Package org.apache.wayang.apps.sgd

Class SGDImprovedImpl

java.lang.Object

org.apache.wayang.apps.sgd.SGDImprovedImpl

public class SGDImprovedImpl
extends java.lang.Object

This class executes a stochastic gradient descent optimization on Apache Wayang (incubating), just like SGDImpl. However, it used the MapPartitionsOperator for performance improvements.

Constructor Summary

Constructors

Constructor	Description
SGDImprovedImpl(Configuration configuration, Plugin[] plugins)

Method Summary

Modifier and Type	Method	Description
double[]	apply(java.lang.String datasetUrl, int datasetSize, int features, int maxIterations, double accuracy, int sampleSize)
double[]	apply(java.lang.String datasetUrl, int datasetSize, int features, int maxIterations, double accuracy, int sampleSize, Experiment experiment)

Methods inherited from class java.lang.Object

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

Constructor Detail

SGDImprovedImpl

public SGDImprovedImpl(Configuration configuration,
                       Plugin[] plugins)

Method Detail

apply

public double[] apply(java.lang.String datasetUrl,
                      int datasetSize,
                      int features,
                      int maxIterations,
                      double accuracy,
                      int sampleSize)

apply

public double[] apply(java.lang.String datasetUrl,
                      int datasetSize,
                      int features,
                      int maxIterations,
                      double accuracy,
                      int sampleSize,
                      Experiment experiment)