Re: Running spark from Eclipse and then Jar
nknown Source) > at > > org.apache.spark.sql.execution.datasources.DataSource$$anonfun$5$$anonfun$apply$1.apply(DataSource.scala:132) > at > > org.apache.spark.sql.execution.datasources.DataSource$$anonfun$5$$anonfun$apply$1.apply(DataSource.scala:132) > at scala.util.Try$.apply(Try.scala:192) > at > > org.apache.spark.sql.execution.datasources.DataSource$$anonfun$5.apply(DataSource.scala:132) > at > > org.apache.spark.sql.execution.datasources.DataSource$$anonfun$5.apply(DataSource.scala:132) > at scala.util.Try.orElse(Try.scala:84) > at > > org.apache.spark.sql.execution.datasources.DataSource.lookupDataSource(DataSource.scala:132) > ... 8 more > 16/12/07 15:16:46 INFO SparkContext: Invoking stop() from shutdown hook > 16/12/07 15:16:46 INFO SparkUI: Stopped Spark web UI at > http://192.168.19.2:4040 > 16/12/07 15:16:46 INFO MapOutputTrackerMasterEndpoint: > MapOutputTrackerMasterEndpoint stopped! > 16/12/07 15:16:46 INFO MemoryStore: MemoryStore cleared > 16/12/07 15:16:46 INFO BlockManager: BlockManager stopped > 16/12/07 15:16:46 INFO BlockManagerMaster: BlockManagerMaster stopped > 16/12/07 15:16:46 INFO > OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: > OutputCommitCoordinator stopped! > 16/12/07 15:16:46 INFO SparkContext: Successfully stopped SparkContext > 16/12/07 15:16:46 INFO ShutdownHookManager: Shutdown hook called > 16/12/07 15:16:46 INFO ShutdownHookManager: Deleting directory > > C:\Users\Owner\AppData\Local\Temp\spark-dab2587b-a794-4947-ac13-d40056cf71d8 > > C:\Users\Owner> > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > public final class JavaWordCount { > private static final Pattern SPACE = Pattern.compile(" "); > > public static void main(String[] args) throws Exception { > > if (args.length < 1) { > System.err.println("Usage: JavaWordCount "); > System.exit(1); > } > > //boiler plate needed to run locally > SparkConf conf = new SparkConf().setAppName("Word Count > Application").setMaster("local[*]"); > JavaSparkContext sc = new JavaSparkContext(conf); > > SparkSession spark = SparkSession > .builder() > .appName("Word Count") > .getOrCreate() > .newSession(); > > > JavaRDD lines = spark.read().textFile(args[0]).javaRDD(); > > > JavaRDD words = lines.flatMap(new FlatMapFunction<String, > String>() { > @Override > public Iterator call(String s) { > return Arrays.asList(SPACE.split(s)).iterator(); > } > }); > > JavaPairRDD<String, Integer> ones = words.mapToPair( > new PairFunction<String, String, Integer>() { > @Override > public Tuple2<String, Integer> call(String s) { > return new Tuple2<>(s, 1); > } > }); > > JavaPairRDD<String, Integer> counts = ones.reduceByKey( > new Function2<Integer, Integer, Integer>() { > @Override > public Integer call(Integer i1, Integer i2) { > return i1 + i2; > } > }); > > List<Tuple2String, Integer>> output = counts.collect(); > for (Tuple2 tuple : output) { > System.out.println(tuple._1() + ": " + tuple._2()); > } > spark.stop(); > } > } > > > > > -- > View this message in context: > http://apache-spark-user-list.1001560.n3.nabble.com/Running-spark-from-Eclipse-and-then-Jar-tp28182.html > Sent from the Apache Spark User List mailing list archive at Nabble.com. > > - > To unsubscribe e-mail: user-unsubscr...@spark.apache.org > > > > >
Re: Running spark from Eclipse and then Jar
