srowen commented on a change in pull request #26803: [SPARK-30178][ML]
RobustScaler support large numFeatures
URL: https://github.com/apache/spark/pull/26803#discussion_r355845501
##########
File path: mllib/src/main/scala/org/apache/spark/ml/feature/RobustScaler.scala
##########
@@ -147,49 +146,43 @@ class RobustScaler (override val uid: String)
override def fit(dataset: Dataset[_]): RobustScalerModel = {
transformSchema(dataset.schema, logging = true)
- val localRelativeError = $(relativeError)
- val summaries = dataset.select($(inputCol)).rdd.map {
- case Row(vec: Vector) => vec
- }.mapPartitions { iter =>
- var agg: Array[QuantileSummaries] = null
- while (iter.hasNext) {
- val vec = iter.next()
- if (agg == null) {
- agg = Array.fill(vec.size)(
- new QuantileSummaries(QuantileSummaries.defaultCompressThreshold,
localRelativeError))
- }
- require(vec.size == agg.length,
- s"Number of dimensions must be ${agg.length} but got ${vec.size}")
- var i = 0
- while (i < vec.size) {
- agg(i) = agg(i).insert(vec(i))
- i += 1
- }
- }
-
- if (agg == null) {
- Iterator.empty
- } else {
- Iterator.single(agg.map(_.compress))
- }
- }.treeReduce { (agg1, agg2) =>
- require(agg1.length == agg2.length)
- var i = 0
- while (i < agg1.length) {
- agg1(i) = agg1(i).merge(agg2(i))
- i += 1
- }
- agg1
- }
+ val vectors = dataset.select($(inputCol)).rdd.map { case Row(vec: Vector)
=> vec }
+ val numFeatures = MetadataUtils.getNumFeatures(dataset.schema($(inputCol)))
+ .getOrElse(vectors.first().size)
- val (range, median) = summaries.map { s =>
- (s.query($(upper)).get - s.query($(lower)).get,
- s.query(0.5).get)
- }.unzip
+ val localRelativeError = $(relativeError)
+ val localUpper = $(upper)
+ val localLower = $(lower)
+
+ val collected = vectors.flatMap { vec =>
+ require(vec.size == numFeatures,
+ s"Number of dimensions must be $numFeatures but got ${vec.size}")
+ Iterator.range(0, numFeatures).map { i => (i, vec(i)) }
+ }.aggregateByKey(
Review comment:
Hm, then I don't think there's any way around it, as at least two summaries
have to be merged at some point. Can you tune things like the relative
threshold?
As I say I think this new implementation will have a more common failure
mode: large data, few dimensions. Can it be adapted? like what if they key is
not the dimension i, but something like `(i, partition)` and then by `i` or
something?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
