org.scalatest.exceptions.TestFailedException: Timed out waiting for stream: The code passed to failAfter did not complete within 10 seconds. java.lang.Thread.getStackTrace(Thread.java:1559) org.scalatest.concurrent.TimeLimits.failAfterImpl(TimeLimits.scala:234) org.scalatest.concurrent.TimeLimits.failAfterImpl$(TimeLimits.scala:233) org.apache.spark.ml.feature.RFormulaSuite.failAfterImpl(RFormulaSuite.scala:28) org.scalatest.concurrent.TimeLimits.failAfter(TimeLimits.scala:230) org.scalatest.concurrent.TimeLimits.failAfter$(TimeLimits.scala:229) org.apache.spark.ml.feature.RFormulaSuite.failAfter(RFormulaSuite.scala:28) org.apache.spark.sql.streaming.StreamTest.$anonfun$testStream$7(StreamTest.scala:472) org.apache.spark.sql.streaming.StreamTest.$anonfun$testStream$7$adapted(StreamTest.scala:471) scala.collection.mutable.HashMap.$anonfun$foreach$1(HashMap.scala:149) Caused by: null java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:2151) org.apache.spark.sql.execution.streaming.StreamExecution.awaitOffset(StreamExecution.scala:408) org.apache.spark.sql.streaming.StreamTest.$anonfun$testStream$8(StreamTest.scala:473) scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23) org.scalatest.enablers.Timed$$anon$1.timeoutAfter(Timed.scala:127) org.scalatest.concurrent.TimeLimits.failAfterImpl(TimeLimits.scala:239) org.scalatest.concurrent.TimeLimits.failAfterImpl$(TimeLimits.scala:233) org.apache.spark.ml.feature.RFormulaSuite.failAfterImpl(RFormulaSuite.scala:28) org.scalatest.concurrent.TimeLimits.failAfter(TimeLimits.scala:230) org.scalatest.concurrent.TimeLimits.failAfter$(TimeLimits.scala:229) == Progress == AddData to MemoryStream[_1#97235,_2#97236,_3#97237]: (1,foo,4),(2,bar,4),(3,bar,5),(4,baz,5) => CheckAnswerByFunc == Stream == Output Mode: Append Stream state: {} Thread state: alive Thread stack trace: scala.collection.mutable.LinkedHashSet.createNewEntry(LinkedHashSet.scala:109) scala.collection.mutable.LinkedHashSet.createNewEntry(LinkedHashSet.scala:44) scala.collection.mutable.HashTable.findOrAddEntry(HashTable.scala:170) scala.collection.mutable.HashTable.findOrAddEntry$(HashTable.scala:167) scala.collection.mutable.LinkedHashSet.findOrAddEntry(LinkedHashSet.scala:44) scala.collection.mutable.LinkedHashSet.add(LinkedHashSet.scala:68) scala.collection.mutable.LinkedHashSet.$plus$eq(LinkedHashSet.scala:63) scala.collection.mutable.LinkedHashSet.$plus$eq(LinkedHashSet.scala:44) scala.collection.generic.Growable.$anonfun$$plus$plus$eq$1(Growable.scala:62) scala.collection.generic.Growable$$Lambda$7/245475541.apply(Unknown Source) scala.collection.immutable.Set$Set1.foreach(Set.scala:97) scala.collection.generic.Growable.$plus$plus$eq(Growable.scala:62) scala.collection.generic.Growable.$plus$plus$eq$(Growable.scala:53) scala.collection.mutable.AbstractSet.$plus$plus$eq(Set.scala:48) org.apache.spark.sql.catalyst.expressions.AttributeSet$.$anonfun$fromAttributeSets$1(AttributeSet.scala:49) org.apache.spark.sql.catalyst.expressions.AttributeSet$$$Lambda$1582/1440923470.apply(Unknown Source) scala.collection.IndexedSeqOptimized.foldLeft(IndexedSeqOptimized.scala:60) scala.collection.IndexedSeqOptimized.foldLeft$(IndexedSeqOptimized.scala:68) scala.collection.mutable.ArrayBuffer.foldLeft(ArrayBuffer.scala:49) org.apache.spark.sql.catalyst.expressions.AttributeSet$.fromAttributeSets(AttributeSet.scala:49) org.apache.spark.sql.catalyst.expressions.AttributeSet$.apply(AttributeSet.scala:44) org.apache.spark.sql.catalyst.plans.QueryPlan.outputSet(QueryPlan.scala:40) org.apache.spark.sql.catalyst.optimizer.ColumnPruning$$anonfun$apply$6.applyOrElse(Optimizer.scala:546) org.apache.spark.sql.catalyst.optimizer.ColumnPruning$$anonfun$apply$6.applyOrElse(Optimizer.scala:544) org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDown$1(TreeNode.scala:258) org.apache.spark.sql.catalyst.trees.TreeNode$$Lambda$1517/366518998.apply(Unknown