-
-
Notifications
You must be signed in to change notification settings - Fork 8.7k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
1. Updated the test logic 2. Added smoke tests for Spark examples. 3. Added integration tests for Spark with Scala 2.13
- Loading branch information
Showing
24 changed files
with
326 additions
and
161 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,2 +1,4 @@ | ||
| tracker.py | ||
| build.sh | ||
| xgboost4j-tester/pom.xml | ||
| xgboost4j-tester/iris.csv |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
123 changes: 123 additions & 0 deletions
123
...st4j-example/src/test/scala/ml/dmlc/xgboost4j/scala/example/spark/SparkExamplesTest.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,123 @@ | ||
| /* | ||
| Copyright (c) 2014-2023 by Contributors | ||
| Licensed under the Apache License, Version 2.0 (the "License"); | ||
| you may not use this file except in compliance with the License. | ||
| You may obtain a copy of the License at | ||
| http://www.apache.org/licenses/LICENSE-2.0 | ||
| Unless required by applicable law or agreed to in writing, software | ||
| distributed under the License is distributed on an "AS IS" BASIS, | ||
| WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| See the License for the specific language governing permissions and | ||
| limitations under the License. | ||
| */ | ||
| package ml.dmlc.xgboost4j.scala.example.spark | ||
|
|
||
| import org.apache.spark.sql.SparkSession | ||
| import org.scalatest.BeforeAndAfterAll | ||
| import org.scalatest.funsuite.AnyFunSuite | ||
| import org.slf4j.LoggerFactory | ||
|
|
||
| import java.io.File | ||
| import java.nio.file.{Files, StandardOpenOption} | ||
| import scala.jdk.CollectionConverters._ | ||
| import scala.util.{Random, Try} | ||
|
|
||
| class SparkExamplesTest extends AnyFunSuite with BeforeAndAfterAll { | ||
| private val logger = LoggerFactory.getLogger(classOf[SparkExamplesTest]) | ||
| private val random = new Random(42) | ||
| protected val numWorkers: Int = scala.math.min(Runtime.getRuntime.availableProcessors(), 4) | ||
|
|
||
| private val pathToTestDataset = Files.createTempFile("", "iris.csv").toAbsolutePath | ||
| private var spark: SparkSession = _ | ||
|
|
||
| override def beforeAll(): Unit = { | ||
|
|
||
| def generateLine(i: Int): String = { | ||
| val getIrisName = (int: Int) => { | ||
| int % 3 match { | ||
| case 0 => "Iris-versicolor" | ||
| case 1 => "Iris-virginica" | ||
| case 2 => "Iris-setosa" | ||
| } | ||
| } | ||
| val generateValue = () => Math.abs(random.nextInt(99) * 0.1) | ||
| val sepalLength = generateValue() | ||
| val sepalWidth = generateValue() | ||
| val petalLength = generateValue() | ||
| val petalWidth = generateValue() | ||
| val irisName = getIrisName(Math.abs(random.nextInt()) + i) | ||
| s"$sepalLength,$sepalWidth,$petalLength,$petalWidth,$irisName" | ||
| } | ||
|
|
||
| if (spark == null) { | ||
| spark = SparkSession | ||
| .builder() | ||
| .appName("XGBoost4J-Spark Pipeline Example") | ||
| .master(s"local[${numWorkers}]") | ||
| .config("spark.ui.enabled", value = false) | ||
| .config("spark.driver.memory", "512m") | ||
| .config("spark.barrier.sync.timeout", 10) | ||
| .config("spark.task.cpus", 1) | ||
| .getOrCreate() | ||
| spark.sparkContext.setLogLevel("ERROR") | ||
| } | ||
| val data = (0 until 150) | ||
| .map(i => generateLine(i)) | ||
| .toList | ||
| .asJava | ||
| Files.write(pathToTestDataset, | ||
| data, | ||
| StandardOpenOption.CREATE, | ||
| StandardOpenOption.WRITE, | ||
| StandardOpenOption.TRUNCATE_EXISTING) | ||
| logger.info(s"${new String(Files.readAllBytes(pathToTestDataset))}") | ||
|
|
||
| } | ||
|
|
||
| override def afterAll(): Unit = { | ||
| if (spark != null) { | ||
| spark.stop() | ||
| cleanExternalCache(spark.sparkContext.appName) | ||
| spark = null | ||
| } | ||
|
|
||
| Try(Files.deleteIfExists(pathToTestDataset)) | ||
| .recover { | ||
| case e => | ||
| logger.warn( | ||
| s"Could not delete temporary file $pathToTestDataset. Please, remove it manually", | ||
| e | ||
| ) | ||
| true | ||
| } | ||
| } | ||
|
|
||
| private def cleanExternalCache(prefix: String): Unit = { | ||
| val dir = new File(".") | ||
| for (file <- dir.listFiles() if file.getName.startsWith(prefix)) { | ||
| file.delete() | ||
| } | ||
| } | ||
|
|
||
| test("Smoke test for SparkMLlibPipeline example") { | ||
| SparkMLlibPipeline.run(spark, pathToTestDataset.toString, "target/native-model", | ||
| "target/pipeline-model", "auto", 2) | ||
| } | ||
|
|
||
| test("Smoke test for SparkTraining example") { | ||
| val spark = SparkSession | ||
| .builder() | ||
| .appName("XGBoost4J-Spark Pipeline Example") | ||
| .master(s"local[${numWorkers}]") | ||
| .config("spark.ui.enabled", value = false) | ||
| .config("spark.driver.memory", "512m") | ||
| .config("spark.barrier.sync.timeout", 10) | ||
| .config("spark.task.cpus", 1) | ||
| .getOrCreate() | ||
|
|
||
| SparkTraining.run(spark, pathToTestDataset.toString, "auto", 2) | ||
| } | ||
| } |
Oops, something went wrong.