Word2Vec.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Workplace"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from preprocess_and_parse import *\n",
    "from wordcloud_function import * "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Parsing all text "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10258 text files detected!\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "directory = r\"C:\\nlp\\Science-related texts\"\n",
    "file_list = [file for file in os.listdir(directory) if file.endswith('.txt')]\n",
    "\n",
    "print( len(file_list), \"text files detected!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "all_text = []\n",
    "\n",
    "progress = [i * 1000 for i in range(1, 11) ] \n",
    "k = 0\n",
    "\n",
    "for i, text in enumerate(file_list):\n",
    "    \n",
    "    if(i > progress[k]): # display after every thoudsand files\n",
    "        print(\"File number\", i, \"parsed\")\n",
    "        k += 1\n",
    "        \n",
    "    try:\n",
    "        text = preprocess(os.path.join(directory, text))\n",
    "        text = text.split(\" \")[1:-1]  # filter blanks\n",
    "        text = [word.lower() for word in text]\n",
    "        text = \" \".join(text)\n",
    "        text = parse_text(text, show_pos = True)\n",
    "        text = lemmatizer(text, acceptPeriods= True)\n",
    "        text = removeStopWords(text)\n",
    "        all_text.extend(text)\n",
    "    \n",
    "    except Exception as e: \n",
    "        print(\"Error at file\", i, \":\", e)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Load parsed sentences"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true,
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "# all_sentences = \" \".join(all_text)\n",
    "# file = open(r\"C:\\nlp\\all_text_parsed.txt\", 'w', encoding= \"UTF-8\")\n",
    "# file.write(all_sentences)\n",
    "# file.close()\n",
    "\n",
    "file = open(r\"C:\\nlp\\all_text_parsed.txt\", 'r', encoding= \"UTF-8\")\n",
    "all_text = file.read()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import re\n",
    "\n",
    "class sentenceGen(object):\n",
    "    \"\"\"\n",
    "    Creates a sentence until it meets \"._.\" (period with period tag)\n",
    "    Upon meeting a period, concatenates the words collected so far and returns them as a sentence\n",
    "    \"\"\"\n",
    "\n",
    "    def __init__(self, text):\n",
    "        self.text= text.split(\" \")\n",
    "        \n",
    "    def __iter__(self):\n",
    "        sentence = []\n",
    "        \n",
    "        for word in self.text:\n",
    "            if word != \"._.\":\n",
    "                sentence.append(word)\n",
    "            elif word == \"._.\":\n",
    "                yield sentence\n",
    "                sentence = []"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2017-11-26 12:52:16,100 : INFO : collecting all words and their counts\n",
      "2017-11-26 12:52:16,106 : INFO : PROGRESS: at sentence #0, processed 0 words, keeping 0 word types\n",
      "2017-11-26 12:52:16,205 : INFO : PROGRESS: at sentence #10000, processed 115154 words, keeping 18571 word types\n",
      "2017-11-26 12:52:16,336 : INFO : PROGRESS: at sentence #20000, processed 238256 words, keeping 28858 word types\n",
      "2017-11-26 12:52:16,416 : INFO : PROGRESS: at sentence #30000, processed 363828 words, keeping 38341 word types\n",
      "2017-11-26 12:52:16,495 : INFO : PROGRESS: at sentence #40000, processed 478677 words, keeping 45611 word types\n",
      "2017-11-26 12:52:16,580 : INFO : PROGRESS: at sentence #50000, processed 594496 words, keeping 52776 word types\n",
      "2017-11-26 12:52:16,632 : INFO : PROGRESS: at sentence #60000, processed 717207 words, keeping 58952 word types\n",
      "2017-11-26 12:52:16,679 : INFO : PROGRESS: at sentence #70000, processed 822346 words, keeping 63418 word types\n",
      "2017-11-26 12:52:16,734 : INFO : PROGRESS: at sentence #80000, processed 934121 words, keeping 68576 word types\n",
      "2017-11-26 12:52:16,791 : INFO : PROGRESS: at sentence #90000, processed 1060102 words, keeping 72642 word types\n",
      "2017-11-26 12:52:16,850 : INFO : PROGRESS: at sentence #100000, processed 1181018 words, keeping 77034 word types\n",
      "2017-11-26 12:52:16,917 : INFO : PROGRESS: at sentence #110000, processed 1287930 words, keeping 81704 word types\n",
      "2017-11-26 12:52:16,979 : INFO : PROGRESS: at sentence #120000, processed 1412487 words, keeping 85704 word types\n",
      "2017-11-26 12:52:17,040 : INFO : PROGRESS: at sentence #130000, processed 1531961 words, keeping 89827 word types\n",
      "2017-11-26 12:52:17,098 : INFO : PROGRESS: at sentence #140000, processed 1650203 words, keeping 93592 word types\n",
      "2017-11-26 12:52:17,152 : INFO : PROGRESS: at sentence #150000, processed 1764158 words, keeping 97674 word types\n",
      "2017-11-26 12:52:17,211 : INFO : PROGRESS: at sentence #160000, processed 1883001 words, keeping 101649 word types\n",
      "2017-11-26 12:52:17,272 : INFO : PROGRESS: at sentence #170000, processed 2006349 words, keeping 104891 word types\n",
      "2017-11-26 12:52:17,329 : INFO : PROGRESS: at sentence #180000, processed 2119143 words, keeping 108920 word types\n",
      "2017-11-26 12:52:17,383 : INFO : PROGRESS: at sentence #190000, processed 2232884 words, keeping 112006 word types\n",
      "2017-11-26 12:52:17,443 : INFO : PROGRESS: at sentence #200000, processed 2351969 words, keeping 116008 word types\n",
      "2017-11-26 12:52:17,499 : INFO : PROGRESS: at sentence #210000, processed 2466319 words, keeping 119975 word types\n",
      "2017-11-26 12:52:17,559 : INFO : PROGRESS: at sentence #220000, processed 2578668 words, keeping 123238 word types\n",
      "2017-11-26 12:52:17,614 : INFO : PROGRESS: at sentence #230000, processed 2689117 words, keeping 126902 word types\n",
      "2017-11-26 12:52:17,662 : INFO : PROGRESS: at sentence #240000, processed 2786952 words, keeping 130144 word types\n",
      "2017-11-26 12:52:17,713 : INFO : PROGRESS: at sentence #250000, processed 2889547 words, keeping 133223 word types\n",
      "2017-11-26 12:52:17,764 : INFO : PROGRESS: at sentence #260000, processed 2994188 words, keeping 136511 word types\n",
      "2017-11-26 12:52:17,822 : INFO : PROGRESS: at sentence #270000, processed 3094653 words, keeping 139965 word types\n",
      "2017-11-26 12:52:17,880 : INFO : PROGRESS: at sentence #280000, processed 3194547 words, keeping 143391 word types\n",
      "2017-11-26 12:52:17,939 : INFO : PROGRESS: at sentence #290000, processed 3308578 words, keeping 149292 word types\n",
      "2017-11-26 12:52:17,986 : INFO : PROGRESS: at sentence #300000, processed 3398153 words, keeping 153044 word types\n",
      "2017-11-26 12:52:18,041 : INFO : PROGRESS: at sentence #310000, processed 3498349 words, keeping 156674 word types\n",
      "2017-11-26 12:52:18,093 : INFO : PROGRESS: at sentence #320000, processed 3611969 words, keeping 159302 word types\n",
      "2017-11-26 12:52:18,159 : INFO : PROGRESS: at sentence #330000, processed 3730529 words, keeping 162041 word types\n",
      "2017-11-26 12:52:18,220 : INFO : PROGRESS: at sentence #340000, processed 3848257 words, keeping 165055 word types\n",
      "2017-11-26 12:52:18,277 : INFO : PROGRESS: at sentence #350000, processed 3955482 words, keeping 168396 word types\n",
      "2017-11-26 12:52:18,341 : INFO : PROGRESS: at sentence #360000, processed 4079238 words, keeping 171073 word types\n",
      "2017-11-26 12:52:18,399 : INFO : PROGRESS: at sentence #370000, processed 4197068 words, keeping 173872 word types\n",
      "2017-11-26 12:52:18,467 : INFO : PROGRESS: at sentence #380000, processed 4312196 words, keeping 177507 word types\n",
      "2017-11-26 12:52:18,523 : INFO : PROGRESS: at sentence #390000, processed 4428683 words, keeping 179937 word types\n",
      "2017-11-26 12:52:18,597 : INFO : PROGRESS: at sentence #400000, processed 4540879 words, keeping 182925 word types\n",
      "2017-11-26 12:52:18,657 : INFO : PROGRESS: at sentence #410000, processed 4659710 words, keeping 185403 word types\n",
      "2017-11-26 12:52:18,715 : INFO : PROGRESS: at sentence #420000, processed 4766997 words, keeping 188901 word types\n",
      "2017-11-26 12:52:18,775 : INFO : PROGRESS: at sentence #430000, processed 4886356 words, keeping 191393 word types\n",
      "2017-11-26 12:52:18,832 : INFO : PROGRESS: at sentence #440000, processed 4996060 words, keeping 193935 word types\n",
      "2017-11-26 12:52:18,897 : INFO : PROGRESS: at sentence #450000, processed 5109290 words, keeping 196235 word types\n",
      "2017-11-26 12:52:18,975 : INFO : PROGRESS: at sentence #460000, processed 5216850 words, keeping 199925 word types\n",
      "2017-11-26 12:52:19,057 : INFO : PROGRESS: at sentence #470000, processed 5338919 words, keeping 202032 word types\n",
      "2017-11-26 12:52:19,121 : INFO : PROGRESS: at sentence #480000, processed 5461530 words, keeping 204643 word types\n",
      "2017-11-26 12:52:19,175 : INFO : PROGRESS: at sentence #490000, processed 5571407 words, keeping 207364 word types\n",
      "2017-11-26 12:52:19,242 : INFO : PROGRESS: at sentence #500000, processed 5696589 words, keeping 209602 word types\n",
      "2017-11-26 12:52:19,305 : INFO : PROGRESS: at sentence #510000, processed 5813884 words, keeping 212513 word types\n",
      "2017-11-26 12:52:19,365 : INFO : PROGRESS: at sentence #520000, processed 5930119 words, keeping 214675 word types\n",
      "2017-11-26 12:52:19,425 : INFO : PROGRESS: at sentence #530000, processed 6045492 words, keeping 217052 word types\n",
      "2017-11-26 12:52:19,485 : INFO : PROGRESS: at sentence #540000, processed 6167660 words, keeping 219372 word types\n",
      "2017-11-26 12:52:19,547 : INFO : PROGRESS: at sentence #550000, processed 6290779 words, keeping 221835 word types\n",
      "2017-11-26 12:52:19,612 : INFO : PROGRESS: at sentence #560000, processed 6411075 words, keeping 224104 word types\n",
      "2017-11-26 12:52:19,671 : INFO : PROGRESS: at sentence #570000, processed 6526818 words, keeping 226172 word types\n",
      "2017-11-26 12:52:19,735 : INFO : PROGRESS: at sentence #580000, processed 6647043 words, keeping 228375 word types\n",
      "2017-11-26 12:52:19,796 : INFO : PROGRESS: at sentence #590000, processed 6765325 words, keeping 230524 word types\n",
      "2017-11-26 12:52:19,859 : INFO : PROGRESS: at sentence #600000, processed 6886023 words, keeping 232793 word types\n",
      "2017-11-26 12:52:19,936 : INFO : PROGRESS: at sentence #610000, processed 7006426 words, keeping 234813 word types\n",
      "2017-11-26 12:52:20,004 : INFO : PROGRESS: at sentence #620000, processed 7118381 words, keeping 237923 word types\n",
      "2017-11-26 12:52:20,071 : INFO : PROGRESS: at sentence #630000, processed 7231157 words, keeping 241451 word types\n",
      "2017-11-26 12:52:20,122 : INFO : PROGRESS: at sentence #640000, processed 7328873 words, keeping 244903 word types\n",
      "2017-11-26 12:52:20,188 : INFO : PROGRESS: at sentence #650000, processed 7442092 words, keeping 248210 word types\n",
      "2017-11-26 12:52:20,240 : INFO : PROGRESS: at sentence #660000, processed 7542985 words, keeping 250782 word types\n",
      "2017-11-26 12:52:20,300 : INFO : PROGRESS: at sentence #670000, processed 7644724 words, keeping 254640 word types\n",
      "2017-11-26 12:52:20,361 : INFO : PROGRESS: at sentence #680000, processed 7757855 words, keeping 257955 word types\n",
      "2017-11-26 12:52:20,416 : INFO : PROGRESS: at sentence #690000, processed 7858017 words, keeping 260224 word types\n",
      "2017-11-26 12:52:20,478 : INFO : PROGRESS: at sentence #700000, processed 7965982 words, keeping 264020 word types\n",
      "2017-11-26 12:52:20,541 : INFO : PROGRESS: at sentence #710000, processed 8078418 words, keeping 267571 word types\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2017-11-26 12:52:20,603 : INFO : PROGRESS: at sentence #720000, processed 8195666 words, keeping 270318 word types\n",
      "2017-11-26 12:52:20,659 : INFO : PROGRESS: at sentence #730000, processed 8293758 words, keeping 273265 word types\n",
      "2017-11-26 12:52:20,717 : INFO : PROGRESS: at sentence #740000, processed 8399598 words, keeping 276456 word types\n",
      "2017-11-26 12:52:20,771 : INFO : PROGRESS: at sentence #750000, processed 8499688 words, keeping 279354 word types\n",
      "2017-11-26 12:52:20,827 : INFO : PROGRESS: at sentence #760000, processed 8600918 words, keeping 283112 word types\n",
      "2017-11-26 12:52:20,891 : INFO : PROGRESS: at sentence #770000, processed 8699196 words, keeping 285786 word types\n",
      "2017-11-26 12:52:20,957 : INFO : PROGRESS: at sentence #780000, processed 8803717 words, keeping 288654 word types\n",
      "2017-11-26 12:52:21,011 : INFO : PROGRESS: at sentence #790000, processed 8900909 words, keeping 291118 word types\n",
      "2017-11-26 12:52:21,070 : INFO : PROGRESS: at sentence #800000, processed 9005042 words, keeping 294574 word types\n",
      "2017-11-26 12:52:21,129 : INFO : PROGRESS: at sentence #810000, processed 9108998 words, keeping 297733 word types\n",
