gensim-test.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Testing gensim\n",
    "See https://radimrehurek.com/gensim/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install --upgrade gensim"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import gensim.downloader as api"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "__testing_word2vec-matrix-synopsis (-1 records): [THIS IS ONLY FOR TESTING] Word vecrors of the movie matrix....\n",
      "conceptnet-numberbatch-17-06-300 (1917247 records): ConceptNet Numberbatch consists of state-of-the-art semantic vectors (also known...\n",
      "fasttext-wiki-news-subwords-300 (999999 records): 1 million word vectors trained on Wikipedia 2017, UMBC webbase corpus and statmt...\n",
      "glove-twitter-100 (1193514 records): Pre-trained vectors based on  2B tweets, 27B tokens, 1.2M vocab, uncased (https:...\n",
      "glove-twitter-200 (1193514 records): Pre-trained vectors based on 2B tweets, 27B tokens, 1.2M vocab, uncased (https:/...\n",
      "glove-twitter-25 (1193514 records): Pre-trained vectors based on 2B tweets, 27B tokens, 1.2M vocab, uncased (https:/...\n",
      "glove-twitter-50 (1193514 records): Pre-trained vectors based on 2B tweets, 27B tokens, 1.2M vocab, uncased (https:/...\n",
      "glove-wiki-gigaword-100 (400000 records): Pre-trained vectors based on Wikipedia 2014 + Gigaword 5.6B tokens, 400K vocab, ...\n",
      "glove-wiki-gigaword-200 (400000 records): Pre-trained vectors based on Wikipedia 2014 + Gigaword, 5.6B tokens, 400K vocab,...\n",
      "glove-wiki-gigaword-300 (400000 records): Pre-trained vectors based on Wikipedia 2014 + Gigaword, 5.6B tokens, 400K vocab,...\n",
      "glove-wiki-gigaword-50 (400000 records): Pre-trained vectors based on Wikipedia 2014 + Gigaword, 5.6B tokens, 400K vocab,...\n",
      "word2vec-google-news-300 (3000000 records): Pre-trained vectors trained on a part of the Google News dataset (about 100 bill...\n",
      "word2vec-ruscorpora-300 (184973 records): Word2vec Continuous Skipgram vectors trained on full Russian National Corpus (ab...\n"
     ]
    }
   ],
   "source": [
    "info = api.info()\n",
    "for model_name, model_data in sorted(info['models'].items()):\n",
    "    print('%s (%d records): %s' % (model_name, model_data.get('num_records', -1), model_data['description'][:80] + '...'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[==================================================] 100.0% 1662.8/1662.8MB downloaded\n"
     ]
    }
   ],
   "source": [
    "wv = api.load('word2vec-google-news-300')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('jews', 0.606805145740509),\n",
       " ('jewish', 0.5944611430168152),\n",
       " ('rahm', 0.5944365859031677),\n",
       " ('mhux', 0.5918845534324646),\n",
       " ('yid', 0.5769580006599426),\n",
       " ('jessie', 0.5755242109298706),\n",
       " ('yur', 0.5660163164138794),\n",
       " ('israel', 0.5639604330062866),\n",
       " ('gilbert', 0.5632734894752502),\n",
       " ('kol', 0.5615833401679993)]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.most_similar(\"jew\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('nazis', 0.6923775672912598),\n",
       " ('fascist', 0.657628059387207),\n",
       " ('Nazi', 0.6324446201324463),\n",
       " ('facist', 0.6276720762252808),\n",
       " ('fascists', 0.6110973358154297),\n",
       " ('Hilter', 0.5978641510009766),\n",
       " ('Hitler', 0.5964925289154053),\n",
       " ('hitler', 0.5891590714454651),\n",
       " ('NAZI', 0.5822753310203552),\n",
       " ('Fascist', 0.5806231498718262)]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.most_similar(\"nazi\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('Donald_Trump', 0.8103920221328735),\n",
       " ('impersonator_entertained', 0.5942257046699524),\n",
       " ('Ivanka_Trump', 0.5924582481384277),\n",
       " ('Ivanka', 0.5607207417488098),\n",
       " ('mogul_Donald_Trump', 0.5592453479766846),\n",
       " ('Trump_Tower', 0.548555314540863),\n",
       " ('Kepcher', 0.5468589067459106),\n",
       " ('billionaire_Donald_Trump', 0.5447269082069397),\n",
       " ('Trumpster', 0.5412818193435669),\n",
       " ('tycoon_Donald_Trump', 0.5383972525596619)]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.most_similar(\"Trump\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('Israeli', 0.8130459785461426),\n",
       " ('Israelis', 0.779090940952301),\n",
       " ('Palestinians', 0.7580956220626831),\n",
       " ('Palestinian', 0.7473597526550293),\n",
       " ('Netanyahu', 0.7082809805870056),\n",
       " ('Gaza', 0.7046299576759338),\n",
       " ('Hamas', 0.6912718415260315),\n",
       " ('Gaza_Strip', 0.6873201727867126),\n",
       " ('Palestinian_Authority', 0.6648115515708923),\n",
       " ('Prime_Minister_Binyamin_Netanyahu', 0.6640220880508423)]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.most_similar(\"Israel\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('Fuchs', 0.5700803995132446),\n",
       " ('Weil', 0.5526396632194519),\n",
       " ('weekly_newsmagazine_Der', 0.5345348119735718),\n",
       " ('Berman', 0.5249170660972595),\n",
       " ('Stein', 0.5195315480232239),\n",
       " ('Der_Spiegel', 0.5161873698234558),\n",
       " ('Nussbaum', 0.5158510208129883),\n",
       " ('Welt', 0.5128974914550781),\n",
       " ('Klein', 0.5109302401542664),\n",
