spark的scala项目Maven构建和使用
一、使用
spark-sql使用
spark-sql --master yarn --num-executors 30 --executor-memory 12g
二、建立项目
1.建立Maven项目:吧java文件夹 重命名为scala文件夹
2.修改xxx.xml配置
3.删除./idea下文件 scala_compier.xml的行<parameter value="-make:transitive" />,在edit configuration里配置VM options:
-Dspark.master=local 或-Dspark.master=local[k]或-Dspark.master=local[*]
local 本地单线程
local[K] 本地多线程(指定K个内核)
local[*] 本地多线程(指定所有可用内核)
spark://HOST:PORT 连接到指定的 Spark standalone cluster master,需要指定端口。
mesos://HOST:PORT 连接到指定的 Mesos 集群,需要指定端口。
yarn-client客户端模式 连接到 YARN 集群。需要配置 HADOOP_CONF_DIR。
yarn-cluster集群模式 连接到 YARN 集群。需要配置 HADOOP_CONF_DIR。
4.配置.xml文件如下
<?xml version="1.0" encoding="UTF-8"?> <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> <modelVersion>4.0.0</modelVersion> <groupId>rec.spark</groupId> <artifactId>recoment-model</artifactId> <version>1.0-SNAPSHOT</version> <name>${project.artifactId}</name> <description>My scala app</description> <inceptionYear>2016</inceptionYear> <licenses> <license> <name>My License</name> <url>http://....</url> <distribution>repo</distribution> </license> </licenses> <properties> <maven.compiler.source>1.8</maven.compiler.source> <maven.compiler.target>1.8</maven.compiler.target> <encoding>UTF-8</encoding> <scala.version>2.11.8</scala.version> <scala.compat.version>2.11</scala.compat.version> </properties> <dependencies> <dependency> <groupId>org.scala-lang</groupId> <artifactId>scala-library</artifactId> <version>${scala.version}</version> </dependency> <dependency> <groupId>org.scala-lang</groupId> <artifactId>scala-compiler</artifactId> <version>${scala.version}</version> </dependency> <dependency> <groupId>org.scala-lang</groupId> <artifactId>scala-reflect</artifactId> <version>${scala.version}</version> </dependency> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-core_2.11</artifactId> <version>2.0.0</version> </dependency> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-mllib_2.11</artifactId> <version>2.0.0</version> </dependency> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-streaming_2.11</artifactId> <version>2.0.0</version> </dependency> <dependency> <groupId>org.scalanlp</groupId> <artifactId>breeze-viz_2.11</artifactId> <version>0.12</version> </dependency> <dependency> <groupId>com.github.scopt</groupId> <artifactId>scopt_2.11</artifactId> <version>3.3.0</version> </dependency> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-hive_2.10</artifactId> <version>1.3.0</version> </dependency> <dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-client</artifactId> <version>2.7.2</version> </dependency> <dependency> <groupId> org.apache.cassandra</groupId> <artifactId>cassandra-all</artifactId> <version>0.8.1</version> <exclusions> <exclusion> <groupId>org.slf4j</groupId> <artifactId>slf4j-log4j12</artifactId> </exclusion> <exclusion> <groupId>log4j</groupId> <artifactId>log4j</artifactId> </exclusion> </exclusions> </dependency> <!-- Test --> <dependency> <groupId>junit</groupId> <artifactId>junit</artifactId> <version>4.11</version> <scope>test</scope> </dependency> <dependency> <groupId>org.specs2</groupId> <artifactId>specs2-core_${scala.compat.version}</artifactId> <version>2.4.16</version> <scope>test</scope> </dependency> <dependency> <groupId>org.scalatest</groupId> <artifactId>scalatest_${scala.compat.version}</artifactId> <version>2.2.4</version> <scope>test</scope> </dependency> </dependencies> <build> <sourceDirectory>src/main/scala</sourceDirectory> <testSourceDirectory>src/test/scala</testSourceDirectory> <plugins> <plugin> <groupId>net.alchim31.maven</groupId> <artifactId>scala-maven-plugin</artifactId> <version>3.2.0</version> <executions> <execution> <goals> <goal>compile</goal> <goal>testCompile</goal> </goals> <configuration> <args> <arg>-make:transitive</arg> <arg>-dependencyfile</arg> <arg>${project.build.directory}/.scala_dependencies</arg> </args> </configuration> </execution> </executions> </plugin> <plugin> <groupId>org.apache.maven.plugins</groupId> <artifactId>maven-surefire-plugin</artifactId> <version>2.18.1</version> <configuration> <useFile>false</useFile> <disableXmlReport>true</disableXmlReport> <includes> <include>**/*Test.*</include> <include>**/*Suite.*</include> </includes> </configuration> </plugin> <plugin> <groupId>org.apache.maven.plugins</groupId> <artifactId>maven-shade-plugin</artifactId> <version>2.3</version> <executions> <execution> <phase>package</phase> <goals> <goal>shade</goal> </goals> <configuration> <filters> <filter> <artifact>*:*</artifact> <excludes> <exclude>META-INF/*.SF</exclude> <exclude>META-INF/*.DSA</exclude> <exclude>META-INF/*.RSA</exclude> </excludes> </filter> </filters> </configuration> </execution> </executions> </plugin> </plugins> </build> </project>