You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@spark.apache.org by Rachana Srivastava <Ra...@markmonitor.com> on 2015/12/16 22:01:28 UTC
RandomForestModel Save is throwing NoSuchMethodError with Spark
Version 1.5x
final RandomForestModel model = RandomForest.trainClassifier(trainrdd, NUM_CLASSES,
categoricalFeaturesInfo, NUM_TREES, FEATURESUBSETSTRATEGY, IMPURITY, MAX_TREE_DEPTH, MAX_BIN, SEED);
model.save(sc.sc(), MODEL_DIRECTORY);
I have just these two packages in my maven folder
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-mllib_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
</dependencies>
Maven dependency Tree:
+- org.apache.spark:spark-streaming-kafka_2.11:jar:1.5.2:compile
[INFO] | +- org.apache.kafka:kafka_2.11:jar:0.8.2.1:compile
[INFO] | | +- org.scala-lang.modules:scala-xml_2.11:jar:1.0.2:compile
[INFO] | | +- com.yammer.metrics:metrics-core:jar:2.2.0:compile
[INFO] | | +- org.scala-lang.modules:scala-parser-combinators_2.11:jar:1.0.2:compile
[INFO] | | +- com.101tec:zkclient:jar:0.3:compile
[INFO] | | +- org.scala-lang:scala-library:jar:2.11.5:compile
[INFO] | | \- org.apache.kafka:kafka-clients:jar:0.8.2.1:compile
[INFO] | \- org.spark-project.spark:unused:jar:1.0.0:compile
[INFO] \- org.apache.spark:spark-mllib_2.11:jar:1.5.2:compile
[INFO] +- org.apache.spark:spark-core_2.11:jar:1.5.2:compile
[INFO] | +- org.apache.avro:avro-mapred:jar:hadoop2:1.7.7:compile
[INFO] | | +- org.apache.avro:avro-ipc:jar:1.7.7:compile
[INFO] | | | \- org.apache.avro:avro:jar:1.7.7:compile
[INFO] | | +- org.apache.avro:avro-ipc:jar:tests:1.7.7:compile
[INFO] | | +- org.codehaus.jackson:jackson-core-asl:jar:1.9.13:compile
[INFO] | | \- org.codehaus.jackson:jackson-mapper-asl:jar:1.9.13:compile
[INFO] | +- com.twitter:chill_2.11:jar:0.5.0:compile
[INFO] | | \- com.esotericsoftware.kryo:kryo:jar:2.21:compile
[INFO] | | +- com.esotericsoftware.reflectasm:reflectasm:jar:shaded:1.07:compile
[INFO] | | +- com.esotericsoftware.minlog:minlog:jar:1.2:compile
[INFO] | | \- org.objenesis:objenesis:jar:1.2:compile
[INFO] | +- com.twitter:chill-java:jar:0.5.0:compile
[INFO] | +- org.apache.hadoop:hadoop-client:jar:2.2.0:compile
[INFO] | | +- org.apache.hadoop:hadoop-common:jar:2.2.0:compile
[INFO] | | | +- commons-cli:commons-cli:jar:1.2:compile
[INFO] | | | +- org.apache.commons:commons-math:jar:2.1:compile
[INFO] | | | +- xmlenc:xmlenc:jar:0.52:compile
[INFO] | | | +- commons-configuration:commons-configuration:jar:1.6:compile
[INFO] | | | | +- commons-collections:commons-collections:jar:3.2.1:compile
[INFO] | | | | +- commons-digester:commons-digester:jar:1.8:compile
[INFO] | | | | | \- commons-beanutils:commons-beanutils:jar:1.7.0:compile
[INFO] | | | | \- commons-beanutils:commons-beanutils-core:jar:1.8.0:compile
[INFO] | | | +- org.apache.hadoop:hadoop-auth:jar:2.2.0:compile
[INFO] | | | \- org.apache.commons:commons-compress:jar:1.4.1:compile
[INFO] | | | \- org.tukaani:xz:jar:1.0:compile
[INFO] | | +- org.apache.hadoop:hadoop-hdfs:jar:2.2.0:compile
[INFO] | | | \- org.mortbay.jetty:jetty-util:jar:6.1.26:compile
[INFO] | | +- org.apache.hadoop:hadoop-mapreduce-client-app:jar:2.2.0:compile
[INFO] | | | +- org.apache.hadoop:hadoop-mapreduce-client-common:jar:2.2.0:compile
[INFO] | | | | +- org.apache.hadoop:hadoop-yarn-client:jar:2.2.0:compile
[INFO] | | | | \- org.apache.hadoop:hadoop-yarn-server-common:jar:2.2.0:compile
[INFO] | | | \- org.apache.hadoop:hadoop-mapreduce-client-shuffle:jar:2.2.0:compile
[INFO] | | +- org.apache.hadoop:hadoop-yarn-api:jar:2.2.0:compile
[INFO] | | +- org.apache.hadoop:hadoop-mapreduce-client-core:jar:2.2.0:compile
[INFO] | | | \- org.apache.hadoop:hadoop-yarn-common:jar:2.2.0:compile
