smile.classification

Class LogisticRegression.Trainer

java.lang.Object

smile.classification.ClassifierTrainer<double[]>

smile.classification.LogisticRegression.Trainer

Enclosing class:

LogisticRegression

public static class LogisticRegression.Trainer
extends ClassifierTrainer<double[]>

Trainer for logistic regression.

Constructor Summary

Constructors

Constructor and Description
Trainer() Constructor.

Method Summary

Modifier and Type	Method and Description
LogisticRegression.Trainer	setMaxNumIteration(int maxIter) Sets the maximum number of iterations.
LogisticRegression.Trainer	setRegularizationFactor(double lambda) Sets the regularization factor.
LogisticRegression.Trainer	setTolerance(double tol) Sets the tolerance for BFGS stopping iterations.
LogisticRegression	train(double[][] x, int[] y) Learns a classifier with given training data.

Methods inherited from class smile.classification.ClassifierTrainer

setAttributes

Methods inherited from class java.lang.Object

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

Constructor Detail

Trainer

public Trainer()

Constructor.

Method Detail

setRegularizationFactor

public LogisticRegression.Trainer setRegularizationFactor(double lambda)

Sets the regularization factor. λ > 0 gives a "regularized" estimate of linear weights which often has superior generalization performance, especially when the dimensionality is high.

Parameters:

lambda - regularization factor.

setTolerance

public LogisticRegression.Trainer setTolerance(double tol)

Sets the tolerance for BFGS stopping iterations.

Parameters:

tol - the tolerance for stopping iterations.

setMaxNumIteration

public LogisticRegression.Trainer setMaxNumIteration(int maxIter)

Sets the maximum number of iterations.

Parameters:

maxIter - the maximum number of iterations.

train

public LogisticRegression train(double[][] x,
                                int[] y)

Description copied from class: ClassifierTrainer

Learns a classifier with given training data.

Specified by:

train in class ClassifierTrainer<double[]>

Parameters:

x - the training instances.

y - the training labels.

Returns:

a trained classifier.