intial comming to sample apps

javaApp/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>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-client</artifactId>
+      <version>2.3.0</version>
+    </dependency>
+  </dependencies>
+</project>

javaApp/src/main/java/SimpleApp.java

+import org.apache.spark.api.java.*;
+import org.apache.spark.api.java.function.Function;
+
+public class SimpleApp {
+  public static void main(String[] args) {
+    String logFile = "spark-env.sh"; // Should be some file on your system
+    JavaSparkContext sc = new JavaSparkContext("local", "Simple App",
+       new String[]{"target/simple-project-1.0.jar"});
+    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);
+  }
+}

pythonApp/sampleApp.py

+from pyspark import SparkContext
+
+sc = SparkContext(appName='test')
+data = [1, 2, 3, 4, 5]
+distData = sc.parallelize(data)
+print(distData.reduce(lambda a, b: a + b))
+

pythonApp/sqlApp.py

+from pyspark import SparkContext
+from pyspark.sql import SQLContext
+
+sc = SparkContext(appName='testSQL')
+sqlCtx = SQLContext(sc)
+lines = sc.textFile("hdfs://daas/user/hdfs/trd_gw1_12_01_normalized.csv")
+parts = lines.map(lambda l: l.split(","))
+records = parts.map(lambda p: {"date": p[0], "src_ip": p[1], "dest_ip": p[2], "port": int(p[3])})
+recordsTable = sqlCtx.inferSchema(records)
+recordsTable.registerAsTable("records")
+
+http = sqlCtx.sql("SELECT count(*) FROM records WHERE port <= 80)")
+
+print(http)