Smote on Spark https://issues.apache.org/jira/browse/SPARK-18441

Smote on Spark

package org.apache.spark.ml.feature

import org.apache.spark.ml.linalg.BLAS.axpy
import org.apache.spark.ml.linalg._
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.SparkSession

import scala.util.Random

/**
  * Created by yuhao on 12/1/16.
  */
object SmoteSampler {

  def generateSamples(data: RDD[(Long, Vector)], k: Int, N: Int): RDD[Vector] = {

    val knei = data.cartesian(data).map { case ((id1, vec1), (id2, vec2)) =>
      (id1, vec1, vec2)
    }.groupBy(_._1)
      .map { case (id, iter) =>
        val arr = iter.toArray
        (arr(0)._2, arr.sortBy(t => Vectors.sqdist(t._2, t._3)).take(k + 1).tail.map(_._3))
      }

    knei.foreach(t => println(t._1 + "\t" + t._2.mkString(", ")))

    knei.flatMap { case (vec, neighbours) =>
      (1 to N).map { i =>
        val rn = neighbours(Random.nextInt(k))
        val diff = rn.copy
        axpy(-1.0, vec, diff)
        val newVec = vec.copy
        axpy(Random.nextDouble(), diff, newVec)
        newVec
      }.iterator
    }
  }

}



// put it in another file.


package org.apache.spark.ml.feature

import org.apache.spark.ml.linalg.BLAS.axpy
import org.apache.spark.ml.linalg._
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.SparkSession

import scala.util.Random

object SmoteTest {

  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder
      .master("local[2]")
      .appName("smote example")
      .getOrCreate()

    // $example on$
    val df = spark.createDataFrame(Seq(
      (0L, Vectors.dense(1, 2)),
      (1L, Vectors.dense(3, 4)),
      (2L, Vectors.dense(5, 6))
    )).toDF("id", "features")
    
    val k = 2
    val N = 3
    val data = df.rdd.map(r => (r.getLong(0), r.getAs[Vector](1)))
    val newSamples = SmoteSampler.generateSamples(data, k, N)
    newSamples.collect().foreach(println)
    spark.stop()
  }
  
}

You implementation may be too slow.