Cars.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Marking com.databricks:spark-csv_2.10:1.4.0 for download\n",
      "Preparing to fetch from:\n",
      "-> file:/tmp/.ivy2/\n",
      "-> https://repo1.maven.org/maven2\n",
      "-> New file at /tmp/.ivy2/https/repo1.maven.org/maven2/org/apache/commons/commons-csv/1.1/commons-csv-1.1.jar\n",
      "-> New file at /tmp/.ivy2/https/repo1.maven.org/maven2/com/databricks/spark-csv_2.10/1.4.0/spark-csv_2.10-1.4.0.jar\n",
      "-> New file at /tmp/.ivy2/https/repo1.maven.org/maven2/com/univocity/univocity-parsers/1.5.1/univocity-parsers-1.5.1.jar\n"
     ]
    }
   ],
   "source": [
    "%AddDeps com.databricks spark-csv_2.10 1.4.0 --transitive"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import org.apache.spark.sql.SQLContext\n",
    "import sqlContext._\n",
    "import sqlContext.implicits._\n",
    "import SQLContext._\n",
    "val sqlContext = new SQLContext(sc)\n",
    "import sqlContext.implicits._\n",
    "val df = sqlContext.read.format(\"com.databricks.spark.csv\").option(\"header\", \"true\").option(\"inferSchema\", \"true\").load(\"cars.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+----+-----+-----+--------------------+-----+\n",
      "|year| make|model|             comment|blank|\n",
      "+----+-----+-----+--------------------+-----+\n",
      "|2012|Tesla|    S|          No comment|     |\n",
      "|1997| Ford| E350|Go get one now th...|     |\n",
      "|2015|Chevy| Volt|                null| null|\n",
      "+----+-----+-----+--------------------+-----+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "df.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Toree",
   "language": "",
   "name": "toree"
  },
  "language_info": {
   "name": "scala"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}