mvpa2.featsel.rfeΒΆ
Recursive feature elimination.
Functions
BibTeX(\*args, \*\*kwargs) |
Perform no good and no bad |
Doi(\*args, \*\*kwargs) |
Perform no good and no bad |
copy(x) |
Shallow copy operation on arbitrary Python objects. |
maxofabs_sample() |
Returns a mapper that finds max of absolute values of all samples. |
mean_mismatch_error(predicted, target) |
Computes the percentage of mismatches between some target and some predicted values. |
Classes
BestDetector([func, lastminimum]) |
Determine whether the last value in a sequence is the best one given some criterion. |
BinaryFxNode(fx, space, \*\*kwargs) |
Extract a dataset attribute and call a function with it and the samples. |
ClassifierError(clf[, labels, train]) |
Compute (or return) some error of a (trained) classifier on a dataset. |
ConditionalAttribute([enabled]) |
Simple container intended to conditionally store the value |
FeatureSelectionClassifier(clf, mapper, \*\*kwargs) |
This is nothing but a MappedClassifier. |
FractionTailSelector(felements, \*\*kwargs) |
Given a sequence, provide Ids for a fraction of elements |
IterativeFeatureSelection(fmeasure, ...[, ...]) |
Notes |
NBackHistoryStopCrit([bestdetector, steps]) |
Stop computation if for a number of steps error was increasing |
ProxyClassifier(clf, \*\*kwargs) |
Classifier which decorates another classifier |
ProxyMeasure(measure[, skip_train]) |
Wrapper to allow for alternative post-processing of a shared measure. |
RFE(fmeasure, pmeasure, splitter[, ...]) |
Recursive feature elimination. |
Repeater(count[, space]) |
Node that yields the same dataset for a certain number of repetitions. |
Sensitivity(clf[, force_train]) |
Sensitivities of features for a given Classifier. |
SplitRFE(lrn, partitioner, fselector[, ...]) |
RFE with the nested cross-validation to estimate optimal number of features. |
Splitter(attr[, attr_values, count, ...]) |
Generator node for dataset splitting. |
