org.apache.spark.rdd.HadoopRDD Scala Examples

The following examples show how to use org.apache.spark.rdd.HadoopRDD. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example.
Example 1
Source File: JavaHadoopRDD.scala    From drizzle-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.api.java

import scala.collection.JavaConverters._
import scala.reflect.ClassTag

import org.apache.hadoop.mapred.InputSplit

import org.apache.spark.annotation.DeveloperApi
import org.apache.spark.api.java.JavaSparkContext._
import org.apache.spark.api.java.function.{Function2 => JFunction2}
import org.apache.spark.rdd.HadoopRDD

@DeveloperApi
class JavaHadoopRDD[K, V](rdd: HadoopRDD[K, V])
    (implicit override val kClassTag: ClassTag[K], implicit override val vClassTag: ClassTag[V])
  extends JavaPairRDD[K, V](rdd) {

  
  @DeveloperApi
  def mapPartitionsWithInputSplit[R](
      f: JFunction2[InputSplit, java.util.Iterator[(K, V)], java.util.Iterator[R]],
      preservesPartitioning: Boolean = false): JavaRDD[R] = {
    new JavaRDD(rdd.mapPartitionsWithInputSplit((a, b) => f.call(a, b.asJava).asScala,
      preservesPartitioning)(fakeClassTag))(fakeClassTag)
  }
}
Example 2
Source File: L9-11CollabFilteringPreprocessing.scala    From prosparkstreaming   with Apache License 2.0 5 votes vote down vote up 
package org.apress.prospark

import org.apache.hadoop.io.LongWritable
import org.apache.hadoop.io.Text
import org.apache.hadoop.mapred.FileSplit
import org.apache.hadoop.mapred.TextInputFormat
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.rdd.HadoopRDD
import org.apache.spark.rdd.RDD.rddToPairRDDFunctions

import com.google.common.io.Files

object CollabFilteringPreprocessingApp {

  def main(args: Array[String]) {
    if (args.length != 3) {
      System.err.println(
        "Usage: CollabFilteringPreprocessingApp <appname> <inputpath> <outputpath>")
      System.exit(1)
    }
    val Seq(appName, iPath, oPath) = args.toSeq

    val conf = new SparkConf()
      .setAppName(appName)
      .setJars(SparkContext.jarOfClass(this.getClass).toSeq)

    val delim = " "

    val sc = new SparkContext(conf)
    sc.hadoopFile(iPath, classOf[TextInputFormat], classOf[LongWritable], classOf[Text], sc.defaultMinPartitions)
      .asInstanceOf[HadoopRDD[LongWritable, Text]]
      .mapPartitionsWithInputSplit((iSplit, iter) =>
        iter.map(splitAndLine => (Files.getNameWithoutExtension(iSplit.asInstanceOf[FileSplit].getPath.toString), splitAndLine._2.toString.split(" ")(1))))
      .filter(r => r._2 != "0")
      .map(r => ((r._1, r._2), 1))
      .reduceByKey(_ + _)
      .map(r => r._1._1.replace("subject", "") + delim + r._1._2 + delim + r._2)
      .sample(false, 0.7)
      .coalesce(1)
      .saveAsTextFile(oPath)
  }
}
Example 3
Source File: L9-13FPMiningPreprocessing.scala    From prosparkstreaming   with Apache License 2.0 5 votes vote down vote up 
package org.apress.prospark

import org.apache.hadoop.io.LongWritable
import org.apache.hadoop.io.Text
import org.apache.hadoop.mapred.FileSplit
import org.apache.hadoop.mapred.TextInputFormat
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.rdd.HadoopRDD
import org.apache.spark.rdd.RDD.rddToPairRDDFunctions

import com.google.common.io.Files

object FPMiningPreprocessingApp {

  def main(args: Array[String]) {
    if (args.length != 3) {
      System.err.println(
        "Usage: FPMiningPreprocessingApp <appname> <inputpath> <outputpath>")
      System.exit(1)
    }
    val Seq(appName, iPath, oPath) = args.toSeq

    val conf = new SparkConf()
      .setAppName(appName)
      .setJars(SparkContext.jarOfClass(this.getClass).toSeq)

    val delim = " "

    val sc = new SparkContext(conf)
    sc.hadoopFile(iPath, classOf[TextInputFormat], classOf[LongWritable], classOf[Text], sc.defaultMinPartitions)
      .asInstanceOf[HadoopRDD[LongWritable, Text]]
      .mapPartitionsWithInputSplit((iSplit, iter) =>
        iter.map(splitAndLine => (Files.getNameWithoutExtension(iSplit.asInstanceOf[FileSplit].getPath.toString), splitAndLine._2.toString.split(" ")(1))))
      .filter(r => r._2 != "0")
      .map(r => (r._1, r._2))
      .distinct()
      .groupByKey()
      .map(r => r._2.mkString(" "))
      .sample(false, 0.7)
      .coalesce(1)
      .saveAsTextFile(oPath)
  }
}
Example 4
Source File: JavaHadoopRDD.scala    From sparkoscope   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.api.java

import scala.collection.JavaConverters._
import scala.reflect.ClassTag

import org.apache.hadoop.mapred.InputSplit

import org.apache.spark.annotation.DeveloperApi
import org.apache.spark.api.java.JavaSparkContext._
import org.apache.spark.api.java.function.{Function2 => JFunction2}
import org.apache.spark.rdd.HadoopRDD

