word2vec examples

word2vec.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from gensim.models import Word2Vec"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "fn = \"freebase-vectors-skipgram1000-en.bin\"\n",
    "model = Word2Vec.load_word2vec_format(fn, binary=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Expect 'trip' to be top hit, at 0.723, from Chris' blog"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('/en/summer_vacation', 0.35146796703338623),\n",
       " ('/en/assistant_manager', 0.34348905086517334),\n",
       " ('/en/annual_leave', 0.3420445919036865),\n",
       " ('/en/sick_leave', 0.3194432854652405),\n",
       " ('/en/hospital_beds', 0.31834304332733154),\n",
       " ('/en/bonus_track', 0.2938608229160309),\n",
       " ('/en/part_time', 0.28707462549209595),\n",
       " ('/en/day-tripper', 0.2864302694797516),\n",
       " ('/en/spring_break', 0.284801185131073),\n",
       " ('/en/staycation', 0.28439220786094666)]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.most_similar('/en/vacation')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'/en/trip' in model.vocab"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('/en/t_i_vs_t_i_p', 0.4389854669570923),\n",
       " ('/en/shoulder_lean', 0.4161432087421417),\n",
       " ('/en/what_you_know', 0.40737658739089966),\n",
       " ('/en/the_adventures_of_b_o_b', 0.4072108864784241),\n",
       " ('/en/the_inspiration_thug_motivation_102', 0.40640342235565186),\n",
       " ('/en/rubberband_man', 0.4014279246330261),\n",
       " ('/en/just_like_you', 0.4010814428329468),\n",
       " ('/en/the_red_light_district', 0.3974035680294037),\n",
       " ('/en/the_sound_of_revenge', 0.39560556411743164),\n",
       " ('/en/confessions', 0.38883811235427856)]"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.most_similar(['/en/woman', '/en/king'], ['/en/man'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('/en/king', 0.7387572526931763),\n",
       " ('/en/t_i_vs_t_i_p', 0.4389854669570923),\n",
       " ('/en/shoulder_lean', 0.41614317893981934),\n",
       " ('/en/what_you_know', 0.40737655758857727),\n",
       " ('/en/the_adventures_of_b_o_b', 0.4072108864784241),\n",
       " ('/en/the_inspiration_thug_motivation_102', 0.40640342235565186),\n",
       " ('/en/rubberband_man', 0.4014279246330261),\n",
       " ('/en/just_like_you', 0.40108147263526917),\n",
       " ('/en/the_red_light_district', 0.3974035680294037),\n",
       " ('/en/the_sound_of_revenge', 0.39560556411743164)]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.most_similar([model['/en/woman'] + model['/en/king'] - model['/en/man']])"
   ]
  }
 ],
 "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": "3.4.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}