IPython Notebook with examples, and TypeError, in Learning Spark book dated 2015-03-27: "Second Release"

LearningSparkCh03.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Notebooks by Neal McBurnett based on the book _Learning Spark_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Example 3-5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "lines = sc.parallelize([\"pandas\", \"i like pandas\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "inputRDD = sc.parallelize([\"success\", \"error: issue 1\", \"warning: issue 2\", \"error and warning: weird!\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "errorsRDD = inputRDD.filter(lambda x: \"error\" in x)\n",
    "warningsRDD = inputRDD.filter(lambda x: \"warning\" in x)\n",
    "badLinesRDD = errorsRDD.union(warningsRDD)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(8) UnionRDD[12] at union at NativeMethodAccessorImpl.java:-2 []\n",
      " |  PythonRDD[10] at RDD at PythonRDD.scala:43 []\n",
      " |  ParallelCollectionRDD[3] at parallelize at PythonRDD.scala:392 []\n",
      " |  PythonRDD[11] at RDD at PythonRDD.scala:43 []\n",
      " |  ParallelCollectionRDD[3] at parallelize at PythonRDD.scala:392 []\n"
     ]
    }
   ],
   "source": [
    "print badLinesRDD.toDebugString()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Example 3-15 (with semantic error)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "cannot concatenate 'str' and 'int' objects",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-10-078b22c97d4b>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[1;32mprint\u001b[0m \u001b[1;34m\"Input had \"\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0mbadLinesRDD\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcount\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m+\u001b[0m \u001b[1;34m\" concerning lines\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      2\u001b[0m \u001b[1;32mprint\u001b[0m \u001b[1;34m\"Here are 10 examples:\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mline\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mbadLinesRDD\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtake\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m10\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      4\u001b[0m     \u001b[1;32mprint\u001b[0m \u001b[0mline\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mTypeError\u001b[0m: cannot concatenate 'str' and 'int' objects"
     ]
    }
   ],
   "source": [
    "print \"Input had \" + badLinesRDD.count() + \" concerning lines\"\n",
    "print \"Here are 10 examples:\"\n",
    "for line in badLinesRDD.take(10):\n",
    "    print line"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Example 3-15 (fix error and language usage)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Input had 4 worrisome lines\n",
      "Here are 10 examples:\n",
      "error: issue 1\n",
      "error and warning: weird!\n",
      "warning: issue 2\n",
      "error and warning: weird!\n"
     ]
    }
   ],
   "source": [
    "print \"Input had %d worrisome lines\" % (badLinesRDD.count())\n",
    "print \"Here are 10 examples:\"\n",
    "for line in badLinesRDD.take(10):\n",
    "    print line"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}