mvpa2.algorithms.searchlight_hyperalignment.SurfaceVerticesQueryEngine

class mvpa2.algorithms.searchlight_hyperalignment.SurfaceVerticesQueryEngine(voxsel, space='voxel_indices', add_fa=None)

Query-engine that maps center nodes to indices of features (voxels) that are near each center node.

In a typical use case such an instance is generated using the function ‘disc_surface_queryengine’

This class is for mappings from surface to voxel features; for mappings from surface to surface features, use SurfaceQueryEngine.

Attributes

add_fa
ids

Methods

__call__(\*\*kwargs)
feature_id2linear_voxel_ids(feature_id)
feature_id2nearest_vertex_id(feature_id[, ...])	Compute the index of the vertex nearest to a given voxel.
get_masked_nifti_image([center_ids])	Return a NIfTI image binary mask with voxels covered by searchlights
linear_voxel_id2feature_id(linear_voxel_id)
query(\*\*kwargs)
query_byid(vertexid)	Given a vertex ID give us indices of dataset features (voxels)
train(dataset)	Train the query engine on a dataset
untrain()
vertex_id2nearest_feature_id(vertex_id)	Compute the index of the voxel nearest to a given vertex.

Makes a new SurfaceVerticesQueryEngine

Parameters:

voxsel: volume_mask_dict.VolumeMaskDictionary

mapping from center node indices to indices of voxels in a searchlight

space: str (default: ‘voxel_indices’)

defines by which space voxels are indexed.

add_fa: list of str

additional feature attributes that should be returned when this instance is called with a center node id.

Attributes

add_fa
ids

Methods

__call__(\*\*kwargs)
feature_id2linear_voxel_ids(feature_id)
feature_id2nearest_vertex_id(feature_id[, ...])	Compute the index of the vertex nearest to a given voxel.
get_masked_nifti_image([center_ids])	Return a NIfTI image binary mask with voxels covered by searchlights
linear_voxel_id2feature_id(linear_voxel_id)
query(\*\*kwargs)
query_byid(vertexid)	Given a vertex ID give us indices of dataset features (voxels)
train(dataset)	Train the query engine on a dataset
untrain()
vertex_id2nearest_feature_id(vertex_id)	Compute the index of the voxel nearest to a given vertex.

add_fa

feature_id2linear_voxel_ids(feature_id)

feature_id2nearest_vertex_id(feature_id, fallback_euclidean_distance=False)

Compute the index of the vertex nearest to a given voxel.

Parameters:

feature_id: int

Feature index (referring to a voxel).

fallback_euclidean_distance: bool (default: False)

If the voxel indexed by feature_id was not selected by any searchlight, then None is returned if fallback_euclidean_distance is False, but vertex_id with the nearest Euclidean distance is returned if True.

Returns:

vertex_id: int

Vertex index of vertex nearest to the feature with id feature_id. By default this function only considers vertices that are in one or more searchlights

get_masked_nifti_image(center_ids=None)

Return a NIfTI image binary mask with voxels covered by searchlights

Parameters:

center_ids: list or None

Indices of center ids for which the associated masks must be used. If None, all center_ids are used.

Returns:

img: nibabel.Nifti1Image

Nifti image with value zero for voxels that we not selected, and non-zero values for selected voxels.

Notes

When using surface-based searchlights, a use case of this function is to get the voxels that were associated with the searchlights in a subset of all nodes on a cortical surface.

ids

linear_voxel_id2feature_id(linear_voxel_id)

query(**kwargs)

query_byid(vertexid)

Given a vertex ID give us indices of dataset features (voxels)

Parameters:

vertexid: int

Index of searchlight center vertex on the surface. This value should be an element in self.ids

Returns:

voxel_ids: list of int or AttrDataset

The linear indices of voxels near the vertex with index vertexid. If the instance was constructed with add_fa=None, then voxel_ids is a list; otherwise it is a AttrDataset with additional feature attributes stored in voxel_ids.fa.

train(dataset)

Train the query engine on a dataset

untrain()

vertex_id2nearest_feature_id(vertex_id)

Compute the index of the voxel nearest to a given vertex.

Parameters:

vertex_id: int

Vertex id (referring to a node on the surface).

Returns:

feature_id: int

Index of feature nearest to the vertex with id vertex_id.

Notes

This function only considers feature ids that are selected by at least one vertex_id..