diff options
Diffstat (limited to 'core')
-rw-r--r-- | core/src/main/scala/org/apache/spark/util/Utils.scala | 2 | ||||
-rw-r--r-- | core/src/test/scala/org/apache/spark/util/UtilsSuite.scala | 35 |
2 files changed, 36 insertions, 1 deletions
diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala index 0ae44a2ed7..9b4274a27b 100644 --- a/core/src/main/scala/org/apache/spark/util/Utils.scala +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala @@ -824,7 +824,7 @@ private[spark] object Utils extends Logging { */ def randomizeInPlace[T](arr: Array[T], rand: Random = new Random): Array[T] = { for (i <- (arr.length - 1) to 1 by -1) { - val j = rand.nextInt(i) + val j = rand.nextInt(i + 1) val tmp = arr(j) arr(j) = arr(i) arr(i) = tmp diff --git a/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala b/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala index 30952a9458..4715fd2937 100644 --- a/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala +++ b/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala @@ -31,6 +31,7 @@ import scala.util.Random import com.google.common.io.Files import org.apache.commons.lang3.SystemUtils +import org.apache.commons.math3.stat.inference.ChiSquareTest import org.apache.hadoop.conf.Configuration import org.apache.hadoop.fs.Path @@ -874,4 +875,38 @@ class UtilsSuite extends SparkFunSuite with ResetSystemProperties with Logging { } } } + + test("chi square test of randomizeInPlace") { + // Parameters + val arraySize = 10 + val numTrials = 1000 + val threshold = 0.05 + val seed = 1L + + // results(i)(j): how many times Utils.randomize moves an element from position j to position i + val results = Array.ofDim[Long](arraySize, arraySize) + + // This must be seeded because even a fair random process will fail this test with + // probability equal to the value of `threshold`, which is inconvenient for a unit test. + val rand = new java.util.Random(seed) + val range = 0 until arraySize + + for { + _ <- 0 until numTrials + trial = Utils.randomizeInPlace(range.toArray, rand) + i <- range + } results(i)(trial(i)) += 1L + + val chi = new ChiSquareTest() + + // We expect an even distribution; this array will be rescaled by `chiSquareTest` + val expected = Array.fill(arraySize * arraySize)(1.0) + val observed = results.flatten + + // Performs Pearson's chi-squared test. Using the sum-of-squares as the test statistic, gives + // the probability of a uniform distribution producing results as extreme as `observed` + val pValue = chi.chiSquareTest(expected, observed) + + assert(pValue > threshold) + } } |