sample spark

sample_spark.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyspark.sql import SparkSession\n",
    "import os\n",
    "app_name = \"wk12_demo\"\n",
    "master = \"local[*]\"\n",
    "ui_prefix = os.environ.get('JUPYTERHUB_SERVICE_PREFIX', '/') + 'sparkui'\n",
    "\n",
    "spark = SparkSession\\\n",
    "        .builder\\\n",
    "        .appName(app_name)\\\n",
    "        .master(master)\\\n",
    "        .config('spark.ui.proxyBase', ui_prefix)\\\n",
    "        .getOrCreate()\n",
    "\n",
    "sc = spark.sparkContext"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1249975000"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rdd = sc.parallelize(list(range(50000)))\n",
    "rdd.sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}