Source) org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:72) org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:258) org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDown(LogicalPlan.scala:29) org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDown(AnalysisHelper.scala:149) org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDown$(AnalysisHelper.scala:147) org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29) org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29) org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:247) org.apache.spark.sql.catalyst.optimizer.ColumnPruning$.apply(Optimizer.scala:544) org.apache.spark.sql.catalyst.optimizer.ColumnPruning$.apply(Optimizer.scala:542) org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$2(RuleExecutor.scala:102) org.apache.spark.sql.catalyst.rules.RuleExecutor$$Lambda$1501/2106141367.apply(Unknown Source) scala.collection.LinearSeqOptimized.foldLeft(LinearSeqOptimized.scala:126) scala.collection.LinearSeqOptimized.foldLeft$(LinearSeqOptimized.scala:122) scala.collection.immutable.List.foldLeft(List.scala:89) org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1(RuleExecutor.scala:99) org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1$adapted(RuleExecutor.scala:91) org.apache.spark.sql.catalyst.rules.RuleExecutor$$Lambda$1500/281516395.apply(Unknown Source) scala.collection.immutable.List.foreach(List.scala:392) org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:91) org.apache.spark.sql.execution.streaming.IncrementalExecution.$anonfun$optimizedPlan$1(IncrementalExecution.scala:80) org.apache.spark.sql.execution.streaming.IncrementalExecution$$Lambda$2339/1358008810.apply(Unknown Source) org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111) org.apache.spark.sql.execution.streaming.IncrementalExecution.optimizedPlan$lzycompute(IncrementalExecution.scala:80) org.apache.spark.sql.execution.streaming.IncrementalExecution.optimizedPlan(IncrementalExecution.scala:79) org.apache.spark.sql.execution.QueryExecution.$anonfun$sparkPlan$1(QueryExecution.scala:79) org.apache.spark.sql.execution.QueryExecution$$Lambda$1688/1545683621.apply(Unknown Source) org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111) org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:75) org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:75) org.apache.spark.sql.execution.QueryExecution.$anonfun$executedPlan$1(QueryExecution.scala:85) org.apache.spark.sql.execution.QueryExecution$$Lambda$1687/1031086586.apply(Unknown Source) org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111) org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:85) org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:84) org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$14(MicroBatchExecution.scala:537) org.apache.spark.sql.execution.streaming.MicroBatchExecution$$Lambda$2337/654111784.apply(Unknown Source) org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:325) org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:323) org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:60) org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:527) org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:203) org.apache.spark.sql.execution.streaming.MicroBatchExecution$$Lambda$2244/726337336.apply$mcV$sp(Unknown Source) scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23) org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:325) org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:323) org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:60) org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:171) org.apache.spark.sql.execution.streaming.MicroBatchExecution$$Lambda$2242/874718659.apply$mcZ$sp(Unknown Source) org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:56) org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:165) org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:286) org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:198) == Sink == == Plan == == Parsed Logical Plan == Project [id#97238, a#97239, b#97240, features#97281, label#97292] +- Project [id#97238, a#97239, b#97240, features#97281, cast(id#97238 as double) AS label#97292] +- Project [id#97238, a#97239, b#97240, features#97281] +- Project [id#97238, a#97239, b#97240, stridx_2f45842fe317#97261, onehot_922d3217070b#97267, features#97274 AS features#97281] +- Project [id#97238, a#97239, b#97240, stridx_2f45842fe317#97261, onehot_922d3217070b#97267, UDF(named_struct(onehot_922d3217070b, onehot_922d3217070b#97267, b_double_rFormula_84ede8fece19, cast(b#97240 as double))) AS features#97274] +- Project [id#97238, a#97239, b#97240, stridx_2f45842fe317#97261, if ((isnull(cast(stridx_2f45842fe317#97261 as double)) || isnull(0))) null else UDF(cast(stridx_2f45842fe317#97261 as double), 0) AS onehot_922d3217070b#97267] +- Project [id#97238, a#97239, b#97240, UDF(cast(a#97239 as string)) AS stridx_2f45842fe317#97261] +- Project [id#97245 AS id#97238, a#97246 AS a#97239, b#97247 AS b#97240] +- Project [_1#97235 AS id#97245, _2#97236 AS a#97246, _3#97237 AS b#97247] +- Project [_1#97308 AS _1#97235, _2#97309 AS _2#97236, _3#97310 AS _3#97237] +- Streaming RelationV2 MemoryStreamDataSource$[_1#97308, _2#97309, _3#97310] == Analyzed Logical Plan == id: int, a: string, b: int, features: vector, label: double Project [id#97238, a#97239, b#97240, features#97281, label#97292] +- Project [id#97238, a#97239, b#97240, features#97281, cast(id#97238 as double) AS label#97292] +- Project [id#97238, a#97239, b#97240, features#97281] +- Project [id#97238, a#97239, b#97240, stridx_2f45842fe317#97261, onehot_922d3217070b#97267, features#97274 AS features#97281] +- Project [id#97238, a#97239, b#97240, stridx_2f45842fe317#97261, onehot_922d3217070b#97267, UDF(named_struct(onehot_922d3217070b, onehot_922d3217070b#97267, b_double_rFormula_84ede8fece19, cast(b#97240 as double))) AS features#97274] +- Project [id#97238, a#97239, b#97240, stridx_2f45842fe317#97261, if ((isnull(cast(stridx_2f45842fe317#97261 as double)) || isnull(0))) null else UDF(cast(stridx_2f45842fe317#97261 as double), 0) AS onehot_922d3217070b#97267] +- Project [id#97238, a#97239, b#97240, UDF(cast(a#97239 as string)) AS stridx_2f45842fe317#97261] +- Project [id#97245 AS id#97238, a#97246 AS a#97239, b#97247 AS b#97240] +- Project [_1#97235 AS id#97245, _2#97236 AS a#97246, _3#97237 AS b#97247] +- Project [_1#97308 AS _1#97235, _2#97309 AS _2#97236, _3#97310 AS _3#97237] +- Streaming RelationV2 MemoryStreamDataSource$[_1#97308, _2#97309, _3#97310] == Optimized Logical Plan == Project [id#97238, a#97239, b#97240, features#97274 AS features#97281, cast(id#97238 as double) AS label#97292] +- Project [id#97238, a#97239, b#97240, UDF(named_struct(onehot_922d3217070b, UDF(stridx_2f45842fe317#97261, 0), b_double_rFormula_84ede8fece19, cast(b#97240 as double))) AS features#97274] +- Project [_1#97308 AS id#97238, _2#97309 AS a#97239, _3#97310 AS b#97240, UDF(_2#97309) AS stridx_2f45842fe317#97261] +- Streaming RelationV2 MemoryStreamDataSource$[_1#97308, _2#97309, _3#97310] == Physical Plan == *(1) Project [id#97238, a#97239, b#97240, features#97274 AS features#97281, cast(id#97238 as double) AS label#97292] +- *(1) Project [id#97238, a#97239, b#97240, UDF(named_struct(onehot_922d3217070b, UDF(stridx_2f45842fe317#97261, 0), b_double_rFormula_84ede8fece19, cast(b#97240 as double))) AS features#97274] +- *(1) Project [_1#97308 AS id#97238, _2#97309 AS a#97239, _3#97310 AS b#97240, UDF(_2#97309) AS stridx_2f45842fe317#97261] +- *(1) Project [_1#97308, _2#97309, _3#97310] +- *(1) ScanV2 MemoryStreamDataSource$[_1#97308, _2#97309, _3#97310]
sbt.ForkMain$ForkError: org.scalatest.exceptions.TestFailedException:
Timed out waiting for stream: The code passed to failAfter did not complete within 10 seconds.