      "2017-11-26 12:52:21,185 : INFO : PROGRESS: at sentence #820000, processed 9209164 words, keeping 300263 word types\n",
      "2017-11-26 12:52:21,243 : INFO : PROGRESS: at sentence #830000, processed 9312731 words, keeping 303892 word types\n",
      "2017-11-26 12:52:21,304 : INFO : PROGRESS: at sentence #840000, processed 9419643 words, keeping 306779 word types\n",
      "2017-11-26 12:52:21,362 : INFO : PROGRESS: at sentence #850000, processed 9523683 words, keeping 309876 word types\n",
      "2017-11-26 12:52:21,430 : INFO : PROGRESS: at sentence #860000, processed 9631692 words, keeping 313346 word types\n",
      "2017-11-26 12:52:21,490 : INFO : PROGRESS: at sentence #870000, processed 9730892 words, keeping 315836 word types\n",
      "2017-11-26 12:52:21,549 : INFO : PROGRESS: at sentence #880000, processed 9829566 words, keeping 318037 word types\n",
      "2017-11-26 12:52:21,604 : INFO : PROGRESS: at sentence #890000, processed 9928516 words, keeping 320313 word types\n",
      "2017-11-26 12:52:21,665 : INFO : PROGRESS: at sentence #900000, processed 10032730 words, keeping 323435 word types\n",
      "2017-11-26 12:52:21,722 : INFO : PROGRESS: at sentence #910000, processed 10135705 words, keeping 326299 word types\n",
      "2017-11-26 12:52:21,780 : INFO : PROGRESS: at sentence #920000, processed 10238669 words, keeping 328731 word types\n",
      "2017-11-26 12:52:21,838 : INFO : PROGRESS: at sentence #930000, processed 10340779 words, keeping 331463 word types\n",
      "2017-11-26 12:52:21,906 : INFO : PROGRESS: at sentence #940000, processed 10457737 words, keeping 334181 word types\n",
      "2017-11-26 12:52:21,975 : INFO : PROGRESS: at sentence #950000, processed 10558727 words, keeping 336691 word types\n",
      "2017-11-26 12:52:22,045 : INFO : PROGRESS: at sentence #960000, processed 10662390 words, keeping 339560 word types\n",
      "2017-11-26 12:52:22,107 : INFO : PROGRESS: at sentence #970000, processed 10756072 words, keeping 341759 word types\n",
      "2017-11-26 12:52:22,170 : INFO : PROGRESS: at sentence #980000, processed 10860390 words, keeping 344393 word types\n",
      "2017-11-26 12:52:22,231 : INFO : PROGRESS: at sentence #990000, processed 10969867 words, keeping 346860 word types\n",
      "2017-11-26 12:52:22,292 : INFO : PROGRESS: at sentence #1000000, processed 11073543 words, keeping 349437 word types\n",
      "2017-11-26 12:52:22,371 : INFO : PROGRESS: at sentence #1010000, processed 11175670 words, keeping 352118 word types\n",
      "2017-11-26 12:52:22,435 : INFO : PROGRESS: at sentence #1020000, processed 11282658 words, keeping 354591 word types\n",
      "2017-11-26 12:52:22,494 : INFO : PROGRESS: at sentence #1030000, processed 11372723 words, keeping 355884 word types\n",
      "2017-11-26 12:52:22,561 : INFO : PROGRESS: at sentence #1040000, processed 11483231 words, keeping 357701 word types\n",
      "2017-11-26 12:52:22,616 : INFO : PROGRESS: at sentence #1050000, processed 11581900 words, keeping 359515 word types\n",
      "2017-11-26 12:52:22,678 : INFO : PROGRESS: at sentence #1060000, processed 11687160 words, keeping 361194 word types\n",
      "2017-11-26 12:52:22,738 : INFO : PROGRESS: at sentence #1070000, processed 11797246 words, keeping 362724 word types\n",
      "2017-11-26 12:52:22,796 : INFO : PROGRESS: at sentence #1080000, processed 11908445 words, keeping 364731 word types\n",
      "2017-11-26 12:52:22,851 : INFO : PROGRESS: at sentence #1090000, processed 12005466 words, keeping 366719 word types\n",
      "2017-11-26 12:52:22,910 : INFO : PROGRESS: at sentence #1100000, processed 12106344 words, keeping 368239 word types\n",
      "2017-11-26 12:52:22,972 : INFO : PROGRESS: at sentence #1110000, processed 12212248 words, keeping 370786 word types\n",
      "2017-11-26 12:52:23,025 : INFO : PROGRESS: at sentence #1120000, processed 12304071 words, keeping 372754 word types\n",
      "2017-11-26 12:52:23,084 : INFO : PROGRESS: at sentence #1130000, processed 12410970 words, keeping 375140 word types\n",
      "2017-11-26 12:52:23,148 : INFO : PROGRESS: at sentence #1140000, processed 12518274 words, keeping 378162 word types\n",
      "2017-11-26 12:52:23,215 : INFO : PROGRESS: at sentence #1150000, processed 12617027 words, keeping 380303 word types\n",
      "2017-11-26 12:52:23,270 : INFO : PROGRESS: at sentence #1160000, processed 12721800 words, keeping 380303 word types\n",
      "2017-11-26 12:52:23,310 : INFO : collected 380303 word types from a corpus of 12791903 raw words and 1166675 sentences\n",
      "2017-11-26 12:52:23,311 : INFO : Loading a fresh vocabulary\n",
      "2017-11-26 12:52:24,101 : INFO : min_count=5 retains 89008 unique words (23% of original 380303, drops 291295)\n",
      "2017-11-26 12:52:24,103 : INFO : min_count=5 leaves 12366345 word corpus (96% of original 12791903, drops 425558)\n",
      "2017-11-26 12:52:24,415 : INFO : deleting the raw counts dictionary of 380303 items\n",
      "2017-11-26 12:52:24,425 : INFO : sample=0.001 downsamples 5 most-common words\n",
      "2017-11-26 12:52:24,427 : INFO : downsampling leaves estimated 12353392 word corpus (99.9% of prior 12366345)\n",
      "2017-11-26 12:52:24,429 : INFO : estimated required memory for 89008 words and 100 dimensions: 115710400 bytes\n",
      "2017-11-26 12:52:24,783 : INFO : resetting layer weights\n",
      "2017-11-26 12:52:25,941 : INFO : training model with 3 workers on 89008 vocabulary and 100 features, using sg=0 hs=0 sample=0.001 negative=5 window=5\n",
      "2017-11-26 12:52:27,044 : INFO : PROGRESS: at 0.88% examples, 540639 words/s, in_qsize 4, out_qsize 2\n",
      "2017-11-26 12:52:28,060 : INFO : PROGRESS: at 1.94% examples, 611802 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:52:29,069 : INFO : PROGRESS: at 2.96% examples, 634964 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:52:30,071 : INFO : PROGRESS: at 3.80% examples, 612076 words/s, in_qsize 5, out_qsize 1\n",
      "2017-11-26 12:52:31,079 : INFO : PROGRESS: at 5.00% examples, 627927 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:52:32,094 : INFO : PROGRESS: at 5.87% examples, 610543 words/s, in_qsize 5, out_qsize 1\n",
      "2017-11-26 12:52:33,095 : INFO : PROGRESS: at 6.94% examples, 622574 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:52:34,102 : INFO : PROGRESS: at 7.81% examples, 613178 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:52:35,106 : INFO : PROGRESS: at 8.69% examples, 610555 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:52:36,113 : INFO : PROGRESS: at 9.66% examples, 615022 words/s, in_qsize 5, out_qsize 1\n",
      "2017-11-26 12:52:37,113 : INFO : PROGRESS: at 10.50% examples, 610388 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:52:38,115 : INFO : PROGRESS: at 11.62% examples, 615466 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:52:39,115 : INFO : PROGRESS: at 12.50% examples, 608855 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:52:40,122 : INFO : PROGRESS: at 13.70% examples, 613584 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:52:41,145 : INFO : PROGRESS: at 14.62% examples, 607537 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:52:42,157 : INFO : PROGRESS: at 15.80% examples, 611076 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:52:43,164 : INFO : PROGRESS: at 16.73% examples, 607104 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:52:44,184 : INFO : PROGRESS: at 17.88% examples, 609583 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:52:45,245 : INFO : PROGRESS: at 18.86% examples, 606152 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:52:46,251 : INFO : PROGRESS: at 20.01% examples, 609041 words/s, in_qsize 6, out_qsize 1\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2017-11-26 12:52:47,253 : INFO : PROGRESS: at 21.06% examples, 613546 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:52:48,255 : INFO : PROGRESS: at 21.93% examples, 611193 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:52:49,256 : INFO : PROGRESS: at 22.95% examples, 614532 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:52:50,264 : INFO : PROGRESS: at 23.78% examples, 611335 words/s, in_qsize 4, out_qsize 1\n",
      "2017-11-26 12:52:51,267 : INFO : PROGRESS: at 24.94% examples, 613629 words/s, in_qsize 5, out_qsize 1\n",
      "2017-11-26 12:52:52,277 : INFO : PROGRESS: at 25.85% examples, 611280 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:52:53,287 : INFO : PROGRESS: at 26.92% examples, 614203 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:52:54,291 : INFO : PROGRESS: at 28.01% examples, 617020 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:52:55,299 : INFO : PROGRESS: at 28.84% examples, 614979 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:52:56,300 : INFO : PROGRESS: at 29.87% examples, 617412 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:52:57,300 : INFO : PROGRESS: at 30.68% examples, 615036 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:52:58,314 : INFO : PROGRESS: at 31.83% examples, 616868 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:52:59,325 : INFO : PROGRESS: at 32.72% examples, 614280 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:00,340 : INFO : PROGRESS: at 33.91% examples, 615639 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:01,357 : INFO : PROGRESS: at 34.85% examples, 613374 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:02,364 : INFO : PROGRESS: at 36.02% examples, 614868 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:03,415 : INFO : PROGRESS: at 37.00% examples, 612983 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:04,421 : INFO : PROGRESS: at 38.14% examples, 613997 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:05,599 : INFO : PROGRESS: at 39.19% examples, 611109 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:06,608 : INFO : PROGRESS: at 40.22% examples, 611246 words/s, in_qsize 6, out_qsize 1\n",
      "2017-11-26 12:53:07,619 : INFO : PROGRESS: at 41.30% examples, 613584 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:08,623 : INFO : PROGRESS: at 42.11% examples, 611895 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:09,634 : INFO : PROGRESS: at 43.15% examples, 613721 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:10,635 : INFO : PROGRESS: at 44.03% examples, 612295 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:11,651 : INFO : PROGRESS: at 45.25% examples, 613937 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:12,651 : INFO : PROGRESS: at 46.34% examples, 615943 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:13,659 : INFO : PROGRESS: at 47.19% examples, 614476 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:14,681 : INFO : PROGRESS: at 48.27% examples, 615898 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:15,689 : INFO : PROGRESS: at 49.11% examples, 614718 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:16,702 : INFO : PROGRESS: at 50.14% examples, 616228 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:17,712 : INFO : PROGRESS: at 51.01% examples, 614835 words/s, in_qsize 6, out_qsize 1\n",
      "2017-11-26 12:53:18,721 : INFO : PROGRESS: at 52.13% examples, 615833 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:19,766 : INFO : PROGRESS: at 53.11% examples, 614564 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:20,768 : INFO : PROGRESS: at 54.29% examples, 615568 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:21,884 : INFO : PROGRESS: at 55.33% examples, 613926 words/s, in_qsize 5, out_qsize 1\n",
      "2017-11-26 12:53:22,888 : INFO : PROGRESS: at 56.47% examples, 614893 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:24,035 : INFO : PROGRESS: at 57.55% examples, 613480 words/s, in_qsize 5, out_qsize 1\n",
      "2017-11-26 12:53:25,039 : INFO : PROGRESS: at 58.70% examples, 614532 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:26,210 : INFO : PROGRESS: at 59.83% examples, 613320 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:27,225 : INFO : PROGRESS: at 60.90% examples, 614725 words/s, in_qsize 6, out_qsize 1\n",
      "2017-11-26 12:53:28,228 : INFO : PROGRESS: at 61.96% examples, 616045 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:29,255 : INFO : PROGRESS: at 62.78% examples, 614790 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:30,257 : INFO : PROGRESS: at 63.83% examples, 615759 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:31,292 : INFO : PROGRESS: at 64.81% examples, 614671 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:32,304 : INFO : PROGRESS: at 65.92% examples, 615573 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:33,445 : INFO : PROGRESS: at 66.93% examples, 614925 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:34,453 : INFO : PROGRESS: at 68.00% examples, 615899 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:35,462 : INFO : PROGRESS: at 68.94% examples, 616027 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:36,475 : INFO : PROGRESS: at 69.72% examples, 614617 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:37,480 : INFO : PROGRESS: at 70.74% examples, 615472 words/s, in_qsize 5, out_qsize 1\n",
