[jvm-packages]support multiple validation datasets in Spark (#3910)

* 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

* wrap iterators

* enable copartition training and validationset

* add parameters

* converge code path and have init unit test

* enable multi evals for ranking

* unit test and doc

* update example

* fix early stopping

* address the offline comments

* udpate doc

* test eval metrics

* fix compilation issue

* fix example
This commit is contained in:
Nan Zhu
2018-12-17 21:03:57 -08:00
committed by GitHub
parent c8c7b9649c
commit c055a32609
14 changed files with 477 additions and 136 deletions

View File

@@ -222,14 +222,19 @@ public class XGBoost {
if (iter < earlyStoppingRounds - 1) {
return true;
}
float[] criterion = metrics[metrics.length - 1];
for (int shift = 0; shift < earlyStoppingRounds - 1; shift++) {
// the initial value of onTrack is false and if the metrics in any of `earlyStoppingRounds`
// iterations goes to the expected direction, we should consider these `earlyStoppingRounds`
// as `onTrack`
onTrack |= maximizeEvaluationMetrics ?
criterion[iter - shift] >= criterion[iter - shift - 1] :
criterion[iter - shift] <= criterion[iter - shift - 1];
for (int metricsId = metrics.length == 1 ? 0 : 1; metricsId < metrics.length; metricsId++) {
float[] criterion = metrics[metricsId];
for (int shift = 0; shift < earlyStoppingRounds - 1; shift++) {
// the initial value of onTrack is false and if the metrics in any of `earlyStoppingRounds`
// iterations goes to the expected direction, we should consider these `earlyStoppingRounds`
// as `onTrack`
onTrack |= maximizeEvaluationMetrics ?
criterion[iter - shift] >= criterion[iter - shift - 1] :
criterion[iter - shift] <= criterion[iter - shift - 1];
}
if (!onTrack) {
return false;
}
}
return onTrack;
}