       " ('Ulrich', 0.5099592208862305)]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.most_similar(\"Spiegel\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('magazine_Der_Spiegel', 0.7872042655944824),\n",
       " ('weekly_Der_Spiegel', 0.7623571753501892),\n",
       " ('Die_Zeit', 0.7383401393890381),\n",
       " ('Frankfurter_Allgemeine_Zeitung', 0.7346989512443542),\n",
       " ('Die_Welt', 0.7314777374267578),\n",
       " ('Der_Spiegel_magazine', 0.7263863682746887),\n",
       " ('Süddeutsche_Zeitung', 0.7214947938919067),\n",
       " ('Handelsblatt', 0.7061707377433777),\n",
       " ('Tagesspiegel_daily', 0.7048733830451965),\n",
       " ('Spiegel_Online', 0.7014873623847961)]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.most_similar(\"Der_Spiegel\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.26165980100631714"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.distance(\"Der_Spiegel\", \"Die_Zeit\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.2685222625732422"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.distance(\"Der_Spiegel\", \"Die_Welt\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.2785053253173828"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.distance(\"Der_Spiegel\", \"Süddeutsche_Zeitung\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('imperialism', 0.7371744513511658),\n",
       " ('colonialists', 0.7273486852645874),\n",
       " ('neo_colonialism', 0.7152635455131531),\n",
       " ('Colonialism', 0.6945492029190063),\n",
       " ('colonial_domination', 0.6901723146438599),\n",
       " ('colonialist', 0.6886431574821472),\n",
       " ('colonial', 0.6881863474845886),\n",
       " ('slavery_colonialism', 0.6797659397125244),\n",
       " ('colonial_rule', 0.6758955717086792),\n",
       " ('colonization', 0.6730928421020508)]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.most_similar(\"colonialism\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('colonial', 0.8822019100189209),\n",
       " ('oppression', 0.8728238940238953),\n",
       " ('colonialists', 0.8726308941841125),\n",
       " ('feminism', 0.8686202764511108),\n",
       " ('imperialism', 0.8678603768348694),\n",
       " ('patriarchy', 0.8666298389434814),\n",
       " ('colonization', 0.8656938076019287),\n",
       " ('colonial_rule', 0.86388099193573),\n",
       " ('slavery', 0.8588250875473022),\n",
       " ('subjugation', 0.8580973744392395)]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.most_similar_cosmul(positive=['colonialism', 'woman'], negative=['man'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('neo_colonialism', 0.8733060956001282),\n",
       " ('imperialism', 0.869311511516571),\n",
       " ('slavery_colonialism', 0.866578996181488),\n",
       " ('colonialists', 0.8548066020011902),\n",
       " ('colonialist', 0.8444662094116211),\n",
       " ('imperialist_domination', 0.8404235243797302),\n",
       " ('Colonialism', 0.8400565981864929),\n",
       " ('imperialism_colonialism', 0.8381094932556152),\n",
       " ('colonial_domination', 0.8354700207710266),\n",
       " ('colonialization', 0.8350632190704346)]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.most_similar_cosmul(positive=['colonialism', 'man'], negative=['woman'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('colonial_subjugation', 0.6939011216163635),\n",
       " ('colonized_peoples', 0.678598940372467),\n",
       " ('colonial_conquest', 0.6679588556289673),\n",
       " ('imperialist_domination', 0.6554943323135376),\n",
       " ('colonial_settler', 0.6515358686447144),\n",
       " ('slavery_colonialism', 0.6513102054595947),\n",
       " ('ethnocracy', 0.6486039161682129),\n",
       " ('colonial_domination', 0.6479084491729736),\n",
       " ('settler_colonial', 0.644547700881958),\n",
       " ('imperialism_colonialism', 0.6408925652503967)]"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.most_similar(\"settler_colonialism\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('colonial_subjugation', 0.8631111979484558),\n",
       " ('subjugation', 0.8551343679428101),\n",
       " ('colonized_peoples', 0.8545337915420532),\n",
       " ('colonial_conquest', 0.8533400893211365),\n",
       " ('colonial_settler', 0.8425801396369934),\n",
       " ('colonialism', 0.8342924118041992),\n",
       " ('patriarchy', 0.8340162634849548),\n",
       " ('colonial_domination', 0.8334349393844604),\n",
       " ('Zionist_expansionism', 0.8305999040603638),\n",
       " ('colonial_empires', 0.8288437724113464)]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.most_similar_cosmul(positive=['settler_colonialism', 'woman'], negative=['man'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('slavery_colonialism', 0.8518989086151123),\n",
       " ('settler_colonial', 0.8481582403182983),\n",
       " ('Hitlerism', 0.8431347012519836),\n",
       " ('imperialism_colonialism', 0.8403087258338928),\n",
       " ('Nazism_fascism', 0.8380133509635925),\n",
       " ('imperialist_domination', 0.8367621898651123),\n",
       " ('totalitarian_ideologies', 0.8347264528274536),\n",
       " ('neo_colonialists', 0.8338908553123474),\n",
       " ('predatory_capitalism', 0.8327714800834656),\n",
       " ('proletarian_internationalism', 0.8313636779785156)]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wv.most_similar_cosmul(positive=['settler_colonialism', 'man'], negative=['woman'])"
   ]
  }
 ],
 "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": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}