{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "scrolled": false }, "outputs": [], "source": [ "%%classpath add mvn\n", "org.apache.spark spark-sql_2.11 2.2.1" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "%%spark\n", "SparkSession.builder()\n", " .appName(\"Simple Application\")\n", " .master(\"local[4]\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "val NUM_SAMPLES = 10000000\n", "\n", "val count2 = 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 * count2 / NUM_SAMPLES)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "val tornadoesPath = java.nio.file.Paths.get(\"../../resources/data/tornadoes_2014.csv\").toAbsolutePath()\n", "\n", "val ds = spark.read.format(\"csv\").option(\"header\", \"true\").load(tornadoesPath.toString())\n", "ds" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "ds.display(1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### AutoConnect: use --connect or -c" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "%%spark --connect" ] } ], "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": "2.11.12" }, "toc": { "base_numbering": 1, "nav_menu": {}, "number_sections": false, "sideBar": false, "skip_h1_title": false, "title_cell": "Table of Contents", "title_sidebar": "Contents", "toc_cell": false, "toc_position": {}, "toc_section_display": false, "toc_window_display": false } }, "nbformat": 4, "nbformat_minor": 2 }