Appendix 2: For Scala

import org.apache.spark.sql.SparkSession
import scala.sys.process._
//val spark = SparkSession.builder.getOrCreate

val region = "<region>"
val trainingData = spark.read.format("libsvm")
.option("numFeatures", "784")
.load(s"s3://sagemaker-sample-data-$region/spark/mnist/train/")

val testData = spark.read.format("libsvm")
.option("numFeatures", "784")
.load(s"s3://sagemaker-sample-data-$region/spark/mnist/test/")

val roleArn = "<role_Arn>"

import com.amazonaws.services.sagemaker.sparksdk.IAMRole
import com.amazonaws.services.sagemaker.sparksdk.algorithms
import com.amazonaws.services.sagemaker.sparksdk.algorithms.KMeansSageMakerEstimator

val estimator = new KMeansSageMakerEstimator(
sagemakerRole = IAMRole(roleArn),
trainingInstanceType = "ml.p2.xlarge",
trainingInstanceCount = 1,
endpointInstanceType = "ml.c4.xlarge",
endpointInitialInstanceCount = 1)
.setK(10).setFeatureDim(784)

val model = estimator.fit(trainingData)

val transformedData = model.transform(testData)