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

[Blocking][jvm-packages] fix the early stopping feature (#3808)

Browse Source 
* add back train method but mark as deprecated

* add back train method but mark as deprecated

* add back train method but mark as deprecated

* add back train method but mark as deprecated

* fix scalastyle error

* fix scalastyle error

* fix scalastyle error

* fix scalastyle error

* temp

* add method for classifier and regressor

* update tutorial

* address the comments

* update
This commit is contained in:
Nan Zhu
2018-10-23 14:53:13 -07:00
committed by GitHub
parent e26b5d63b2
commit 4ae225a08d
7 changed files with 134 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
jvm-packages/xgboost4j-spark/src/main/scala/ml/dmlc/xgboost4j/scala/spark/XGBoost.scala
View File

@@ -132,6 +132,11 @@ object XGBoost extends Serializable {
try {
val numEarlyStoppingRounds = params.get("num_early_stopping_rounds")
.map(_.toString.toInt).getOrElse(0)
if (numEarlyStoppingRounds > 0) {
if (!params.contains("maximize_evaluation_metrics")) {
throw new IllegalArgumentException("maximize_evaluation_metrics has to be specified")
}
}
val metrics = Array.tabulate(watches.size)(_ => Array.ofDim[Float](round))
val booster = SXGBoost.train(watches.train, params, round,
watches.toMap, metrics, obj, eval,

3
jvm-packages/xgboost4j-spark/src/main/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostClassifier.scala
View File

@@ -140,6 +140,9 @@ class XGBoostClassifier (
def setNumEarlyStoppingRounds(value: Int): this.type = set(numEarlyStoppingRounds, value)
def setMaximizeEvaluationMetrics(value: Boolean): this.type =
set(maximizeEvaluationMetrics, value)
def setCustomObj(value: ObjectiveTrait): this.type = set(customObj, value)
def setCustomEval(value: EvalTrait): this.type = set(customEval, value)

3
jvm-packages/xgboost4j-spark/src/main/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostRegressor.scala
View File

@@ -140,6 +140,9 @@ class XGBoostRegressor (
def setNumEarlyStoppingRounds(value: Int): this.type = set(numEarlyStoppingRounds, value)
def setMaximizeEvaluationMetrics(value: Boolean): this.type =
set(maximizeEvaluationMetrics, value)
def setCustomObj(value: ObjectiveTrait): this.type = set(customObj, value)
def setCustomEval(value: EvalTrait): this.type = set(customEval, value)

7
jvm-packages/xgboost4j-spark/src/main/scala/ml/dmlc/xgboost4j/scala/spark/params/LearningTaskParams.scala
View File

@@ -87,6 +87,13 @@ private[spark] trait LearningTaskParams extends Params {
final def getNumEarlyStoppingRounds: Int = $(numEarlyStoppingRounds)
final val maximizeEvaluationMetrics = new BooleanParam(this, "maximizeEvaluationMetrics",
"define the expected optimization to the evaluation metrics, true to maximize otherwise" +
" minimize it")
final def getMaximizeEvaluationMetrics: Boolean = $(maximizeEvaluationMetrics)
setDefault(objective -> "reg:linear", baseScore -> 0.5,
trainTestRatio -> 1.0, numEarlyStoppingRounds -> 0)
}