x-tech.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Finding \"X-Tech\" Candidates"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Get the name of industries\n",
    "\n",
    "Categories/Pages under [Category:Industries - Wikipedia, the free encyclopedia](https://en.wikipedia.org/wiki/Category:Industries), via DBpedia."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "%%bash\n",
    "pip install SPARQLWrapper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from SPARQLWrapper import SPARQLWrapper, JSON"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "sparql = SPARQLWrapper(\"http://dbpedia.org/sparql\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "sparql.setQuery(\"\"\"\n",
    "    PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>\n",
    "    PREFIX skos: <http://www.w3.org/2004/02/skos/core#>\n",
    "    PREFIX dcterms: <http://purl.org/dc/terms/>\n",
    "\n",
    "    SELECT DISTINCT ?label WHERE {\n",
    "        {\n",
    "            {?s dcterms:subject <http://dbpedia.org/resource/Category:Industries>} \n",
    "            UNION {?s skos:broader <http://dbpedia.org/resource/Category:Industries>}\n",
    "        } .\n",
    "      ?s rdfs:label ?label .\n",
    "      filter langMatches(lang(?label),\"en\")\n",
    "    }\n",
    "\"\"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "sparql.setReturnFormat(JSON)\n",
    "results = sparql.query().convert()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "list_industries = [result[\"label\"][\"value\"] for result in results[\"results\"][\"bindings\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[u'Chemical industry',\n",
       " u'Show business',\n",
       " u'Companies by arms sales',\n",
       " u'Motorsport industry',\n",
       " u'Poverty industry',\n",
       " u'Leisure industry',\n",
       " u'Celebrity\\u2013industrial complex',\n",
       " u'Sport industry',\n",
       " u'Aircraft industry',\n",
       " u'Arms industry',\n",
       " u'Professional sports',\n",
       " u'Semiconductor industry',\n",
       " u'Video game industry',\n",
       " u'Electric power industry',\n",
       " u'Payment card industry',\n",
       " u'Personal care',\n",
       " u'Bicycle industry',\n",
       " u'Creative industries',\n",
       " u'Textile industry',\n",
       " u'Professional audiovisual industry',\n",
       " u'New manufacturing economy',\n",
       " u'Alcohol industry',\n",
       " u'Tobacco industry',\n",
       " u'Cultural industry',\n",
       " u'Information industry',\n",
       " u'Activism industry',\n",
       " u'Sustainable industries',\n",
       " u'Health care industry',\n",
       " u'Software industry',\n",
       " u'Zu Audio',\n",
       " u'Space-based industry',\n",
       " u'Radio industry',\n",
       " u'Energy industry',\n",
       " u'Naval stores industry',\n",
       " u'Housing industry',\n",
       " u'Converters (industry)',\n",
       " u'Entertainment industry',\n",
       " u'Commercial item transport and distribution',\n",
       " u'Food industry',\n",
       " u'Fur trade',\n",
       " u'Industrial agriculture',\n",
       " u'Metalworking',\n",
       " u'Mining',\n",
       " u'Real estate',\n",
       " u'Service industries',\n",
       " u'Shipping',\n",
       " u'Plastics industry',\n",
       " u'Trade unions by industry',\n",
       " u'Companies by industry',\n",
       " u'Fishing industry',\n",
       " u'Industries by country',\n",
       " u'Media industry',\n",
       " u'Toy industry',\n",
       " u'Automotive industry',\n",
       " u'Computer industry',\n",
       " u'Cosmetics',\n",
       " u'Manufactured goods',\n",
       " u'Military industry',\n",
       " u'Pharmaceutical industry',\n",
       " u'Private spaceflight',\n",
       " u'Pulp and paper industry',\n",
       " u'Recycling industry',\n",
       " u'Businesspeople by industry',\n",
       " u'Death care industry',\n",
       " u'Industries by city',\n",
       " u'Communities by industry',\n",
       " u'Space industry',\n",
       " u'Electronics industry',\n",
       " u'Banking',\n",
       " u'Garment industry',\n",
       " u'Timber industry',\n",
       " u'Transport',\n",
       " u'Water industry',\n",
       " u'Stock market indices by industry',\n",
       " u'Petroleum industry',\n",
       " u'Steel industry']"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list_industries"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create  names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def techize(s):\n",
    "    return s.replace(\"industry\", \"\").replace(\"industries\", \"\").strip().title().replace(\" \", \"\") + \"Tech\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[u'ChemicalTech',\n",
       " u'ShowBusinessTech',\n",
       " u'CompaniesByArmsSalesTech',\n",
       " u'MotorsportTech',\n",
       " u'PovertyTech',\n",
       " u'LeisureTech',\n",
       " u'Celebrity\\u2013IndustrialComplexTech',\n",
       " u'SportTech',\n",
       " u'AircraftTech',\n",
       " u'ArmsTech',\n",
       " u'ProfessionalSportsTech',\n",
       " u'SemiconductorTech',\n",
       " u'VideoGameTech',\n",
       " u'ElectricPowerTech',\n",
       " u'PaymentCardTech',\n",
       " u'PersonalCareTech',\n",
       " u'BicycleTech',\n",
       " u'CreativeTech',\n",
       " u'TextileTech',\n",
       " u'ProfessionalAudiovisualTech',\n",
       " u'NewManufacturingEconomyTech',\n",
       " u'AlcoholTech',\n",
       " u'TobaccoTech',\n",
       " u'CulturalTech',\n",
       " u'InformationTech',\n",
       " u'ActivismTech',\n",
       " u'SustainableTech',\n",
       " u'HealthCareTech',\n",
       " u'SoftwareTech',\n",
       " u'ZuAudioTech',\n",
       " u'Space-BasedTech',\n",
       " u'RadioTech',\n",
       " u'EnergyTech',\n",
       " u'NavalStoresTech',\n",
       " u'HousingTech',\n",
       " u'Converters()Tech',\n",
       " u'EntertainmentTech',\n",
       " u'CommercialItemTransportAndDistributionTech',\n",
       " u'FoodTech',\n",
       " u'FurTradeTech',\n",
       " u'IndustrialAgricultureTech',\n",
       " u'MetalworkingTech',\n",
       " u'MiningTech',\n",
       " u'RealEstateTech',\n",
       " u'ServiceTech',\n",
       " u'ShippingTech',\n",
       " u'PlasticsTech',\n",
       " u'TradeUnionsByTech',\n",
       " u'CompaniesByTech',\n",
       " u'FishingTech',\n",
       " u'IndustriesByCountryTech',\n",
       " u'MediaTech',\n",
       " u'ToyTech',\n",
       " u'AutomotiveTech',\n",
       " u'ComputerTech',\n",
       " u'CosmeticsTech',\n",
       " u'ManufacturedGoodsTech',\n",
       " u'MilitaryTech',\n",
       " u'PharmaceuticalTech',\n",
       " u'PrivateSpaceflightTech',\n",
       " u'PulpAndPaperTech',\n",
       " u'RecyclingTech',\n",
       " u'BusinesspeopleByTech',\n",
       " u'DeathCareTech',\n",
       " u'IndustriesByCityTech',\n",
       " u'CommunitiesByTech',\n",
       " u'SpaceTech',\n",
       " u'ElectronicsTech',\n",
       " u'BankingTech',\n",
       " u'GarmentTech',\n",
       " u'TimberTech',\n",
       " u'TransportTech',\n",
       " u'WaterTech',\n",
       " u'StockMarketIndicesByTech',\n",
       " u'PetroleumTech',\n",
       " u'SteelTech']"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "map(techize, list_industries)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}