spark.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "import pyspark\n",
    "from pyspark import SparkContext, SQLContext, SparkConf\n",
    "\n",
    "from pyspark.sql.functions import udf, col\n",
    "from pyspark.sql.types import FloatType\n",
    "\n",
    "import os\n",
    "\n",
    "\n",
    "os.environ['SPARK_HOME'] = \"/home/jlaura/bigdata/spark-2.1.1-bin-hadoop2.7\"\n",
    "os.environ['SPARK_CONF_DIR'] = \"/tmp/spark/j_spark/749078/conf/\"  # This is a per job variable\n",
    "\n",
    "conf = SparkConf()\\\n",
    "        .setMaster('spark://neb1:7077')\\\n",
    "        .setAppName(\"KelvinJobs\")\\\n",
    "        .set(\"spark.cores.max\", 20)\n",
    "sc = SparkContext(conf=conf)\n",
    "sqlContext = SQLContext(sc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true,
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "# df = sqlContext.read.format(\"jdbc\").options(url=\"jdbc:postgresql://172.16.3.181:31180/tes?user=postgres&password=pass\", dbtable=\"tiy25\",driver=\"org.postgresql.Driver\").load()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "properties = {\n",
    "    \"driver\": \"org.postgresql.Driver\",\n",
    "    \"user\": \"postgres\",\n",
    "    \"password\" : \"pass\"\n",
    "}\n",
    "url = 'jdbc:postgresql://dcos-node1:31180/tes'\n",
    "df = sqlContext.read.jdbc(url=url, table='global_y25', properties=properties)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Row(ti=0.0, long_idx=1, lat_idx=1, lsubs_idx=75),\n",
       " Row(ti=0.0, long_idx=1, lat_idx=1, lsubs_idx=76),\n",
       " Row(ti=0.3888888888888889, long_idx=1, lat_idx=2, lsubs_idx=43),\n",
       " Row(ti=0.06666666666666667, long_idx=1, lat_idx=2, lsubs_idx=44),\n",
       " Row(ti=0.6111111111111112, long_idx=1, lat_idx=2, lsubs_idx=60)]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "sc.stop()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.5.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}