Package org.tribuo.classification.sgd.linear

Class LogisticRegressionTrainer

java.lang.Object

org.tribuo.common.sgd.AbstractSGDTrainer<T,U,V,LinearParameters>

org.tribuo.common.sgd.AbstractLinearSGDTrainer<Label,Integer,LinearSGDModel>

org.tribuo.classification.sgd.linear.LinearSGDTrainer

org.tribuo.classification.sgd.linear.LogisticRegressionTrainer

All Implemented Interfaces:

com.oracle.labs.mlrg.olcut.config.Configurable, com.oracle.labs.mlrg.olcut.provenance.Provenancable<TrainerProvenance>, Trainer<Label>, WeightedExamples

public class LogisticRegressionTrainer
extends LinearSGDTrainer

A logistic regression trainer that uses a reasonable objective, optimiser, number of epochs and minibatch size. If you wish to modify any of these aspects, you can create your own LinearSGDTrainer.

This is strictly a convenience class for folks who are looking for a simple logistic regression.

Field Summary

Fields inherited from class org.tribuo.common.sgd.AbstractSGDTrainer

addBias, epochs, loggingInterval, minibatchSize, optimiser, rng, seed, shuffle

Fields inherited from interface org.tribuo.Trainer

DEFAULT_SEED, INCREMENT_INVOCATION_COUNT

Constructor Summary

Constructors

Constructor	Description
LogisticRegressionTrainer()	Constructs a simple logistic regression, using AdaGrad with a learning rate of 1.0 as the gradient optimizer, training for 5 epochs.

Method Summary

Methods inherited from class org.tribuo.classification.sgd.linear.LinearSGDTrainer

createModel, getModelClassName, getObjective, getTarget, toString

Methods inherited from class org.tribuo.common.sgd.AbstractLinearSGDTrainer

createParameters, getName

Methods inherited from class org.tribuo.common.sgd.AbstractSGDTrainer

getInvocationCount, getProvenance, postConfig, setInvocationCount, setShuffle, shuffleInPlace, train, train, train

Methods inherited from class java.lang.Object

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

Constructor Details

LogisticRegressionTrainer

public LogisticRegressionTrainer()

Constructs a simple logistic regression, using AdaGrad with a learning rate of 1.0 as the gradient optimizer, training for 5 epochs. It's equivalent to this: new LinearSGDTrainer(new LogMulticlass(), new AdaGrad(1.0, 0.1), 5, Trainer.DEFAULT_SEED);