[INFO] | | +- org.apache.hadoop:hadoop-mapreduce-client-jobclient:jar:2.2.0:compile
[INFO] | | \- org.apache.hadoop:hadoop-annotations:jar:2.2.0:compile
[INFO] | +- org.apache.spark:spark-launcher_2.11:jar:1.5.2:compile
[INFO] | +- org.apache.spark:spark-network-common_2.11:jar:1.5.2:compile
[INFO] | +- org.apache.spark:spark-network-shuffle_2.11:jar:1.5.2:compile
[INFO] | +- org.apache.spark:spark-unsafe_2.11:jar:1.5.2:compile
[INFO] | +- net.java.dev.jets3t:jets3t:jar:0.7.1:compile
[INFO] | | \- commons-httpclient:commons-httpclient:jar:3.1:compile
[INFO] | +- org.apache.curator:curator-recipes:jar:2.4.0:compile
[INFO] | | +- org.apache.curator:curator-framework:jar:2.4.0:compile
[INFO] | | +- org.apache.zookeeper:zookeeper:jar:3.4.5:compile
[INFO] | | | \- jline:jline:jar:0.9.94:compile
[INFO] | | \- com.google.guava:guava:jar:14.0.1:compile
[INFO] | +- org.eclipse.jetty.orbit:javax.servlet:jar:3.0.0.v201112011016:compile
[INFO] | +- org.apache.commons:commons-lang3:jar:3.3.2:compile
[INFO] | +- org.slf4j:jul-to-slf4j:jar:1.7.10:compile
[INFO] | +- org.slf4j:jcl-over-slf4j:jar:1.7.10:compile
[INFO] | +- com.ning:compress-lzf:jar:1.0.3:compile
[INFO] | +- org.xerial.snappy:snappy-java:jar:1.1.1.7:compile
[INFO] | +- net.jpountz.lz4:lz4:jar:1.3.0:compile
[INFO] | +- org.roaringbitmap:RoaringBitmap:jar:0.4.5:compile
[INFO] | +- commons-net:commons-net:jar:2.2:compile
[INFO] | +- com.typesafe.akka:akka-remote_2.11:jar:2.3.11:compile
[INFO] | | +- com.typesafe.akka:akka-actor_2.11:jar:2.3.11:compile
[INFO] | | | \- com.typesafe:config:jar:1.2.1:compile
[INFO] | | +- io.netty:netty:jar:3.8.0.Final:compile
[INFO] | | +- com.google.protobuf:protobuf-java:jar:2.5.0:compile
[INFO] | | \- org.uncommons.maths:uncommons-maths:jar:1.2.2a:compile
[INFO] | +- com.typesafe.akka:akka-slf4j_2.11:jar:2.3.11:compile
[INFO] | +- org.json4s:json4s-jackson_2.11:jar:3.2.10:compile
[INFO] | | \- org.json4s:json4s-core_2.11:jar:3.2.10:compile
[INFO] | | +- org.json4s:json4s-ast_2.11:jar:3.2.10:compile
[INFO] | | \- org.scala-lang:scalap:jar:2.11.0:compile
[INFO] | | \- org.scala-lang:scala-compiler:jar:2.11.0:compile
[INFO] | +- com.sun.jersey:jersey-server:jar:1.9:compile
[INFO] | | \- asm:asm:jar:3.1:compile
[INFO] | +- com.sun.jersey:jersey-core:jar:1.9:compile
[INFO] | +- org.apache.mesos:mesos:jar:shaded-protobuf:0.21.1:compile
[INFO] | +- io.netty:netty-all:jar:4.0.29.Final:compile
[INFO] | +- com.clearspring.analytics:stream:jar:2.7.0:compile
[INFO] | +- io.dropwizard.metrics:metrics-core:jar:3.1.2:compile
[INFO] | +- io.dropwizard.metrics:metrics-jvm:jar:3.1.2:compile
[INFO] | +- io.dropwizard.metrics:metrics-json:jar:3.1.2:compile
[INFO] | +- io.dropwizard.metrics:metrics-graphite:jar:3.1.2:compile
[INFO] | +- com.fasterxml.jackson.core:jackson-databind:jar:2.4.4:compile
[INFO] | | +- com.fasterxml.jackson.core:jackson-annotations:jar:2.4.0:compile
[INFO] | | \- com.fasterxml.jackson.core:jackson-core:jar:2.4.4:compile
[INFO] | +- com.fasterxml.jackson.module:jackson-module-scala_2.11:jar:2.4.4:compile
[INFO] | | +- org.scala-lang:scala-reflect:jar:2.11.2:compile
[INFO] | | \- com.thoughtworks.paranamer:paranamer:jar:2.6:compile
[INFO] | +- org.apache.ivy:ivy:jar:2.4.0:compile
[INFO] | +- oro:oro:jar:2.0.8:compile
[INFO] | +- org.tachyonproject:tachyon-client:jar:0.7.1:compile
[INFO] | | +- commons-lang:commons-lang:jar:2.4:compile
[INFO] | | +- commons-io:commons-io:jar:2.4:compile
[INFO] | | +- org.apache.curator:curator-client:jar:2.1.0-incubating:compile
[INFO] | | +- org.tachyonproject:tachyon-underfs-hdfs:jar:0.7.1:compile
[INFO] | | \- org.tachyonproject:tachyon-underfs-local:jar:0.7.1:compile
[INFO] | +- net.razorvine:pyrolite:jar:4.4:compile
[INFO] | \- net.sf.py4j:py4j:jar:0.8.2.1:compile