java.lang.Thread.getStackTrace(Thread.java:1559)
org.scalatest.concurrent.TimeLimits.failAfterImpl(TimeLimits.scala:234)
org.scalatest.concurrent.TimeLimits.failAfterImpl$(TimeLimits.scala:233)
org.apache.spark.ml.feature.RFormulaSuite.failAfterImpl(RFormulaSuite.scala:28)
org.scalatest.concurrent.TimeLimits.failAfter(TimeLimits.scala:230)
org.scalatest.concurrent.TimeLimits.failAfter$(TimeLimits.scala:229)
org.apache.spark.ml.feature.RFormulaSuite.failAfter(RFormulaSuite.scala:28)
org.apache.spark.sql.streaming.StreamTest.$anonfun$testStream$7(StreamTest.scala:472)
org.apache.spark.sql.streaming.StreamTest.$anonfun$testStream$7$adapted(StreamTest.scala:471)
scala.collection.mutable.HashMap.$anonfun$foreach$1(HashMap.scala:149)
Caused by: null
java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:2151)
org.apache.spark.sql.execution.streaming.StreamExecution.awaitOffset(StreamExecution.scala:408)
org.apache.spark.sql.streaming.StreamTest.$anonfun$testStream$8(StreamTest.scala:473)
scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
org.scalatest.enablers.Timed$$anon$1.timeoutAfter(Timed.scala:127)
org.scalatest.concurrent.TimeLimits.failAfterImpl(TimeLimits.scala:239)
org.scalatest.concurrent.TimeLimits.failAfterImpl$(TimeLimits.scala:233)
org.apache.spark.ml.feature.RFormulaSuite.failAfterImpl(RFormulaSuite.scala:28)
org.scalatest.concurrent.TimeLimits.failAfter(TimeLimits.scala:230)
org.scalatest.concurrent.TimeLimits.failAfter$(TimeLimits.scala:229)
== Progress ==
AddData to MemoryStream[_1#97235,_2#97236,_3#97237]: (1,foo,4),(2,bar,4),(3,bar,5),(4,baz,5)
=> CheckAnswerByFunc
== Stream ==
Output Mode: Append
Stream state: {}
Thread state: alive
Thread stack trace: scala.collection.mutable.LinkedHashSet.createNewEntry(LinkedHashSet.scala:109)
scala.collection.mutable.LinkedHashSet.createNewEntry(LinkedHashSet.scala:44)
scala.collection.mutable.HashTable.findOrAddEntry(HashTable.scala:170)
scala.collection.mutable.HashTable.findOrAddEntry$(HashTable.scala:167)
scala.collection.mutable.LinkedHashSet.findOrAddEntry(LinkedHashSet.scala:44)
scala.collection.mutable.LinkedHashSet.add(LinkedHashSet.scala:68)
scala.collection.mutable.LinkedHashSet.$plus$eq(LinkedHashSet.scala:63)
scala.collection.mutable.LinkedHashSet.$plus$eq(LinkedHashSet.scala:44)
scala.collection.generic.Growable.$anonfun$$plus$plus$eq$1(Growable.scala:62)
scala.collection.generic.Growable$$Lambda$7/245475541.apply(Unknown Source)
scala.collection.immutable.Set$Set1.foreach(Set.scala:97)
scala.collection.generic.Growable.$plus$plus$eq(Growable.scala:62)
scala.collection.generic.Growable.$plus$plus$eq$(Growable.scala:53)
scala.collection.mutable.AbstractSet.$plus$plus$eq(Set.scala:48)
org.apache.spark.sql.catalyst.expressions.AttributeSet$.$anonfun$fromAttributeSets$1(AttributeSet.scala:49)
org.apache.spark.sql.catalyst.expressions.AttributeSet$$$Lambda$1582/1440923470.apply(Unknown Source)
scala.collection.IndexedSeqOptimized.foldLeft(IndexedSeqOptimized.scala:60)
scala.collection.IndexedSeqOptimized.foldLeft$(IndexedSeqOptimized.scala:68)
scala.collection.mutable.ArrayBuffer.foldLeft(ArrayBuffer.scala:49)
org.apache.spark.sql.catalyst.expressions.AttributeSet$.fromAttributeSets(AttributeSet.scala:49)
org.apache.spark.sql.catalyst.expressions.AttributeSet$.apply(AttributeSet.scala:44)
org.apache.spark.sql.catalyst.plans.QueryPlan.outputSet(QueryPlan.scala:40)
org.apache.spark.sql.catalyst.optimizer.ColumnPruning$$anonfun$apply$6.applyOrElse(Optimizer.scala:546)
org.apache.spark.sql.catalyst.optimizer.ColumnPruning$$anonfun$apply$6.applyOrElse(Optimizer.scala:544)
org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDown$1(TreeNode.scala:258)
org.apache.spark.sql.catalyst.trees.TreeNode$$Lambda$1517/366518998.apply(Unknown Source)
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:72)
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:258)
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDown(LogicalPlan.scala:29)
