I'm trying to do a algorithm in Spark Mllib. I'm trying to do a Market Basket Analysis. And I've as a data set this:
ID bigint,
Chain int,
Dept int,
Category int,
Company bigint,
Brand bigint,
Date string,
Product_Size double,
Product_Measure string,
Purchase_Quantity int,
Purchase_Amount double
The code that I found is this:
import org.apache.spark.mllib.fpm.FPGrowth
import org.apache.spark.rdd.RDD
import sys.process._
val data = sc.textFile("/user/admin/retail/marketbaskets/part-r-00000")
val transactions: RDD[Array[String]] = data.map(s => s.trim.split(','))
val fpg = new FPGrowth()
.setMinSupport(0.007)
.setNumPartitions(10)
val model = fpg.run(transactions)
model.freqItemsets.collect().foreach { itemset =>
println(itemset.items.mkString("[", ",", "]") + ", " + itemset.freq)
}
val minConfidence = 0.8
model.generateAssociationRules(minConfidence).collect().foreach { rule =>
println(
rule.antecedent.mkString("[", ",", "]")
+ " => " + rule.consequent .mkString("[", ",", "]")
+ ", " + rule.confidence)
}
However when I submit this line of code:
val model = fpg.run(transactions)
I get the fowllowing error:
val model = fpg.run(transactions)
16/08/26 10:56:09 WARN fpm.FPGrowth: Input data is not cached.
16/08/26 10:56:21 ERROR executor.Executor: Exception in task 0.0 in stage 10.0 (TID 7)
org.apache.spark.SparkException: Items in a transaction must be unique but got WrappedArray(13873775, 4, 99, 9909, 102113020, 15704, 2012-03-19:00, 6.25, OZ, 4, 11.96).
at org.apache.spark.mllib.fpm.FPGrowth$$anonfun$1.apply(FPGrowth.scala:143)
at org.apache.spark.mllib.fpm.FPGrowth$$anonfun$1.apply(FPGrowth.scala:140)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at org.apache.spark.util.collection.ExternalSorter.insertAll(ExternalSorter.scala:189)
at org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:64)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
16/08/26 10:56:21 WARN scheduler.TaskSetManager: Lost task 0.0 in stage 10.0 (TID 7, localhost): org.apache.spark.SparkException: Items in a transaction must be unique but got WrappedArray(13873775, 4, 99, 9909, 102113020, 15704, 2012-03-19:00, 6.25, OZ, 4, 11.96).
at org.apache.spark.mllib.fpm.FPGrowth$$anonfun$1.apply(FPGrowth.scala:143)
at org.apache.spark.mllib.fpm.FPGrowth$$anonfun$1.apply(FPGrowth.scala:140)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at org.apache.spark.util.collection.ExternalSorter.insertAll(ExternalSorter.scala:189)
at org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:64)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
16/08/26 10:56:21 ERROR scheduler.TaskSetManager: Task 0 in stage 10.0 failed 1 times; aborting job
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 10.0 failed 1 times, most recent failure: Lost task 0.0 in stage 10.0 (TID 7, localhost): org.apache.spark.SparkException: Items in a transaction must be unique but got WrappedArray(13873775, 4, 99, 9909, 102113020, 15704, 2012-03-19:00, 6.25, OZ, 4, 11.96).
at org.apache.spark.mllib.fpm.FPGrowth$$anonfun$1.apply(FPGrowth.scala:143)
at org.apache.spark.mllib.fpm.FPGrowth$$anonfun$1.apply(FPGrowth.scala:140)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at org.apache.spark.util.collection.ExternalSorter.insertAll(ExternalSorter.scala:189)
at org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:64)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1843)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1856)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1869)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1940)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:927)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.collect(RDD.scala:926)
at org.apache.spark.mllib.fpm.FPGrowth.genFreqItems(FPGrowth.scala:149)
at org.apache.spark.mllib.fpm.FPGrowth.run(FPGrowth.scala:118)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:38)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:43)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:45)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:47)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:49)
at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:51)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:53)
at $iwC$$iwC$$iwC.<init>(<console>:55)
at $iwC$$iwC.<init>(<console>:57)
at $iwC.<init>(<console>:59)
at <init>(<console>:61)
at .<init>(<console>:65)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1045)
at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1326)
at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:821)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:852)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:800)
at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1064)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: org.apache.spark.SparkException: Items in a transaction must be unique but got WrappedArray(13873775, 4, 99, 9909, 102113020, 15704, 2012-03-19:00, 6.25, OZ, 4, 11.96).
at org.apache.spark.mllib.fpm.FPGrowth$$anonfun$1.apply(FPGrowth.scala:143)
at org.apache.spark.mllib.fpm.FPGrowth$$anonfun$1.apply(FPGrowth.scala:140)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at org.apache.spark.util.collection.ExternalSorter.insertAll(ExternalSorter.scala:189)
at org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:64)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
I already try to use this:
val model = fpg.run(transactions.values.map(_.toArray))
But it still gives me an error. I also see in the Hive if this error was a duplicate case but it isn't.
Anyone knows how can I solve this error?
Many thanks!
