Hello,
I am trying to use the Flink implementation of XGBoost, but I am facing some problems I cannot solve. Just using the “DistTrainWithFlink.scala” class I get the following exception:
Tracker started, with env={DMLC_NUM_SERVER=0, DMLC_TRACKER_URI=192.168.1.12, DMLC_TRACKER_PORT=9092, DMLC_NUM_WORKER=8}
Exception in thread “main” org.apache.flink.runtime.client.JobExecutionException: Job execution failed.
at org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:146)
at org.apache.flink.runtime.minicluster.MiniCluster.executeJobBlocking(MiniCluster.java:647)
at org.apache.flink.client.LocalExecutor.executePlan(LocalExecutor.java:223)
at org.apache.flink.api.java.LocalEnvironment.execute(LocalEnvironment.java:91)
at org.apache.flink.api.java.ExecutionEnvironment.execute(ExecutionEnvironment.java:817)
at org.apache.flink.api.scala.ExecutionEnvironment.execute(ExecutionEnvironment.scala:525)
at org.apache.flink.api.scala.DataSet.collect(DataSet.scala:737)
at ml.dmlc.xgboost4j.scala.flink.XGBoost$.train(XGBoost.scala:93)
at ml.dmlc.xgboost4j.scala.example.flink.DistTrainWithFlink$.main(DistTrainWithFlink.scala:37)
at ml.dmlc.xgboost4j.scala.example.flink.DistTrainWithFlink.main(DistTrainWithFlink.scala)
Caused by: java.lang.IllegalArgumentException: requirement failed: -1 not in [0, 125)
at scala.Predef$.require(Predef.scala:281)
at org.apache.flink.ml.math.SparseVector$.$anonfun$fromCOO$1(SparseVector.scala:202)
at org.apache.flink.ml.math.SparseVector$.$anonfun$fromCOO$1$adapted(SparseVector.scala:201)
at scala.collection.IndexedSeqOptimized.foreach(IndexedSeqOptimized.scala:36)
at scala.collection.IndexedSeqOptimized.foreach$(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:198)
at org.apache.flink.ml.math.SparseVector$.fromCOO(SparseVector.scala:201)
at org.apache.flink.ml.MLUtils$$anon$5.map(MLUtils.scala:101)
at org.apache.flink.ml.MLUtils$$anon$5.map(MLUtils.scala:93)
at org.apache.flink.runtime.operators.MapDriver.run(MapDriver.java:103)
at org.apache.flink.runtime.operators.BatchTask.run(BatchTask.java:503)
at org.apache.flink.runtime.operators.BatchTask.invoke(BatchTask.java:368)
at org.apache.flink.runtime.taskmanager.Task.run(Task.java:704)
at java.lang.Thread.run(Thread.java:748)
task 6 connected to the tracker
task 5 connected to the tracker
task 0 connected to the tracker
task 2 connected to the tracker
task 3 connected to the tracker
task 4 connected to the tracker
task 7 connected to the tracker
task 1 connected to the tracker
task 6 got new rank 0
task 5 got new rank 1
task 0 got new rank 2
task 2 got new rank 3
task 3 got new rank 4
task 4 got new rank 5
task 7 got new rank 6
task 1 got new rank 7
Process finished with exit code 1
The training and test files were created as described in the binary classification example and do NOT contain any value with “-1”. What am I doing wrong? I am using the 1.0.0 version of XGBoost.