data-science-ipython-notebooks/spark/spark.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:6de81fb20a6c3dee884019beb8604ace32cb3be3e7d63d3547dd433075d62e69"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Spark\n",
      "\n",
      "* Python Shell\n",
      "* RDDs"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Python Shell"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Start the pyspark shell:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pyspark"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "View the spark context:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "sc"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## RDDs"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Create an RDD from the contents of a directory:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "my_data = sc.textFile(\"file:/path/*\")"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Count the number of lines in the data:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "my_data.count()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Display the data in the data:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "my_data.collect()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Return the first 10 lines in the data:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "my_data.take(10)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Create an RDD with lines matching the given filter:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "my_data.filter(lambda line: \".txt\" in line)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Chain a series of commands:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "sc.textFile(\"file:/path/file.txt\") \\\n",
      "    .filter(lambda line: \".txt\" in line) \\\n",
      "    .count()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Create a new RDD mapping each line to an array of words, taking only the first word of each array:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "first_words = my_data.map(lambda line: line.split()[0])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Output each word in first_words:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "for word in first_words.take(10):\n",
      "    print word"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Save the first words to a text file:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "first_words.saveAsTextFile(\"file:/path/file\")"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}