Reader.load(DataFrameReader.scala:149) >> at >> org.apache.spark.sql.DataFrameReader.text(DataFrameReader.scala:504) >> at >> org.apache.spark.sql.DataFrameReader.textFile(DataFrameReader.scala:540) >> at >> org.apache.spark.sql.DataFrameReader.textFile(DataFrameReader.scala:513) >> at JavaWordCount.main(JavaWordCount.java:57) >> Caused by: java.lang.ClassNotFoundException: text.DefaultSource >> at java.net.URLClassLoader.findClass(Unknown Source) >> at java.lang.ClassLoader.loadClass(Unknown Source) >> at sun.misc.Launcher$AppClassLoader.loadClass(Unknown Source) >> at java.lang.ClassLoader.loadClass(Unknown Source) >> at >> org.apache.spark.sql.execution.datasources.DataSource$$anonfun$5$$ >> anonfun$apply$1.apply(DataSource.scala:132) >> at >> org.apache.spark.sql.execution.datasources.DataSource$$anonfun$5$$ >> anonfun$apply$1.apply(DataSource.scala:132) >> at scala.util.Try$.apply(Try.scala:192) >> at >> org.apache.spark.sql.execution.datasources.DataSource$$anonfun$5.apply( >> DataSource.scala:132) >> at >> org.apache.spark.sql.execution.datasources.DataSource$$anonfun$5.apply( >> DataSource.scala:132) >> at scala.util.Try.orElse(Try.scala:84) >> at >> org.apache.spark.sql.execution.datasources.DataSource.lookupDataSource( >> DataSource.scala:132) >> ... 8 more >> 16/12/07 15:16:46 INFO SparkContext: Invoking stop() from shutdown hook >> 16/12/07 15:16:46 INFO SparkUI: Stopped Spark web UI at >> http://192.168.19.2:4040 >> 16/12/07 15:16:46 INFO MapOutputTrackerMasterEndpoint: >> MapOutputTrackerMasterEndpoint stopped! >> 16/12/07 15:16:46 INFO MemoryStore: MemoryStore cleared >> 16/12/07 15:16:46 INFO BlockManager: BlockManager stopped >> 16/12/07 15:16:46 INFO BlockManagerMaster: BlockManagerMaster stopped >> 16/12/07 15:16:46 INFO >> OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: >> OutputCommitCoordinator stopped! >> 16/12/07 15:16:46 INFO SparkContext: Successfully stopped SparkContext >> 16/12/07 15:16:46 INFO ShutdownHookManager: Shutdown hook called >> 16/12/07 15:16:46 INFO ShutdownHookManager: Deleting directory >> C:\Users\Owner\AppData\Local\Temp\spark-dab2587b-a794-4947- >> ac13-d40056cf71d8 >> >> C:\Users\Owner> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> public final class JavaWordCount { >> private static final Pattern SPACE = Pattern.compile(" "); >> >> public static void main(String[] args) throws Exception { >> >> if (args.length < 1) { >> System.err.println("Usage: JavaWordCount "); >> System.exit(1); >> } >> >> //boiler plate needed to run locally >> SparkConf conf = new SparkConf().setAppName("Word Count >> Application").setMaster("local[*]"); >> JavaSparkContext sc = new JavaSparkContext(conf); >> >> SparkSession spark = SparkSession >> .builder() >> .appName("Word Count") >> .getOrCreate() >> .newSession(); >> >> >> JavaRDD lines = spark.read().textFile(args[0]).javaRDD(); >> >> >> JavaRDD words = lines.flatMap(new FlatMapFunction<String, >> String>() { >> @Override >> public Iterator call(String s) { >> return Arrays.asList(SPACE.split(s)).iterator(); >> } >> }); >> >> JavaPairRDD<String, Integer> ones = words.mapToPair( >> new PairFunction<String, String, Integer>() { >> @Override >> public Tuple2<String, Integer> call(String s) { >> return new Tuple2<>(s, 1); >> } >> }); >> >> JavaPairRDD<String, Integer> counts = ones.reduceByKey( >> new Function2<Integer, Integer, Integer>() { >> @Override >> public Integer call(Integer i1, Integer i2) { >> return i1 + i2; >> } >> }); >> >> List<Tuple2String, Integer>> output = counts.collect(); >> for (Tuple2 tuple : output) { >> System.out.println(tuple._1() + ": " + tuple._2()); >> } >> spark.stop(); >> } >> } >> >> >> >> >> -- >> View this message in context: http://apache-spark-user-list. >> 1001560.n3.nabble.com/Running-spark-from-Eclipse-and-then- >> Jar-tp28182.html >> Sent from the Apache Spark User List mailing list archive at Nabble.com. >> >> - >> To unsubscribe e-mail: user-unsubscr...@spark.apache.org >> >> >> >>