      "2017-11-26 12:53:38,493 : INFO : PROGRESS: at 71.66% examples, 614428 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:39,497 : INFO : PROGRESS: at 72.80% examples, 615312 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:40,500 : INFO : PROGRESS: at 73.77% examples, 614357 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:41,522 : INFO : PROGRESS: at 74.93% examples, 614923 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:42,535 : INFO : PROGRESS: at 75.89% examples, 613938 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:43,538 : INFO : PROGRESS: at 77.03% examples, 614650 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:44,604 : INFO : PROGRESS: at 78.03% examples, 613554 words/s, in_qsize 5, out_qsize 1\n",
      "2017-11-26 12:53:45,604 : INFO : PROGRESS: at 79.16% examples, 614219 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:46,608 : INFO : PROGRESS: at 80.28% examples, 614999 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:47,625 : INFO : PROGRESS: at 81.11% examples, 614215 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:48,633 : INFO : PROGRESS: at 82.18% examples, 615177 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:49,647 : INFO : PROGRESS: at 83.03% examples, 614565 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:50,650 : INFO : PROGRESS: at 84.12% examples, 615380 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:51,653 : INFO : PROGRESS: at 85.11% examples, 614752 words/s, in_qsize 5, out_qsize 0\n",
      "2017-11-26 12:53:52,668 : INFO : PROGRESS: at 86.19% examples, 615477 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:53,683 : INFO : PROGRESS: at 87.27% examples, 616292 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:54,684 : INFO : PROGRESS: at 88.11% examples, 615551 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:55,698 : INFO : PROGRESS: at 89.16% examples, 616273 words/s, in_qsize 6, out_qsize 1\n",
      "2017-11-26 12:53:56,706 : INFO : PROGRESS: at 89.97% examples, 615637 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:53:57,715 : INFO : PROGRESS: at 91.06% examples, 616449 words/s, in_qsize 4, out_qsize 1\n",
      "2017-11-26 12:53:58,721 : INFO : PROGRESS: at 91.97% examples, 615572 words/s, in_qsize 5, out_qsize 1\n",
      "2017-11-26 12:53:59,753 : INFO : PROGRESS: at 93.13% examples, 616050 words/s, in_qsize 6, out_qsize 1\n",
      "2017-11-26 12:54:00,786 : INFO : PROGRESS: at 94.11% examples, 615198 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:54:01,790 : INFO : PROGRESS: at 95.27% examples, 615765 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:54:02,915 : INFO : PROGRESS: at 96.32% examples, 614946 words/s, in_qsize 6, out_qsize 1\n",
      "2017-11-26 12:54:03,916 : INFO : PROGRESS: at 97.46% examples, 615413 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:54:05,132 : INFO : PROGRESS: at 98.53% examples, 614220 words/s, in_qsize 6, out_qsize 0\n",
      "2017-11-26 12:54:06,148 : INFO : PROGRESS: at 99.68% examples, 614514 words/s, in_qsize 5, out_qsize 1\n",
      "2017-11-26 12:54:06,396 : INFO : worker thread finished; awaiting finish of 2 more threads\n",
      "2017-11-26 12:54:06,404 : INFO : worker thread finished; awaiting finish of 1 more threads\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2017-11-26 12:54:06,410 : INFO : worker thread finished; awaiting finish of 0 more threads\n",
      "2017-11-26 12:54:06,411 : INFO : training on 63959515 raw words (61767148 effective words) took 100.5s, 614860 effective words/s\n"
     ]
    }
   ],
   "source": [
    "import gensim\n",
    "import os\n",
    "import logging\n",
    "\n",
    "# Log settings\n",
    "logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)\n",
    "\n",
    "\n",
    "# a memory - friendly iterator\n",
    "# sentences = MySentences('D:\\\\coca and GloWbE\\\\coca\\\\texts\\\\text_newspaper_lsp')\n",
    "model = gensim.models.Word2Vec(sentenceGen(all_text))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2017-11-26 13:13:53,546 : INFO : saving Word2Vec object under C:\\nlp\\word2vec_1.bin, separately None\n",
      "2017-11-26 13:13:53,549 : INFO : not storing attribute syn0norm\n",
      "2017-11-26 13:13:53,551 : INFO : not storing attribute cum_table\n",
      "2017-11-26 13:13:55,714 : INFO : saved C:\\nlp\\word2vec_1.bin\n"
     ]
    }
   ],
   "source": [
    "model.save(r\"C:\\nlp\\word2vec_1.bin\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'section_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d8d0>,\n",
       " 'museum_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aa9e8>,\n",
       " 'centenary_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80aaa90>,\n",
       " 'birth_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aab38>,\n",
       " 'margaret_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aa898>,\n",
       " 'mead_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aa860>,\n",
       " 'remember_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aaa58>,\n",
       " 'world_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aa9b0>,\n",
       " 'influential_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80aab00>,\n",
       " 'anthropologist_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aa828>,\n",
       " 'arrive_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80aaac8>,\n",
       " 'american_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80aa8d0>,\n",
       " 'natural_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80aab70>,\n",
       " 'history_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aaba8>,\n",
       " 'complete_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aabe0>,\n",
       " 'first_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80aac18>,\n",
       " 'significant_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80aac50>,\n",
       " 'ethnographic_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80aac88>,\n",
       " 'research_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aacc0>,\n",
       " 'samoa_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aacf8>,\n",
       " 'appoint_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aad30>,\n",
       " 'assistant_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80aad68>,\n",
       " 'curator_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aada0>,\n",
       " 'department_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aadd8>,\n",
       " 'anthropology_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aae10>,\n",
       " 'year_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80aae48>,\n",
       " 'old_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80aae80>,\n",
       " 'give_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aaeb8>,\n",
       " 'temporary_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80aaef0>,\n",
       " 'office_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aaf28>,\n",
       " 'attic_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aaf60>,\n",
       " 'room_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aaf98>,\n",
       " 'west_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80aafd0>,\n",
       " 'tower_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb048>,\n",
       " 'out-of-the-way_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb080>,\n",
       " 'view_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb0b8>,\n",
       " 'rooftop_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb0f0>,\n",
       " 'new_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb128>,\n",
       " 'york_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb160>,\n",
       " 'city_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb198>,\n",
       " 'stairway_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb1d0>,\n",
       " 'ideal_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb208>,\n",
       " 'say_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb240>,\n",
       " 'creep_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb278>,\n",
       " 'stairway_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb2b0>,\n",
       " 'someone_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb2e8>,\n",
       " 'avoid_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb320>,\n",
       " 'elderly_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb358>,\n",
       " 'labor_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb390>,\n",
       " 'stay_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb3c8>,\n",
       " 'rest_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb400>,\n",
       " 'life_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb438>,\n",
       " 'arrive_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb470>,\n",
       " 'interview_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb4a8>,\n",
       " 'position_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb4e0>,\n",
       " 'assistant_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb518>,\n",
       " 'undergraduate_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb550>,\n",
       " 'major_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb588>,\n",
       " 'barnard_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb5c0>,\n",
       " 'college_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb5f8>,\n",
       " 'felt_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb630>,\n",
       " 'find_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb668>,\n",
       " 'way_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb6a0>,\n",
       " 'maze_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb6d8>,\n",
       " 'inner_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb710>,\n",
       " 'sanctum_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb748>,\n",
       " 'test_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb780>,\n",
       " \"'d_VBD\": <gensim.models.keyedvectors.Vocab at 0x1bcc80eb7b8>,\n",
       " 'devise_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb7f0>,\n",
       " 'determine_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb828>,\n",
       " 'suitability_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb860>,\n",
       " 'grow_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb898>,\n",
       " 'fond_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb8d0>,\n",
       " 'remote_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb908>,\n",
       " 'location_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb940>,\n",
       " 'bird_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb978>,\n",
       " 'eye_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb9b0>,\n",
       " 'view_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eb9e8>,\n",
       " 'busy_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eba20>,\n",
       " 'street_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80eba58>,\n",
       " 'symbolize_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eba90>,\n",
       " 'relationship_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebac8>,\n",
       " 'part_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebb00>,\n",
       " 'set_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebb38>,\n",
       " 'overall_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebb70>,\n",
       " 'structure_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebba8>,\n",
       " 'institution_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebbe0>,\n",
       " 'discipline_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebc18>,\n",
       " 'repository_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebc50>,\n",
       " 'artifact_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebc88>,\n",
       " 'engage_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebcc0>,\n",
       " 'solution_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebcf8>,\n",
       " 'challenge_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebd30>,\n",
       " 'face_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebd68>,\n",
       " 'society_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebda0>,\n",
       " 'course_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebdd8>,\n",
       " 'association_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebe10>,\n",
       " 'scientist_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebe48>,\n",
       " 'teacher_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebe80>,\n",
       " 'author_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebeb8>,\n",
       " 'social_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebef0>,\n",
       " 'activist_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebf28>,\n",
       " 'medium_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebf60>,\n",
       " 'celebrity_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebf98>,\n",
       " 'success_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ebfd0>,\n",
