mport org.apache.log4j.{Level, Logger}

import org.apache.spark.rdd.RDD

import org.apache.spark.{SparkConf, SparkContext}

/**

 * Created by Lee_Rz on 2017/8/30.

 */

object SparkDemo {

  def main(args: Array[String]) {

    Logger.getLogger("org.apache.spark").setLevel(Level.OFF)

    val sc: SparkContext = new SparkContext(new SparkConf().setAppName(this.getClass().getName()).setMaster("local[2]"))

    val rdd1: RDD[String] = sc.textFile("C:\\Users\\166\\Desktop\\text.txt")   //一行一行的读数据   //懒算子

    val key: RDD[(String, Int)] = rdd1.flatMap(_.split(" ")).map((_,)).reduceByKey(_+_)

    println(key.collect().toBuffer)//收集到Driver

  }

}

Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties

// :: WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable

// :: INFO Slf4jLogger: Slf4jLogger started

// :: INFO Remoting: Starting remoting

// :: INFO Remoting: Remoting started; listening on addresses :[akka.tcp://sparkDriverActorSystem@192.168.0.166:51388]

// :: ERROR Shell: Failed to locate the winutils binary in the hadoop binary path

java.io.IOException: Could not locate executable null\bin\winutils.exe in the Hadoop binaries.

    at org.apache.hadoop.util.Shell.getQualifiedBinPath(Shell.java:)

    at org.apache.hadoop.util.Shell.getWinUtilsPath(Shell.java:)

    at org.apache.hadoop.util.Shell.<clinit>(Shell.java:)

    at org.apache.hadoop.util.StringUtils.<clinit>(StringUtils.java:)

    at org.apache.hadoop.mapred.FileInputFormat.setInputPaths(FileInputFormat.java:)

    at org.apache.spark.SparkContext$$anonfun$hadoopFile$$$anonfun$.apply(SparkContext.scala:)

    at org.apache.spark.SparkContext$$anonfun$hadoopFile$$$anonfun$.apply(SparkContext.scala:)

    at org.apache.spark.rdd.HadoopRDD$$anonfun$getJobConf$.apply(HadoopRDD.scala:)

    at org.apache.spark.rdd.HadoopRDD$$anonfun$getJobConf$.apply(HadoopRDD.scala:)

    at scala.Option.map(Option.scala:)

    at org.apache.spark.rdd.HadoopRDD.getJobConf(HadoopRDD.scala:)

    at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:)

    at org.apache.spark.rdd.RDD$$anonfun$partitions$.apply(RDD.scala:)

    at org.apache.spark.rdd.RDD$$anonfun$partitions$.apply(RDD.scala:)

    at scala.Option.getOrElse(Option.scala:)

    at org.apache.spark.rdd.RDD.partitions(RDD.scala:)

    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:)

    at org.apache.spark.rdd.RDD$$anonfun$partitions$.apply(RDD.scala:)

    at org.apache.spark.rdd.RDD$$anonfun$partitions$.apply(RDD.scala:)

    at scala.Option.getOrElse(Option.scala:)

    at org.apache.spark.rdd.RDD.partitions(RDD.scala:)

    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:)

    at org.apache.spark.rdd.RDD$$anonfun$partitions$.apply(RDD.scala:)

    at org.apache.spark.rdd.RDD$$anonfun$partitions$.apply(RDD.scala:)

    at scala.Option.getOrElse(Option.scala:)

    at org.apache.spark.rdd.RDD.partitions(RDD.scala:)

    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:)

    at org.apache.spark.rdd.RDD$$anonfun$partitions$.apply(RDD.scala:)

    at org.apache.spark.rdd.RDD$$anonfun$partitions$.apply(RDD.scala:)

    at scala.Option.getOrElse(Option.scala:)

    at org.apache.spark.rdd.RDD.partitions(RDD.scala:)

    at org.apache.spark.Partitioner$.defaultPartitioner(Partitioner.scala:)

    at org.apache.spark.rdd.PairRDDFunctions$$anonfun$reduceByKey$.apply(PairRDDFunctions.scala:)

    at org.apache.spark.rdd.PairRDDFunctions$$anonfun$reduceByKey$.apply(PairRDDFunctions.scala:)

    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:)

    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:)

    at org.apache.spark.rdd.RDD.withScope(RDD.scala:)

    at org.apache.spark.rdd.PairRDDFunctions.reduceByKey(PairRDDFunctions.scala:)

    at zx.SparkDemo$.main(SparkDemo.scala:)

    at zx.SparkDemo.main(SparkDemo.scala)

    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)

    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:)

    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:)

    at java.lang.reflect.Method.invoke(Method.java:)

    at com.intellij.rt.execution.application.AppMain.main(AppMain.java:)

// :: INFO FileInputFormat: Total input paths to process :

// :: INFO deprecation: mapred.tip.id is deprecated. Instead, use mapreduce.task.id

// :: INFO deprecation: mapred.task.id is deprecated. Instead, use mapreduce.task.attempt.id

// :: INFO deprecation: mapred.task.is.map is deprecated. Instead, use mapreduce.task.ismap

// :: INFO deprecation: mapred.task.partition is deprecated. Instead, use mapreduce.task.partition

// :: INFO deprecation: mapred.job.id is deprecated. Instead, use mapreduce.job.id

ArrayBuffer((are,), (hello,), (any,), (ok,), (world,), (me,), (alone,), (you,), (no,), (believie,), (more,))

// :: INFO RemoteActorRefProvider$RemotingTerminator: Shutting down remote daemon.

Process finished with exit code