package com.curso.spark

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.rdd.RDD
import org.apache.spark.mllib.linalg.{Vector, Vectors, Matrix, Matrices}
import org.apache.log4j._

object temario1_1 {

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

      val sc = new SparkContext("local[*]", "Curso3")
      sc.setLogLevel("ERROR")

      Logger.getLogger("org").setLevel(Level.ERROR)

   try {

     val observations: RDD[Vector] = sc.parallelize( Array(
     Vectors.dense(1.0,2.0),
     Vectors.dense(4.0,5.0),
     Vectors.dense(7.0,8.0)))

     import org.apache.spark.mllib.stat._

     val resumen: MultivariateStatisticalSummary = Statistics.colStats(observations)

     val media = resumen.mean
     println("Media: " + media)
//Media: [4.0,5.0]

    val varianza = resumen.variance
    println("Varianza: " + varianza)
//Varianza: [9.0,9.0]

    val sinceros = resumen.numNonzeros
  println("Numero No Zeros: " + sinceros)
// Numero No Zeros: [3.0,3.0]

    val norma1 = resumen.normL1
    println("Norma L1: " + norma1)
// Norma L1: [12.0,15.0]

    val norma2 = resumen.normL2
    println("Norma L2: " + norma2)
// Norma L2: [8.12403840463596,9.643650760992955]

   println("Pulsar una tecla para finalizar el trabajo...");
     Console.in.read()

    } finally {
      sc.stop()
    }

  }
}