       " 'book_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee048>,\n",
       " 'come_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee080>,\n",
       " 'age_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee0b8>,\n",
       " 'publish_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee0f0>,\n",
       " 'thrust_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee128>,\n",
       " 'spotlight_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee160>,\n",
       " 'comparison_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee198>,\n",
       " 'adolescence_NN': <gensim.models.keyedvectors.Vocab at 0x1bcaea5e9b0>,\n",
       " 'south_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcafa60c18>,\n",
       " 'sea_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcb6243668>,\n",
       " 'time_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b94128>,\n",
       " 'public_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b94400>,\n",
       " 'concern_VBN': <gensim.models.keyedvectors.Vocab at 0x1bc80b94278>,\n",
       " 'transformation_NNS': <gensim.models.keyedvectors.Vocab at 0x1bc80b94080>,\n",
       " 'jazz_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b94208>,\n",
       " 'youth_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b940b8>,\n",
       " 'early_JJ': <gensim.models.keyedvectors.Vocab at 0x1bc80b94198>,\n",
       " 'television_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b94240>,\n",
       " 'become_VBD': <gensim.models.keyedvectors.Vocab at 0x1bc80b940f0>,\n",
       " 'widespread_JJ': <gensim.models.keyedvectors.Vocab at 0x1bc80b94160>,\n",
       " 'appear_VBD': <gensim.models.keyedvectors.Vocab at 0x1bc80b94048>,\n",
       " 'cbs_NNS': <gensim.models.keyedvectors.Vocab at 0x1bc80b942e8>,\n",
       " 'program_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b941d0>,\n",
       " 'adventure_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b942b0>,\n",
       " 'series_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d588>,\n",
       " 'produce_VBD': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d240>,\n",
       " 'live_JJ': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d550>,\n",
       " 'talk_VB': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d0f0>,\n",
       " 'trance_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d1d0>,\n",
       " 'balinese_JJ': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d438>,\n",
       " 'impact_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d710>,\n",
       " 'war_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d7b8>,\n",
       " 'change_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d780>,\n",
       " 'society_NNS': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d208>,\n",
       " 'guinea_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d748>,\n",
       " 'flair_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d630>,\n",
       " 'write_VBG': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d470>,\n",
       " 'public_JJ': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d4e0>,\n",
       " 'speaking_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d4a8>,\n",
       " 'combine_VBN': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d320>,\n",
       " 'belief_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d358>,\n",
       " 'anthropologist_NNS': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d400>,\n",
       " 'museum_NNS': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d390>,\n",
       " 'address_VB': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d3c8>,\n",
       " 'contemporary_JJ': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d5c0>,\n",
       " 'issue_NNS': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d278>,\n",
       " 'lead_VBD': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d198>,\n",
       " 'expert_NN': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d128>,\n",
       " 'human_JJ': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d0b8>,\n",
       " 'unite_VBN': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d160>,\n",
       " 'nation_NNS': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d2e8>,\n",
       " 'conference_NNS': <gensim.models.keyedvectors.Vocab at 0x1bc80b9d518>,\n",
       " 'international_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcb63dbc50>,\n",
       " 'forum_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcb63dbf60>,\n",
       " 'consultant_NN': <gensim.models.keyedvectors.Vocab at 0x1bcb63dbf98>,\n",
       " 'institution_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcb63dbc18>,\n",
       " 'organization_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcb63dbd68>,\n",
       " 'discuss_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcb63dbf28>,\n",
       " 'role_NN': <gensim.models.keyedvectors.Vocab at 0x1bcb63dbc88>,\n",
       " 'change_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcb63dbfd0>,\n",
       " 'nature_NN': <gensim.models.keyedvectors.Vocab at 0x1bcb63dbda0>,\n",
       " 'family_NN': <gensim.models.keyedvectors.Vocab at 0x1bcb63dbef0>,\n",
       " 'racial_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcb63dbe48>,\n",
       " 'inequality_NN': <gensim.models.keyedvectors.Vocab at 0x1bcb63dbeb8>,\n",
       " 'peaceful_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee1d0>,\n",
       " 'alternative_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee208>,\n",
       " 'population_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee240>,\n",
       " 'growth_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee278>,\n",
       " 'environmental_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee2b0>,\n",
       " 'degradation_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee2e8>,\n",
       " 'creation_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee320>,\n",
       " 'humane_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee358>,\n",
       " 'settlement_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee390>,\n",
       " 'wide-ranging_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee3c8>,\n",
       " 'concern_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee400>,\n",
       " 'humanity_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee438>,\n",
       " 'declare_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee470>,\n",
       " 'mother_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee4a8>,\n",
       " 'surprising_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee4e0>,\n",
       " 'celebrate_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee518>,\n",
       " 'treasure_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee550>,\n",
       " 'margaret_NNP': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee588>,\n",
       " 'mead_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee5c0>,\n",
       " 'list_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee5f8>,\n",
       " 'treasure_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee630>,\n",
       " 'no._NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee668>,\n",
       " 'right_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee6a0>,\n",
       " 'folsom_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee6d8>,\n",
       " 'point_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee710>,\n",
       " 'peregrine_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee748>,\n",
       " 'falcon_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee780>,\n",
       " 'diorama_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee7b8>,\n",
       " 'guidebook_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee7f0>,\n",
       " 'state_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee828>,\n",
       " 'bring_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee860>,\n",
       " 'serious_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee898>,\n",
       " 'work_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee8d0>,\n",
       " 'consciousness_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee908>,\n",
       " 'book_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee940>,\n",
       " 'course_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee978>,\n",
       " 'teach_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee9b0>,\n",
       " 'columbia_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ee9e8>,\n",
       " 'university_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eea20>,\n",
       " 'article_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80eea58>,\n",
       " 'write_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80eea90>,\n",
       " 'monthly_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eeac8>,\n",
       " 'column_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eeb00>,\n",
       " 'frequent_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eeb38>,\n",
       " 'interview_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80eeb70>,\n",
       " 'magazine_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80eeba8>,\n",
       " 'newspaper_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80eebe0>,\n",
       " 'broadcast_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eec18>,\n",
       " 'radio_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eec50>,\n",
       " 'visit_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80eec88>,\n",
       " 'last_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eecc0>,\n",
       " 'spring_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eecf8>,\n",
       " 'renovate_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eed30>,\n",
       " 'hall_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eed68>,\n",
       " 'people_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80eeda0>,\n",
       " 'open_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eedd8>,\n",
       " 'decade_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80eee10>,\n",
       " 'begin_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80eee48>,\n",
       " 'plan_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80eee80>,\n",
       " 'reopen_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80eeeb8>,\n",
       " 'please_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eeef0>,\n",
       " 'see_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80eef28>,\n",
       " 'incorporate_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eef60>,\n",
       " 'exhibition_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eef98>,\n",
       " 'continuous_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80eefd0>,\n",
       " 'videotape_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef048>,\n",
       " 'show_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef080>,\n",
       " 'photograph_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef0b8>,\n",
       " 'study_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef0f0>,\n",
       " 'quote_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef128>,\n",
       " 'note_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef160>,\n",
       " 'lecture_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef198>,\n",
       " 'collect_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef1d0>,\n",
       " 'give_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef208>,\n",
       " 'viewer_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef240>,\n",
       " 'insight_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef278>,\n",
       " 'process_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef2b0>,\n",
       " 'fieldwork_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef2e8>,\n",
       " 'add_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef320>,\n",
       " 'historical_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef358>,\n",
       " 'context_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef390>,\n",
       " 'presidential_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef3c8>,\n",
       " 'medal_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef400>,\n",
       " 'freedom_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef438>,\n",
       " 'receive_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef470>,\n",
       " 'president_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef4a8>,\n",
       " 'jimmy_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef4e0>,\n",
       " 'carter_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef518>,\n",
       " 'signature_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef550>,\n",
       " 'red_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef588>,\n",
       " 'cape_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef5c0>,\n",
       " 'stick_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef5f8>,\n",
       " 'label_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef630>,\n",
       " 'read_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef668>,\n",
