Spark Stage error when performing PCA analysis in R - r

Question

when I run the below line of code
>model_pca <- tbl(sc, "flights") %>% select(air_time,distance,dep_time) %>%
ml_pca()
results into a stage failure but I cannot understand the reason
org.apache.spark.SparkException: Failed to execute user defined function($anonfun$3: (struct<air_time:double,distance:double,dep_time_double_vector_assembler_801c364a4ab0:double>) => vector)
It says user defined function but I am not using any user defined function, have I missed any package installation or is it because I am using spark 2.2.0 with hadoop 2.7
Below is the full error message:
Error: org.apache.spark.SparkException: Job aborted due to stage failure:
Task 0 in stage 12.0 failed 1 times, most recent failure: Lost task 0.0 in
stage 12.0 (TID 12, localhost, executor driver):
org.apache.spark.SparkException: Failed to execute user defined
function($anonfun$3:
(struct<air_time:double,distance:double,dep_time_double_vector_assembler_801c364a4ab0:double>) => vector)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:395)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:157)
at scala.collection.AbstractIterator.foldLeft(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.aggregate(TraversableOnce.scala:214)
at scala.collection.AbstractIterator.aggregate(Iterator.scala:1336)
at org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$24.apply(RDD.scala:1136)
at org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$24.apply(RDD.scala:1136)
at org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$25.apply(RDD.scala:1137)
at org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1$$anonfun$25.apply(RDD.scala:1137)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:797)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:797)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:108)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:335)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
Caused by: org.apache.spark.SparkException: Values to assemble cannot be null.
at org.apache.spark.ml.feature.VectorAssembler$$anonfun$assemble$1.apply(VectorAssembler.scala:160)
at org.apache.spark.ml.feature.VectorAssembler$$anonfun$assemble$1.apply(VectorAssembler.scala:143)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.WrappedArray.foreach(WrappedArray.scala:35)
at org.apache.spark.ml.feature.VectorAssembler$.assemble(VectorAssembler.scala:143)
at org.apache.spark.ml.feature.VectorAssembler$$anonfun$3.apply(VectorAssembler.scala:99)
at org.apache.spark.ml.feature.VectorAssembler$$anonfun$3.apply(VectorAssembler.scala:98)
... 27 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1499)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1487)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1486)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1486)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:814)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1714)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1669)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1658)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2022)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2119)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:1026)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.RDD.reduce(RDD.scala:1008)
at org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1.apply(RDD.scala:1151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.RDD.treeAggregate(RDD.scala:1128)
at org.apache.spark.mllib.linalg.distributed.RowMatrix.computeColumnSummaryStatistics(RowMatrix.scala:419)
at org.apache.spark.mllib.linalg.distributed.RowMatrix.computeCovariance(RowMatrix.scala:334)
at org.apache.spark.mllib.linalg.distributed.RowMatrix.computePrincipalComponentsAndExplainedVariance(RowMatrix.scala:387)
at org.apache.spark.mllib.feature.PCA.fit(PCA.scala:48)
at org.apache.spark.ml.feature.PCA.fit(PCA.scala:99)
at org.apache.spark.ml.feature.PCA.fit(PCA.scala:70)
at org.apache.spark.ml.Pipeline$$anonfun$fit$2.apply(Pipeline.scala:153)
at org.apache.spark.ml.Pipeline$$anonfun$fit$2.apply(Pipeline.scala:149)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.IterableViewLike$Transformed$class.foreach(IterableViewLike.scala:44)
at scala.collection.SeqViewLike$AbstractTransformed.foreach(SeqViewLike.scala:37)
at org.apache.spark.ml.Pipeline.fit(Pipeline.scala:149)
at org.apache.spark.ml.Pipeline.fit(Pipeline.scala:96)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
at java.lang.reflect.Method.invoke(Unknown Source)
at sparklyr.Invoke$.invoke(invoke.scala:102)
at sparklyr.StreamHandler$.handleMethodCall(stream.scala:97)
at sparklyr.StreamHandler$.read(stream.scala:62)
at sparklyr.BackendHandler.channelRead0(handler.scala:52)
at sparklyr.BackendHandler.channelRead0(handler.scala:14)
at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:357)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:343)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:336)
at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:102)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:357)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:343)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:336)
at io.netty.handler.codec.ByteToMessageDecoder.fireChannelRead(ByteToMessageDecoder.java:293)
at io.netty.handler.co

Answer 1

It's because of the "%>%" operator in your code. What it does depends on the library you're importing or how you defined. Try to "unchain" that.