CollectTest.scala

package com

import org.apache.spark.mllib.linalg
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.linalg.distributed.RowMatrix
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.SparkSession

object CollectTest {
  def main(args: Array[String]): Unit = {

    val spark = SparkSession.builder().master("local[*]").getOrCreate()
    val sc = spark.sparkContext

    val arr = Array(
      Vectors.dense(1, 2, 3),
      Vectors.dense(4, 5, 6),
      Vectors.dense(7, 8, 9),
      Vectors.dense(10, 11, 12)
    )

    val rdd: RDD[linalg.Vector] = sc.makeRDD(arr, numSlices = 4)

    val m1 = new RowMatrix(rdd, 4, 3)

    val rdd2: RDD[linalg.Vector] = m1.rows.map { v => Vectors.dense(v.toArray.map(_ * 2.0)) }

    val m2 = new RowMatrix(rdd2, 4, 3)

    m2.rows.collect().map(_.toArray.toSeq).foreach(println)

//    WrappedArray(2.0, 4.0, 6.0)
//    WrappedArray(8.0, 10.0, 12.0)
//    WrappedArray(14.0, 16.0, 18.0)
//    WrappedArray(20.0, 22.0, 24.0)
  }
}