       " 'late_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef6a0>,\n",
       " 'wear_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef6d8>,\n",
       " 'use_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef710>,\n",
       " 'style_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef748>,\n",
       " 'walk_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef780>,\n",
       " 'call_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef7b8>,\n",
       " 'thumbstick_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef7f0>,\n",
       " 'item_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef828>,\n",
       " 'familiar_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef860>,\n",
       " 'sight_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef898>,\n",
       " 'dr._NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef8d0>,\n",
       " 'travel_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef908>,\n",
       " 'numerous_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef940>,\n",
       " 'use_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef978>,\n",
       " 'joke_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef9b0>,\n",
       " 'want_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80ef9e8>,\n",
       " 'recognize_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efa20>,\n",
       " 'leave_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80efa58>,\n",
       " 'home_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efa90>,\n",
       " 'fitting_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80efac8>,\n",
       " 'become_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efb00>,\n",
       " 'artifact_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efb38>,\n",
       " 'december_NNP': <gensim.models.keyedvectors.Vocab at 0x1bcc80efb70>,\n",
       " 'lecture_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efba8>,\n",
       " 'cosmic_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80efbe0>,\n",
       " 'habitat_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efc18>,\n",
       " 'distinguish_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efc50>,\n",
       " 'author_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80efc88>,\n",
       " 'astronomy_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efcc0>,\n",
       " 'astronomer_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efcf8>,\n",
       " 'royal_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efd30>,\n",
       " 'martin_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efd68>,\n",
       " 'rees_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80efda0>,\n",
       " 'royal_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80efdd8>,\n",
       " 'professor_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efe10>,\n",
       " 'cambridge_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efe48>,\n",
       " 'p.m._NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efe80>,\n",
       " 'space_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efeb8>,\n",
       " 'theater_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80efef0>,\n",
       " 'hayden_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eff28>,\n",
       " 'planetarium_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eff60>,\n",
       " 'panel_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80eff98>,\n",
       " 'discussion_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80effd0>,\n",
       " 'use_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2048>,\n",
       " 'genome_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2080>,\n",
       " 'understand_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80f20b8>,\n",
       " 'ancestry_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f20f0>,\n",
       " 'moderate_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2128>,\n",
       " 'nicholas_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2160>,\n",
       " 'wade_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2198>,\n",
       " 'york_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f21d0>,\n",
       " 'time_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2208>,\n",
       " 'biologist_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2240>,\n",
       " 'andrew_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2278>,\n",
       " 'clark_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f22b0>,\n",
       " 'pennsylvania_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f22e8>,\n",
       " 'state_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2320>,\n",
       " 'douglas_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2358>,\n",
       " 'wallace_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2390>,\n",
       " 'center_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f23c8>,\n",
       " 'molecular_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2400>,\n",
       " 'medicine_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2438>,\n",
       " 'emory_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2470>,\n",
       " 'evolutionary_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f24a8>,\n",
       " 'joseph_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f24e0>,\n",
       " 'grave_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2518>,\n",
       " 'jr._NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2550>,\n",
       " 'arizona_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2588>,\n",
       " 'kaufmann_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f25c0>,\n",
       " 'present_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f25f8>,\n",
       " 'conjunction_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2630>,\n",
       " 'genomic_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2668>,\n",
       " 'revolution_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f26a0>,\n",
       " 'january_NNP': <gensim.models.keyedvectors.Vocab at 0x1bcc80f26d8>,\n",
       " 'gallery_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2710>,\n",
       " 'workshop_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2748>,\n",
       " 'genetics_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2780>,\n",
       " 'a.m._NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f27b8>,\n",
       " 'follow-up_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f27f0>,\n",
       " 'explanation_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2828>,\n",
       " 'session_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2860>,\n",
       " 'roundtable_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2898>,\n",
       " 'presentation_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f28d0>,\n",
       " 'border_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2908>,\n",
       " 'cross_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2940>,\n",
       " 'cultural_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2978>,\n",
       " 'appropriation_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f29b0>,\n",
       " 'artistic_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f29e8>,\n",
       " 'art_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2a20>,\n",
       " 'literature_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2a58>,\n",
       " 'indigenous_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2a90>,\n",
       " 'woman_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2ac8>,\n",
       " 'identity_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2b00>,\n",
       " 'border_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2b38>,\n",
       " 'writer_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2b70>,\n",
       " 'helena_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2ba8>,\n",
       " 'maria_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2be0>,\n",
       " 'cornell_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2c18>,\n",
       " 'artist_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2c50>,\n",
       " 'participant_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2c88>,\n",
       " 'carol_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2cc0>,\n",
       " 'kind_JJR': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2cf8>,\n",
       " 'visit_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2d30>,\n",
       " 'virgin_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2d68>,\n",
       " 'guadalupe_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2da0>,\n",
       " '?_.': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2dd8>,\n",
       " 'artist_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2e10>,\n",
       " 'henry_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2e48>,\n",
       " 'street_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2e80>,\n",
       " 'settlement_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2eb8>,\n",
       " 'art_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2ef0>,\n",
       " 'shuttle_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2f28>,\n",
       " 'amnh_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2f60>,\n",
       " 'lecture_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2f98>,\n",
       " 'hubble_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f2fd0>,\n",
       " 'machine_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7048>,\n",
       " 'frontier_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7080>,\n",
       " 'astrophysics_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f70b8>,\n",
       " 'james_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f70f0>,\n",
       " 'massachusetts_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7128>,\n",
       " 'amherst_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7160>,\n",
       " 'upcoming_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7198>,\n",
       " 'sky_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f71d0>,\n",
       " 'event_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7208>,\n",
       " 'celestial_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7240>,\n",
       " 'highlight_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7278>,\n",
       " 'lecturer_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f72b0>,\n",
       " 'amateur_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f72e8>,\n",
       " 'hank_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7320>,\n",
       " 'bartol_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7358>,\n",
       " 'kwanzaa_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7390>,\n",
       " 'celebration_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f73c8>,\n",
       " 'performance_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7400>,\n",
       " 'marketplace_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7438>,\n",
       " 'african_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7470>,\n",
       " 'holiday_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f74a8>,\n",
       " 'ocean_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f74e0>,\n",
       " 'schedule_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7518>,\n",
       " 'call_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7550>,\n",
       " 'visit_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7588>,\n",
       " 'riddle_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f75c0>,\n",
       " 'compass_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f75f8>,\n",
       " 'mathematician_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7630>,\n",
       " 'amir_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7668>,\n",
       " 'd._NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f76a0>,\n",
       " 'weekend_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f76d8>,\n",
       " 'program_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7710>,\n",
       " 'america_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7748>,\n",
       " 'arab_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7780>,\n",
       " 'american_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f77b8>,\n",
       " 'asian_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f77f0>,\n",
       " 'community-based_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7828>,\n",
       " 'present_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7860>,\n",
       " 'film_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7898>,\n",
       " 'talk_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f78d0>,\n",
       " 'discussion_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7908>,\n",
       " 'reading_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7940>,\n",
       " 'leonhardt_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7978>,\n",
       " 'frederick_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f79b0>,\n",
       " 'p._NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f79e8>,\n",
       " 'rise_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7a20>,\n",
