Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/7804#discussion_r35925352
--- Diff:
mllib/src/test/scala/org/apache/spark/mllib/tree/GradientBoostedTreesSuite.scala
---
@@ -166,43 +166,59 @@ class GradientBoostedTreesSuite extends SparkFunSuite
with MLlibTestSparkContext
val algos = Array(Regression, Regression, Classification)
val losses = Array(SquaredError, AbsoluteError, LogLoss)
- (algos zip losses) map {
- case (algo, loss) => {
- val treeStrategy = new Strategy(algo = algo, impurity = Variance,
maxDepth = 2,
- categoricalFeaturesInfo = Map.empty)
- val boostingStrategy =
- new BoostingStrategy(treeStrategy, loss, numIterations,
validationTol = 0.0)
- val gbtValidate = new GradientBoostedTrees(boostingStrategy)
- .runWithValidation(trainRdd, validateRdd)
- val numTrees = gbtValidate.numTrees
- assert(numTrees !== numIterations)
-
- // Test that it performs better on the validation dataset.
- val gbt = new GradientBoostedTrees(boostingStrategy).run(trainRdd)
- val (errorWithoutValidation, errorWithValidation) = {
- if (algo == Classification) {
- val remappedRdd = validateRdd.map(x => new LabeledPoint(2 *
x.label - 1, x.features))
- (loss.computeError(gbt, remappedRdd),
loss.computeError(gbtValidate, remappedRdd))
- } else {
- (loss.computeError(gbt, validateRdd),
loss.computeError(gbtValidate, validateRdd))
- }
- }
- assert(errorWithValidation <= errorWithoutValidation)
-
- // Test that results from evaluateEachIteration comply with
runWithValidation.
- // Note that convergenceTol is set to 0.0
- val evaluationArray = gbt.evaluateEachIteration(validateRdd, loss)
- assert(evaluationArray.length === numIterations)
- assert(evaluationArray(numTrees) > evaluationArray(numTrees - 1))
- var i = 1
- while (i < numTrees) {
- assert(evaluationArray(i) <= evaluationArray(i - 1))
- i += 1
+ algos.zip(losses).foreach { case (algo, loss) =>
+ val treeStrategy = new Strategy(algo = algo, impurity = Variance,
maxDepth = 2,
+ categoricalFeaturesInfo = Map.empty)
+ val boostingStrategy =
+ new BoostingStrategy(treeStrategy, loss, numIterations,
validationTol = 0.0)
+ val gbtValidate = new GradientBoostedTrees(boostingStrategy)
+ .runWithValidation(trainRdd, validateRdd)
+ val numTrees = gbtValidate.numTrees
+ assert(numTrees !== numIterations)
+
+ // Test that it performs better on the validation dataset.
+ val gbt = new GradientBoostedTrees(boostingStrategy).run(trainRdd)
+ val (errorWithoutValidation, errorWithValidation) = {
+ if (algo == Classification) {
+ val remappedRdd = validateRdd.map(x => new LabeledPoint(2 *
x.label - 1, x.features))
+ (loss.computeError(gbt, remappedRdd),
loss.computeError(gbtValidate, remappedRdd))
+ } else {
+ (loss.computeError(gbt, validateRdd),
loss.computeError(gbtValidate, validateRdd))
}
}
+ assert(errorWithValidation <= errorWithoutValidation)
+
+ // Test that results from evaluateEachIteration comply with
runWithValidation.
+ // Note that convergenceTol is set to 0.0
+ val evaluationArray = gbt.evaluateEachIteration(validateRdd, loss)
+ assert(evaluationArray.length === numIterations)
+ assert(evaluationArray(numTrees) > evaluationArray(numTrees - 1))
+ var i = 1
+ while (i < numTrees) {
+ assert(evaluationArray(i) <= evaluationArray(i - 1))
+ i += 1
+ }
}
}
+ test("Checkpointing") {
+ val tempDir = Utils.createTempDir()
+ val path = tempDir.toURI.toString
+ val checkpointInterval = 2
+ sc.setCheckpointDir(path)
+
+ val rdd = sc.parallelize(GradientBoostedTreesSuite.data, 2)
+
+ val treeStrategy = new Strategy(algo = Regression, impurity =
Variance, maxDepth = 2,
+ categoricalFeaturesInfo = Map.empty, checkpointInterval = 2)
--- End diff --
`= 2` -> `checkpointInterval` or remove line 207
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
