Want to switch Decision Trees to Neural Net in Random Forest to make avNNet ?
There is no curse in elvish, entish or the tongues of men for this treachery.
But it's easy now !
val randomForest = new BaggingClassifier() .setBaseLearner(new DecisionTreeClassifier())
val avNNet = new BaggingClassifier() .setBaseLearner(new MultiLayerPerceptronClassifier())
Le classico of meta-algorithms have been implemented in this library as closely as described in the papers of the original authors.
Here is the current list :
They all work with Multiclass Classification and Regression.
Ready to Install ?
Download the dependency from Maven Central
libraryDependencies += "com.github.pierrenodet" %% "spark-ensemble" % "0.8.0"
<dependency> <groupId>com.github.pierrenodet</groupId> <artifactId>spark-ensemble_2.12</artifactId> <version>0.8.0</version> </dependency>