Package mvpa :: Package measures :: Module irelief :: Class IterativeRelief
[hide private]
[frames] | no frames]

Class IterativeRelief

source code


FeaturewiseDatasetMeasure that performs multivariate I-RELIEF algorithm. Batch version.

Batch I-RELIEF-2 feature weighting algorithm. Works for binary or multiclass class-labels. Batch version with complexity O(T*N^2*I), where T is the number of iterations, N the number of instances, I the number of features.

See: Y. Sun, Iterative RELIEF for Feature Weighting: Algorithms, Theories, and Applications, IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), vol. 29, no. 6, pp. 1035-1051, June 2007. http://plaza.ufl.edu/sunyijun/Paper/PAMI_1.pdf

Note that current implementation allows to use only exponential-like kernels. Support for linear kernel will be added later.

Nested Classes [hide private]

Inherited from misc.state.ClassWithCollections: __metaclass__

Instance Methods [hide private]
 
__init__(self, threshold=1.0e-2, kernel_width=1.0, w_guess=None, **kwargs)
Constructor of the IRELIEF class.
source code
 
compute_M_H(self, label)
Compute hit/miss dictionaries.
source code
 
k(self, distances)
Exponential kernel.
source code
 
_call(self, dataset)
Computes featurewise I-RELIEF weights.
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 [hide private]

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 [hide private]

Inherited from object: __class__

Method Details [hide private]

__init__(self, threshold=1.0e-2, kernel_width=1.0, w_guess=None, **kwargs)
(Constructor)

source code 
Constructor of the IRELIEF class.
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__

compute_M_H(self, label)

source code 

Compute hit/miss dictionaries.

For each instance compute the set of indices having the same class label and different class label.

Note that this computation is independent of the number of features.

XXX should it be some generic function since it doesn't use self

_call(self, dataset)

source code 
Computes featurewise I-RELIEF weights.
Overrides: base.DatasetMeasure._call