spark-core(完结)

构建Sparkwindows环境

配置windowsHadoop

解压到本地磁盘,配置环境变量 bin目录和sbin目录

构建Maven配置pom.xml(学习用)

<artifactId>spark-core</artifactId>

    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>

        <scala.version>2.12.0</scala.version>
        <hadoop.version>2.7.7</hadoop.version>
        <spark.version>2.4.7</spark.version>
    </properties>
    <dependencies>
        <!-- https://mvnrepository.com/artifact/org.apache.spark/spark-core -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.12</artifactId>
            <version>2.4.7</version>
        </dependency>
        <!--Scala-->
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <!--Spark-->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.12</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.12</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.47</version>
        </dependency>
        <!--Hadoop-->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <!--  https://mvnrepository.com/artifact/com.google.code.gson/gson
         <dependency>
             <groupId>com.google.code.gson</groupId>
             <artifactId>gson</artifactId>
             <version>2.8.0</version>
         </dependency>

         &lt;!&ndash; https://mvnrepository.com/artifact/org.apache.kafka/kafka &ndash;&gt;
         <dependency>
             <groupId>org.apache.kafka</groupId>
             <artifactId>kafka_2.11</artifactId>
             <version>1.0.0</version>
         </dependency>-->

        <!-- https://mvnrepository.com/artifact/org.apache.spark/spark-mllib -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-mllib_2.12</artifactId>
            <version>${spark.version}</version>
        </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>3.2.2</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                        <configuration>
                            <args>
                                <arg>-dependencyfile</arg>
                                <arg>${project.build.directory}/.scala_dependencies</arg>
                            </args>
                        </configuration>
                    </execution>
                </executions>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.4.3</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>
                            <transformers>
                                <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

快速上手WordCount

测试是否环境正常

object wc {
  def main(args: Array[String]): Unit = {
    val sparConf = new SparkConf().setMaster("local").setAppName("wordcount")
    val context = new SparkContext(sparConf)
    context.stop()
  }
}

功能实现

object wc {
  def main(args: Array[String]): Unit = {
    //建立连接
    val sparConf = new SparkConf().setMaster("local").setAppName("wordcount")
    val context = new SparkContext(sparConf)
    //读取数据
    val value: RDD[String] = context.textFile("data")
    //扁平映射,将每一行数据铲粪成一个一个单词
    val word: RDD[String] = value.flatMap(_.split(" "))
    //根据单词分组
    val wordGroup: RDD[(String, Iterable[String])] = word.groupBy(word => word)
    //结构转换
    val wordToCount: RDD[(String, Int)] = wordGroup.map {
      case (word, list) =>(word, list.size)
    }
    //采集转化结果
    val tuples: Array[(String, Int)] = wordToCount.collect()
    tuples.foreach(println)
    context.stop()
  }
}

第二种

object wc2 {
  def main(args: Array[String]): Unit = {
    //建立连接
    val sparConf = new SparkConf().setMaster("local").setAppName("wordcount")
    val context = new SparkContext(sparConf)
    //读取数据
    val value: RDD[String] = context.textFile("data")
    //扁平映射,将每一行数据铲粪成一个一个单词
    val word: RDD[String] = value.flatMap(_.split(" "))
    //结构转化
    val wordM: RDD[(String, Int)] = word.map(i => (i, 1))
    val wordGroup: RDD[(String, Iterable[(Strin