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDown(AnalysisHelper.scala:149)
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDown$(AnalysisHelper.scala:147)
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29)
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29)
org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:247)
org.apache.spark.sql.catalyst.optimizer.ColumnPruning$.apply(Optimizer.scala:544)
org.apache.spark.sql.catalyst.optimizer.ColumnPruning$.apply(Optimizer.scala:542)
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$2(RuleExecutor.scala:102)
org.apache.spark.sql.catalyst.rules.RuleExecutor$$Lambda$1501/2106141367.apply(Unknown Source)
scala.collection.LinearSeqOptimized.foldLeft(LinearSeqOptimized.scala:126)
scala.collection.LinearSeqOptimized.foldLeft$(LinearSeqOptimized.scala:122)
scala.collection.immutable.List.foldLeft(List.scala:89)
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1(RuleExecutor.scala:99)
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1$adapted(RuleExecutor.scala:91)
org.apache.spark.sql.catalyst.rules.RuleExecutor$$Lambda$1500/281516395.apply(Unknown Source)
scala.collection.immutable.List.foreach(List.scala:392)
org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:91)
org.apache.spark.sql.execution.streaming.IncrementalExecution.$anonfun$optimizedPlan$1(IncrementalExecution.scala:80)
org.apache.spark.sql.execution.streaming.IncrementalExecution$$Lambda$2339/1358008810.apply(Unknown Source)
org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111)
org.apache.spark.sql.execution.streaming.IncrementalExecution.optimizedPlan$lzycompute(IncrementalExecution.scala:80)
org.apache.spark.sql.execution.streaming.IncrementalExecution.optimizedPlan(IncrementalExecution.scala:79)
org.apache.spark.sql.execution.QueryExecution.$anonfun$sparkPlan$1(QueryExecution.scala:79)
org.apache.spark.sql.execution.QueryExecution$$Lambda$1688/1545683621.apply(Unknown Source)
org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111)
org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:75)
org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:75)
org.apache.spark.sql.execution.QueryExecution.$anonfun$executedPlan$1(QueryExecution.scala:85)
org.apache.spark.sql.execution.QueryExecution$$Lambda$1687/1031086586.apply(Unknown Source)
org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111)
org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:85)
org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:84)
org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$14(MicroBatchExecution.scala:537)
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$Lambda$2337/654111784.apply(Unknown Source)
org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:325)
org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:323)
org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:60)
org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:527)
org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:203)
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$Lambda$2244/726337336.apply$mcV$sp(Unknown Source)
scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:325)
org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:323)
org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:60)
org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:171)
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$Lambda$2242/874718659.apply$mcZ$sp(Unknown Source)
org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:56)
org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:165)
org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:286)
org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:198)
== Sink ==
== Plan ==
== Parsed Logical Plan ==
Project [id#97238, a#97239, b#97240, features#97281, label#97292]
+- Project [id#97238, a#97239, b#97240, features#97281, cast(id#97238 as double) AS label#97292]
