Helpers for feature selection (scoring, selection strategies)

Inheritance diagram of mvpa2.featsel.helpers


floor(x) Return the floor of x as a float.


AttrDataset(samples[, sa, fa, a]) Generic storage class for datasets with multiple attributes.
BestDetector([func, lastminimum]) Determine whether the last value in a sequence is the best one given some criterion.
ClassWithCollections([descr]) Base class for objects which contain any known collection
ConditionalAttribute([enabled]) Simple container intended to conditionally store the value
ElementSelector([mode]) Base class to implement functors to select some elements based on a sequence of values.
FixedErrorThresholdStopCrit(threshold) Stop computation if the latest error drops below a certain threshold.
FixedNElementTailSelector(nelements, \*\*kwargs) Given a sequence, provide set of IDs for a fixed number of to be selected elements.
FractionTailSelector(felements, \*\*kwargs) Given a sequence, provide Ids for a fraction of elements
MultiStopCrit(crits[, mode]) Stop computation if the latest error drops below a certain threshold.
NBackHistoryStopCrit([bestdetector, steps]) Stop computation if for a number of steps error was increasing
NStepsStopCrit(steps) Stop computation after a certain number of steps.
RangeElementSelector([lower, upper, ...]) Select elements based on specified range of values
StoppingCriterion Base class for all functors to decide when to stop RFE (or may be general optimization...
TailSelector([tail, sort]) Select elements from a tail of a distribution.