YAML CONFIGURATION

<?xml version="1.0"?>
<!-- core-site.xml -->
<configuration>
<property>
<name>fs.default.name</name>
<value>hdfs://isi-bigcluster1.csr.unibo.it</value>
</property>
</configuration>

<?xml version="1.0"?>
<!-- hdfs-site.xml -->
<configuration>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
</configuration>

<?xml version="1.0"?>
<!-- mapred-site.xml -->
<configuration>
<property>
<name>mapred.job.tracker</name>
<value>isi-bigcluster1.csr.unibo.it:8021</value>
</property>
</configuration>

<?xml version="1.0"?>
<!-- yarn-site.xml -->
<configuration>
<property>
<name>yarn.resourcemanager.address</name>
<value>isi-bigcluster1.csr.unibo.it:8032</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce.shuffle</value>
</property>
</configuration>

MAVEN:
<project>
<groupId>com.oreilly.learningsparkexamples.mini</groupId>
<artifactId>learning-spark-mini-example</artifactId>
<modelVersion>4.0.0</modelVersion>
<name>example</name>
<packaging>jar</packaging>
<version>0.0.1</version>
<dependencies>
<dependency> <!-- Spark dependency -->
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-core_2.10</artifactId>
    <version>1.2.0</version>
    <scope>provided</scope>
</dependency>
<dependency> <!-- Hive dependency -->
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-hive_2.10</artifactId>
    <version>1.2.0</version>
    <scope>provided</scope>
</dependency>
</dependencies>
<properties>
<java.version>1.8</java.version>
</properties>
<build>
<pluginManagement>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.1</version>
<configuration>
<source>${java.version}</source>
<target>${java.version}</target>
</configuration> </plugin>
</plugins>
</pluginManagement>
</build>
</project>