Package mvpa :: Package measures :: Module base :: Class Sensitivity
[hide private]
[frames] | no frames]

Class Sensitivity

source code


Nested Classes [hide private]

Inherited from misc.state.ClassWithCollections: __metaclass__

Instance Methods [hide private]
 
__init__(self, clf, force_training=True, **kwargs)
Initialize the analyzer with the classifier it shall use.
source code
 
__repr__(self, prefixes=None)
String representation of DatasetMeasure
source code
 
__call__(self, dataset=None)
Train classifier on dataset and then compute actual sensitivity.
source code
 
_setClassifier(self, clf) source code
 
untrain(self)
Untrain corresponding classifier for Sensitivity
source code
 
feature_ids(self)
Return feature_ids used by the underlying classifier
source code

Inherited from FeaturewiseDatasetMeasure: combiner

Inherited from FeaturewiseDatasetMeasure (private): _call, _postcall

Inherited from DatasetMeasure: null_dist, transformer

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

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

Class Variables [hide private]
  _LEGAL_CLFS = []
If Sensitivity is classifier specific, classes of classifiers should be listed in the list
  clf = property(fget= lambda self: self.__clf, fset= _setClassi...

Inherited from FeaturewiseDatasetMeasure: base_sensitivities

Inherited from DatasetMeasure: __doc__, null_prob, null_t, raw_results

Inherited from misc.state.ClassWithCollections: _DEV__doc__, descr

Instance Variables [hide private]
  __clf
Classifier used to computed sensitivity
  _force_training
Either to force it to train
Properties [hide private]

Inherited from object: __class__

Method Details [hide private]

__init__(self, clf, force_training=True, **kwargs)
(Constructor)

source code 
Initialize the analyzer with the classifier it shall use.

:Parameters:
  clf : :class:`Classifier`
    classifier to use.
  force_training : Bool
    if classifier was already trained -- do not retrain

Parameters:
  • combiner - The combiner is only applied if the computed featurewise dataset measure is more than one-dimensional. This is different from a transformer, which is always applied. By default, the sum of absolute values along the second axis is computed.
Overrides: object.__init__

__repr__(self, prefixes=None)
(Representation operator)

source code 

String representation of DatasetMeasure

Includes only arguments which differ from default ones

Parameters:
  • fullname - Either to include full name of the module
  • prefixes - What other prefixes to prepend to list of arguments
Overrides: object.__repr__
(inherited documentation)

__call__(self, dataset=None)
(Call operator)

source code 

Train classifier on dataset and then compute actual sensitivity.

If the classifier is already trained it is possible to extract the sensitivities without passing a dataset.

Overrides: DatasetMeasure.__call__

untrain(self)

source code 
Untrain corresponding classifier for Sensitivity
Overrides: DatasetMeasure.untrain

feature_ids(self)

source code 
Return feature_ids used by the underlying classifier
Decorators:
  • @property

Class Variable Details [hide private]

clf

Value:
property(fget= lambda self: self.__clf, fset= _setClassifier)