diff options
Diffstat (limited to 'mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala')
-rw-r--r-- | mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala | 16 |
1 files changed, 9 insertions, 7 deletions
diff --git a/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala index fc7349330c..6cc6ec94eb 100644 --- a/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala @@ -345,6 +345,7 @@ class ALSSuite extends FunSuite with MLlibTestSparkContext with Logging { .setImplicitPrefs(implicitPrefs) .setNumUserBlocks(numUserBlocks) .setNumItemBlocks(numItemBlocks) + .setSeed(0) val alpha = als.getAlpha val model = als.fit(training.toDF()) val predictions = model.transform(test.toDF()) @@ -425,17 +426,18 @@ class ALSSuite extends FunSuite with MLlibTestSparkContext with Logging { val (ratings, _) = genImplicitTestData(numUsers = 20, numItems = 40, rank = 2, noiseStd = 0.01) val longRatings = ratings.map(r => Rating(r.user.toLong, r.item.toLong, r.rating)) - val (longUserFactors, _) = ALS.train(longRatings, rank = 2, maxIter = 4) + val (longUserFactors, _) = ALS.train(longRatings, rank = 2, maxIter = 4, seed = 0) assert(longUserFactors.first()._1.getClass === classOf[Long]) val strRatings = ratings.map(r => Rating(r.user.toString, r.item.toString, r.rating)) - val (strUserFactors, _) = ALS.train(strRatings, rank = 2, maxIter = 4) + val (strUserFactors, _) = ALS.train(strRatings, rank = 2, maxIter = 4, seed = 0) assert(strUserFactors.first()._1.getClass === classOf[String]) } test("nonnegative constraint") { val (ratings, _) = genImplicitTestData(numUsers = 20, numItems = 40, rank = 2, noiseStd = 0.01) - val (userFactors, itemFactors) = ALS.train(ratings, rank = 2, maxIter = 4, nonnegative = true) + val (userFactors, itemFactors) = + ALS.train(ratings, rank = 2, maxIter = 4, nonnegative = true, seed = 0) def isNonnegative(factors: RDD[(Int, Array[Float])]): Boolean = { factors.values.map { _.forall(_ >= 0.0) }.reduce(_ && _) } @@ -459,7 +461,7 @@ class ALSSuite extends FunSuite with MLlibTestSparkContext with Logging { test("partitioner in returned factors") { val (ratings, _) = genImplicitTestData(numUsers = 20, numItems = 40, rank = 2, noiseStd = 0.01) val (userFactors, itemFactors) = ALS.train( - ratings, rank = 2, maxIter = 4, numUserBlocks = 3, numItemBlocks = 4) + ratings, rank = 2, maxIter = 4, numUserBlocks = 3, numItemBlocks = 4, seed = 0) for ((tpe, factors) <- Seq(("User", userFactors), ("Item", itemFactors))) { assert(userFactors.partitioner.isDefined, s"$tpe factors should have partitioner.") val part = userFactors.partitioner.get @@ -476,8 +478,8 @@ class ALSSuite extends FunSuite with MLlibTestSparkContext with Logging { test("als with large number of iterations") { val (ratings, _) = genExplicitTestData(numUsers = 4, numItems = 4, rank = 1) - ALS.train(ratings, rank = 1, maxIter = 50, numUserBlocks = 2, numItemBlocks = 2) - ALS.train( - ratings, rank = 1, maxIter = 50, numUserBlocks = 2, numItemBlocks = 2, implicitPrefs = true) + ALS.train(ratings, rank = 1, maxIter = 50, numUserBlocks = 2, numItemBlocks = 2, seed = 0) + ALS.train(ratings, rank = 1, maxIter = 50, numUserBlocks = 2, numItemBlocks = 2, + implicitPrefs = true, seed = 0) } } |