregation
+from .sphere_aggregation import SphereAggregation
+from .functional_connectivity import (
+    FunctionalConnectivityParcels,
+    FunctionalConnectivitySpheres,
+    CrossParcellationFC,
+    EdgeCentricFCParcels,
+    EdgeCentricFCSpheres,
+)
+from .reho import ReHoParcels, ReHoSpheres
+from .falff import ALFFParcels, ALFFSpheres
+from .temporal_snr import (
+    TemporalSNRParcels,
+    TemporalSNRSpheres,
+)
+from .brainprint import BrainPrint

junifer/markers/base.py

@@ -6,16 +6,13 @@
 
 from abc import ABC, abstractmethod
 from copy import deepcopy
-from typing import TYPE_CHECKING, Any, Dict, List, Optional, Union
+from typing import Any, Optional, Union
 
 from ..pipeline import PipelineStepMixin, UpdateMetaMixin
+from ..typing import StorageLike
 from ..utils import logger, raise_error
 
 
-if TYPE_CHECKING:
-    from junifer.storage import BaseFeatureStorage
-
-
 __all__ = ["BaseMarker"]
 
 
@@ -45,7 +42,7 @@ class BaseMarker(ABC, PipelineStepMixin, UpdateMetaMixin):
 
     def __init__(
         self,
-        on: Optional[Union[List[str], str]] = None,
+        on: Optional[Union[list[str], str]] = None,
         name: Optional[str] = None,
     ) -> None:
         # Check for missing mapping attribute
@@ -68,7 +65,7 @@ class BaseMarker(ABC, PipelineStepMixin, UpdateMetaMixin):
             raise_error(f"{self.name} cannot be computed on {wrong_on}")
         self._on = on
 
-    def validate_input(self, input: List[str]) -> List[str]:
+    def validate_input(self, input: list[str]) -> list[str]:
         """Validate input.
 
         Parameters
@@ -97,7 +94,7 @@ class BaseMarker(ABC, PipelineStepMixin, UpdateMetaMixin):
             )
         return [x for x in self._on if x in input]
 
-    def get_valid_inputs(self) -> List[str]:
+    def get_valid_inputs(self) -> list[str]:
         """Get valid data types for input.
 
         Returns
@@ -127,7 +124,7 @@ class BaseMarker(ABC, PipelineStepMixin, UpdateMetaMixin):
         return self._MARKER_INOUT_MAPPINGS[input_type][output_feature]
 
     @abstractmethod
-    def compute(self, input: Dict, extra_input: Optional[Dict] = None) -> Dict:
+    def compute(self, input: dict, extra_input: Optional[dict] = None) -> dict:
         """Compute.
 
         Parameters
@@ -158,8 +155,8 @@ class BaseMarker(ABC, PipelineStepMixin, UpdateMetaMixin):
         self,
         type_: str,
         feature: str,
-        out: Dict[str, Any],
-        storage: "BaseFeatureStorage",
+        out: dict[str, Any],
+        storage: StorageLike,
     ) -> None:
         """Store.
 
@@ -181,9 +178,9 @@ class BaseMarker(ABC, PipelineStepMixin, UpdateMetaMixin):
 
     def _fit_transform(
         self,
-        input: Dict[str, Dict],
-        storage: Optional["BaseFeatureStorage"] = None,
-    ) -> Dict:
+        input: dict[str, dict],
+        storage: Optional[StorageLike] = None,
+    ) -> dict:
         """Fit and transform.
 
         Parameters