Run PageRank on a small example site to show the PR of an orphaned page -- one with no links

generate-site-orphaned-page.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Build a dummy small site with some arbitrary links"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import networkx as nx\n",
    "site = nx.DiGraph()\n",
    "\n",
    "def add_one_level_down(name):\n",
    "    site.add_edges_from([('home',name)])\n",
    "    site.add_edges_from([(name,'home')])\n",
    "\n",
    "add_one_level_down(\"one\")\n",
    "add_one_level_down(\"two\")\n",
    "add_one_level_down(\"three\")\n",
    "add_one_level_down(\"four\")\n",
    "add_one_level_down(\"five\")\n",
    "\n",
    "\n",
    "def interlink(pages):\n",
    "    for page in pages:\n",
    "        for page2 in pages:\n",
    "            if page != page2:\n",
    "                site.add_edges_from([(page,page2)])\n",
    "\n",
    "interlink([\"one\", \"two\", \"three\", \"four\", \"five\"])\n",
    "\n",
    "def add_sub_page(page, sub_page):\n",
    "    site.add_edges_from([(page,sub_page),(sub_page,'home')])\n",
    "\n",
    "add_sub_page(\"one\", \"one1\")\n",
    "add_sub_page(\"two\", \"two1\")\n",
    "add_sub_page(\"three\", \"three1\")\n",
    "add_sub_page(\"four\", \"four1\")\n",
    "add_sub_page(\"five\", \"five1\")\n",
    "\n",
    "add_one_level_down(\"terms\")\n",
    "add_one_level_down(\"contact\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Add an orphaned page and run the PR algo"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "site.add_edges_from([(\"orphan\",\"one\")])\n",
    "orphan_pr = nx.pagerank(site)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Name: \n",
      "Type: DiGraph\n",
      "Number of nodes: 14\n",
      "Number of edges: 45\n",
      "Average in degree:   3.2143\n",
      "Average out degree:   3.2143\n"
     ]
    }
   ],
   "source": [
    "print(nx.info(site))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Show that the PR of the orphaned page is what we'd expect it to be from our naive calculations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.0107142857\n"
     ]
    }
   ],
   "source": [
    "print(round(orphan_pr[\"orphan\"], 10))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.0107142857\n"
     ]
    }
   ],
   "source": [
    "print(round(1/len(nx.nodes(site))*.15, 10))"
   ]
  }
 ],
 "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": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}