       " 'director_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7a58>,\n",
       " 'charles_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7a90>,\n",
       " 'follow_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7ac8>,\n",
       " 'beat_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7b00>,\n",
       " 'base_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7b38>,\n",
       " 'instrument_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7b70>,\n",
       " 'neil_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7ba8>,\n",
       " 'clarke_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7be0>,\n",
       " 'origin_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7c18>,\n",
       " 'evolution_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7c50>,\n",
       " 'sea_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7c88>,\n",
       " 'marine_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7cc0>,\n",
       " 'richard_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7cf8>,\n",
       " 'ellis_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7d30>,\n",
       " 'division_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7d68>,\n",
       " 'paleontology_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7da0>,\n",
       " 'tree_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7dd8>,\n",
       " 'decorate_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7e10>,\n",
       " 'animal_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7e48>,\n",
       " 'display_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7e80>,\n",
       " 'theodore_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7eb8>,\n",
       " 'roosevelt_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7ef0>,\n",
       " 'memorial_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7f28>,\n",
       " 'teacher_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7f60>,\n",
       " 'resource_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7f98>,\n",
       " 'musing_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80f7fd0>,\n",
       " 'web_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb048>,\n",
       " 'newsletter_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb080>,\n",
       " 'science_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb0b8>,\n",
       " 'educator_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb0f0>,\n",
       " 'toolong_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb128>,\n",
       " 'wall_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb160>,\n",
       " 'telephone_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb198>,\n",
       " 'science_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb1d0>,\n",
       " 'education_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb208>,\n",
       " 'nonprofit_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb240>,\n",
       " 'serve_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb278>,\n",
       " 'information_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb2b0>,\n",
       " 'call_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb2e8>,\n",
       " 'toll-free_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb320>,\n",
       " 'adult_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb358>,\n",
       " 'begin_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb390>,\n",
       " 'choose_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb3c8>,\n",
       " 'telescope_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb400>,\n",
       " 'star_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb438>,\n",
       " 'constellation_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb470>,\n",
       " 'legend_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb4a8>,\n",
       " 'many_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb4e0>,\n",
       " 'others_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb518>,\n",
       " 'complete_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb550>,\n",
       " 'description_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb588>,\n",
       " 'visit_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb5c0>,\n",
       " 'news_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb5f8>,\n",
       " 'biodiversity_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb630>,\n",
       " 'conservation_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb668>,\n",
       " 'go_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb6a0>,\n",
       " 'located_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb6d8>,\n",
       " 'central_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb710>,\n",
       " 'park_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb748>,\n",
       " '79th_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb780>,\n",
       " 'listing_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb7b8>,\n",
       " 'exhibition_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb7f0>,\n",
       " 'hour_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb828>,\n",
       " 'site_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb860>,\n",
       " 'www.amnh.org_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb898>,\n",
       " 'show_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb8d0>,\n",
       " 'ticket_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb908>,\n",
       " 'retail_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb940>,\n",
       " 'product_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb978>,\n",
       " 'membership_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb9b0>,\n",
       " 'available_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fb9e8>,\n",
       " 'online_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fba20>,\n",
       " 'nancy_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fba58>,\n",
       " 'c._NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fba90>,\n",
       " 'chair_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbac8>,\n",
       " 'gender_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbb00>,\n",
       " 'study_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbb38>,\n",
       " 'associate_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbb70>,\n",
       " 'southern_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbba8>,\n",
       " 'california_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbbe0>,\n",
       " 'forthcoming_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbc18>,\n",
       " 'icon_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbc50>,\n",
       " 'finding_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbc88>,\n",
       " 'reader_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbcc0>,\n",
       " 'cosmo_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbcf8>,\n",
       " 'animal_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbd30>,\n",
       " 'behaviour_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbd68>,\n",
       " 'obvious_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbda0>,\n",
       " 'female_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbdd8>,\n",
       " 'right_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbe10>,\n",
       " 'mate_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbe48>,\n",
       " 'specie_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbe80>,\n",
       " 'swan_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbeb8>,\n",
       " 'mate_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbef0>,\n",
       " 'monogamous_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbf28>,\n",
       " 'monkey_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbf60>,\n",
       " 'competency_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbf98>,\n",
       " 'fatherhood_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fbfd0>,\n",
       " 'potential_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd048>,\n",
       " 'desirable_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd080>,\n",
       " 'quality_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd0b8>,\n",
       " 'court_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd0f0>,\n",
       " 'male_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd128>,\n",
       " 'display_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd160>,\n",
       " 'paternal_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd198>,\n",
       " 'skill_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd1d0>,\n",
       " 'male_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd208>,\n",
       " 'example_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd240>,\n",
       " 'snatch_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd278>,\n",
       " 'worm_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd2b0>,\n",
       " 'pretend_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd2e8>,\n",
       " 'fee_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd320>,\n",
       " 'desire_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd358>,\n",
       " 'female_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd390>,\n",
       " 'select_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd3c8>,\n",
       " 'good_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd400>,\n",
       " 'high_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd438>,\n",
       " 'list_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd470>,\n",
       " 'female_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd4a8>,\n",
       " 'homo_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd4e0>,\n",
       " 'sapiens_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd518>,\n",
       " 'rat_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd550>,\n",
       " 'textbook_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd588>,\n",
       " 'decade_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd5c0>,\n",
       " 'psychologist_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd5f8>,\n",
       " 'david_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd630>,\n",
       " 'm._NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd668>,\n",
       " 'bus_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd6a0>,\n",
       " 'publish_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd6d8>,\n",
       " 'celebrated_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd710>,\n",
       " 'study_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd748>,\n",
       " 'examine_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd780>,\n",
       " 'attribute_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd7b8>,\n",
       " 'men_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd7f0>,\n",
       " 'desire_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd828>,\n",
       " 'canvass_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd860>,\n",
       " 'different_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd898>,\n",
       " 'culture_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd8d0>,\n",
       " 'race_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd908>,\n",
       " 'religion_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd940>,\n",
       " 'ethnicity_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd978>,\n",
       " 'live_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd9b0>,\n",
       " 'urban_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fd9e8>,\n",
       " 'rural_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fda20>,\n",
       " 'setting_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fda58>,\n",
       " 'western_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fda90>,\n",
       " 'develop_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdac8>,\n",
       " 'capitalist_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdb00>,\n",
       " 'socialist_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdb38>,\n",
       " 'economy_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdb70>,\n",
       " 'find_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdba8>,\n",
       " 'likely_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdbe0>,\n",
       " 'consider_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdc18>,\n",
       " 'economic_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdc50>,\n",
       " 'prospect_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdc88>,\n",
       " 'priority_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdcc0>,\n",
       " 'interpret_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdcf8>,\n",
       " 'sign_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdd30>,\n",
       " 'want_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdd68>,\n",
       " 'mate_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdda0>,\n",
       " 'effective_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fddd8>,\n",
       " 'one_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc80fde10>,\n",
