public class StackedAutoencodersClassifier extends Object implements Serializable
Constructor and Description |
---|
StackedAutoencodersClassifier() |
Modifier and Type | Method and Description |
---|---|
org.apache.spark.api.java.JavaPairRDD<Double,Double> |
test(org.apache.spark.api.java.JavaSparkContext ctxt,
hex.deeplearning.DeepLearningModel deeplearningModel,
org.apache.spark.api.java.JavaRDD<org.apache.spark.mllib.regression.LabeledPoint> test)
This method applies a stacked autoencoders model to a given dataset and make predictions
|
hex.deeplearning.DeepLearningModel |
train(org.apache.spark.api.java.JavaRDD<org.apache.spark.mllib.regression.LabeledPoint> trainData,
int batchSize,
int[] layerSizes,
String activationType,
int epochs,
String responseColumn,
long modelID)
This method trains a stacked autoencoder
|
public hex.deeplearning.DeepLearningModel train(org.apache.spark.api.java.JavaRDD<org.apache.spark.mllib.regression.LabeledPoint> trainData, int batchSize, int[] layerSizes, String activationType, int epochs, String responseColumn, long modelID)
trainData
- Training dataset as a JavaRDDbatchSize
- Size of a training mini-batchlayerSizes
- Number of neurons for each layerepochs
- Number of epochs to trainresponseColumn
- Name of the response columnmodelID
- Id of the modelpublic org.apache.spark.api.java.JavaPairRDD<Double,Double> test(org.apache.spark.api.java.JavaSparkContext ctxt, hex.deeplearning.DeepLearningModel deeplearningModel, org.apache.spark.api.java.JavaRDD<org.apache.spark.mllib.regression.LabeledPoint> test) throws MLModelBuilderException
ctxt
- JavaSparkContextdeeplearningModel
- Stacked Autoencoders modeltest
- Testing dataset as a JavaRDD of labeled pointsMLModelBuilderException
Copyright © 2015 WSO2, Inc.. All Rights Reserved.