@DeveloperApi
class JavaHadoopRDD[K, V](rdd: HadoopRDD[K, V])
    (implicit override val kClassTag: ClassTag[K], implicit override val vClassTag: ClassTag[V])
  extends JavaPairRDD[K, V](rdd) {

  
  @DeveloperApi
  def mapPartitionsWithInputSplit[R](
      f: JFunction2[InputSplit, java.util.Iterator[(K, V)], java.util.Iterator[R]],
      preservesPartitioning: Boolean = false): JavaRDD[R] = {
    new JavaRDD(rdd.mapPartitionsWithInputSplit((a, b) => f.call(a, b.asJava).asScala,
      preservesPartitioning)(fakeClassTag))(fakeClassTag)
  }
}
Example 5
Source File: JavaHadoopRDD.scala    From SparkCore   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.api.java

import scala.collection.JavaConversions._
import scala.reflect.ClassTag

import org.apache.hadoop.mapred.InputSplit

import org.apache.spark.annotation.DeveloperApi
import org.apache.spark.api.java.JavaSparkContext._
import org.apache.spark.api.java.function.{Function2 => JFunction2}
import org.apache.spark.rdd.HadoopRDD

@DeveloperApi
class JavaHadoopRDD[K, V](rdd: HadoopRDD[K, V])
    (implicit override val kClassTag: ClassTag[K], implicit override val vClassTag: ClassTag[V])
  extends JavaPairRDD[K, V](rdd) {

  
  @DeveloperApi
  def mapPartitionsWithInputSplit[R](
      f: JFunction2[InputSplit, java.util.Iterator[(K, V)], java.util.Iterator[R]],
      preservesPartitioning: Boolean = false): JavaRDD[R] = {
    new JavaRDD(rdd.mapPartitionsWithInputSplit((a, b) => f.call(a, asJavaIterator(b)),
      preservesPartitioning)(fakeClassTag))(fakeClassTag)
  }
}
Example 6
Source File: JavaHadoopRDD.scala    From multi-tenancy-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.api.java

import scala.collection.JavaConverters._
import scala.reflect.ClassTag

import org.apache.hadoop.mapred.InputSplit

import org.apache.spark.annotation.DeveloperApi
import org.apache.spark.api.java.JavaSparkContext._
import org.apache.spark.api.java.function.{Function2 => JFunction2}
import org.apache.spark.rdd.HadoopRDD

@DeveloperApi
class JavaHadoopRDD[K, V](rdd: HadoopRDD[K, V])
    (implicit override val kClassTag: ClassTag[K], implicit override val vClassTag: ClassTag[V])
  extends JavaPairRDD[K, V](rdd) {

  
  @DeveloperApi
  def mapPartitionsWithInputSplit[R](
      f: JFunction2[InputSplit, java.util.Iterator[(K, V)], java.util.Iterator[R]],
      preservesPartitioning: Boolean = false): JavaRDD[R] = {
    new JavaRDD(rdd.mapPartitionsWithInputSplit((a, b) => f.call(a, b.asJava).asScala,
      preservesPartitioning)(fakeClassTag))(fakeClassTag)
  }
}
Example 7
Source File: JavaHadoopRDD.scala    From iolap   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.api.java

import scala.collection.JavaConversions._
import scala.reflect.ClassTag

import org.apache.hadoop.mapred.InputSplit

import org.apache.spark.annotation.DeveloperApi
import org.apache.spark.api.java.JavaSparkContext._
import org.apache.spark.api.java.function.{Function2 => JFunction2}
import org.apache.spark.rdd.HadoopRDD

@DeveloperApi
class JavaHadoopRDD[K, V](rdd: HadoopRDD[K, V])
    (implicit override val kClassTag: ClassTag[K], implicit override val vClassTag: ClassTag[V])
  extends JavaPairRDD[K, V](rdd) {

