Github user WeichenXu123 commented on a diff in the pull request: https://github.com/apache/spark/pull/16774#discussion_r136719383 --- Diff: mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala --- @@ -100,31 +113,53 @@ class CrossValidator @Since("1.2.0") (@Since("1.4.0") override val uid: String) val eval = $(evaluator) val epm = $(estimatorParamMaps) val numModels = epm.length - val metrics = new Array[Double](epm.length) + + // Create execution context based on $(parallelism) + val executionContext = getExecutionContext val instr = Instrumentation.create(this, dataset) - instr.logParams(numFolds, seed) + instr.logParams(numFolds, seed, parallelism) logTuningParams(instr) + // Compute metrics for each model over each split val splits = MLUtils.kFold(dataset.toDF.rdd, $(numFolds), $(seed)) - splits.zipWithIndex.foreach { case ((training, validation), splitIndex) => + val metrics = splits.zipWithIndex.map { case ((training, validation), splitIndex) => val trainingDataset = sparkSession.createDataFrame(training, schema).cache() val validationDataset = sparkSession.createDataFrame(validation, schema).cache() - // multi-model training logDebug(s"Train split $splitIndex with multiple sets of parameters.") - val models = est.fit(trainingDataset, epm).asInstanceOf[Seq[Model[_]]] - trainingDataset.unpersist() - var i = 0 - while (i < numModels) { - // TODO: duplicate evaluator to take extra params from input - val metric = eval.evaluate(models(i).transform(validationDataset, epm(i))) - logDebug(s"Got metric $metric for model trained with ${epm(i)}.") - metrics(i) += metric - i += 1 + + // Fit models in a Future for training in parallel + val models = epm.map { paramMap => --- End diff -- I think use var name `modelFutures` instead of `models` will be more clear.
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org