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

[jvm-packages] Disable fast histo for spark (#2296)

Browse Source 
* add back train method but mark as deprecated

* fix scalastyle error

* disable fast histogram in xgboost4j-spark temporarily
This commit is contained in:
Nan Zhu 2017-05-15 20:43:16 -07:00 committed by GitHub
parent c66ca79221
commit a607f697e3
3 changed files with 13 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
jvm-packages/xgboost4j-spark/src/main/scala/ml/dmlc/xgboost4j/scala/spark/XGBoost.scala
View File

@ -266,6 +266,10 @@ object XGBoost extends Serializable {
trainingData: RDD[MLLabeledPoint], params: Map[String, Any], round: Int,
nWorkers: Int, obj: ObjectiveTrait = null, eval: EvalTrait = null,
useExternalMemory: Boolean = false, missing: Float = Float.NaN): XGBoostModel = {
if (params.contains("tree_method")) {
require(params("tree_method") != "hist", "xgboost4j-spark does not support fast histogram" +
" for now")
}
require(nWorkers > 0, "you must specify more than 0 workers")
if (obj != null) {
require(params.get("obj_type").isDefined, "parameter \"obj_type\" is not defined," +

2
jvm-packages/xgboost4j-spark/src/test/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostDFSuite.scala
View File

@ -194,7 +194,7 @@ class XGBoostDFSuite extends SharedSparkContext with Utils {
assert(xgbEstimatorCopy1.fromParamsToXGBParamMap("eval_metric") === "logloss")
}
test("fast histogram algorithm parameters are exposed correctly") {
ignore("fast histogram algorithm parameters are exposed correctly") {
val paramMap = Map("eta" -> "1", "gamma" -> "0.5", "max_depth" -> "0", "silent" -> "0",
"objective" -> "binary:logistic", "tree_method" -> "hist",
"grow_policy" -> "depthwise", "max_depth" -> "2", "max_bin" -> "2",

13
jvm-packages/xgboost4j-spark/src/test/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostGeneralSuite.scala
View File

@ -23,9 +23,12 @@ import scala.collection.mutable.ListBuffer
import scala.io.Source
import scala.util.Random
import scala.concurrent.duration._
import ml.dmlc.xgboost4j.java.{Rabit, DMatrix => JDMatrix, RabitTracker => PyRabitTracker}
import ml.dmlc.xgboost4j.scala.DMatrix
import ml.dmlc.xgboost4j.scala.rabit.RabitTracker
import org.scalatest.Ignore
import org.apache.spark.SparkContext
import org.apache.spark.ml.feature.LabeledPoint
import org.apache.spark.ml.linalg.{Vectors, Vector => SparkVector}
@ -117,7 +120,7 @@ class XGBoostGeneralSuite extends SharedSparkContext with Utils {
testSetDMatrix) < 0.1)
}
test("test with fast histo depthwise") {
ignore("test with fast histo depthwise") {
val eval = new EvalError()
val trainingRDD = buildTrainingRDD(sc)
val testSet = loadLabelPoints(getClass.getResource("/agaricus.txt.test").getFile).iterator
@ -133,7 +136,7 @@ class XGBoostGeneralSuite extends SharedSparkContext with Utils {
testSetDMatrix) < 0.1)
}
test("test with fast histo lossguide") {
ignore("test with fast histo lossguide") {
val eval = new EvalError()
val trainingRDD = buildTrainingRDD(sc)
val testSet = loadLabelPoints(getClass.getResource("/agaricus.txt.test").getFile).iterator
@ -149,7 +152,7 @@ class XGBoostGeneralSuite extends SharedSparkContext with Utils {
assert(x < 0.1)
}
test("test with fast histo lossguide with max bin") {
ignore("test with fast histo lossguide with max bin") {
val eval = new EvalError()
val trainingRDD = buildTrainingRDD(sc)
val testSet = loadLabelPoints(getClass.getResource("/agaricus.txt.test").getFile).iterator
@ -166,7 +169,7 @@ class XGBoostGeneralSuite extends SharedSparkContext with Utils {
assert(x < 0.1)
}
test("test with fast histo depthwidth with max depth") {
ignore("test with fast histo depthwidth with max depth") {
val eval = new EvalError()
val trainingRDD = buildTrainingRDD(sc)
val testSet = loadLabelPoints(getClass.getResource("/agaricus.txt.test").getFile).iterator
@ -183,7 +186,7 @@ class XGBoostGeneralSuite extends SharedSparkContext with Utils {
assert(x < 0.1)
}
test("test with fast histo depthwidth with max depth and max bin") {
ignore("test with fast histo depthwidth with max depth and max bin") {
val eval = new EvalError()
val trainingRDD = buildTrainingRDD(sc)
val testSet = loadLabelPoints(getClass.getResource("/agaricus.txt.test").getFile).iterator