Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/19108#discussion_r174977495 --- Diff: mllib/src/test/scala/org/apache/spark/ml/stat/KolmogorovSmirnovTestSuite.scala --- @@ -0,0 +1,133 @@ +/* + * 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.stat + +import org.apache.commons.math3.distribution.{ExponentialDistribution, NormalDistribution} +import org.apache.commons.math3.stat.inference.{KolmogorovSmirnovTest => Math3KSTest} + +import org.apache.spark.SparkFunSuite +import org.apache.spark.ml.util.DefaultReadWriteTest +import org.apache.spark.ml.util.TestingUtils._ +import org.apache.spark.mllib.util.MLlibTestSparkContext +import org.apache.spark.sql.Row + +class KolmogorovSmirnovTestSuite + extends SparkFunSuite with MLlibTestSparkContext with DefaultReadWriteTest { + + import testImplicits._ + + test("1 sample Kolmogorov-Smirnov test: apache commons math3 implementation equivalence") { + // Create theoretical distributions + val stdNormalDist = new NormalDistribution(0, 1) + val expDist = new ExponentialDistribution(0.6) + + // set seeds + val seed = 10L + stdNormalDist.reseedRandomGenerator(seed) + expDist.reseedRandomGenerator(seed) + + // Sample data from the distributions and parallelize it + val n = 100000 + val sampledNormArray = stdNormalDist.sample(n) + val sampledNormDF = sc.parallelize(sampledNormArray, 10).toDF("sample") + val sampledExpArray = expDist.sample(n) + val sampledExpDF = sc.parallelize(sampledExpArray, 10).toDF("sample") + + // Use a apache math commons local KS test to verify calculations + val ksTest = new Math3KSTest() + val pThreshold = 0.05 + + // Comparing a standard normal sample to a standard normal distribution --- End diff -- Can this and the next set of code lines be combined into a single helper method? That could help with adding in the test for the uniform distribution as well.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org