Home

Trees

Indices

Help

Package mvpa :: Package clfs :: Module lars :: Class LARSWeights

[frames] | no frames]

Class LARSWeights

SensitivityAnalyzer that reports the weights LARS trained on a given Dataset.

By default LARS provides multiple weights per feature (one per label in training dataset). By default, all weights are combined into a single sensitivity value. Please, see the FeaturewiseDatasetMeasure constructor arguments how to custmize this behavior.

Nested Classes

Inherited from misc.state.ClassWithCollections: __metaclass__

Instance Methods

_call(self, dataset=None)
Extract weights from LARS classifier.

source code

Inherited from measures.base.Sensitivity: __call__, __init__, __repr__, feature_ids

Inherited from measures.base.Sensitivity (private): _setClassifier

Inherited from measures.base.FeaturewiseDatasetMeasure (private): _postcall

Inherited from measures.base.DatasetMeasure: null_dist

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

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

Class Variables

_LEGAL_CLFS = [LARS]
If Sensitivity is classifier specific, classes of classifiers should be listed in the list

Inherited from measures.base.Sensitivity: clf

Inherited from measures.base.FeaturewiseDatasetMeasure: base_sensitivities

Inherited from measures.base.DatasetMeasure: __doc__, null_prob, null_t, raw_result

Inherited from misc.state.ClassWithCollections: _DEV__doc__, descr

Instance Variables

Inherited from measures.base.Sensitivity (private): _force_training

Properties

Inherited from object: __class__

Method Details

_call(self, dataset=None)

Extract weights from LARS classifier.

LARS always has weights available, so nothing has to be computed here.

Overrides: measures.base.DatasetMeasure._call

Home

Trees

Indices

Help