[INFO] +- org.apache.spark:spark-streaming_2.11:jar:1.5.2:compile
[INFO] +- org.apache.spark:spark-sql_2.11:jar:1.5.2:compile
[INFO] | +- org.apache.spark:spark-catalyst_2.11:jar:1.5.2:compile
[INFO] | | \- org.codehaus.janino:janino:jar:2.7.8:compile
[INFO] | | \- org.codehaus.janino:commons-compiler:jar:2.7.8:compile
[INFO] | +- org.apache.parquet:parquet-column:jar:1.7.0:compile
[INFO] | | +- org.apache.parquet:parquet-common:jar:1.7.0:compile
[INFO] | | \- org.apache.parquet:parquet-encoding:jar:1.7.0:compile
[INFO] | | \- org.apache.parquet:parquet-generator:jar:1.7.0:compile
[INFO] | \- org.apache.parquet:parquet-hadoop:jar:1.7.0:compile
[INFO] | +- org.apache.parquet:parquet-format:jar:2.3.0-incubating:compile
[INFO] | \- org.apache.parquet:parquet-jackson:jar:1.7.0:compile
[INFO] +- org.apache.spark:spark-graphx_2.11:jar:1.5.2:compile
[INFO] | +- com.github.fommil.netlib:core:jar:1.1.2:compile
[INFO] | \- net.sourceforge.f2j:arpack_combined_all:jar:0.1:compile
[INFO] +- org.scalanlp:breeze_2.11:jar:0.11.2:compile
[INFO] | +- org.scalanlp:breeze-macros_2.11:jar:0.11.2:compile
[INFO] | +- net.sf.opencsv:opencsv:jar:2.3:compile
[INFO] | +- com.github.rwl:jtransforms:jar:2.4.0:compile
[INFO] | \- org.spire-math:spire_2.11:jar:0.7.4:compile
[INFO] | \- org.spire-math:spire-macros_2.11:jar:0.7.4:compile
[INFO] +- org.apache.commons:commons-math3:jar:3.4.1:compile
[INFO] \- org.jpmml:pmml-model:jar:1.1.15:compile
[INFO] +- org.jpmml:pmml-agent:jar:1.1.15:compile
[INFO] +- org.jpmml:pmml-schema:jar:1.1.15:compile
[INFO] \- com.sun.xml.bind:jaxb-impl:jar:2.2.7:compile
[INFO] \- com.sun.xml.bind:jaxb-core:jar:2.2.7:compile
[INFO] \- javax.xml.bind:jaxb-api:jar:2.2.7:compile
Exception Details:
ERROR: org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation - Aborting job.
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 22.0 failed 1 times, most recent failure: Lost task 0.0 in stage 22.0 (TID 230, localhost): java.lang.NoSuchMethodError: parquet.schema.Types$GroupBuilder.addField(Lparquet/schema/Type;)Lparquet/schema/Types$BaseGroupBuilder;
at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:517)
at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:516)
at scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:51)
at scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:60)
at scala.collection.mutable.ArrayOps$ofRef.foldLeft(ArrayOps.scala:108)
at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:516)
at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:312)
at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:305)
at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:305)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at org.apache.spark.sql.types.StructType.foreach(StructType.scala:92)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at org.apache.spark.sql.types.StructType.map(StructType.scala:92)
at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convert(CatalystSchemaConverter.scala:305)
at org.apache.spark.sql.execution.datasources.parquet.ParquetTypesConverter$.convertFromAttributes(ParquetTypesConverter.scala:58)
at org.apache.spark.sql.execution.datasources.parquet.RowWriteSupport.init(ParquetTableSupport.scala:55)
at parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:287)
at parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:261)
at org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.<init>(ParquetRelation.scala:94)
at org.apache.spark.sql.execution.datasources.parquet.ParquetRelation$$anon$3.newInstance(ParquetRelation.scala:272)
at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:233)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$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)