Table Of Contents

Previous topic

mvpa.featsel

Next topic

mvpa.featsel.helpers

This Page

Quick search

mvpa.featsel.base

Feature selection base class and related stuff base classes and helpers.

The comprehensive API documentation for this module, including all technical details, is available in the Epydoc-generated API reference for mvpa.featsel.base (for developers).

Classes

FeatureSelection

class mvpa.featsel.base.FeatureSelection(**kwargs)

Bases: mvpa.misc.state.ClassWithCollections

Base class for any feature selection

Base class for Functors which implement feature selection on the datasets.

See also

Derived classes might provide additional methods via their base classes. Please refer to the list of base classes (if it exists) at the begining of the FeatureSelection documentation.

Full API documentation of FeatureSelection in module mvpa.featsel.base.

FeatureSelectionPipeline

class mvpa.featsel.base.FeatureSelectionPipeline(feature_selections, **kwargs)

Bases: mvpa.featsel.base.FeatureSelection

Feature elimination through the list of FeatureSelection’s.

Given as list of FeatureSelections it applies them in turn.

Initialize feature selection pipeline

Parameters:
  • feature_selections (lisf of FeatureSelection) – selections which to use. Order matters
feature_selections
List of FeatureSelections

See also

Derived classes might provide additional methods via their base classes. Please refer to the list of base classes (if it exists) at the begining of the FeatureSelectionPipeline documentation.

Full API documentation of FeatureSelectionPipeline in module mvpa.featsel.base.

SensitivityBasedFeatureSelection

class mvpa.featsel.base.SensitivityBasedFeatureSelection(sensitivity_analyzer, feature_selector=FractionTailSelector() fraction=0.050000, **kwargs)

Bases: mvpa.featsel.base.FeatureSelection

Feature elimination.

A FeaturewiseDatasetMeasure is used to compute sensitivity maps given a certain dataset. These sensitivity maps are in turn used to discard unimportant features.

Initialize feature selection

Parameters:
  • sensitivity_analyzer (FeaturewiseDatasetMeasure) – sensitivity analyzer to come up with sensitivity
  • feature_selector (Functor) – Given a sensitivity map it has to return the ids of those features that should be kept.
sensitivity_analyzer
Measure which was used to do selection

See also

Derived classes might provide additional methods via their base classes. Please refer to the list of base classes (if it exists) at the begining of the SensitivityBasedFeatureSelection documentation.

Full API documentation of SensitivityBasedFeatureSelection in module mvpa.featsel.base.