junifer 0.0.6.dev6__tar.gz → 0.0.6.dev16__tar.gz

{junifer-0.0.6.dev6 → junifer-0.0.6.dev16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: junifer
-Version: 0.0.6.dev6
+Version: 0.0.6.dev16
 Summary: JUelich NeuroImaging FEature extractoR
 Author-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Synchon Mandal <s.mandal@fz-juelich.de>
 Maintainer-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Synchon Mandal <s.mandal@fz-juelich.de>

{junifer-0.0.6.dev6 → junifer-0.0.6.dev16}/docs/api/onthefly.rst

@@ -4,3 +4,6 @@ On-the-fly
 .. automodule:: junifer.onthefly
    :members:
    :imported-members:
+
+.. automodule:: junifer.onthefly.brainprint
+   :members:

junifer-0.0.6.dev16/docs/changes/newsfragments/335.enh

@@ -0,0 +1 @@
+Add support for Spearman's correlation in :class:`.JuniferConnectivityMeasure` by `Leonard Sasse`_

junifer-0.0.6.dev16/docs/changes/newsfragments/354.feature

@@ -0,0 +1 @@
+Introduce :func:`.normalize` and :func:`.reweight` functions for downstream BrainPrint analysis in :mod:`.onthefly.brainprint` by `Synchon Mandal`_

{junifer-0.0.6.dev6 → junifer-0.0.6.dev16}/junifer/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.0.6.dev6'
-__version_tuple__ = version_tuple = (0, 0, 6, 'dev6')
+__version__ = version = '0.0.6.dev16'
+__version_tuple__ = version_tuple = (0, 0, 6, 'dev16')

{junifer-0.0.6.dev6 → junifer-0.0.6.dev16}/junifer/external/nilearn/junifer_connectivity_measure.py

@@ -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
 
@@ -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-0.0.6.dev6 → junifer-0.0.6.dev16}/junifer/external/nilearn/tests/test_junifer_connectivity_measure.py

@@ -71,6 +71,7 @@ CONNECTIVITY_KINDS = (
     "tangent",
     "precision",
     "partial correlation",
+    "spearman correlation",
 )
 
 N_FEATURES = 49

{junifer-0.0.6.dev6 → junifer-0.0.6.dev16}/junifer/onthefly/__init__.py

@@ -4,6 +4,7 @@
 # License: AGPL
 
 from .read_transform import read_transform
+from . import _brainprint as brainprint
 
 
-__all__ = ["read_transform"]
+__all__ = ["read_transform", "brainprint"]

