{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Spark\n",
    "\n",
    "[Apache Spark](https://spark.apache.org/) is a lightning-fast cluster computing API based on Scala. Deeper integration with Spark is on the [agenda](https://github.com/twosigma/beakerx/issues/6513)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "%classpath add mvn org.apache.spark spark-sql_2.11 2.2.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import org.apache.spark.sql.SparkSession\n",
    "\n",
    "val spark = SparkSession.builder()\n",
    "                        .appName(\"Simple Application\")\n",
    "                        .master(\"local[4]\")\n",
    "                        .config(\"spark.ui.enabled\", \"false\")\n",
    "                        .getOrCreate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "val NUM_SAMPLES = 10000000\n",
    "\n",
    "val count = spark.sparkContext.parallelize(1 to NUM_SAMPLES).map{i =>\n",
    "  val x = Math.random()\n",
    "  val y = Math.random()\n",
    "  if (x*x + y*y < 1) 1 else 0\n",
    "}.reduce(_ + _)\n",
    "\n",
    "println(\"Pi is roughly \" + 4.0 * count / NUM_SAMPLES)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "spark.stop()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Scala",
   "language": "scala",
   "name": "scala"
  },
  "language_info": {
   "codemirror_mode": "text/x-scala",
   "file_extension": ".scala",
   "mimetype": "",
   "name": "Scala",
   "nbconverter_exporter": "",
   "version": "2.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}