show_w2v.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "from gensim.models import word2vec\n",
    "from gensim.models.keyedvectors import KeyedVectors\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "word_vectors = KeyedVectors.load_word2vec_format('./src/main/resources/text8.vec', binary=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# word_vectors = KeyedVectors.load_word2vec_format('./src/main/resources/enwiki9.txt.vec', binary=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('daughter', 0.5485425591468811),\n",
       " ('empress', 0.5350010991096497),\n",
       " ('prince', 0.5310357809066772),\n",
       " ('throne', 0.5217003226280212),\n",
       " ('son', 0.517214298248291),\n",
       " ('queen', 0.5135539770126343),\n",
       " ('minamoto', 0.506763756275177),\n",
       " ('viii', 0.5048807859420776),\n",
       " ('mary', 0.498077392578125),\n",
       " ('heir', 0.49674057960510254)]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "word_vectors.most_similar(positive=['woman', 'king'], negative=['man'], topn=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('daughter', 0.5485425591468811),\n",
       " ('empress', 0.5350010991096497),\n",
       " ('prince', 0.5310357809066772),\n",
       " ('throne', 0.5217003226280212),\n",
       " ('son', 0.517214298248291),\n",
       " ('queen', 0.5135539770126343),\n",
       " ('minamoto', 0.506763756275177),\n",
       " ('viii', 0.5048807859420776),\n",
       " ('mary', 0.498077392578125),\n",
       " ('heir', 0.49674057960510254)]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "word_vectors.most_similar(positive=['woman', 'king'], negative=['man'], topn=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('file', 0.67220139503479),\n",
       " ('compression', 0.6693793535232544),\n",
       " ('stored', 0.6680015921592712),\n",
       " ('files', 0.6367778778076172),\n",
       " ('routing', 0.6301351189613342),\n",
       " ('ip', 0.6274353265762329),\n",
       " ('format', 0.6236443519592285),\n",
       " ('packet', 0.6220601797103882),\n",
       " ('bits', 0.619074821472168),\n",
       " ('ipv', 0.6162351965904236)]"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "word_vectors.most_similar(positive=['data'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('elizabeth', 0.7907043695449829),\n",
       " ('prince', 0.6521976590156555),\n",
       " ('king', 0.636025607585907),\n",
       " ('princess', 0.6347065567970276),\n",
       " ('anne', 0.6185387969017029),\n",
       " ('crown', 0.6120067834854126),\n",
       " ('monarch', 0.6079266667366028),\n",
       " ('victoria', 0.6078702211380005),\n",
       " ('isabella', 0.6061561107635498),\n",
       " ('majesty', 0.6058646440505981)]"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "word_vectors.most_similar(positive=['queen'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('france', 0.9623157382011414),\n",
       " ('hirohito', 0.9062392115592957),\n",
       " ('imposition', 0.8845174312591553),\n",
       " ('mountbatten', 0.8710086941719055),\n",
       " ('feudal', 0.8627457022666931),\n",
       " ('formalised', 0.8624369502067566),\n",
       " ('discuss', 0.8617070913314819),\n",
       " ('revolutionary', 0.8540736436843872),\n",
       " ('overturn', 0.8520448207855225),\n",
       " ('carthaginian', 0.8508167266845703),\n",
       " ('sanction', 0.8474399447441101),\n",
       " ('germany', 0.8420551419258118),\n",
       " ('declared', 0.8412027359008789),\n",
       " ('italy', 0.8404319882392883),\n",
       " ('stalin', 0.837766170501709),\n",
       " ('tried', 0.83773273229599),\n",
       " ('napoleon', 0.8374594449996948),\n",
       " ('portugal', 0.8338634371757507),\n",
       " ('intervene', 0.8285016417503357),\n",
       " ('unification', 0.8258130550384521),\n",
       " ('informed', 0.8245867490768433),\n",
       " ('impetus', 0.8214332461357117),\n",
       " ('ambitions', 0.8208622336387634),\n",
       " ('miko', 0.8205797076225281),\n",
       " ('undertake', 0.8186885118484497),\n",
       " ('possessions', 0.8185335397720337),\n",
       " ('kimmei', 0.8183091878890991),\n",
       " ('warrant', 0.8182796239852905),\n",
       " ('nihonshoki', 0.8158888816833496),\n",
       " ('accession', 0.813630998134613)]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "word_vectors.most_similar_cosmul(positive=['paris', 'japan'], negative=['tokyo'], topn=30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('france', 0.5960692167282104),\n",
       " ('italy', 0.4693019390106201),\n",
       " ('germany', 0.4654536843299866),\n",
       " ('portugal', 0.4551469683647156),\n",
       " ('hirohito', 0.4550001323223114),\n",
       " ('napoleon', 0.4326018989086151),\n",
       " ('mountbatten', 0.42282170057296753),\n",
       " ('china', 0.41148364543914795),\n",
       " ('ambitions', 0.40866583585739136),\n",
       " ('revolutionary', 0.40459465980529785),\n",
       " ('kimmei', 0.40294909477233887),\n",
       " ('vienna', 0.40291261672973633),\n",
       " ('ferdinand', 0.3996574580669403),\n",
       " ('feudal', 0.39800015091896057),\n",
       " ('miko', 0.3969685137271881),\n",
       " ('korea', 0.3895190358161926),\n",
       " ('kojiki', 0.3892173171043396),\n",
       " ('declared', 0.3865616023540497),\n",
       " ('nihonshoki', 0.3864176273345947),\n",
       " ('kun', 0.38556843996047974),\n",
       " ('discuss', 0.3840706944465637),\n",
       " ('netherlands', 0.3836057186126709),\n",
       " ('possessions', 0.38359445333480835),\n",
       " ('unification', 0.38304412364959717),\n",
       " ('stalin', 0.37952858209609985),\n",
       " ('jing', 0.37798911333084106),\n",
       " ('isabella', 0.37629127502441406),\n",
       " ('britain', 0.37476783990859985),\n",
       " ('habsburgs', 0.37454771995544434),\n",
       " ('treaty', 0.37411004304885864)]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "word_vectors.most_similar(positive=['paris', 'japan'], negative=['tokyo'], topn=30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}