阿龙学堂-SparkGraphx基本操作篇-第一篇

0、需求实现

我们要构建一个由 GraphX 项目上的各种协作者组成的属性图。vertex 属性可能包含用户名和职业。我们可以使用描述协作者之间关系的字符串来注释边：

1、加载已有测试数据

1.1、加载依赖

<?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>cn.along.com</groupId>
    <artifactId>along-root</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <spark.version>2.0.2</spark.version>
        <hbase.version>1.3.1</hbase.version>
        <hadoop.version>2.7.5</hadoop.version>
        <scala.version>2.11.8</scala.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-mllib_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-compiler</artifactId>
            <version>${scala.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-reflect</artifactId>
            <version>${scala.version}</version>
            <scope>provided</scope>
        </dependency>
    </dependencies>

    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <finalName>networdcount</finalName>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <configuration>
                    <archive>
                        <manifest>
                            <mainClass>cn.along.streaming.WorldCount</mainClass>
                        </manifest>
                    </archive>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>

1.2、代码实现

def main(args: Array[String]): Unit = {
    //准备环境
    val conf: SparkConf = new SparkConf().setAppName("test1").setMaster("local[4]")
    val sc = new SparkContext(conf)
    sc.setLogLevel("WARN")
    //读取数据
    val vertex: RDD[(VertexId, (String, String))] = sc.parallelize(Array(
      (3L, ("rxin", "stu")),
      (2L, ("istoic", "prof")),
      (5L, ("franklin", "prof")),
      (7L, ("jgzal", "postdoc"))))
    //准备顶点
    //准备边
    val edge: RDD[Edge[String]] = sc.parallelize(Array(Edge(3L, 7L, "collab"),
      Edge(5L, 3L, "Adavisor"), Edge(2L, 5L, "Collaeage"), Edge(8L, 7L, "PI")))
    //构建图
    val defaultUser = ("wilson", "Missing")
    val graph = Graph(vertex, edge, defaultUser)
    //顶点集合
    val vertices: VertexRDD[(String, String)] = graph.vertices
    //边集合
    val edges: EdgeRDD[String] = graph.edges
    //释放资源
    sc.stop()
  }

有问题请联系QQ:765120845