Apache Spark ドキュメント和訳 - Quick Start ref: http://qiita.com/mychaelstyle/items/46440cd27ef641892a58

file16.scala

name := "Simple Project"

version := "1.0"

scalaVersion := "2.10.4"

libraryDependencies += "org.apache.spark" %% "spark-core" % "1.0.0"

resolvers += "Akka Repository" at "http://repo.akka.io/releases/"

file17.txt

# Your directory layout should look like this
$ find .
.
./simple.sbt
./src
./src/main
./src/main/scala
./src/main/scala/SimpleApp.scala

# Package a jar containing your application
$ sbt package
...
[info] Packaging {..}/{..}/target/scala-2.10/simple-project_2.10-1.0.jar

# Use spark-submit to run your application
$ YOUR_SPARK_HOME/bin/spark-submit \
  --class "SimpleApp" \
  --master local[4] \
  target/scala-2.10/simple-project_2.10-1.0.jar
...
Lines with a: 46, Lines with b: 23

file20.txt

$ find .
./pom.xml
./src
./src/main
./src/main/java
./src/main/java/SimpleApp.java

file21.txt

# Package a jar containing your application
$ mvn package
...
[INFO] Building jar: {..}/{..}/target/simple-project-1.0.jar

# Use spark-submit to run your application
$ YOUR_SPARK_HOME/bin/spark-submit \
  --class "SimpleApp" \
  --master local[4] \
  target/simple-project-1.0.jar
...
Lines with a: 46, Lines with b: 23

file23.txt

# Use spark-submit to run your application
$ YOUR_SPARK_HOME/bin/spark-submit \
  --master local[4] \
  SimpleApp.py
...
Lines with a: 46, Lines with b: 23

file24.txt

# For Scala and Java, use run-example:
./bin/run-example SparkPi

# For Python examples, use spark-submit directly:
./bin/spark-submit examples/src/main/python/pi.py

pom.xml

<project>
  <groupId>edu.berkeley</groupId>
  <artifactId>simple-project</artifactId>
  <modelVersion>4.0.0</modelVersion>
  <name>Simple Project</name>
  <packaging>jar</packaging>
  <version>1.0</version>
  <repositories>
    <repository>
      <id>Akka repository</id>
      <url>http://repo.akka.io/releases</url>
    </repository>
  </repositories>
  <dependencies>
    <dependency> <!-- Spark dependency -->
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-core_2.10</artifactId>
      <version>1.0.0</version>
    </dependency>
  </dependencies>
</project>

Python

>>> textFile.filter(lambda line: "Spark" in line).count() # How many lines contain "Spark"?
15

Scala

scala> linesWithSpark.cache()
res7: spark.RDD[String] = spark.FilteredRDD@17e51082

scala> linesWithSpark.count()
res8: Long = 15

scala> linesWithSpark.count()
res9: Long = 15

scala

scala> import java.lang.Math
import java.lang.Math

scala> textFile.map(line => line.split(" ").size).reduce((a, b) => Math.max(a, b))
res5: Int = 15

SimpleApp.java

/* SimpleApp.java */
import org.apache.spark.api.java.*;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.Function;

public class SimpleApp {
  public static void main(String[] args) {
    String logFile = "YOUR_SPARK_HOME/README.md"; // Should be some file on your system
    SparkConf conf = new SparkConf().setAppName("Simple Application");
    JavaSparkContext sc = new JavaSparkContext(conf);
    JavaRDD<String> logData = sc.textFile(logFile).cache();

    long numAs = logData.filter(new Function<String, Boolean>() {
      public Boolean call(String s) { return s.contains("a"); }
    }).count();

    long numBs = logData.filter(new Function<String, Boolean>() {
      public Boolean call(String s) { return s.contains("b"); }
    }).count();

    System.out.println("Lines with a: " + numAs + ", lines with b: " + numBs);
  }
}

SimpleApp.py

"""SimpleApp.py"""
from pyspark import SparkContext

logFile = "YOUR_SPARK_HOME/README.md"  # Should be some file on your system
sc = SparkContext("local", "Simple App")
logData = sc.textFile(logFile).cache()

numAs = logData.filter(lambda s: 'a' in s).count()
numBs = logData.filter(lambda s: 'b' in s).count()

print "Lines with a: %i, lines with b: %i" % (numAs, numBs)

SimpleApp.scala

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

object SimpleApp {
  def main(args: Array[String]) {
    val logFile = "YOUR_SPARK_HOME/README.md" // あなたのマシン上のパス
    val conf = new SparkConf().setAppName("Simple Application")
    val sc = new SparkContext(conf)
    val logData = sc.textFile(logFile, 2).cache()
    val numAs = logData.filter(line => line.contains("a")).count()
    val numBs = logData.filter(line => line.contains("b")).count()
    println("Lines with a: %s, Lines with b: %s".format(numAs, numBs))
  }
}