Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix examples

Browse Source
This commit is contained in:
CodingCat
2016-03-11 13:57:03 -05:00
parent aca0096b33
commit ab68a0ccc7
5 changed files with 29 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
jvm-packages/xgboost4j-example/src/main/scala/ml/dmlc/xgboost4j/scala/example/flink/DistTrainWithFlink.scala
View File

@@ -34,7 +34,7 @@ object DistTrainWithFlink {
// number of iterations
val round = 2
// train the model
val model = XGBoost.train(paramMap, trainData, round)
val model = XGBoost.train(trainData, paramMap, round)
val predTest = model.predict(testData.map{x => x.vector})
model.saveModelAsHadoopFile("file:///path/to/xgboost.model")
}

17
jvm-packages/xgboost4j-example/src/main/scala/ml/dmlc/xgboost4j/scala/example/spark/DistTrainWithSpark.scala
View File

@@ -16,29 +16,34 @@
package ml.dmlc.xgboost4j.scala.example.spark
import ml.dmlc.xgboost4j.scala.spark.XGBoost
import ml.dmlc.xgboost4j.scala.DMatrix
import ml.dmlc.xgboost4j.scala.spark.{DataUtils, XGBoost}
import org.apache.spark.SparkContext
import org.apache.spark.mllib.util.MLUtils
object DistTrainWithSpark {
def main(args: Array[String]): Unit = {
if (args.length != 4) {
if (args.length != 5) {
println(
"usage: program num_of_rounds num_workers training_path model_path")
"usage: program num_of_rounds num_workers training_path test_path model_path")
sys.exit(1)
}
val sc = new SparkContext()
val inputTrainPath = args(2)
val outputModelPath = args(3)
val inputTestPath = args(3)
val outputModelPath = args(4)
// number of iterations
val numRound = args(0).toInt
val trainRDD = MLUtils.loadLibSVMFile(sc, inputTrainPath).repartition(args(1).toInt)
import DataUtils._
val trainRDD = MLUtils.loadLibSVMFile(sc, inputTrainPath)
val testSet = MLUtils.loadLibSVMFile(sc, inputTestPath).collect().iterator
// training parameters
val paramMap = List(
"eta" -> 0.1f,
"max_depth" -> 2,
"objective" -> "binary:logistic").toMap
val xgboostModel = XGBoost.train(trainRDD, paramMap, numRound)
val xgboostModel = XGBoost.train(trainRDD, paramMap, numRound, nWorkers = args(1).toInt)
xgboostModel.predict(new DMatrix(testSet))
// save model to HDFS path
xgboostModel.saveModelAsHadoopFile(outputModelPath)
}