smile.feature

Class GAFeatureSelection

java.lang.Object

smile.feature.GAFeatureSelection

public class GAFeatureSelection
extends java.lang.Object

Genetic algorithm based feature selection. This method finds many (random) subsets of variables of expected classification power using a Genetic Algorithm. The "fitness" of each subset of variables is determined by its ability to classify the samples according to a given classification method. When many such subsets of variables are obtained, the one with best performance may be used as selected features. Alternatively, the frequencies with which variables are selected may be analyzed further. The most frequently selected variables may be presumed to be the most relevant to sample distinction and are finally used for prediction. Although GA avoids brute-force search, it is still much slower than univariate feature selection.

References

1. Leping Li and Clarice R. Weinberg. Gene Selection and Sample Classification Using a Genetic Algorithm/k-Nearest Neighbor Method.

Constructor Summary

Constructors

Constructor and Description
GAFeatureSelection() Constructor.
GAFeatureSelection(GeneticAlgorithm.Selection selection, BitString.Crossover crossover, double crossoverRate, double mutationRate) Constructor.

Method Summary

Modifier and Type	Method and Description
BitString[]	learn(int size, int generation, ClassifierTrainer<double[]> trainer, ClassificationMeasure measure, double[][] x, int[] y, double[][] testx, int[] testy) Genetic algorithm based feature selection for classification.
BitString[]	learn(int size, int generation, ClassifierTrainer<double[]> trainer, ClassificationMeasure measure, double[][] x, int[] y, int k) Genetic algorithm based feature selection for classification.
BitString[]	learn(int size, int generation, RegressionTrainer<double[]> trainer, RegressionMeasure measure, double[][] x, double[] y, double[][] testx, double[] testy) Genetic algorithm based feature selection for regression.
BitString[]	learn(int size, int generation, RegressionTrainer<double[]> trainer, RegressionMeasure measure, double[][] x, double[] y, int k) Genetic algorithm based feature selection for regression.

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

GAFeatureSelection

public GAFeatureSelection()

Constructor.

GAFeatureSelection

public GAFeatureSelection(GeneticAlgorithm.Selection selection,
                          BitString.Crossover crossover,
                          double crossoverRate,
                          double mutationRate)

Constructor.

Parameters:

selection - the selection strategy.

crossover - the strategy of crossover operation.

crossoverRate - the crossover rate.

mutationRate - the mutation rate.

Method Detail

learn

public BitString[] learn(int size,
                         int generation,
                         ClassifierTrainer<double[]> trainer,
                         ClassificationMeasure measure,
                         double[][] x,
                         int[] y,
                         int k)

Genetic algorithm based feature selection for classification.

Parameters:

size - the population size of Genetic Algorithm.

generation - the maximum number of iterations.

trainer - classifier trainer.

measure - classification measure as the chromosome fitness measure.

x - training instances.

y - training labels.

k - k-fold cross validation for the evaluation.

Returns:

bit strings of last generation.

learn

public BitString[] learn(int size,
                         int generation,
                         ClassifierTrainer<double[]> trainer,
                         ClassificationMeasure measure,
                         double[][] x,
                         int[] y,
                         double[][] testx,
                         int[] testy)

Genetic algorithm based feature selection for classification.

Parameters:

size - the population size of Genetic Algorithm.

generation - the maximum number of iterations.

trainer - classifier trainer.

measure - classification measure as the chromosome fitness measure.

x - training instances.

y - training instance labels.

testx - testing instances.

testy - testing instance labels.

Returns:

bit strings of last generation.

learn

public BitString[] learn(int size,
                         int generation,
                         RegressionTrainer<double[]> trainer,
                         RegressionMeasure measure,
                         double[][] x,
                         double[] y,
                         int k)

Genetic algorithm based feature selection for regression.

Parameters:

size - the population size of Genetic Algorithm.

generation - the maximum number of iterations.

trainer - regression model trainer.

measure - classification measure as the chromosome fitness measure.

x - training instances.

y - training instance response variable.

k - k-fold cross validation for the evaluation.

Returns:

bit strings of last generation.

learn

public BitString[] learn(int size,
                         int generation,
                         RegressionTrainer<double[]> trainer,
                         RegressionMeasure measure,
                         double[][] x,
                         double[] y,
                         double[][] testx,
                         double[] testy)

Genetic algorithm based feature selection for regression.

Parameters:

size - the population size of Genetic Algorithm.

generation - the maximum number of iterations.

trainer - regression model trainer.

measure - classification measure as the chromosome fitness measure.

x - training instances.

y - training instance response variable.

testx - testing instances.

testy - testing instance labels.

Returns:

bit strings of last generation.