Digging into GANE data

Digging into GANE data.ipynb

{
 "metadata": {
  "name": "Digging into GANE data"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from collections import defaultdict\n",
      "import glob\n",
      "import json\n",
      "import pprint"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "gane_names = []\n",
      "\n",
      "for fname in glob.glob(\"names-0*.json\"):\n",
      "    f = open(fname)\n",
      "    text = f.read()\n",
      "    gane_names.extend(json.loads(text))\n",
      "    f.close()\n",
      "    \n",
      "print len(gane_names)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "600\n"
       ]
      }
     ],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "gane_tree = defaultdict(dict)\n",
      "\n",
      "for n in gane_names:\n",
      "    try:\n",
      "        placeURI = n.get('placeURI')\n",
      "        if \"pleiades.stoa.org\" in placeURI:\n",
      "            branch = int(n.get('GANEid', -1))\n",
      "        else:\n",
      "            branch = int(n.get('placeURI').split(\"placeID=\")[1])\n",
      "    except:\n",
      "        print n \n",
      "        raise\n",
      "    leaf = int(n.get('GANEid', -1))\n",
      "    gane_tree[branch][leaf] = n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print len(gane_tree) # the number of GANE places"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "470\n"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print gane_tree.items()[0]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "(17067, {17067: {u'externalURIs': False, u'placeURI': u'http://pleiades.stoa.org/places/746700', u'reference': {u'text': u'A place name in the T\\xfcbingen Atlas Index (Vol. 1, pp. 463)', u'index-page': 463, u'index-volume': 1}, u'title': u'\\u1eb8\\u0304lat', u'maxDate': 2000, u'authors': u'B. Siewert-Mayer, H. Kopp, W. R\\xf6llig, F. Deblauwe, E. Kansa', u'GANEid': 17067, u'periods': [u'Modern Middle East'], u'extent': {u'type': u'Point', u'coordinates': [34.55, 29.3]}, u'nameTransliterated': False, u'creators': u'B. Siewert-Mayer, H. Kopp, W. R\\xf6llig', u'minDate': 1918}})\n"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def in_pleiades(args):\n",
      "    # is a GANE place in Pleiades?\n",
      "    k, v = args\n",
      "    return \"pleiades.stoa.org\" in v[k]['placeURI']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 14
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "x = gane_tree[13]\n",
      "print in_pleiades((13, x))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "False\n"
       ]
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pprint.pprint(gane_tree[x])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "{12: {u'GANEid': 12,\n",
        "      u'authors': u'B. Siewert-Mayer, H. Kopp, W. R\\xf6llig, F. Deblauwe, E. Kansa',\n",
        "      u'creators': u'B. Siewert-Mayer, H. Kopp, W. R\\xf6llig',\n",
        "      u'extent': {u'coordinates': [48, 30], u'type': u'Point'},\n",
        "      u'externalURIs': False,\n",
        "      u'maxDate': 1950,\n",
        "      u'minDate': 1900,\n",
        "      u'nameTransliterated': False,\n",
        "      u'periods': [u'Ottoman Decline-Mandate Middle East'],\n",
        "      u'placeURI': u'http://gap.alexandriaarchive.org/gane/edit-place?placeID=13',\n",
        "      u'reference': {u'index-page': 1,\n",
        "                     u'index-volume': 1,\n",
        "                     u'text': u'A place name in the T\\xfcbingen Atlas Index (Vol. 1, pp. 1)'},\n",
        "      u'title': u'\\u02bfAba\\u0304d\\u0101n'},\n",
        " 13: {u'GANEid': 13,\n",
        "      u'authors': u'B. Siewert-Mayer, H. Kopp, W. R\\xf6llig, F. Deblauwe, E. Kansa',\n",
        "      u'creators': u'B. Siewert-Mayer, H. Kopp, W. R\\xf6llig',\n",
        "      u'extent': {u'coordinates': [48.1, 30.2], u'type': u'Point'},\n",
        "      u'externalURIs': [u'http://en.wikipedia.org/wiki/Abadan,_Iran',\n",
        "                        u'http://www.iranicaonline.org/articles/abadan'],\n",
        "      u'maxDate': 2000,\n",
        "      u'minDate': 819,\n",
        "      u'nameTransliterated': [u'Abadan'],\n",
        "      u'periods': [u'Samanid-Ghaznavid Iran',\n",
        "                   u'Safavid Middle East',\n",
        "                   u'Ottoman Decline-Mandate Middle East',\n",
        "                   u'Modern Middle East'],\n",
        "      u'placeURI': u'http://gap.alexandriaarchive.org/gane/edit-place?placeID=13',\n",
        "      u'reference': {u'index-page': 1,\n",
        "                     u'index-volume': 1,\n",
        "                     u'text': u'A place name in the T\\xfcbingen Atlas Index (Vol. 1, pp. 1)'},\n",
        "      u'title': u'\\u0100b\\u0101d\\u0101n'},\n",
        " 78: {u'GANEid': 78,\n",
        "      u'authors': u'B. Siewert-Mayer, H. Kopp, W. R\\xf6llig, F. Deblauwe, E. Kansa',\n",
        "      u'creators': u'B. Siewert-Mayer, H. Kopp, W. R\\xf6llig',\n",
        "      u'extent': {u'coordinates': [48.15, 30.15], u'type': u'Point'},\n",
        "      u'externalURIs': False,\n",
        "      u'maxDate': 1950,\n",
        "      u'minDate': 750,\n",
        "      u'nameTransliterated': [u'Abbadan', u\"'Abbadan\"],\n",
        "      u'periods': [u'Abassid Middle East',\n",
        "                   u'Samanid-Ghaznavid Iran',\n",
        "                   u'Seljuq-Khwarezmian Middle East',\n",
        "                   u'Khwarezmian Middle East',\n",
        "                   u'1200 BC Middle East',\n",
        "                   u'Mongol Middle East',\n",
        "                   u'Ilkhanate Middle East',\n",
        "                   u'Timurid Middle East',\n",
        "                   u'Ottoman Decline-Mandate Middle East'],\n",
        "      u'placeURI': u'http://gap.alexandriaarchive.org/gane/edit-place?placeID=13',\n",
        "      u'reference': {u'index-page': 3,\n",
        "                     u'index-volume': 1,\n",
        "                     u'text': u'A place name in the T\\xfcbingen Atlas Index (Vol. 1, pp. 3)'},\n",
        "      u'title': u'\\u02bfAbb\\u0101d\\u0101n'}}\n"
       ]
      }
     ],
     "prompt_number": 16
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "for k, v in x.items():\n",
      "    print k, v['title'], v['nameTransliterated']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "12 \u02bfAba\u0304d\u0101n False\n",
        "13 \u0100b\u0101d\u0101n [u'Abadan']\n",
        "78 \u02bfAbb\u0101d\u0101n [u'Abbadan', u\"'Abbadan\"]\n"
       ]
      }
     ],
     "prompt_number": 19
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}