spark issue 2620.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\u001b[32mimport \u001b[39m\u001b[36m$exclude.$                        , $ivy.$                           \n",
       "\u001b[39m\n",
       "\u001b[32mimport \u001b[39m\u001b[36m$profile.$           \n",
       "\u001b[39m\n",
       "\u001b[32mimport \u001b[39m\u001b[36m$ivy.$                                  \n",
       "\u001b[39m\n",
       "\u001b[32mimport \u001b[39m\u001b[36m$ivy.$                                   \n",
       "\u001b[39m\n",
       "\u001b[32mimport \u001b[39m\u001b[36m$ivy.$                               \n",
       "\n",
       "\u001b[39m\n",
       "\u001b[32mimport \u001b[39m\u001b[36morg.apache.spark._\n",
       "\u001b[39m\n",
       "\u001b[32mimport \u001b[39m\u001b[36morg.apache.spark.sql._\n",
       "\u001b[39m\n",
       "\u001b[32mimport \u001b[39m\u001b[36mjupyter.spark.session._\u001b[39m"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import $exclude.`org.slf4j:slf4j-log4j12`, $ivy.`org.slf4j:slf4j-nop:1.7.21`\n",
    "import $profile.`hadoop-2.6`\n",
    "import $ivy.`org.apache.spark::spark-sql:2.1.0`\n",
    "import $ivy.`org.apache.hadoop:hadoop-aws:2.6.4`\n",
    "import $ivy.`org.jupyter-scala::spark:0.4.2`\n",
    "\n",
    "import org.apache.spark._\n",
    "import org.apache.spark.sql._\n",
    "import jupyter.spark.session._"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "log4j:WARN No appenders could be found for logger (io.netty.util.internal.logging.InternalLoggerFactory).\n",
      "log4j:WARN Please initialize the log4j system properly.\n",
      "log4j:WARN See http://logging.apache.org/log4j/1.2/faq.html#noconfig for more info.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\u001b[36msparkSession\u001b[39m: \u001b[32mSparkSession\u001b[39m = org.apache.spark.sql.SparkSession@44523f03"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "val sparkSession = JupyterSparkSession.builder()\n",
    "  .jupyter()\n",
    "  .master(\"local\")\n",
    "  .appName(\"notebook\")\n",
    "  .getOrCreate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "defined \u001b[32mclass\u001b[39m \u001b[36mP\u001b[39m"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "case class P(name: String)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\u001b[36mps\u001b[39m: \u001b[32mArray\u001b[39m[\u001b[32mP\u001b[39m] = \u001b[33mArray\u001b[39m(\u001b[33mP\u001b[39m(\u001b[32m\"alice\"\u001b[39m), \u001b[33mP\u001b[39m(\u001b[32m\"bob\"\u001b[39m), \u001b[33mP\u001b[39m(\u001b[32m\"charly\"\u001b[39m), \u001b[33mP\u001b[39m(\u001b[32m\"bob\"\u001b[39m))\n",
       "\u001b[36mres3_1\u001b[39m: \u001b[32mArray\u001b[39m[(\u001b[32mP\u001b[39m, \u001b[32mInt\u001b[39m)] = \u001b[33mArray\u001b[39m((\u001b[33mP\u001b[39m(\u001b[32m\"alice\"\u001b[39m), \u001b[32m1\u001b[39m), (\u001b[33mP\u001b[39m(\u001b[32m\"charly\"\u001b[39m), \u001b[32m1\u001b[39m), (\u001b[33mP\u001b[39m(\u001b[32m\"bob\"\u001b[39m), \u001b[32m2\u001b[39m))"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "val ps = Array(P(\"alice\"), P(\"bob\"), P(\"charly\"), P(\"bob\"))\n",
    "\n",
    "sparkSession\n",
    "  .sparkContext\n",
    "  .parallelize(ps)\n",
    "  .map(x => (x,1))\n",
    "  .reduceByKey((x,y) => x + y)\n",
    "  .collect()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Scala (staged)",
   "language": "scala",
   "name": "scala-staged"
  },
  "language_info": {
   "codemirror_mode": "text/x-scala",
   "file_extension": ".scala",
   "mimetype": "text/x-scala",
   "name": "scala211",
   "nbconvert_exporter": "script",
   "pygments_lexer": "scala",
   "version": "2.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}