【Spark】02.Spark-IDEA配置

1.基于jdk1.8创建一个maven项目

2.增加scala-sdk
Project Structure - Platform Settings - Global Libraries
因为在学习中使用的spark版本，需要适配scala2.12.x版本（该文中用到的是scala_2.12.11）

3.增加Spark的Maven依赖

<dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.12</artifactId>
            <version>3.0.0</version>
        </dependency>
    </dependencies>

4.WrodCount试运行

package com.atguigu.bigdta.spark.core

import org.apache.spark.api.java.JavaSparkContext.fromSparkContext
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}

object Test01 {
  def main(args: Array[String]): Unit = {
    val sparkConf = new SparkConf().setMaster("local").setAppName("WordCount")
    val sc = new SparkContext(sparkConf)

    val lines: RDD[String] = sc.textFile("datas")
    val words: RDD[String] = lines.flatMap(_.split(" "))
    val wordGroup: RDD[(String, Iterable[String])] = words.groupBy(word => word)
    val wordToCount: RDD[(String, Int)] = wordGroup.map {
      case (word, list) => {
        (word, list.size)
      }
    }
    val array: Array[(String, Int)] = wordToCount.collect()
    array.foreach(println)
    //TODO 关闭连接
    sc.close()
  }
}