Re: Running spark from Eclipse and then Jar
r: BlockManager stopped > 16/12/07 15:16:46 INFO BlockManagerMaster: BlockManagerMaster stopped > 16/12/07 15:16:46 INFO > OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: > OutputCommitCoordinator stopped! > 16/12/07 15:16:46 INFO SparkContext: Successfully stopped SparkContext > 16/12/07 15:16:46 INFO ShutdownHookManager: Shutdown hook called > 16/12/07 15:16:46 INFO ShutdownHookManager: Deleting directory > > C:\Users\Owner\AppData\Local\Temp\spark-dab2587b-a794-4947-ac13-d40056cf71d8 > > C:\Users\Owner> > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > public final class JavaWordCount { > private static final Pattern SPACE = Pattern.compile(" "); > > public static void main(String[] args) throws Exception { > > if (args.length < 1) { > System.err.println("Usage: JavaWordCount "); > System.exit(1); > } > > //boiler plate needed to run locally > SparkConf conf = new SparkConf().setAppName("Word Count > Application").setMaster("local[*]"); > JavaSparkContext sc = new JavaSparkContext(conf); > > SparkSession spark = SparkSession > .builder() > .appName("Word Count") > .getOrCreate() > .newSession(); > > > JavaRDD lines = spark.read().textFile(args[0]).javaRDD(); > > > JavaRDD words = lines.flatMap(new FlatMapFunction<String, > String>() { > @Override > public Iterator call(String s) { > return Arrays.asList(SPACE.split(s)).iterator(); > } > }); > > JavaPairRDD<String, Integer> ones = words.mapToPair( > new PairFunction<String, String, Integer>() { > @Override > public Tuple2<String, Integer> call(String s) { > return new Tuple2<>(s, 1); > } > }); > > JavaPairRDD<String, Integer> counts = ones.reduceByKey( > new Function2<Integer, Integer, Integer>() { > @Override > public Integer call(Integer i1, Integer i2) { > return i1 + i2; > } > }); > > List<Tuple2String, Integer>> output = counts.collect(); > for (Tuple2 tuple : output) { > System.out.println(tuple._1() + ": " + tuple._2()); > } > spark.stop(); > } > } > > > > > -- > View this message in context: > http://apache-spark-user-list.1001560.n3.nabble.com/Running-spark-from-Eclipse-and-then-Jar-tp28182.html > Sent from the Apache Spark User List mailing list archive at Nabble.com. > > - > To unsubscribe e-mail: user-unsubscr...@spark.apache.org > > > >
Re: Running spark from Eclipse and then Jar
at >> org.apache.spark.sql.execution.datasources.DataSource$$anonfun$5.apply( >> DataSource.scala:132) >> at >> org.apache.spark.sql.execution.datasources.DataSource$$anonfun$5.apply( >> DataSource.scala:132) >> at scala.util.Try.orElse(Try.scala:84) >> at >> org.apache.spark.sql.execution.datasources.DataSource.lookupDataSource( >> DataSource.scala:132) >> ... 8 more >> 16/12/07 15:16:46 INFO SparkContext: Invoking stop() from shutdown hook >> 16/12/07 15:16:46 INFO SparkUI: Stopped Spark web UI at >> http://192.168.19.2:4040 >> 16/12/07 15:16:46 INFO MapOutputTrackerMasterEndpoint: >> MapOutputTrackerMasterEndpoint stopped! >> 16/12/07 15:16:46 INFO MemoryStore: MemoryStore cleared >> 16/12/07 15:16:46 INFO BlockManager: BlockManager stopped >> 16/12/07 15:16:46 INFO BlockManagerMaster: BlockManagerMaster stopped >> 16/12/07 15:16:46 INFO >> OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: >> OutputCommitCoordinator stopped! >> 16/12/07 15:16:46 INFO SparkContext: Successfully stopped SparkContext >> 16/12/07 15:16:46 INFO ShutdownHookManager: Shutdown hook called >> 16/12/07 15:16:46 INFO ShutdownHookManager: Deleting directory >> C:\Users\Owner\AppData\Local\Temp\spark-dab2587b-a794-4947- >> ac13-d40056cf71d8 >> >> C:\Users\Owner> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> public final class JavaWordCount { >> private static final Pattern SPACE = Pattern.compile(" "); >> >> public static void main(String[] args) throws Exception { >> >> if (args.length < 1) { >> System.err.println("Usage: JavaWordCount "); >> System.exit(1); >> } >> >> //boiler plate needed to run locally >> SparkConf conf = new SparkConf().setAppName("Word Count >> Application").setMaster("local[*]"); >> JavaSparkContext sc = new JavaSparkContext(conf); >> >> SparkSession spark = SparkSession >> .builder() >> .appName("Word Count") >> .getOrCreate() >> .newSession(); >> >> >> JavaRDD lines = spark.read().textFile(args[0]).javaRDD(); >> >> >> JavaRDD words = lines.flatMap(new FlatMapFunction<String, >> String>() { >> @Override >> public Iterator call(String s) { >> return Arrays.asList(SPACE.split(s)).iterator(); >> } >> }); >> >> JavaPairRDD<String, Integer> ones = words.mapToPair( >> new PairFunction<String, String, Integer>() { >> @Override >> public Tuple2<String, Integer> call(String s) { >> return new Tuple2<>(s, 1); >> } >> }); >> >> JavaPairRDD<String, Integer> counts = ones.reduceByKey( >> new Function2<Integer, Integer, Integer>() { >> @Override >> public Integer call(Integer i1, Integer i2) { >> return i1 + i2; >> } >> }); >> >> List<Tuple2String, Integer>> output = counts.collect(); >> for (Tuple2 tuple : output) { >> System.out.println(tuple._1() + ": " + tuple._2()); >> } >> spark.stop(); >> } >> } >> >> >> >> >> -- >> View this message in context: http://apache-spark-user-list. >> 1001560.n3.nabble.com/Running-spark-from-Eclipse-and-then- >> Jar-tp28182.html >> Sent from the Apache Spark User List mailing list archive at Nabble.com. >> >> - >> To unsubscribe e-mail: user-unsubscr...@spark.apache.org >> >> >>
Re: Running spark from Eclipse and then Jar
nt "); > System.exit(1); > } > > //boiler plate needed to run locally > SparkConf conf = new SparkConf().setAppName("Word Count > Application").setMaster("local[*]"); > JavaSparkContext sc = new JavaSparkContext(conf); > > SparkSession spark = SparkSession > .builder() > .appName("Word Count") > .getOrCreate() > .newSession(); > > > JavaRDD lines = spark.read().textFile(args[0]).javaRDD(); > > > JavaRDD words = lines.flatMap(new FlatMapFunction<String, > String>() { > @Override > public Iterator call(String s) { > return Arrays.asList(SPACE.split(s)).iterator(); > } > }); > > JavaPairRDD<String, Integer> ones = words.mapToPair( > new PairFunction<String, String, Integer>() { > @Override > public Tuple2<String, Integer> call(String s) { > return new Tuple2<>(s, 1); > } > }); > > JavaPairRDD<String, Integer> counts = ones.reduceByKey( > new Function2<Integer, Integer, Integer>() { > @Override > public Integer call(Integer i1, Integer i2) { > return i1 + i2; > } > }); > > List<Tuple2String, Integer>> output = counts.collect(); > for (Tuple2 tuple : output) { > System.out.println(tuple._1() + ": " + tuple._2()); > } > spark.stop(); > } > } > > > > > -- > View this message in context: > http://apache-spark-user-list.1001560.n3.nabble.com/Running-spark-from-Eclipse-and-then-Jar-tp28182.html > Sent from the Apache Spark User List mailing list archive at Nabble.com. > > - > To unsubscribe e-mail: user-unsubscr...@spark.apache.org > > >
Re: Running spark from Eclipse and then Jar
