Repository: spark Updated Branches: refs/heads/master a7a9b1837 -> 439c69511
[SPARK-24114] Add instrumentation to FPGrowth. ## What changes were proposed in this pull request? Have FPGrowth keep track of model training using the Instrumentation class. ## How was this patch tested? manually Please review http://spark.apache.org/contributing.html before opening a pull request. Author: Bago Amirbekian <b...@databricks.com> Closes #21344 from MrBago/fpgrowth-instr. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/439c6951 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/439c6951 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/439c6951 Branch: refs/heads/master Commit: 439c69511812776cb4b82956547ce958d0669c52 Parents: a7a9b18 Author: Bago Amirbekian <b...@databricks.com> Authored: Thu May 17 13:42:10 2018 -0700 Committer: Joseph K. Bradley <jos...@databricks.com> Committed: Thu May 17 13:42:10 2018 -0700 ---------------------------------------------------------------------- mllib/src/main/scala/org/apache/spark/ml/fpm/FPGrowth.scala | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/439c6951/mllib/src/main/scala/org/apache/spark/ml/fpm/FPGrowth.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/ml/fpm/FPGrowth.scala b/mllib/src/main/scala/org/apache/spark/ml/fpm/FPGrowth.scala index 0bf405d..d7fbe28 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/fpm/FPGrowth.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/fpm/FPGrowth.scala @@ -161,6 +161,8 @@ class FPGrowth @Since("2.2.0") ( private def genericFit[T: ClassTag](dataset: Dataset[_]): FPGrowthModel = { val handlePersistence = dataset.storageLevel == StorageLevel.NONE + val instr = Instrumentation.create(this, dataset) + instr.logParams(params: _*) val data = dataset.select($(itemsCol)) val items = data.where(col($(itemsCol)).isNotNull).rdd.map(r => r.getSeq[Any](0).toArray) val mllibFP = new MLlibFPGrowth().setMinSupport($(minSupport)) @@ -183,7 +185,9 @@ class FPGrowth @Since("2.2.0") ( items.unpersist() } - copyValues(new FPGrowthModel(uid, frequentItems)).setParent(this) + val model = copyValues(new FPGrowthModel(uid, frequentItems)).setParent(this) + instr.logSuccess(model) + model } @Since("2.2.0") --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org