spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From feynmanliang <...@git.apache.org>
Subject [GitHub] spark pull request: [SPARK-8998][MLlib] Collect enough frequent pr...
Date Wed, 15 Jul 2015 21:41:07 GMT
Github user feynmanliang commented on a diff in the pull request:

    https://github.com/apache/spark/pull/7412#discussion_r34733098
  
    --- Diff: mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala ---
    @@ -86,16 +88,69 @@ class PrefixSpan private (
           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
    +
    +    var patternsCount = lengthOnePatternsAndCounts.length
    +    var allPatternAndCounts = sequences.sparkContext.parallelize(
    +      lengthOnePatternsAndCounts.map(x => (Array(x._1), x._2)))
    +    var currentProjectedDatabase = prefixAndProjectedDatabase
    +    while (patternsCount <= minPatternsBeforeShuffle &&
    +      currentProjectedDatabase.count() != 0) {
    +      val (nextPatternAndCounts, nextProjectedDatabase) =
    +        getPatternCountsAndProjectedDatabase(minCount, currentProjectedDatabase)
    +      patternsCount = nextPatternAndCounts.count().toInt
    +      currentProjectedDatabase = nextProjectedDatabase
    +      allPatternAndCounts = allPatternAndCounts ++ nextPatternAndCounts
    +    }
    +    if (patternsCount > 0) {
    +      val groupedProjectedDatabase = currentProjectedDatabase
    +        .map(x => (x._1.toSeq, x._2))
    +        .groupByKey()
    +        .map(x => (x._1.toArray, x._2.toArray))
    +      val nextPatternAndCounts = getPatternsInLocal(minCount, groupedProjectedDatabase)
    +      allPatternAndCounts = allPatternAndCounts ++ nextPatternAndCounts
    +    }
    +    allPatternAndCounts
    +  }
    +
    +  /**
    +   * Get the pattern and counts, and projected database
    +   * @param minCount minimum count
    +   * @param prefixAndProjectedDatabase prefix and projected database,
    +   * @return pattern and counts, and projected database
    +   *         (Array[pattern, count], RDD[prefix, projected database ])
    +   */
    +  private def getPatternCountsAndProjectedDatabase(
    +      minCount: Long,
    +      prefixAndProjectedDatabase: RDD[(Array[Int], Array[Int])]):
    +  (RDD[(Array[Int], Long)], RDD[(Array[Int], Array[Int])]) = {
    +    val prefixAndFreqentItemAndCounts = prefixAndProjectedDatabase.flatMap{ x =>
    +      x._2.distinct.map(y => ((x._1.toSeq, y), 1L))
    +    }.reduceByKey(_ + _)
    +      .filter(_._2 >= minCount)
    +    val patternAndCounts = prefixAndFreqentItemAndCounts
    +      .map(x => (x._1._1.toArray ++ Array(x._1._2), x._2))
    +    val prefixlength = prefixAndProjectedDatabase.take(1)(0)._1.length
    --- End diff --
    
    Continuing discussion on the latest diff.


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message