rickyngk

/* SimpleApp.scala */
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD

object SimpleApp {
	def textSearch(textData: RDD[String]) {
		val cases = textData.filter(line => line.contains("Spark"))
		println(cases.count());

rickyngk

build:
	sbt package
run:
	~/spark-1.5.2/bin/spark-submit --class "SimpleApp" --master local[4] target/scala-2.11/simple-project_2.11-1.0.jar

rickyngk

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
  Licensed under the Apache License, Version 2.0 (the "License");
  you may not use this file except in compliance with the License.
  You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

  Unless required by applicable law or agreed to in writing, software

rickyngk

<?xml version="1.0"?>
<!--
  Licensed under the Apache License, Version 2.0 (the "License");
  you may not use this file except in compliance with the License.
  You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

  Unless required by applicable law or agreed to in writing, software
  distributed under the License is distributed on an "AS IS" BASIS,

rickyngk

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
  Licensed under the Apache License, Version 2.0 (the "License");
  you may not use this file except in compliance with the License.
  You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

  Unless required by applicable law or agreed to in writing, software

rickyngk

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
  Licensed under the Apache License, Version 2.0 (the "License");
  you may not use this file except in compliance with the License.
  You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

  Unless required by applicable law or agreed to in writing, software

rickyngk

/* SimpleApp.scala */
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD

object SimpleApp {
	val hadoop_uri = "hdfs://172.18.2.108:9000"

	def textSearch(textData: RDD[String]) {

rickyngk

name := "Simple Project"
version := "1.0"
scalaVersion := "2.11.7"
libraryDependencies ++= Seq( 
	"org.apache.spark" %% "spark-core" % "1.5.2",
	"org.apache.hadoop" % "hadoop-client" % "2.6.0"
)

rickyngk

name := "Simple Project"
version := "1.0"
scalaVersion := "2.11.7"
libraryDependencies ++= Seq( 
	"org.apache.spark" %% "spark-core" % "1.5.2",
	"org.apache.hadoop" % "hadoop-client" % "2.6.0",
	"org.apache.spark" % "spark-mllib_2.11" % "1.5.2"
)

rickyngk

/* SimpleApp.scala */
import org.apache.spark.mllib.linalg.{Vector, Vectors}

object SimpleApp {
	def main(args: Array[String]) {
		// Create a dense vector (1.0, 0.0, 3.0).
		val dv: Vector = Vectors.dense(1.0, 0.0, 3.0)
		// Create a sparse vector (1.0, 0.0, 3.0) by specifying its indices and values corresponding to nonzero entries.
		val sv1: Vector = Vectors.sparse(3, Array(0, 2), Array(1.0, 3.0))
		// Create a sparse vector (1.0, 0.0, 3.0) by specifying its nonzero entries.