       " 'imagine_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80fde48>,\n",
       " 'generate_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc80fde80>,\n",
       " 'sort_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdeb8>,\n",
       " 'unsettling_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdef0>,\n",
       " 'accusation_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdf28>,\n",
       " 'political_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdf60>,\n",
       " 'pair_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdf98>,\n",
       " 'reproduce_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc80fdfd0>,\n",
       " 'choose_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8102048>,\n",
       " 'particular_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8102080>,\n",
       " 'male_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81020b8>,\n",
       " 'basis_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81020f0>,\n",
       " 'treat_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8102128>,\n",
       " 'offspring_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102160>,\n",
       " 'olive_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8102198>,\n",
       " 'baboon_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81021d0>,\n",
       " 'prize_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102208>,\n",
       " 'catch_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102240>,\n",
       " 'foul_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8102278>,\n",
       " 'mood_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81022b0>,\n",
       " 'direct_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc81022e8>,\n",
       " 'aggression_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102320>,\n",
       " 'go_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc8102358>,\n",
       " 'get_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc8102390>,\n",
       " 'assistance_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81023c8>,\n",
       " 'much_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8102400>,\n",
       " 'contact_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102438>,\n",
       " 'line_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102470>,\n",
       " 'integrate_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc81024a8>,\n",
       " 'group_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc81024e0>,\n",
       " 'typical_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8102518>,\n",
       " 'arrangement_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102550>,\n",
       " 'golden_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8102588>,\n",
       " 'hamster_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc81025c0>,\n",
       " 'stable_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81025f8>,\n",
       " 'group_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102630>,\n",
       " 'boot_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102668>,\n",
       " 'long_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81026a0>,\n",
       " 'young_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81026d8>,\n",
       " 'bear_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102710>,\n",
       " 'call_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8102748>,\n",
       " 'harem_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102780>,\n",
       " 'primatologist_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81027b8>,\n",
       " 'alison_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81027f0>,\n",
       " 'suggest_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc8102828>,\n",
       " 'call_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102860>,\n",
       " 'get_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc8102898>,\n",
       " 'brief_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81028d0>,\n",
       " 'liaison_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102908>,\n",
       " 'sperm_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102940>,\n",
       " 'pack_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102978>,\n",
       " 'gene_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc81029b0>,\n",
       " 'age-old_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81029e8>,\n",
       " 'problem_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102a20>,\n",
       " 'figure_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8102a58>,\n",
       " 'try_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8102a90>,\n",
       " 'advertise_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8102ac8>,\n",
       " 'peacock_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8102b00>,\n",
       " 'spread_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc8102b38>,\n",
       " 'gorgeous_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8102b70>,\n",
       " 'tail_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102ba8>,\n",
       " 'fan_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8102be0>,\n",
       " 'lion_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8102c18>,\n",
       " 'elaborate_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8102c50>,\n",
       " 'mane_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8102c88>,\n",
       " 'elk_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8102cc0>,\n",
       " 'ornate_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8102cf8>,\n",
       " 'antler_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8102d30>,\n",
       " 'feature_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8102d68>,\n",
       " 'ornamental_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8102da0>,\n",
       " 'useful_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8102dd8>,\n",
       " 'purpose_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102e10>,\n",
       " 'sexual_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8102e48>,\n",
       " 'attraction_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102e80>,\n",
       " 'question_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102eb8>,\n",
       " 'vex_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102ef0>,\n",
       " 'biologist_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8102f28>,\n",
       " 'ornament_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8102f60>,\n",
       " 'tell_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8102f98>,\n",
       " 'anything_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8102fd0>,\n",
       " 'genetic_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8105048>,\n",
       " 'health_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105080>,\n",
       " 'word_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc81050b8>,\n",
       " 'truth_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81050f0>,\n",
       " 'advertising_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105128>,\n",
       " 'british_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8105160>,\n",
       " 'statistician_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105198>,\n",
       " 'geneticist_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81051d0>,\n",
       " 'ronald_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105208>,\n",
       " 'fisher_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8105240>,\n",
       " 'ornamentation_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105278>,\n",
       " 'something_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81052b0>,\n",
       " 'attract_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc81052e8>,\n",
       " 'huge_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8105320>,\n",
       " 'energy_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105358>,\n",
       " 'expenditure_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105390>,\n",
       " 'grow_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc81053c8>,\n",
       " 'maintain_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8105400>,\n",
       " 'price_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105438>,\n",
       " 'tag_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105470>,\n",
       " 'term_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc81054a8>,\n",
       " 'darwinian_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81054e0>,\n",
       " 'fitness_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105518>,\n",
       " 'accord_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc8105550>,\n",
       " 'spend_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105588>,\n",
       " 'lot_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81055c0>,\n",
       " 'calorie_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc81055f8>,\n",
       " 'grow_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc8105630>,\n",
       " 'big_JJS': <gensim.models.keyedvectors.Vocab at 0x1bcc8105668>,\n",
       " 'sensible_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81056a0>,\n",
       " 'keep_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc81056d8>,\n",
       " 'immune_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8105710>,\n",
       " 'system_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105748>,\n",
       " 'tune_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc8105780>,\n",
       " 'fisher_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81057b8>,\n",
       " 'fall_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc81057f0>,\n",
       " 'favor_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105828>,\n",
       " 'striking_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8105860>,\n",
       " 'support_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105898>,\n",
       " 'emerge_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc81058d0>,\n",
       " 'robert_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105908>,\n",
       " 'brook_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8105940>,\n",
       " 'john_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105978>,\n",
       " 'endler_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81059b0>,\n",
       " 'cook_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc81059e8>,\n",
       " 'australia_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105a20>,\n",
       " 'study_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105a58>,\n",
       " 'attractiveness_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105a90>,\n",
       " 'guppy_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8105ac8>,\n",
       " 'show_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc8105b00>,\n",
       " 'color_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105b38>,\n",
       " 'pattern_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8105b70>,\n",
       " 'consider_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105ba8>,\n",
       " 'attractive_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8105be0>,\n",
       " 'sire_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc8105c18>,\n",
       " 'son_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8105c50>,\n",
       " 'patterning_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105c88>,\n",
       " 'scientist_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8105cc0>,\n",
       " 'determine_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105cf8>,\n",
       " 'heritable_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8105d30>,\n",
       " 'cod_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105d68>,\n",
       " 'cluster_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105da0>,\n",
       " 'chromosome_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105dd8>,\n",
       " 'july_NNP': <gensim.models.keyedvectors.Vocab at 0x1bcc8105e10>,\n",
       " 'survive_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8105e48>,\n",
       " 'average_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8105e80>,\n",
       " 'case_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105eb8>,\n",
       " 'get_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8105ef0>,\n",
       " 'kill_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105f28>,\n",
       " 'predator_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105f60>,\n",
       " 'cost_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8105f98>,\n",
       " 'flashy_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8105fd0>,\n",
       " 'conspicuous_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8108048>,\n",
       " 'survival_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108080>,\n",
       " 'rate_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc81080b8>,\n",
       " 'low_JJR': <gensim.models.keyedvectors.Vocab at 0x1bcc81080f0>,\n",
       " 'reach_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8108128>,\n",
