Hi!
I'm currently trying to understand how to use the implementation of the
FPGrowth algoritm (see :
https://cwiki.apache.org/MAHOUT/parallel-frequent-pattern-mining.html).
Currently, I'm just trying it with stupid data, and scala code. The problem is
that it output only single item itemset.
I probably missed something. Could you give me a hint?
By the way, the code below is scala (calling java implementation directly!). It
that is a problem, I can translate it to java...
sample outuput :
freqList :Buffer((bier,15), (bread,12), (milk,11), (butter,6))
10:47:44,688 INFO ~ Number of unique items 4
10:47:44,688 INFO ~ Number of unique pruned items 4
10:47:44,688 INFO ~ Number of Nodes in the FP Tree: 0
10:47:44,688 INFO ~ Mining FTree Tree for all patterns with 3
updater : FPGrowth Algorithm for a given feature: 3
butter:[butter] : 6
10:47:44,690 INFO ~ Found 1 Patterns with Least Support 6
10:47:44,690 INFO ~ Mining FTree Tree for all patterns with 2
updater : FPGrowth Algorithm for a given feature: 2
updater : FPGrowth Algorithm for a given feature: 3
milk:[milk] : 11
10:47:44,690 INFO ~ Found 1 Patterns with Least Support 11
10:47:44,690 INFO ~ Mining FTree Tree for all patterns with 1
updater : FPGrowth Algorithm for a given feature: 1
updater : FPGrowth Algorithm for a given feature: 2
updater : FPGrowth Algorithm for a given feature: 3
bread:[bread] : 12
10:47:44,690 INFO ~ Found 1 Patterns with Least Support 12
10:47:44,690 INFO ~ Mining FTree Tree for all patterns with 0
updater : FPGrowth Algorithm for a given feature: 0
updater : FPGrowth Algorithm for a given feature: 1
updater : FPGrowth Algorithm for a given feature: 2
updater : FPGrowth Algorithm for a given feature: 3
bier:[bier] : 15
10:47:44,691 INFO ~ Found 1 Patterns with Least Support 15
code :
import org.apache.mahout.fpm.pfpgrowth.fpgrowth.FPGrowth
import java.util.HashSet
import org.apache.mahout.common.iterator.StringRecordIterator
import org.apache.mahout.common.iterator.FileLineIterable
import org.apache.mahout.fpm.pfpgrowth.convertors._
import org.apache.mahout.fpm.pfpgrowth.convertors.integer._
import org.apache.mahout.fpm.pfpgrowth.convertors.string._
import org.apache.hadoop.io.SequenceFile.Writer
import org.apache.mahout.fpm.pfpgrowth.convertors.StatusUpdater
import org.apache.hadoop.mapred.OutputCollector
import scala.collection.JavaConversions._
import java.util.{ List => JList }
import org.apache.mahout.common.{ Pair => JPair }
import java.lang.{ Long => JLong }
import org.apache.hadoop.io.{ Text => JText }
val minSupport = 1L
val k: Int = 50
val fps: FPGrowth[String] = new FPGrowth[String]()
val milk = "milk"
val bread = "bread"
val butter = "butter"
val bier = "bier"
val transactionStream: Iterator[JPair[JList[String], JLong]] = Iterator(
new JPair(List(milk, bread), 1L),
new JPair(List(butter), 1L),
new JPair(List(bier), 10L),
new JPair(List(milk, bread, butter), 5L),
new JPair(List(milk, bread, bier), 5L),
new JPair(List(bread), 1L)
)
val frequencies: Collection[JPair[String, JLong]] = fps.generateFList(
transactionStream, minSupport.toInt)
println("freqList :" + frequencies)
var returnableFeatures: Collection[String] = List(
milk, bread, butter, bier)
var output: OutputCollector[String, JList[JPair[JList[String], JLong]]] = (
new OutputCollector[String, JList[JPair[JList[String], JLong]]] {
def collect(x1: String,
x2: JList[JPair[JList[String], JLong]]) = {
println(x1 + ":" +
x2.map(pair => "[" + pair.getFirst.mkString(",") + "] : " +
pair.getSecond).mkString("; "))
}
}
)
val updater: StatusUpdater = new StatusUpdater {
def update(status: String) = println("updater : " + status)
}
fps.generateTopKFrequentPatterns(
transactionStream,
frequencies,
minSupport,
k,
null, //returnableFeatures
output,
updater)
