UDF error

[thbeh]

I was testing flint example notebook with Spark 2.4.3 (Python 3.7) and get this error on paragraph 8 -

Py4JJavaError Traceback (most recent call last)
in
10 sp500_decayed_return = sp500_joined_return.summarizeWindows(
11 window = windows.past_absolute_time('7day'),
---> 12 summarizer = {'previous_day_return_decayed_sum': decayed(sp500_joined_return[['previous_day_return']])}
13 )
14

/opt/conda/lib/python3.7/site-packages/ts/flint/dataframe.py in summarizeWindows(self, window, summarizer, key)
1269
1270 if isinstance(summarizer, collections.Mapping):
-> 1271 return self._summarizeWindows_udf(window, summarizer, key)
1272 else:
1273 return self._summarizeWindows_builtin(window, summarizer, key)

/opt/conda/lib/python3.7/site-packages/ts/flint/dataframe.py in _summarizeWindows_udf(self, window, columns, key)
1487 windowed = windowed.filter(windowed[base_rows_col_name].isNotNull())
1488
-> 1489 result = windowed._concatArrowAndExplode(base_rows_col_name, schema_col_names, data_col_names)
1490
1491 return result

/opt/conda/lib/python3.7/site-packages/ts/flint/dataframe.py in _concatArrowAndExplode(self, base_rows_col, schema_cols, data_cols)
928 base_rows_col,
929 utils.list_to_seq(self._sc, schema_cols),
--> 930 utils.list_to_seq(self._sc, data_cols))
931 return TimeSeriesDataFrame._from_tsrdd(tsrdd, self.sql_ctx)
932

/vagrant/spark-2.4.3-bin-hadoop2.7/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py in call(self, *args)
1255 answer = self.gateway_client.send_command(command)
1256 return_value = get_return_value(
-> 1257 answer, self.gateway_client, self.target_id, self.name)
1258
1259 for temp_arg in temp_args:

/vagrant/spark-2.4.3-bin-hadoop2.7/python/pyspark/sql/utils.py in deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()

/vagrant/spark-2.4.3-bin-hadoop2.7/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
326 raise Py4JJavaError(
327 "An error occurred while calling {0}{1}{2}.\n".
--> 328 format(target_id, ".", name), value)
329 else:
330 raise Py4JError(

Py4JJavaError: An error occurred while calling o459.concatArrowAndExplode.
: java.lang.NoSuchMethodError: org.apache.spark.sql.catalyst.expressions.codegen.ExprCode.code()Ljava/lang/String;
at org.apache.spark.sql.TimestampCast$class.doGenCode(TimestampCast.scala:76)
at org.apache.spark.sql.NanosToTimestamp.doGenCode(TimestampCast.scala:31)
at org.apache.spark.sql.catalyst.expressions.Expression$$anonfun$genCode$2.apply(Expression.scala:108)
at org.apache.spark.sql.catalyst.expressions.Expression$$anonfun$genCode$2.apply(Expression.scala:105)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.sql.catalyst.expressions.Expression.genCode(Expression.scala:105)
at org.apache.spark.sql.catalyst.expressions.Alias.genCode(namedExpressions.scala:155)
at org.apache.spark.sql.execution.ProjectExec$$anonfun$6.apply(basicPhysicalOperators.scala:60)
at org.apache.spark.sql.execution.ProjectExec$$anonfun$6.apply(basicPhysicalOperators.scala:60)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at org.apache.spark.sql.execution.ProjectExec.doConsume(basicPhysicalOperators.scala:60)
at org.apache.spark.sql.execution.CodegenSupport$class.consume(WholeStageCodegenExec.scala:189)
at org.apache.spark.sql.execution.InputAdapter.consume(WholeStageCodegenExec.scala:374)
at org.apache.spark.sql.execution.InputAdapter.doProduce(WholeStageCodegenExec.scala:403)
at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:90)
at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:85)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:85)
at org.apache.spark.sql.execution.InputAdapter.produce(WholeStageCodegenExec.scala:374)
at org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:45)
at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:90)
at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:85)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:85)
at org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:35)
at org.apache.spark.sql.execution.WholeStageCodegenExec.doCodeGen(WholeStageCodegenExec.scala:544)
at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:598)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.GenerateExec.doExecute(GenerateExec.scala:80)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.InputAdapter.inputRDDs(WholeStageCodegenExec.scala:391)
at org.apache.spark.sql.execution.FilterExec.inputRDDs(basicPhysicalOperators.scala:121)
at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:627)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.python.EvalPythonExec.doExecute(EvalPythonExec.scala:87)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.InputAdapter.inputRDDs(WholeStageCodegenExec.scala:391)
at org.apache.spark.sql.execution.ProjectExec.inputRDDs(basicPhysicalOperators.scala:41)
at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:627)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
at com.twosigma.flint.timeseries.NormalizedDataFrameStore.toOrderedRdd(TimeSeriesStore.scala:252)
at com.twosigma.flint.timeseries.NormalizedDataFrameStore.orderedRdd(TimeSeriesStore.scala:237)
at com.twosigma.flint.timeseries.TimeSeriesRDDImpl.orderedRdd(TimeSeriesRDD.scala:1346)
at com.twosigma.flint.timeseries.TimeSeriesRDDImpl.concatArrowAndExplode(TimeSeriesRDD.scala:1946)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)