Home

Trees

Indices

Help

Package mvpa :: Package measures :: Module corrstability :: Class CorrStability

[frames] | no frames]

Class CorrStability

FeaturewiseDatasetMeasure that assesses feature stability across runs for each unique label by correlating label activity for pairwise combinations of the chunks.

If there are multiple samples with the same label in a single chunk (as is typically the case) this algorithm will take the featurewise average of the sample activations to get a single value per label, per chunk.

Nested Classes

Inherited from misc.state.ClassWithCollections: __metaclass__

Instance Methods

__init__(self, attr='labels', **kwargs)
Initialize

source code

_call(self, dataset)
Computes featurewise scores.

source code

Inherited from base.FeaturewiseDatasetMeasure: __repr__, combiner

Inherited from base.FeaturewiseDatasetMeasure (private): _postcall

Inherited from base.DatasetMeasure: __call__, null_dist, transformer, untrain

Inherited from misc.state.ClassWithCollections: __getattribute__, __new__, __setattr__, __str__, reset

Inherited from object: __delattr__, __format__, __hash__, __reduce__, __reduce_ex__, __sizeof__, __subclasshook__

Class Variables

Inherited from base.FeaturewiseDatasetMeasure: base_sensitivities

Inherited from base.DatasetMeasure: __doc__, null_prob, null_t, raw_results

Inherited from misc.state.ClassWithCollections: _DEV__doc__, descr

Properties

Inherited from object: __class__

Method Details

init(self, attr='labels', **kwargs)
(Constructor)

Initialize

Parameters:

attr (basestring) - Attribute to correlate across chunks.

Overrides: object.__init__

_call(self, dataset)

Computes featurewise scores.

Overrides: base.DatasetMeasure._call

Home

Trees

Indices

Help