+- Project [id#97238, a#97239, b#97240, features#97281]
+- Project [id#97238, a#97239, b#97240, stridx_2f45842fe317#97261, onehot_922d3217070b#97267, features#97274 AS features#97281]
+- Project [id#97238, a#97239, b#97240, stridx_2f45842fe317#97261, onehot_922d3217070b#97267, UDF(named_struct(onehot_922d3217070b, onehot_922d3217070b#97267, b_double_rFormula_84ede8fece19, cast(b#97240 as double))) AS features#97274]
+- Project [id#97238, a#97239, b#97240, stridx_2f45842fe317#97261, if ((isnull(cast(stridx_2f45842fe317#97261 as double)) || isnull(0))) null else UDF(cast(stridx_2f45842fe317#97261 as double), 0) AS onehot_922d3217070b#97267]
+- Project [id#97238, a#97239, b#97240, UDF(cast(a#97239 as string)) AS stridx_2f45842fe317#97261]
+- Project [id#97245 AS id#97238, a#97246 AS a#97239, b#97247 AS b#97240]
+- Project [_1#97235 AS id#97245, _2#97236 AS a#97246, _3#97237 AS b#97247]
+- Project [_1#97308 AS _1#97235, _2#97309 AS _2#97236, _3#97310 AS _3#97237]
+- Streaming RelationV2 MemoryStreamDataSource$[_1#97308, _2#97309, _3#97310]
== Analyzed Logical Plan ==
id: int, a: string, b: int, features: vector, label: double
Project [id#97238, a#97239, b#97240, features#97281, label#97292]
+- Project [id#97238, a#97239, b#97240, features#97281, cast(id#97238 as double) AS label#97292]
+- Project [id#97238, a#97239, b#97240, features#97281]
+- Project [id#97238, a#97239, b#97240, stridx_2f45842fe317#97261, onehot_922d3217070b#97267, features#97274 AS features#97281]
+- Project [id#97238, a#97239, b#97240, stridx_2f45842fe317#97261, onehot_922d3217070b#97267, UDF(named_struct(onehot_922d3217070b, onehot_922d3217070b#97267, b_double_rFormula_84ede8fece19, cast(b#97240 as double))) AS features#97274]
+- Project [id#97238, a#97239, b#97240, stridx_2f45842fe317#97261, if ((isnull(cast(stridx_2f45842fe317#97261 as double)) || isnull(0))) null else UDF(cast(stridx_2f45842fe317#97261 as double), 0) AS onehot_922d3217070b#97267]
+- Project [id#97238, a#97239, b#97240, UDF(cast(a#97239 as string)) AS stridx_2f45842fe317#97261]
+- Project [id#97245 AS id#97238, a#97246 AS a#97239, b#97247 AS b#97240]
+- Project [_1#97235 AS id#97245, _2#97236 AS a#97246, _3#97237 AS b#97247]
+- Project [_1#97308 AS _1#97235, _2#97309 AS _2#97236, _3#97310 AS _3#97237]
+- Streaming RelationV2 MemoryStreamDataSource$[_1#97308, _2#97309, _3#97310]
== Optimized Logical Plan ==
Project [id#97238, a#97239, b#97240, features#97274 AS features#97281, cast(id#97238 as double) AS label#97292]
+- Project [id#97238, a#97239, b#97240, UDF(named_struct(onehot_922d3217070b, UDF(stridx_2f45842fe317#97261, 0), b_double_rFormula_84ede8fece19, cast(b#97240 as double))) AS features#97274]
+- Project [_1#97308 AS id#97238, _2#97309 AS a#97239, _3#97310 AS b#97240, UDF(_2#97309) AS stridx_2f45842fe317#97261]
+- Streaming RelationV2 MemoryStreamDataSource$[_1#97308, _2#97309, _3#97310]
== Physical Plan ==
*(1) Project [id#97238, a#97239, b#97240, features#97274 AS features#97281, cast(id#97238 as double) AS label#97292]
+- *(1) Project [id#97238, a#97239, b#97240, UDF(named_struct(onehot_922d3217070b, UDF(stridx_2f45842fe317#97261, 0), b_double_rFormula_84ede8fece19, cast(b#97240 as double))) AS features#97274]
+- *(1) Project [_1#97308 AS id#97238, _2#97309 AS a#97239, _3#97310 AS b#97240, UDF(_2#97309) AS stridx_2f45842fe317#97261]
+- *(1) Project [_1#97308, _2#97309, _3#97310]
+- *(1) ScanV2 MemoryStreamDataSource$[_1#97308, _2#97309, _3#97310]
at org.scalatest.Assertions.newAssertionFailedException(Assertions.scala:528)
at org.scalatest.Assertions.newAssertionFailedException$(Assertions.scala:527)
at org.scalatest.FunSuite.newAssertionFailedException(FunSuite.scala:1560)
at org.scalatest.Assertions.fail(Assertions.scala:1089)
at org.scalatest.Assertions.fail$(Assertions.scala:1085)
at org.scalatest.FunSuite.fail(FunSuite.scala:1560)
at org.apache.spark.sql.streaming.StreamTest.failTest$1(StreamTest.scala:453)