junifer-0.0.6.dev16/junifer/onthefly/_brainprint.py

@@ -0,0 +1,141 @@
+"""Provide onthefly functions for BrainPrint post-analysis."""
+
+# Authors: Synchon Mandal <s.mandal@fz-juelich.de>
+# License: AGPL
+
+from typing import TYPE_CHECKING, Dict, Optional, Type
+
+import numpy as np
+import pandas as pd
+
+from ..utils import raise_error
+
+
+if TYPE_CHECKING:
+    from junifer.storage import BaseFeatureStorage
+
+
+__all__ = ["normalize", "reweight"]
+
+
+def normalize(
+    storage: Type["BaseFeatureStorage"],
+    features: Dict[str, Dict[str, Optional[str]]],
+    kind: str,
+) -> pd.DataFrame:
+    """Read stored brainprint data and normalize either surfaces or volumes.
+
+    Parameters
+    ----------
+    storage : storage-like
+        The storage class, for example, :class:`.HDF5FeatureStorage`.
+    features : dict, optional
+        The feature names or MD5 hashes to read as dict.
+        The dict should have the keys:
+
+        * ``"areas"`` (if ``kind="surface"``)
+        * ``"volumes"`` (if ``kind="volume"``)
+        * ``"eigenvalues"``
+
+        and the corresponding value for each of the keys is again
+        a dict with the keys:
+
+        * ``"feature_name"`` : str or None
+        * ``"feature_md5"`` : str or None
+
+        Either one of ``"feature_name"`` or ``"feature_md5"`` needs to be
+        not None for each first-level key, but both keys are mandatory.
+
+    kind : {"surface", "volume"}
+        The kind of normalization.
+
+    Returns
+    -------
+    pandas.DataFrame
+        The transformed feature as a ``pandas.DataFrame``.
+
+    Raises
+    ------
+    ValueError
+        If ``kind`` is invalid.
+
+    """
+    # Read storage
+    data_dict = {}
+    for k, v in features.items():
+        data_dict[k] = storage.read_df(**v)  # type: ignore
+
+    # Check and normalize
+    valid_kind = ["surface", "volume"]
+    normalized_df = None
+    if kind == "surface":
+        eigenvalues_df = data_dict["eigenvalues"]
+        areas_df = data_dict["areas"]
+        normalized_df = eigenvalues_df.combine(
+            areas_df, lambda left, right: left * right
+        )
+    elif kind == "volume":
+        eigenvalues_df = data_dict["eigenvalues"]
+        volumes_df = data_dict["volumes"]
+        normalized_df = eigenvalues_df.combine(
+            volumes_df, lambda left, right: left * right ** np.divide(2.0, 3.0)
+        )
+    else:
+        raise_error(
+            "Invalid value for `kind`, should be one of: " f"{valid_kind}"
+        )
+
+    return normalized_df
+
+
+def reweight(
+    storage: Type["BaseFeatureStorage"],
+    feature_name: Optional[str] = None,
+    feature_md5: Optional[str] = None,
+) -> pd.DataFrame:
+    """Read stored brainprint data and reweight eigenvalues.
+
+    Parameters
+    ----------
+    storage : storage-like
+        The storage class, for example, :class:`.HDF5FeatureStorage`.
+    feature_name : str, optional
+        Name of the feature to read (default None).
+    feature_md5 : str, optional
+        MD5 hash of the feature to read (default None).
+
+    Returns
+    -------
+    pandas.DataFrame
+        The transformed feature as a ``pandas.DataFrame``.
+
+    """
+    # Read storage
+    eigenvalues_df = storage.read_df(
+        feature_name=feature_name, feature_md5=feature_md5
+    )  # type: ignore
+
+    # Create data for operation
+    exploded_count_idx_df = (
+        eigenvalues_df.reset_index("eigenvalue")
+        .index.value_counts()
+        .apply(lambda x: np.arange(1, x + 1).astype(float))
+        .to_frame()
+        .explode("count")
+    )
+    idx_data = (
+        pd.concat(
+            [exploded_count_idx_df] * len(eigenvalues_df.columns), axis=1
+        )
+        .reset_index()
+        .drop("subject", axis=1, inplace=False)
+        .to_numpy()
+    )
+    idx_df = pd.DataFrame(
+        data=idx_data,
+        index=eigenvalues_df.index,
+        columns=eigenvalues_df.columns,
+    )
+
+    # Combine
+    return eigenvalues_df.combine(idx_df, lambda left, right: left / right)

{junifer-0.0.6.dev6 → junifer-0.0.6.dev16}/junifer.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: junifer
-Version: 0.0.6.dev6
+Version: 0.0.6.dev16
 Summary: JUelich NeuroImaging FEature extractoR
 Author-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Synchon Mandal <s.mandal@fz-juelich.de>
 Maintainer-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Synchon Mandal <s.mandal@fz-juelich.de>

{junifer-0.0.6.dev6 → junifer-0.0.6.dev16}/junifer.egg-info/SOURCES.txt

@@ -57,6 +57,8 @@ docs/api/testing.rst
 docs/api/utils.rst
 docs/changes/contributors.inc
 docs/changes/newsfragments/.gitignore
+docs/changes/newsfragments/335.enh
+docs/changes/newsfragments/354.feature
 docs/changes/newsfragments/356.bugfix
 docs/changes/newsfragments/357.enh
 docs/extending/coordinates.rst
@@ -310,6 +312,7 @@ junifer/markers/tests/test_markers_base.py
 junifer/markers/tests/test_parcel_aggregation.py
 junifer/markers/tests/test_sphere_aggregation.py
 junifer/onthefly/__init__.py
+junifer/onthefly/_brainprint.py
 junifer/onthefly/read_transform.py
 junifer/onthefly/tests/test_read_transform.py
 junifer/pipeline/__init__.py