org.apache.spark.mllib.tree

Class GradientBoostedTrees

Object

org.apache.spark.mllib.tree.GradientBoostedTrees

All Implemented Interfaces:

java.io.Serializable, Logging

public class GradientBoostedTrees
extends Object
implements scala.Serializable, Logging

:: Experimental :: A class that implements Stochastic Gradient Boosting for regression and binary classification.

The implementation is based upon: J.H. Friedman. "Stochastic Gradient Boosting." 1999.

Notes on Gradient Boosting vs. TreeBoost: - This implementation is for Stochastic Gradient Boosting, not for TreeBoost. - Both algorithms learn tree ensembles by minimizing loss functions. - TreeBoost (Friedman, 1999) additionally modifies the outputs at tree leaf nodes based on the loss function, whereas the original gradient boosting method does not. - When the loss is SquaredError, these methods give the same result, but they could differ for other loss functions.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
GradientBoostedTrees(BoostingStrategy boostingStrategy)

Method Summary

Methods

Modifier and Type	Method and Description
GradientBoostedTreesModel	run(JavaRDD<LabeledPoint> input) Java-friendly API for org.apache.spark.mllib.tree.GradientBoostedTrees!#run.
GradientBoostedTreesModel	run(RDD<LabeledPoint> input) Method to train a gradient boosting model
static GradientBoostedTreesModel	train(JavaRDD<LabeledPoint> input, BoostingStrategy boostingStrategy) Java-friendly API for GradientBoostedTrees$.train(org.apache.spark.rdd.RDD<org.apache.spark.mllib.regression.LabeledPoint>, org.apache.spark.mllib.tree.configuration.BoostingStrategy)
static GradientBoostedTreesModel	train(RDD<LabeledPoint> input, BoostingStrategy boostingStrategy) Method to train a gradient boosting model.

Methods inherited from class Object

equals, 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

GradientBoostedTrees

public GradientBoostedTrees(BoostingStrategy boostingStrategy)

Method Detail

train

public static GradientBoostedTreesModel train(RDD<LabeledPoint> input,
                              BoostingStrategy boostingStrategy)

Method to train a gradient boosting model.

Parameters:

input - Training dataset: RDD of LabeledPoint. For classification, labels should take values {0, 1, ..., numClasses-1}. For regression, labels are real numbers.

boostingStrategy - Configuration options for the boosting algorithm.

Returns:

a gradient boosted trees model that can be used for prediction

train

public static GradientBoostedTreesModel train(JavaRDD<LabeledPoint> input,
                              BoostingStrategy boostingStrategy)

Java-friendly API for GradientBoostedTrees$.train(org.apache.spark.rdd.RDD<org.apache.spark.mllib.regression.LabeledPoint>, org.apache.spark.mllib.tree.configuration.BoostingStrategy)

run

public GradientBoostedTreesModel run(RDD<LabeledPoint> input)

Method to train a gradient boosting model

Parameters:

input - Training dataset: RDD of LabeledPoint.

Returns:

a gradient boosted trees model that can be used for prediction

run

public GradientBoostedTreesModel run(JavaRDD<LabeledPoint> input)

Java-friendly API for org.apache.spark.mllib.tree.GradientBoostedTrees!#run.