at org.apache.spark.sql.streaming.StreamTest.liftedTree1$1(StreamTest.scala:783)
at org.apache.spark.sql.streaming.StreamTest.testStream(StreamTest.scala:759)
at org.apache.spark.sql.streaming.StreamTest.testStream$(StreamTest.scala:329)
at org.apache.spark.ml.feature.RFormulaSuite.testStream(RFormulaSuite.scala:28)
at org.apache.spark.ml.util.MLTest.testTransformerOnStreamData(MLTest.scala:85)
at org.apache.spark.ml.util.MLTest.testTransformerOnStreamData$(MLTest.scala:66)
at org.apache.spark.ml.feature.RFormulaSuite.testTransformerOnStreamData(RFormulaSuite.scala:28)
at org.apache.spark.ml.util.MLTest.testTransformerByGlobalCheckFunc(MLTest.scala:120)
at org.apache.spark.ml.util.MLTest.testTransformerByGlobalCheckFunc$(MLTest.scala:113)
at org.apache.spark.ml.feature.RFormulaSuite.testTransformerByGlobalCheckFunc(RFormulaSuite.scala:28)
at org.apache.spark.ml.feature.RFormulaSuite.testRFormulaTransform(RFormulaSuite.scala:42)
at org.apache.spark.ml.feature.RFormulaSuite.$anonfun$new$13(RFormulaSuite.scala:149)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.scalatest.OutcomeOf.outcomeOf(OutcomeOf.scala:85)
at org.scalatest.OutcomeOf.outcomeOf$(OutcomeOf.scala:83)
at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104)
at org.scalatest.Transformer.apply(Transformer.scala:22)
at org.scalatest.Transformer.apply(Transformer.scala:20)
at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:186)
at org.apache.spark.SparkFunSuite.withFixture(SparkFunSuite.scala:104)
at org.scalatest.FunSuiteLike.invokeWithFixture$1(FunSuiteLike.scala:184)
at org.scalatest.FunSuiteLike.$anonfun$runTest$1(FunSuiteLike.scala:196)
at org.scalatest.SuperEngine.runTestImpl(Engine.scala:289)
at org.scalatest.FunSuiteLike.runTest(FunSuiteLike.scala:196)
at org.scalatest.FunSuiteLike.runTest$(FunSuiteLike.scala:178)
at org.apache.spark.ml.feature.RFormulaSuite.org$scalatest$BeforeAndAfterEach$$super$runTest(RFormulaSuite.scala:28)
at org.scalatest.BeforeAndAfterEach.runTest(BeforeAndAfterEach.scala:221)
at org.scalatest.BeforeAndAfterEach.runTest$(BeforeAndAfterEach.scala:214)
at org.apache.spark.ml.feature.RFormulaSuite.runTest(RFormulaSuite.scala:28)
at org.scalatest.FunSuiteLike.$anonfun$runTests$1(FunSuiteLike.scala:229)
at org.scalatest.SuperEngine.$anonfun$runTestsInBranch$1(Engine.scala:396)
at scala.collection.immutable.List.foreach(List.scala:392)
at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:384)
at org.scalatest.SuperEngine.runTestsInBranch(Engine.scala:379)
at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:461)
at org.scalatest.FunSuiteLike.runTests(FunSuiteLike.scala:229)
at org.scalatest.FunSuiteLike.runTests$(FunSuiteLike.scala:228)
at org.scalatest.FunSuite.runTests(FunSuite.scala:1560)
at org.scalatest.Suite.run(Suite.scala:1147)
at org.scalatest.Suite.run$(Suite.scala:1129)
at org.scalatest.FunSuite.org$scalatest$FunSuiteLike$$super$run(FunSuite.scala:1560)
at org.scalatest.FunSuiteLike.$anonfun$run$1(FunSuiteLike.scala:233)
at org.scalatest.SuperEngine.runImpl(Engine.scala:521)
at org.scalatest.FunSuiteLike.run(FunSuiteLike.scala:233)
at org.scalatest.FunSuiteLike.run$(FunSuiteLike.scala:232)
at org.apache.spark.SparkFunSuite.org$scalatest$BeforeAndAfterAll$$super$run(SparkFunSuite.scala:53)
at org.scalatest.BeforeAndAfterAll.liftedTree1$1(BeforeAndAfterAll.scala:213)
at org.scalatest.BeforeAndAfterAll.run(BeforeAndAfterAll.scala:210)
at org.scalatest.BeforeAndAfterAll.run$(BeforeAndAfterAll.scala:208)
at org.apache.spark.SparkFunSuite.run(SparkFunSuite.scala:53)
at org.scalatest.tools.Framework.org$scalatest$tools$Framework$$runSuite(Framework.scala:314)
at org.scalatest.tools.Framework$ScalaTestTask.execute(Framework.scala:507)
at sbt.ForkMain$Run$2.call(ForkMain.java:296)
at sbt.ForkMain$Run$2.call(ForkMain.java:286)
at java.util.concurrent.FutureTask.run(FutureTask.java:266)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)