Scala HadoopRDD类代码示例

OStack程序员社区-中国程序员成长平台 › 门户 › 编程› Scala›Scala教程

原作者: [db:作者] 来自: [db:来源] 收藏邀请

本文整理汇总了Scala中org.apache.spark.rdd.HadoopRDD类的典型用法代码示例。如果您正苦于以下问题：Scala HadoopRDD类的具体用法？Scala HadoopRDD怎么用？Scala HadoopRDD使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。

在下文中一共展示了HadoopRDD类的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于我们的系统推荐出更棒的Scala代码示例。

示例1: FPMiningPreprocessingApp

//设置package包名称以及导入依赖的类
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)
  }
}

开发者ID:ZubairNabi，项目名称:prosparkstreaming，代码行数:45，代码来源:L9-13FPMiningPreprocessing.scala

示例2: CollabFilteringPreprocessingApp

//设置package包名称以及导入依赖的类
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)
  }
}

开发者ID:ZubairNabi，项目名称:prosparkstreaming，代码行数:44，代码来源:L9-11CollabFilteringPreprocessing.scala

注：本文中的org.apache.spark.rdd.HadoopRDD类示例整理自Github/MSDocs等源码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。