ublic Iterator call(String s) { > return Arrays.asList(SPACE.split(s)).iterator(); > } > }); > > JavaPairRDD<String, Integer> ones = words.mapToPair( > new PairFunction<String, String, Integer>() { > @Override > public Tuple2<String, Integer> call(String s) { > return new Tuple2<>(s, 1); > } > }); > > JavaPairRDD<String, Integer> counts = ones.reduceByKey( > new Function2<Integer, Integer, Integer>() { > @Override > public Integer call(Integer i1, Integer i2) { > return i1 + i2; > } > }); > > List<Tuple2String, Integer>> output = counts.collect(); > for (Tuple2 tuple : output) { > System.out.println(tuple._1() + ": " + tuple._2()); > } > spark.stop(); > } > } > > > > > -- > View this message in context: http://apache-spark-user-list. > 1001560.n3.nabble.com/Running-spark-from-Eclipse-and-then-Jar-tp28182.html > Sent from the Apache Spark User List mailing list archive at Nabble.com. > > - > To unsubscribe e-mail: user-unsubscr...@spark.apache.org > > http://maven.apache.org/POM/4.0.0; xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance; xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd;> 4.0.0 com.examples MillionSongsDatabase 0.0.1-SNAPSHOT jar MillionSongsDatabase http://maven.apache.org UTF-8 1.8 2.0.0 org.apache.spark spark-core_2.11 ${spark.version} org.apache.spark spark-sql_2.11 ${spark.version} org.apache.spark spark-streaming_2.11 ${spark.version} org.apache.bahir spark-streaming-twitter_2.11 ${spark.version} org.apache.spark spark-mllib_2.11 ${spark.version} org.apache.spark spark-hive_2.11 ${spark.version} org.apache.spark spark-graphx_2.11 ${spark.version} org.apache.spark spark-yarn_2.11 ${spark.version} org.apache.spark spark-network-shuffle_2.11 ${spark.version} org.apache.spark spark-streaming-kafka_2.10 1.6.2 org.apache.spark spark-streaming-flume_2.11 ${spark.version} com.databricks spark-csv_2.11 1.3.0 mysql mysql-connector-java 5.1.38 junit junit 3.8.1 test org.apache.maven.plugins maven-eclipse-plugin 2.9 true false org.apache.maven.plugins maven-compiler-plugin 3.5.1 ${jdk.version} ${jdk.version} org.apache.maven.plugins maven-shade-plugin 2.4.3 true org.apache.maven.plugins maven-assembly-plugin 2.4.1 jar-with-dependencies com.example.RandomForest.SongPredictionusingLinear oozie.launcher.mapreduce.job.user.classpath.first true make-assembly package single - To unsubscribe e-mail: user-unsubscr...@spark.apache.org
Re: Running spark from Eclipse and then Jar
rces.DataSource$$anonfun$5.apply(DataSource.scala:132) >at > org.apache.spark.sql.execution.datasources.DataSource$$anonfun$5.apply(DataSource.scala:132) >at scala.util.Try.orElse(Try.scala:84) >at > org.apache.spark.sql.execution.datasources.DataSource.lookupDataSource(DataSource.scala:132) >... 8 more > 16/12/07 15:16:46 INFO SparkContext: Invoking stop() from shutdown hook > 16/12/07 15:16:46 INFO SparkUI: Stopped Spark web UI at > http://192.168.19.2:4040 > 16/12/07 15:16:46 INFO MapOutputTrackerMasterEndpoint: > MapOutputTrackerMasterEndpoint stopped! > 16/12/07 15:16:46 INFO MemoryStore: MemoryStore cleared > 16/12/07 15:16:46 INFO BlockManager: BlockManager stopped > 16/12/07 15:16:46 INFO BlockManagerMaster: BlockManagerMaster stopped > 16/12/07 15:16:46 INFO > OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: > OutputCommitCoordinator stopped! > 16/12/07 15:16:46 INFO SparkContext: Successfully stopped SparkContext > 16/12/07 15:16:46 INFO ShutdownHookManager: Shutdown hook called > 16/12/07 15:16:46 INFO ShutdownHookManager: Deleting directory > C:\Users\Owner\AppData\Local\Temp\spark-dab2587b-a794-4947-ac13-d40056cf71d8 > > C:\Users\Owner> > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > public final class JavaWordCount { > private static final Pattern SPACE = Pattern.compile(" "); > > public static void main(String[] args) throws Exception { > >if (args.length < 1) { > System.err.println("Usage: JavaWordCount "); > System.exit(1); >} > >//boiler plate needed to run locally >SparkConf conf = new SparkConf().setAppName("Word Count > Application").setMaster("local[*]"); >JavaSparkContext sc = new JavaSparkContext(conf); > >SparkSession spark = SparkSession >.builder() >.appName("Word Count") >.getOrCreate() >.newSession(); > > >JavaRDD lines = spark.read().textFile(args[0]).javaRDD(); > > >JavaRDD words = lines.flatMap(new FlatMapFunction<String, > String>() { > @Override > public Iterator call(String s) { >return Arrays.asList(SPACE.split(s)).iterator(); > } >}); > >JavaPairRDD<String, Integer> ones = words.mapToPair( > new PairFunction<String, String, Integer>() { >@Override >public Tuple2<String, Integer> call(String s) { > return new Tuple2<>(s, 1); >} > }); > >JavaPairRDD<String, Integer> counts = ones.reduceByKey( > new Function2<Integer, Integer, Integer>() { >@Override >public Integer call(Integer i1, Integer i2) { > return i1 + i2; >} > }); > >List<Tuple2String, Integer>> output = counts.collect(); >for (Tuple2 tuple : output) { > System.out.println(tuple._1() + ": " + tuple._2()); >} >spark.stop(); > } > } > > > > > -- > View this message in context: > http://apache-spark-user-list.1001560.n3.nabble.com/Running-spark-from-Eclipse-and-then-Jar-tp28182.html > Sent from the Apache Spark User List mailing list archive at Nabble.com. > > - > To unsubscribe e-mail: user-unsubscr...@spark.apache.org > - To unsubscribe e-mail: user-unsubscr...@spark.apache.org
Running spark from Eclipse and then Jar
yStore cleared 16/12/07 15:16:46 INFO BlockManager: BlockManager stopped 16/12/07 15:16:46 INFO BlockManagerMaster: BlockManagerMaster stopped 16/12/07 15:16:46 INFO OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: OutputCommitCoordinator stopped! 16/12/07 15:16:46 INFO SparkContext: Successfully stopped SparkContext 16/12/07 15:16:46 INFO ShutdownHookManager: Shutdown hook called 16/12/07 15:16:46 INFO ShutdownHookManager: Deleting directory C:\Users\Owner\AppData\Local\Temp\spark-dab2587b-a794-4947-ac13-d40056cf71d8 C:\Users\Owner> public final class JavaWordCount { private static final Pattern SPACE = Pattern.compile(" "); public static void main(String[] args) throws Exception { if (args.length < 1) { System.err.println("Usage: JavaWordCount "); System.exit(1); } //boiler plate needed to run locally SparkConf conf = new SparkConf().setAppName("Word Count Application").setMaster("local[*]"); JavaSparkContext sc = new JavaSparkContext(conf); SparkSession spark = SparkSession .builder() .appName("Word Count") .getOrCreate() .newSession(); JavaRDD lines = spark.read().textFile(args[0]).javaRDD(); JavaRDD words = lines.flatMap(new FlatMapFunction<String, String>() { @Override public Iterator call(String s) { return Arrays.asList(SPACE.split(s)).iterator(); } }); JavaPairRDD<String, Integer> ones = words.mapToPair( new PairFunction<String, String, Integer>() { @Override public Tuple2<String, Integer> call(String s) { return new Tuple2<>(s, 1); } }); JavaPairRDD<String, Integer> counts = ones.reduceByKey( new Function2<Integer, Integer, Integer>() { @Override public Integer call(Integer i1, Integer i2) { return i1 + i2; } }); List<Tuple2String, Integer>> output = counts.collect(); for (Tuple2 tuple : output) { System.out.println(tuple._1() + ": " + tuple._2()); } spark.stop(); } } -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/Running-spark-from-Eclipse-and-then-Jar-tp28182.html Sent from the Apache Spark User List mailing list archive at Nabble.com. - To unsubscribe e-mail: user-unsubscr...@spark.apache.org