Check hypotheses with bootstrap using Spark

bootstrap_spark.scala

// Code for blogpost https://fullstackml.com/2016/01/19/how-to-check-hypotheses-with-bootstrap-and-apache-spark/
import scala.util.Sorting.quickSort

def getConfInterval(input: org.apache.spark.rdd.RDD[Double], N: Int, left: Double, right:Double)
            : (Double, Double) = {
    // Simulate by sampling and calculating averages for each of subsamples
    val hist = Array.fill(N){0.0}
    for (i <- 0 to N-1) {
        hist(i) = input.sample(withReplacement = true, fraction = 1.0).mean
    }
    
    // Sort the averages and calculate quantiles
    quickSort(hist)
    val left_quantile  = hist((N*left).toInt)
    val right_quantile = hist((N*right).toInt)
    return (left_quantile, right_quantile)
}