I have a dataframe with DenseVectors as row:
df = spark.createDataFrame([(Vectors.dense([1,2,3]),),(Vectors.dense([3,4,5]),),(Vectors.dense([6,2,5]),)], ["a"])
and I want to find the maximum of each row with UDF. This is what I did:
findmax = F.udf(lambda x: max(x),DoubleType())
df_out = df_out.select('*',findmax(df_out['sensor_data']).alias('MAX'))
After I ran the codes, this is the message i got
Traceback (most recent call last):
File "", line 1, in df.select('*',findmax(df['a'])).show()
File "C:\ProgramData\Anaconda3\envs\python2\lib\site-packages\pyspark\sql\dataframe.py", line 336, in show print(self._jdf.showString(n, 20))
File "C:\ProgramData\Anaconda3\envs\python2\lib\site-packages\py4j\java_gateway.py", line 1133, in call answer, self.gateway_client, self.target_id, self.name)
File "C:\ProgramData\Anaconda3\envs\python2\lib\site-packages\pyspark\sql\utils.py", line 63, in deco return f(*a, **kw)
File "C:\ProgramData\Anaconda3\envs\python2\lib\site-packages\py4j\protocol.py", line 319, in get_return_value format(target_id, ".", name), value)
Py4JJavaError: An error occurred while calling o785.showString. : org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 67.0 failed 1 times, most recent failure: Lost task 2.0 in stage 67.0 (TID 890, localhost, executor driver): net.razorvine.pickle.PickleException: expected zero arguments for construction of ClassDict (for numpy.dtype) at net.razorvine.pickle.objects.ClassDictConstructor.construct(ClassDictConstructor.java:23) at net.razorvine.pickle.Unpickler.load_reduce(Unpickler.java:707) at net.razorvine.pickle.Unpickler.dispatch(Unpickler.java:175) at net.razorvine.pickle.Unpickler.load(Unpickler.java:99) at net.razorvine.pickle.Unpickler.loads(Unpickler.java:112) at org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1$$anonfun$apply$6.apply(BatchEvalPythonExec.scala:156) at org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1$$anonfun$apply$6.apply(BatchEvalPythonExec.scala:155) at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434) at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source) at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43) at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:395) at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:234) at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:228) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:108) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:338) at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source) at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source) at java.lang.Thread.run(Unknown Source)
Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1517) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1505) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1504) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1504) 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:1732) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1687) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1676) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2029) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2050) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2069) at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:336) at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38) at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:2861) at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2150) at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2150) at org.apache.spark.sql.Dataset$$anonfun$55.apply(Dataset.scala:2842) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65) at org.apache.spark.sql.Dataset.withAction(Dataset.scala:2841) at org.apache.spark.sql.Dataset.head(Dataset.scala:2150) at org.apache.spark.sql.Dataset.take(Dataset.scala:2363) at org.apache.spark.sql.Dataset.showString(Dataset.scala:241) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source) at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source) at java.lang.reflect.Method.invoke(Unknown Source) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) at py4j.Gateway.invoke(Gateway.java:280) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.GatewayConnection.run(GatewayConnection.java:214) at java.lang.Thread.run(Unknown Source) Caused by: net.razorvine.pickle.PickleException: expected zero arguments for construction of ClassDict (for numpy.dtype) at net.razorvine.pickle.objects.ClassDictConstructor.construct(ClassDictConstructor.java:23) at net.razorvine.pickle.Unpickler.load_reduce(Unpickler.java:707) at net.razorvine.pickle.Unpickler.dispatch(Unpickler.java:175) at net.razorvine.pickle.Unpickler.load(Unpickler.java:99) at net.razorvine.pickle.Unpickler.loads(Unpickler.java:112) at org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1$$anonfun$apply$6.apply(BatchEvalPythonExec.scala:156) at org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1$$anonfun$apply$6.apply(BatchEvalPythonExec.scala:155) at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434) at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$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 org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:234) at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:228) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:108) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:338) at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source) at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source) 1 more
I have no idea why this wouldn't work: I found that if the rows are just floats instead of DenseVectors it will work, and the python function max accepts DenseVectors as input.
