Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/19843#discussion_r155403356 --- Diff: mllib/src/test/scala/org/apache/spark/ml/util/MLTest.scala --- @@ -0,0 +1,81 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You 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 org.apache.spark.ml.util + +import java.io.File + +import org.scalatest.Suite + +import org.apache.spark.SparkContext +import org.apache.spark.ml.Transformer +import org.apache.spark.sql.{DataFrame, Encoder, Row} +import org.apache.spark.sql.execution.streaming.MemoryStream +import org.apache.spark.sql.streaming.StreamTest +import org.apache.spark.sql.test.TestSparkSession +import org.apache.spark.util.Utils + +trait MLTest extends StreamTest with TempDirectory { self: Suite => + + @transient var sc: SparkContext = _ + @transient var checkpointDir: String = _ + + protected override def createSparkSession: TestSparkSession = { + new TestSparkSession(new SparkContext("local[2]", "MLlibUnitTest", sparkConf)) + } + + override def beforeAll(): Unit = { + super.beforeAll() + sc = spark.sparkContext + checkpointDir = Utils.createDirectory(tempDir.getCanonicalPath, "checkpoints").toString + sc.setCheckpointDir(checkpointDir) + } + + override def afterAll() { + try { + Utils.deleteRecursively(new File(checkpointDir)) + } finally { + super.afterAll() + } + } + + def testTransformer[A : Encoder](dataframe: DataFrame, transformers: Seq[Transformer], --- End diff -- Do we need a Seq of Transformers? Should we not just use a PipelineModel?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org