diff options
Diffstat (limited to 'mllib')
4 files changed, 9 insertions, 9 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/BinaryClassificationMetrics.scala b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/BinaryClassificationMetrics.scala index 079743742d..1af40de2c7 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/BinaryClassificationMetrics.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/BinaryClassificationMetrics.scala @@ -103,11 +103,11 @@ class BinaryClassificationMetrics(scoreAndLabels: RDD[(Double, Double)]) extends mergeValue = (c: BinaryLabelCounter, label: Double) => c += label, mergeCombiners = (c1: BinaryLabelCounter, c2: BinaryLabelCounter) => c1 += c2 ).sortByKey(ascending = false) - val agg = counts.values.mapPartitions({ iter => + val agg = counts.values.mapPartitions { iter => val agg = new BinaryLabelCounter() iter.foreach(agg += _) Iterator(agg) - }, preservesPartitioning = true).collect() + }.collect() val partitionwiseCumulativeCounts = agg.scanLeft(new BinaryLabelCounter())( (agg: BinaryLabelCounter, c: BinaryLabelCounter) => agg.clone() += c) diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala index f4c403bc78..8c2b044ea7 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala @@ -377,9 +377,9 @@ class RowMatrix( s"Only support dense matrix at this time but found ${B.getClass.getName}.") val Bb = rows.context.broadcast(B.toBreeze.asInstanceOf[BDM[Double]].toDenseVector.toArray) - val AB = rows.mapPartitions({ iter => + val AB = rows.mapPartitions { iter => val Bi = Bb.value - iter.map(row => { + iter.map { row => val v = BDV.zeros[Double](k) var i = 0 while (i < k) { @@ -387,8 +387,8 @@ class RowMatrix( i += 1 } Vectors.fromBreeze(v) - }) - }, preservesPartitioning = true) + } + } new RowMatrix(AB, nRows, B.numCols) } diff --git a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala index 15e8855db6..5356790cb5 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala @@ -430,7 +430,7 @@ class ALS private ( val inLinkBlock = makeInLinkBlock(numProductBlocks, ratings, productPartitioner) val outLinkBlock = makeOutLinkBlock(numProductBlocks, ratings, productPartitioner) Iterator.single((blockId, (inLinkBlock, outLinkBlock))) - }, true) + }, preservesPartitioning = true) val inLinks = links.mapValues(_._1) val outLinks = links.mapValues(_._2) inLinks.persist(StorageLevel.MEMORY_AND_DISK) diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala index aaf92a1a88..30de24ad89 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala @@ -264,8 +264,8 @@ object MLUtils { (1 to numFolds).map { fold => val sampler = new BernoulliSampler[T]((fold - 1) / numFoldsF, fold / numFoldsF, complement = false) - val validation = new PartitionwiseSampledRDD(rdd, sampler, seed) - val training = new PartitionwiseSampledRDD(rdd, sampler.cloneComplement(), seed) + val validation = new PartitionwiseSampledRDD(rdd, sampler, true, seed) + val training = new PartitionwiseSampledRDD(rdd, sampler.cloneComplement(), true, seed) (training, validation) }.toArray } |