From c25dd80c09507b2443c753213309b089366bb532 Mon Sep 17 00:00:00 2001
From: Uros Bojanic <221401595+uros-b@users.noreply.github.com>
Date: Wed, 2 Sep 2026 09:46:50 +0000
Subject: [PATCH 1/2] [SPARK-59173][ML] Use isEmpty instead of size == 0 in
 MLlib

---
 .../src/main/scala/org/apache/spark/ml/tree/treeModels.scala  | 2 +-
 .../scala/org/apache/spark/ml/recommendation/ALSSuite.scala   | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala b/mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala
index 5f45cc3315621..b230a18ee0642 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala
@@ -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
diff --git a/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala
index a5bff057bfec8..58cc9900d90de 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala
@@ -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(

From 55f6b5821e20e6fa447fb88d6eb439f2db5a94f2 Mon Sep 17 00:00:00 2001
From: Uros Bojanic <221401595+uros-b@users.noreply.github.com>
Date: Wed, 2 Sep 2026 10:19:35 +0000
Subject: [PATCH 2/2] Use nonEmpty for size > 0 checks

---
 .../org/apache/spark/ml/tree/impl/DecisionTreeMetadata.scala    | 2 +-
 .../org/apache/spark/mllib/tree/configuration/Strategy.scala    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/tree/impl/DecisionTreeMetadata.scala b/mllib/src/main/scala/org/apache/spark/ml/tree/impl/DecisionTreeMetadata.scala
index 181168385011d..ead7b4d27f46d 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/tree/impl/DecisionTreeMetadata.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/tree/impl/DecisionTreeMetadata.scala
@@ -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)
 
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala
index c1f82157e82f2..ab6c6f7467563 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala
@@ -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