make-small-accidents.ipynb

   1 {
   2  "metadata": {
   3   "name": ""
   4  },
   5  "nbformat": 3,
   6  "nbformat_minor": 0,
   7  "worksheets": [
   8   {
   9    "cells": [
  10     {
  11      "cell_type": "code",
  12      "collapsed": false,
  13      "input": [
  14       "import pymongo\n",
  15       "client = pymongo.MongoClient('mongodb://ogedei:27017/')"
  16      ],
  17      "language": "python",
  18      "metadata": {},
  19      "outputs": [],
  20      "prompt_number": 2
  21     },
  22     {
  23      "cell_type": "markdown",
  24      "metadata": {},
  25      "source": [
  26       "Connect to the `accidents` database"
  27      ]
  28     },
  29     {
  30      "cell_type": "code",
  31      "collapsed": false,
  32      "input": [
  33       "db = client.accidents\n",
  34       "accidents = db.accidents"
  35      ],
  36      "language": "python",
  37      "metadata": {},
  38      "outputs": [],
  39      "prompt_number": 3
  40     },
  41     {
  42      "cell_type": "code",
  43      "collapsed": false,
  44      "input": [
  45       "accidents.find().count()"
  46      ],
  47      "language": "python",
  48      "metadata": {},
  49      "outputs": [
  50       {
  51        "metadata": {},
  52        "output_type": "pyout",
  53        "prompt_number": 4,
  54        "text": [
  55         "1355615"
  56        ]
  57       }
  58      ],
  59      "prompt_number": 4
  60     },
  61     {
  62      "cell_type": "markdown",
  63      "metadata": {},
  64      "source": [
  65       "Drop any existing small accident database"
  66      ]
  67     },
  68     {
  69      "cell_type": "code",
  70      "collapsed": false,
  71      "input": [
  72       "client.drop_database('asmall')"
  73      ],
  74      "language": "python",
  75      "metadata": {},
  76      "outputs": [],
  77      "prompt_number": 21
  78     },
  79     {
  80      "cell_type": "markdown",
  81      "metadata": {},
  82      "source": [
  83       "Create a new database with a new collection.\n",
  84       "\n",
  85       "Note that this is created lazily, so neither the database nor the collection will appear on the server until we've put some data in it."
  86      ]
  87     },
  88     {
  89      "cell_type": "code",
  90      "collapsed": false,
  91      "input": [
  92       "small_db = client.asmall\n",
  93       "small_accidents = small_db.accidents"
  94      ],
  95      "language": "python",
  96      "metadata": {},
  97      "outputs": [],
  98      "prompt_number": 22
  99     },
 100     {
 101      "cell_type": "markdown",
 102      "metadata": {},
 103      "source": [
 104       "Copy the first 100 accidents across."
 105      ]
 106     },
 107     {
 108      "cell_type": "code",
 109      "collapsed": false,
 110      "input": [
 111       "for a in accidents.find(limit=100):\n",
 112       "    small_accidents.insert(a)\n",
 113       "small_accidents.find().count()"
 114      ],
 115      "language": "python",
 116      "metadata": {},
 117      "outputs": [
 118       {
 119        "metadata": {},
 120        "output_type": "pyout",
 121        "prompt_number": 23,
 122        "text": [
 123         "100"
 124        ]
 125       }
 126      ],
 127      "prompt_number": 23
 128     },
 129     {
 130      "cell_type": "markdown",
 131      "metadata": {},
 132      "source": [
 133       "Create the index for it."
 134      ]
 135     },
 136     {
 137      "cell_type": "code",
 138      "collapsed": false,
 139      "input": [
 140       "small_accidents.create_index('Accident_Index')"
 141      ],
 142      "language": "python",
 143      "metadata": {},
 144      "outputs": [
 145       {
 146        "metadata": {},
 147        "output_type": "pyout",
 148        "prompt_number": 24,
 149        "text": [
 150         "'Accident_Index_1'"
 151        ]
 152       }
 153      ],
 154      "prompt_number": 24
 155     },
 156     {
 157      "cell_type": "code",
 158      "collapsed": false,
 159      "input": [],
 160      "language": "python",
 161      "metadata": {},
 162      "outputs": []
 163     }
 164    ],
 165    "metadata": {}
 166   }
 167  ]
 168 }