imatiach-msft commented on a change in pull request #21632:
[SPARK-19591][ML][MLlib] Add sample weights to decision trees
URL: https://github.com/apache/spark/pull/21632#discussion_r250458538
##########
File path:
mllib/src/test/scala/org/apache/spark/ml/tree/impl/RandomForestSuite.scala
##########
@@ -700,6 +722,56 @@ class RandomForestSuite extends SparkFunSuite with
MLlibTestSparkContext {
assert(unprunedTree.numNodes === 5)
assert(RandomForestSuite.getSumLeafCounters(List(prunedTree.rootNode)) ===
arr.size)
}
+
+ test("weights at arbitrary scale") {
+ val arr = EnsembleTestHelper.generateOrderedLabeledPoints(3, 10)
+ val rddWithUnitWeights = sc.parallelize(arr.map(_.asML.toInstance))
+ val rddWithSmallWeights = rddWithUnitWeights.map { inst =>
+ Instance(inst.label, 0.001, inst.features)
+ }
+ val rddWithBigWeights = rddWithUnitWeights.map { inst =>
+ Instance(inst.label, 1000, inst.features)
+ }
+ val strategy = new OldStrategy(OldAlgo.Classification, Gini, 3, 2)
+ val unitWeightTrees = RandomForest.run(rddWithUnitWeights, strategy, 3,
"all", 42L, None)
+
+ val smallWeightTrees = RandomForest.run(rddWithSmallWeights, strategy, 3,
"all", 42L, None)
+ unitWeightTrees.zip(smallWeightTrees).foreach { case (unitTree,
smallWeightTree) =>
+ TreeTests.checkEqual(unitTree, smallWeightTree)
+ }
+
+ val bigWeightTrees = RandomForest.run(rddWithBigWeights, strategy, 3,
"all", 42L, None)
+ unitWeightTrees.zip(bigWeightTrees).foreach { case (unitTree,
bigWeightTree) =>
+ TreeTests.checkEqual(unitTree, bigWeightTree)
+ }
+ }
+
+ test("minWeightFraction and minInstancesPerNode") {
+ val data = Array(
+ Instance(0.0, 1.0, Vectors.dense(0.0)),
+ Instance(0.0, 1.0, Vectors.dense(0.0)),
+ Instance(0.0, 1.0, Vectors.dense(0.0)),
+ Instance(0.0, 1.0, Vectors.dense(0.0)),
+ Instance(1.0, 0.1, Vectors.dense(1.0))
+ )
+ val rdd = sc.parallelize(data)
+ val strategy = new OldStrategy(OldAlgo.Classification, Gini, 3, 2,
+ minWeightFractionPerNode = 0.5)
+ val Array(tree1) = RandomForest.run(rdd, strategy, 1, "all", 42L, None)
+ assert(tree1.depth == 0)
Review comment:
done!
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
