Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/7412#discussion_r35735878
--- Diff: mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala
---
@@ -81,78 +99,145 @@ class PrefixSpan private (
if (sequences.getStorageLevel == StorageLevel.NONE) {
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
+
+ // Convert min support to a min number of transactions for this dataset
+ val minCount = if (minSupport == 0) 0L else
math.ceil(sequences.count() * minSupport).toLong
+
+ // (Frequent items -> number of occurrences, all items here satisfy
the `minSupport` threshold
+ val freqItemCounts = sequences
+ .flatMap(seq => seq.distinct.map(item => (item, 1L)))
+ .reduceByKey(_ + _)
+ .filter(_._2 >= minCount)
+
+ // Pairs of (length 1 prefix, suffix consisting of frequent items)
+ val itemSuffixPairs = {
+ val freqItems = freqItemCounts.keys.collect().toSet
+ sequences.flatMap { seq =>
+ val filteredSeq = seq.filter(freqItems.contains(_))
+ freqItems.flatMap { item =>
+ val candidateSuffix = LocalPrefixSpan.getSuffix(item,
filteredSeq)
+ candidateSuffix match {
+ case suffix if !suffix.isEmpty => Some((List(item), suffix))
+ case _ => None
+ }
+ }
+ }
+ }
+
+ // Accumulator for the computed results to be returned, initialized to
the frequent items (i.e.
+ // frequent length-one prefixes)
+ var resultsAccumulator = freqItemCounts.map(x => (List(x._1), x._2))
--- End diff --
We can collect `freqItemCounts` directly to driver.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
