holdenk / learning-spark-examples Goto Github PK
View Code? Open in Web Editor NEWExamples for learning spark
Home Page: http://amzn.to/1tY3EtA
License: MIT License
Examples for learning spark
Home Page: http://amzn.to/1tY3EtA
License: MIT License
Hi,
Not sure if this is the place to report errors, but I'm getting an exception using the BasicParseJsonWithJackson example. Not sure where to go with this now, I looked online and there's was no readily available solution.
Any help would be great, enjoying the book so far.
I've copied it into a new project, but its the same code (different case classes).
package com.companies
import org.apache.spark._
import com.fasterxml.jackson.module.scala.DefaultScalaModule
import com.fasterxml.jackson.module.scala.experimental.ScalaObjectMapper
import com.fasterxml.jackson.databind.ObjectMapper
import com.fasterxml.jackson.databind.DeserializationFeature
object ParseCompanyInformationJson {
def main(args: Array[String]) {
val inputFile = "/data/companies.json"
val outputFile = "/data/companies-output.json"
val conf = new SparkConf().setMaster("local").setAppName("Company Information Json")
val sc = new SparkContext(conf)
val input = sc.textFile(inputFile)
val mapper = new ObjectMapper with ScalaObjectMapper
mapper.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false)
mapper.registerModule(DefaultScalaModule)
// Parse it into a specific case class. We use flatMap to handle errors
// by returning an empty list (None) if we encounter an issue and a
// list with one element if everything is ok (Some(_)).
val result = input.flatMap(record => {
try {
Some(mapper.readValue(record, classOf[Company]))
} catch {
case e: Exception => None
}
})
result.map(mapper.writeValueAsString(_)).saveAsTextFile(outputFile)
}
}
Exception in thread "main" org.apache.spark.SparkException: Task not serializable
at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:166)
at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:158)
at org.apache.spark.SparkContext.clean(SparkContext.scala:1435)
at org.apache.spark.rdd.RDD.flatMap(RDD.scala:278)
at com.elevate.companies.ParseCompanyInformationJson$.main(ParseCompanyInformationJson.scala:26)
at com.elevate.companies.ParseCompanyInformationJson.main(ParseCompanyInformationJson.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.deploy.SparkSubmit$.launch(SparkSubmit.scala:358)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:75)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.io.NotSerializableException: com.fasterxml.jackson.module.scala.modifiers.SetTypeModifier$
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1183)
at java.io.ObjectOutputStream.writeArray(ObjectOutputStream.java:1377)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1173)
at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1547)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1508)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1431)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1177)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:347)
at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:42)
at org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:73)
at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:164)
... 12 more
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.