Skip to content
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

[SPARK-24155][ML] Instrumentation improvements for clustering #21218

Closed
wants to merge 4 commits into from
Closed

[SPARK-24155][ML] Instrumentation improvements for clustering #21218

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
1810dbe
instrumentation improvement for clustering
lu-wang-dl May 2, 2018
07c20a4
add more info for instrument
lu-wang-dl May 2, 2018
9053281
change the bug for logging clustersizes
lu-wang-dl May 3, 2018
4e2cb81
change the mkString and add TODO for logging Array "ClusterSizes"
lu-wang-dl May 11, 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
7 changes: 5 additions & 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 @@ -264,8 +264,9 @@ class BisectingKMeans @Since("2.0.0") (
case Row(point: Vector) => OldVectors.fromML(point)
}

val instr = Instrumentation.create(this, rdd)
instr.logParams(featuresCol, predictionCol, k, maxIter, seed, minDivisibleClusterSize)
val instr = Instrumentation.create(this, dataset)
instr.logParams(featuresCol, predictionCol, k, maxIter, seed,
minDivisibleClusterSize, distanceMeasure)

val bkm = new MLlibBisectingKMeans()
.setK($(k))
Expand All @@ -278,6 +279,8 @@ 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.logSuccess(model)
model
}
Expand Down
5 changes: 4 additions & 1 deletion 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 @@ -350,7 +350,7 @@ class GaussianMixture @Since("2.0.0") (
s"than ${GaussianMixture.MAX_NUM_FEATURES} features because the size of the covariance" +
s" matrix is quadratic in the number of features.")

val instr = Instrumentation.create(this, instances)
val instr = Instrumentation.create(this, dataset)
instr.logParams(featuresCol, predictionCol, probabilityCol, k, maxIter, seed, tol)
instr.logNumFeatures(numFeatures)

Expand Down Expand Up @@ -423,6 +423,9 @@ class GaussianMixture @Since("2.0.0") (
val summary = new GaussianMixtureSummary(model.transform(dataset),
$(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.logSuccess(model)
model
}
Expand Down
4 changes: 3 additions & 1 deletion 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 @@ -361,7 +361,7 @@ class KMeans @Since("1.5.0") (
instances.persist(StorageLevel.MEMORY_AND_DISK)
}

val instr = Instrumentation.create(this, instances)
val instr = Instrumentation.create(this, dataset)
instr.logParams(featuresCol, predictionCol, k, initMode, initSteps, distanceMeasure,
maxIter, seed, tol)
val algo = new MLlibKMeans()
Expand All @@ -378,6 +378,8 @@ 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.logSuccess(model)
if (handlePersistence) {
instances.unpersist()
Expand Down