xgboost/jvm-packages/README.md

XGBoost4J: Distributed XGBoost for Scala/Java

Documentation | Resources | Release Notes

XGBoost4J is the JVM package of xgboost. It brings all the optimizations and power xgboost into JVM ecosystem.

• Train XGBoost models on scala and java with easy customizations.
• Run distributed xgboost natively on jvm frameworks such as Flink and Spark.

You can find more about XGBoost on Documentation and Resource Page.

Hello World

XGBoost Scala

import ml.dmlc.xgboost4j.scala.DMatrix
import ml.dmlc.xgboost4j.scala.XGBoost

object XGBoostScalaExample {
  def main(args: Array[String]) {
    // read trainining data, available at xgboost/demo/data
    val trainData =
      new DMatrix("/path/to/agaricus.txt.train")
    // define parameters
    val paramMap = List(
      "eta" -> 0.1,
      "max_depth" -> 2,
      "objective" -> "binary:logistic").toMap
    // number of iterations
    val round = 2
    // train the model
    val model = XGBoost.train(paramMap, trainData, round)
    // run prediction
    val predTrain = model.predict(trainData)
    // save model to the file.
    model.saveModel("/local/path/to/model")
  }
}

XGBoost Flink

import ml.dmlc.xgboost4j.scala.flink.XGBoost
import org.apache.flink.api.scala._
import org.apache.flink.api.scala.ExecutionEnvironment
import org.apache.flink.ml.MLUtils

object DistTrainWithFlink {
  def main(args: Array[String]) {
    val env: ExecutionEnvironment = ExecutionEnvironment.getExecutionEnvironment
    // read trainining data
    val trainData =
      MLUtils.readLibSVM(env, "/path/to/data/agaricus.txt.train")
    // define parameters
    val paramMap = List(
      "eta" -> 0.1,
      "max_depth" -> 2,
      "objective" -> "binary:logistic").toMap
    // number of iterations
    val round = 2
    // train the model
    val model = XGBoost.train(paramMap, trainData, round)
    val predTrain = model.predict(trainData.map{x => x.vector})
    model.saveModelToHadoop("file:///path/to/xgboost.model")
  }
}

XGBoost Spark