Skip to content

[SPARK-24290][ML] add support for Array input for instrumentation.logNamedValue #21347

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

[SPARK-24290][ML] add support for Array input for instrumentation.logNamedValue #21347

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a98fbc3
add support for Array input for instrumentation.logNamedValue
lu-wang-dl May 16, 2018
759a234
change the way to log the array to a JSON string
lu-wang-dl Jun 4, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,8 +276,7 @@ class BisectingKMeans @Since("2.0.0") (
val summary = new BisectingKMeansSummary(
model.transform(dataset), $(predictionCol), $(featuresCol), $(k))
model.setSummary(Some(summary))
// TODO: need to extend logNamedValue to support Array
instr.logNamedValue("clusterSizes", summary.clusterSizes.mkString("[", ",", "]"))
instr.logNamedValue("clusterSizes", summary.clusterSizes)
instr.logSuccess(model)
model
}
Expand Down
3 changes: 1 addition & 2 deletions mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -426,8 +426,7 @@ class GaussianMixture @Since("2.0.0") (
$(predictionCol), $(probabilityCol), $(featuresCol), $(k), logLikelihood)
model.setSummary(Some(summary))
instr.logNamedValue("logLikelihood", logLikelihood)
// TODO: need to extend logNamedValue to support Array
instr.logNamedValue("clusterSizes", summary.clusterSizes.mkString("[", ",", "]"))
instr.logNamedValue("clusterSizes", summary.clusterSizes)
instr.logSuccess(model)
model
}
Expand Down
3 changes: 1 addition & 2 deletions mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -359,8 +359,7 @@ class KMeans @Since("1.5.0") (
model.transform(dataset), $(predictionCol), $(featuresCol), $(k))

model.setSummary(Some(summary))
// TODO: need to extend logNamedValue to support Array
instr.logNamedValue("clusterSizes", summary.clusterSizes.mkString("[", ",", "]"))
instr.logNamedValue("clusterSizes", summary.clusterSizes)
instr.logSuccess(model)
if (handlePersistence) {
instances.unpersist()
Expand Down
13 changes: 13 additions & 0 deletions mllib/src/main/scala/org/apache/spark/ml/util/Instrumentation.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,6 +125,19 @@ private[spark] class Instrumentation[E <: Estimator[_]] private (
log(compact(render(name -> value)))
}

def logNamedValue(name: String, value: Array[String]): Unit = {
log(compact(render(name -> compact(render(value.toSeq)))))
}

def logNamedValue(name: String, value: Array[Long]): Unit = {
log(compact(render(name -> compact(render(value.toSeq)))))
}

def logNamedValue(name: String, value: Array[Double]): Unit = {
log(compact(render(name -> compact(render(value.toSeq)))))
}


/**
* Logs the successful completion of the training session.
*/
Expand Down