spark-scala-minpricedproductbycategory.scala

val path = "/public/retail_db"
val products = sc.textFile(path + "/products")

val minPricedProductsByCategory = products.
  filter(product => product.split(",")(4) != "").
  map(product => {
    val p = product.split(",")
    (p(1).toInt, product)
  }).
  reduceByKey((agg, product) => {
    if(agg.split(",")(4).toFloat < product.split(",")(4).toFloat)
      agg
    else
      product
  }).
  map(rec => rec._2)
minPricedProductsByCategory.collect.foreach(println)