  
  @DeveloperApi
  def mapPartitionsWithInputSplit[R](
      f: JFunction2[InputSplit, java.util.Iterator[(K, V)], java.util.Iterator[R]],
      preservesPartitioning: Boolean = false): JavaRDD[R] = {
    new JavaRDD(rdd.mapPartitionsWithInputSplit((a, b) => f.call(a, asJavaIterator(b)),
      preservesPartitioning)(fakeClassTag))(fakeClassTag)
  }
}
Example 8
Source File: JavaHadoopRDD.scala    From spark1.52   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.api.java

import scala.collection.JavaConversions._
import scala.reflect.ClassTag

import org.apache.hadoop.mapred.InputSplit

import org.apache.spark.annotation.DeveloperApi
import org.apache.spark.api.java.JavaSparkContext._
import org.apache.spark.api.java.function.{Function2 => JFunction2}
import org.apache.spark.rdd.HadoopRDD

@DeveloperApi
class JavaHadoopRDD[K, V](rdd: HadoopRDD[K, V])
    (implicit override val kClassTag: ClassTag[K], implicit override val vClassTag: ClassTag[V])
  extends JavaPairRDD[K, V](rdd) {

  
  @DeveloperApi
  def mapPartitionsWithInputSplit[R](
      f: JFunction2[InputSplit, java.util.Iterator[(K, V)], java.util.Iterator[R]],
      preservesPartitioning: Boolean = false): JavaRDD[R] = {
    new JavaRDD(rdd.mapPartitionsWithInputSplit((a, b) => f.call(a, asJavaIterator(b)),
      preservesPartitioning)(fakeClassTag))(fakeClassTag)
  }
}
Example 9
Source File: JavaHadoopRDD.scala    From Spark-2.3.1   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.api.java

import scala.collection.JavaConverters._
import scala.reflect.ClassTag

import org.apache.hadoop.mapred.InputSplit

import org.apache.spark.annotation.DeveloperApi
import org.apache.spark.api.java.JavaSparkContext._
import org.apache.spark.api.java.function.{Function2 => JFunction2}
import org.apache.spark.rdd.HadoopRDD

@DeveloperApi
class JavaHadoopRDD[K, V](rdd: HadoopRDD[K, V])
    (implicit override val kClassTag: ClassTag[K], implicit override val vClassTag: ClassTag[V])
  extends JavaPairRDD[K, V](rdd) {

  
  @DeveloperApi
  def mapPartitionsWithInputSplit[R](
      f: JFunction2[InputSplit, java.util.Iterator[(K, V)], java.util.Iterator[R]],
      preservesPartitioning: Boolean = false): JavaRDD[R] = {
    new JavaRDD(rdd.mapPartitionsWithInputSplit((a, b) => f.call(a, b.asJava).asScala,
      preservesPartitioning)(fakeClassTag))(fakeClassTag)
  }
}
Example 10
Source File: TextFileOverwrite.scala    From spark_helper   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark

import org.apache.spark.rdd.{RDD, HadoopRDD}
import org.apache.spark.util.SerializableConfiguration
import org.apache.hadoop.mapred.{FileInputFormat, JobConf, TextInputFormat}
import org.apache.hadoop.io.{LongWritable, Text}
import org.apache.hadoop.fs.Path

object TextFileOverwrite {

  def textFile(
      paths: Seq[String],
      minPartitions: Int,
      sc: SparkContext
  ): RDD[String] = {

    

    val confBroadcast =
      sc.broadcast(new SerializableConfiguration(sc.hadoopConfiguration))

    val setInputPathsFunc =
      (jobConf: JobConf) =>
        FileInputFormat.setInputPaths(jobConf, paths.map(p => new Path(p)): _*)

    new HadoopRDD(
      sc,
      confBroadcast,
      Some(setInputPathsFunc),
      classOf[TextInputFormat],
      classOf[LongWritable],
      classOf[Text],
      minPartitions
    ).map(pair => pair._2.toString)
  }
}
Example 11
Source File: JavaHadoopRDD.scala    From BigDatalog   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.api.java

import scala.collection.JavaConverters._
import scala.reflect.ClassTag

import org.apache.hadoop.mapred.InputSplit

import org.apache.spark.annotation.DeveloperApi
import org.apache.spark.api.java.JavaSparkContext._
import org.apache.spark.api.java.function.{Function2 => JFunction2}
import org.apache.spark.rdd.HadoopRDD

@DeveloperApi
class JavaHadoopRDD[K, V](rdd: HadoopRDD[K, V])
    (implicit override val kClassTag: ClassTag[K], implicit override val vClassTag: ClassTag[V])
  extends JavaPairRDD[K, V](rdd) {

  
  @DeveloperApi
  def mapPartitionsWithInputSplit[R](
      f: JFunction2[InputSplit, java.util.Iterator[(K, V)], java.util.Iterator[R]],
      preservesPartitioning: Boolean = false): JavaRDD[R] = {
    new JavaRDD(rdd.mapPartitionsWithInputSplit((a, b) => f.call(a, b.asJava).asScala,
      preservesPartitioning)(fakeClassTag))(fakeClassTag)
  }
}