Skip to content

[SPARK-59173][ML] Use isEmpty/nonEmpty instead of size comparisons in MLlib #58471

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
uros-b wants to merge 2 commits into from
Closed

[SPARK-59173][ML] Use isEmpty/nonEmpty instead of size comparisons in MLlib #58471

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
c25dd80
[SPARK-59173][ML] Use isEmpty instead of size == 0 in MLlib
uros-b Sep 2, 2026
55f6b58
Use nonEmpty for size > 0 checks
uros-b Sep 2, 2026
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
2 changes: 1 addition & 1 deletion mllib/src/main/scala/org/apache/spark/ml/tree/impl/DecisionTreeMetadata.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@ private[spark] class DecisionTreeMetadata(

def isMulticlass: Boolean = numClasses > 2

def isMulticlassWithCategoricalFeatures: Boolean = isMulticlass && (featureArity.size > 0)
def isMulticlassWithCategoricalFeatures: Boolean = isMulticlass && (featureArity.nonEmpty)

def isCategorical(featureIndex: Int): Boolean = featureArity.contains(featureIndex)

Expand Down
2 changes: 1 addition & 1 deletion mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -229,7 +229,7 @@ private[ml] object TreeEnsembleModel {
maxFeatureIndex + 1
}
if (d == 0) {
assert(totalImportances.size == 0, s"Unknown error in computing feature" +
assert(totalImportances.isEmpty, s"Unknown error in computing feature" +
s" importance: No splits found, but some non-zero importances.")
}
val (indices, values) = totalImportances.iterator.toSeq.sortBy(_._1).unzip
Expand Down
2 changes: 1 addition & 1 deletion mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,7 +98,7 @@ class Strategy @Since("1.3.0") (
*/
@Since("1.2.0")
def isMulticlassWithCategoricalFeatures: Boolean = {
isMulticlassClassification && (categoricalFeaturesInfo.size > 0)
isMulticlassClassification && (categoricalFeaturesInfo.nonEmpty)
}

// scalastyle:off argcount
Expand Down
4 changes: 2 additions & 2 deletions mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -995,8 +995,8 @@ class ALSSuite extends MLTest with DefaultReadWriteTest with Logging {
val shuffledItemFactors = getShuffledDependencies(itemFactors.rdd).filter { dep =>
dep.rdd.name != null && dep.rdd.name.contains("itemFactors")
}
assert(shuffledUserFactors.size == 0)
assert(shuffledItemFactors.size == 0)
assert(shuffledUserFactors.isEmpty)
assert(shuffledItemFactors.isEmpty)
}

private def checkRecommendations(
Expand Down