Github user feynmanliang commented on a diff in the pull request:
https://github.com/apache/spark/pull/7412#discussion_r34737011
--- Diff: mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala
---
@@ -82,20 +84,70 @@ class PrefixSpan private (
logWarning("Input data is not cached.")
}
val minCount = getMinCount(sequences)
- val lengthOnePatternsAndCounts =
- getFreqItemAndCounts(minCount, sequences).collect()
- val prefixAndProjectedDatabase = getPrefixAndProjectedDatabase(
- lengthOnePatternsAndCounts.map(_._1), sequences)
- val groupedProjectedDatabase = prefixAndProjectedDatabase
- .map(x => (x._1.toSeq, x._2))
- .groupByKey()
- .map(x => (x._1.toArray, x._2.toArray))
- val nextPatterns = getPatternsInLocal(minCount,
groupedProjectedDatabase)
- val lengthOnePatternsAndCountsRdd =
- sequences.sparkContext.parallelize(
- lengthOnePatternsAndCounts.map(x => (Array(x._1), x._2)))
- val allPatterns = lengthOnePatternsAndCountsRdd ++ nextPatterns
- allPatterns
+ val lengthOnePatternsAndCounts = getFreqItemAndCounts(minCount,
sequences)
+ val prefixSuffixPairs = getPrefixSuffixPairs(
+ lengthOnePatternsAndCounts.map(_._1).collect(), sequences)
+ var patternsCount: Long = lengthOnePatternsAndCounts.count()
+ var allPatternAndCounts = lengthOnePatternsAndCounts.map(x =>
(Array(x._1), x._2))
+ var currentPrefixSuffixPairs = prefixSuffixPairs
+ while (patternsCount <= minPatternsBeforeShuffle &&
currentPrefixSuffixPairs.count() != 0) {
+ val (nextPatternAndCounts, nextPrefixSuffixPairs) =
+ getPatternCountsAndPrefixSuffixPairs(minCount,
currentPrefixSuffixPairs)
+ patternsCount = nextPatternAndCounts.count().toInt
+ currentPrefixSuffixPairs = nextPrefixSuffixPairs
+ allPatternAndCounts = allPatternAndCounts ++ nextPatternAndCounts
+ }
+ if (patternsCount > 0) {
+ val projectedDatabase = currentPrefixSuffixPairs
+ .map(x => (x._1.toSeq, x._2))
+ .groupByKey()
--- End diff --
This assumes that all the values (suffixes) associated to a key (prefix)
will fit on an executor, but I don't think that `patternsCount >
minPatternsBeforeShuffle` will guarantee that. Better to count the suffixes for
each prefix using `aggregateByKey` before doing local processing.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
