{

 "metadata": {

  "name": "",

  "signature": "sha256:9a606ffda65f7f3f2aabfad8caca6f72a9ce68e461e4250a1a643804b9cd9860"

 },

 "nbformat": 3,

 "nbformat_minor": 0,

 "worksheets": [

  {

   "cells": [

    {

     "cell_type": "code",

     "collapsed": false,

     "input": [

      "import pprint\n",

      "from difflib import SequenceMatcher\n",

      "\n",

      "# http://python-cluster.sourceforge.net/\n",

      "from cluster import HierarchicalClustering\n",

      "\n",

      "# input urls to be clustered\n",

      "urls = [\n",

      "    'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&cid=28814385',\n",

      "    '#articles',\n",

      "    'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&cid=28814335',\n",

      "    'http://yro.slashdot.org/~drDugan/',\n",

      "    'http://web.sourceforge.com/privacy.php',\n",

      "    'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&cid=28815123',\n",

      "    'http://slashdot.org//slashdot.org/~Darkness404',\n",

      "    'http://slashdot.org//radio.slashdot.org',\n",

      "    'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&op=Reply&threshold=1&commentsort=0&mode=thread&pid=28814429',\n",

      "    'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&op=Reply&threshold=1&commentsort=0&mode=thread&pid=28814457',\n",

      "    'http://slashdot.org//slashdot.org/article.pl?sid=09/07/24/1545238',\n",

      "    'http://slashdot.org//slashdot.org/comments.pl?sid=09/07/24/1545238&cid=28810581',\n",

      "    'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&cid=28815269',\n",

      "    'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&cid=28814657',\n",

      "    'http://web.sourceforge.com/terms.php'\n",

      "    'http://slashdot.org//it.slashdot.org/search',\n",

      "    'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&cid=28814581',\n",

      "    'http://xkcd.com/612/',\n",

      "    'http://web.sourceforge.com/advertising',\n",

      "    'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&op=Reply&threshold=1&commentsort=0&mode=thread&pid=28814785',\n",

      "]\n",

      "\n",

      "# distance function compares two urls and finds the distance\n",

      "# uses SequenceMatcher from python standard module difflib\n",

      "def distance(url1, url2):\n",

      "    ratio = SequenceMatcher(None, url1, url2).ratio()\n",

      "    return 1.0 - ratio\n",

      "\n",

      "# Perform clustering\n",

      "hc = HierarchicalClustering(urls, distance)\n",

      "clusters = hc.getlevel(0.2)\n",

      "\n",

      "pprint.pprint(clusters)"

     ],

     "language": "python",

     "metadata": {},

     "outputs": [

      {

       "output_type": "stream",

       "stream": "stdout",

       "text": [

        "[['#articles'],\n",

        " ['http://xkcd.com/612/'],\n",

        " ['http://web.sourceforge.com/advertising'],\n",

        " ['http://web.sourceforge.com/privacy.php'],\n",

        " ['http://web.sourceforge.com/terms.phphttp://slashdot.org//it.slashdot.org/search'],\n",

        " ['http://yro.slashdot.org/~drDugan/'],\n",

        " ['http://slashdot.org//radio.slashdot.org'],\n",

        " ['http://slashdot.org//slashdot.org/~Darkness404'],\n",

        " ['http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&op=Reply&threshold=1&commentsort=0&mode=thread&pid=28814785',\n",

        "  'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&op=Reply&threshold=1&commentsort=0&mode=thread&pid=28814429',\n",

        "  'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&op=Reply&threshold=1&commentsort=0&mode=thread&pid=28814457'],\n",

        " ['http://slashdot.org//slashdot.org/article.pl?sid=09/07/24/1545238',\n",

        "  'http://slashdot.org//slashdot.org/comments.pl?sid=09/07/24/1545238&cid=28810581',\n",

        "  'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&cid=28815123',\n",

        "  'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&cid=28815269',\n",

        "  'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&cid=28814335',\n",

        "  'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&cid=28814385',\n",

        "  'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&cid=28814581',\n",

        "  'http://slashdot.org//it.slashdot.org/comments.pl?sid=1314601&cid=28814657']]\n"

       ]

      }

     ],

     "prompt_number": 2

    },

    {

     "cell_type": "code",

     "collapsed": false,

     "input": [

      "type(urls)"

     ],

     "language": "python",

     "metadata": {},

     "outputs": [

      {

       "metadata": {},

       "output_type": "pyout",

       "prompt_number": 4,

       "text": [

        "list"

       ]

      }

     ],

     "prompt_number": 4

    }

   ],

   "metadata": {}

  }

 ]

}