org.apache.spark.mllib.classification

Class LogisticRegressionWithLBFGS

java.lang.Object

org.apache.spark.mllib.regression.GeneralizedLinearAlgorithm<LogisticRegressionModel>

org.apache.spark.mllib.classification.LogisticRegressionWithLBFGS

All Implemented Interfaces:

java.io.Serializable, Logging

public class LogisticRegressionWithLBFGS
extends GeneralizedLinearAlgorithm<LogisticRegressionModel>
implements scala.Serializable

Train a classification model for Multinomial/Binary Logistic Regression using Limited-memory BFGS. Standard feature scaling and L2 regularization are used by default. NOTE: Labels used in Logistic Regression should be {0, 1, ..., k - 1} for k classes multi-label classification problem.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
LogisticRegressionWithLBFGS()

Method Summary

Methods

Modifier and Type	Method and Description
protected LogisticRegressionModel	createModel(Vector weights, double intercept) Create a model given the weights and intercept
LBFGS	optimizer() The optimizer to solve the problem.
LogisticRegressionWithLBFGS	setNumClasses(int numClasses) :: Experimental :: Set the number of possible outcomes for k classes classification problem in Multinomial Logistic Regression.
protected scala.collection.immutable.List<scala.Function1<RDD<LabeledPoint>,java.lang.Object>>	validators()

Methods inherited from class org.apache.spark.mllib.regression.GeneralizedLinearAlgorithm

addIntercept, getNumFeatures, isAddIntercept, numFeatures, numOfLinearPredictor, run, run, setIntercept, setValidateData, validateData

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.spark.Logging

initializeIfNecessary, initializeLogging, isTraceEnabled, log_, log, logDebug, logDebug, logError, logError, logInfo, logInfo, logName, logTrace, logTrace, logWarning, logWarning

Constructor Detail

LogisticRegressionWithLBFGS

public LogisticRegressionWithLBFGS()

Method Detail

optimizer

public LBFGS optimizer()

Description copied from class: GeneralizedLinearAlgorithm

The optimizer to solve the problem.

Specified by:

optimizer in class GeneralizedLinearAlgorithm<LogisticRegressionModel>

Returns:

(undocumented)

validators

protected scala.collection.immutable.List<scala.Function1<RDD<LabeledPoint>,java.lang.Object>> validators()

Overrides:

validators in class GeneralizedLinearAlgorithm<LogisticRegressionModel>

setNumClasses

public LogisticRegressionWithLBFGS setNumClasses(int numClasses)

:: Experimental :: Set the number of possible outcomes for k classes classification problem in Multinomial Logistic Regression. By default, it is binary logistic regression so k will be set to 2.

Parameters:

numClasses - (undocumented)

Returns:

(undocumented)

createModel

protected LogisticRegressionModel createModel(Vector weights,
                                  double intercept)

Description copied from class: GeneralizedLinearAlgorithm

Create a model given the weights and intercept

Specified by:

createModel in class GeneralizedLinearAlgorithm<LogisticRegressionModel>

Parameters:

weights - (undocumented)

intercept - (undocumented)

Returns:

(undocumented)