       " 'maturity_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108160>,\n",
       " 'develop_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8108198>,\n",
       " 'coloration_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81081d0>,\n",
       " 'experiment_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108208>,\n",
       " 'stand_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc8108240>,\n",
       " 'decoration_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8108278>,\n",
       " 'tell_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc81082b0>,\n",
       " 'bad_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81082e8>,\n",
       " 'say_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8108320>,\n",
       " 'fad_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8108358>,\n",
       " 'jacob_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108390>,\n",
       " 'arne_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81083c8>,\n",
       " 'lundberg_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108400>,\n",
       " 'uppsala_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108438>,\n",
       " 'sweden_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108470>,\n",
       " 'think_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc81084a8>,\n",
       " 'interesting_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81084e0>,\n",
       " 'pair_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108518>,\n",
       " 'black_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8108550>,\n",
       " 'grouse_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108588>,\n",
       " 'chemistry_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81085c0>,\n",
       " 'interested_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81085f8>,\n",
       " 'use_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8108630>,\n",
       " 'low-tech_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8108668>,\n",
       " 'scientific_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81086a0>,\n",
       " 'artifice_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81086d8>,\n",
       " 'turn_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8108710>,\n",
       " 'appear_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc8108748>,\n",
       " 'say_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8108780>,\n",
       " 'surround_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc81087b8>,\n",
       " 'indifferent_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81087f0>,\n",
       " 'decide_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc8108828>,\n",
       " \"'s_VBZ\": <gensim.models.keyedvectors.Vocab at 0x1bcc8108860>,\n",
       " 'kinda_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108898>,\n",
       " 'cute_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81088d0>,\n",
       " 'bandwagon_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108908>,\n",
       " 'effect_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108940>,\n",
       " 'seem_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc8108978>,\n",
       " 'mean_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc81089b0>,\n",
       " 'decide_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc81089e8>,\n",
       " 'neon_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108a20>,\n",
       " 'hot_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8108a58>,\n",
       " 'commodity_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108a90>,\n",
       " 'think_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8108ac8>,\n",
       " 'look_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8108b00>,\n",
       " 'ridiculous_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8108b38>,\n",
       " 'advantage_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108b70>,\n",
       " 'mate_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8108ba8>,\n",
       " 'rage_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108be0>,\n",
       " 'order_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108c18>,\n",
       " 'maximize_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8108c50>,\n",
       " 'pass_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc8108c88>,\n",
       " 'copy_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8108cc0>,\n",
       " 'circular_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8108cf8>,\n",
       " 'logic_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108d30>,\n",
       " 'trait_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108d68>,\n",
       " 'become_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc8108da0>,\n",
       " 'carry_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc8108dd8>,\n",
       " 'carrier_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108e10>,\n",
       " 'possibility_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108e48>,\n",
       " 'translate_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8108e80>,\n",
       " 'meaningful_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8108eb8>,\n",
       " 'message_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8108ef0>,\n",
       " 'bet_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8108f28>,\n",
       " \"'m_VBP\": <gensim.models.keyedvectors.Vocab at 0x1bcc8108f60>,\n",
       " 'afford_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8108f98>,\n",
       " 'waste_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8108fd0>,\n",
       " 'three-foot-long_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc810b048>,\n",
       " 'feather_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc810b080>,\n",
       " 'marlene_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b0b8>,\n",
       " 'biology_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b0f0>,\n",
       " 'formalize_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc810b128>,\n",
       " 'notion_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b160>,\n",
       " 'expensive_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc810b198>,\n",
       " 'signal_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc810b1d0>,\n",
       " 'free_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc810b208>,\n",
       " 'parasite_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc810b240>,\n",
       " 'see_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc810b278>,\n",
       " 'charming_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc810b2b0>,\n",
       " 'response_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b2e8>,\n",
       " 'april_NNP': <gensim.models.keyedvectors.Vocab at 0x1bcc810b320>,\n",
       " 'find_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc810b358>,\n",
       " 'appeal_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc810b390>,\n",
       " 'decrease_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc810b3c8>,\n",
       " 'likelihood_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b400>,\n",
       " 'wind_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc810b438>,\n",
       " 'guy_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b470>,\n",
       " 'reproduce_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc810b4a8>,\n",
       " 'organism_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc810b4e0>,\n",
       " 'need_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc810b518>,\n",
       " 'worry_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc810b550>,\n",
       " 'transmitted_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc810b588>,\n",
       " 'disease_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc810b5c0>,\n",
       " 'version_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b5f8>,\n",
       " 'basic_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc810b630>,\n",
       " 'theme_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b668>,\n",
       " 'signal_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc810b6a0>,\n",
       " 'pass_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b6d8>,\n",
       " 'next_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc810b710>,\n",
       " 'generation_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b748>,\n",
       " 'zahavi_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b780>,\n",
       " 'tel_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b7b8>,\n",
       " 'aviv_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b7f0>,\n",
       " 'israel_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b828>,\n",
       " 'posit_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc810b860>,\n",
       " 'evolve_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b898>,\n",
       " 'ability_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b8d0>,\n",
       " 'differentiate_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc810b908>,\n",
       " 'reflect_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc810b940>,\n",
       " 'kind_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b978>,\n",
       " 'acquire_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc810b9b0>,\n",
       " 'least_JJS': <gensim.models.keyedvectors.Vocab at 0x1bcc810b9e8>,\n",
       " 'method_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc810ba20>,\n",
       " 'answer_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810ba58>,\n",
       " 'isolate_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc810ba90>,\n",
       " 'responsible_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc810bac8>,\n",
       " 'certain_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc810bb00>,\n",
       " 'tend_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc810bb38>,\n",
       " 'inherit_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc810bb70>,\n",
       " 'reliable_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc810bba8>,\n",
       " 'figure_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc810bbe0>,\n",
       " 'function_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810bc18>,\n",
       " 'protein_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc810bc50>,\n",
       " 'neighbor_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc810bc88>,\n",
       " 'advantageous_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc810bcc0>,\n",
       " 'race_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810bcf8>,\n",
       " 'sequence_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810bd30>,\n",
       " 'old-fashioned_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc810bd68>,\n",
       " 'carry_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc810bda0>,\n",
       " 'mat_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc810bdd8>,\n",
       " 'differ_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc810be10>,\n",
       " 'father_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810be48>,\n",
       " 'fit_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc810be80>,\n",
       " 'adulthood_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810beb8>,\n",
       " 'produce_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc810bef0>,\n",
       " \"'ve_VBP\": <gensim.models.keyedvectors.Vocab at 0x1bcc810bf28>,\n",
       " 'get_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc810bf60>,\n",
       " 'reason_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc810bf98>,\n",
       " 'conclude_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc810bfd0>,\n",
       " 'pass_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8110048>,\n",
       " 'adaptive_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8110080>,\n",
       " 'assemblage_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81100b8>,\n",
       " 'number_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81100f0>,\n",
       " 'show_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110128>,\n",
       " 'cast_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc8110160>,\n",
       " 'big_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8110198>,\n",
       " 'vote_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81101d0>,\n",
       " 'hypothesis_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110208>,\n",
       " 'startling_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8110240>,\n",
       " 'creep_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110278>,\n",
       " 'duck_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc81102b0>,\n",
       " 'emma_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81102e8>,\n",
       " 'cunningham_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110320>,\n",
       " 'march_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110358>,\n",
       " 'mallard_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8110390>,\n",
       " 'increase_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc81103c8>,\n",
       " 'vote_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8110400>,\n",
       " 'lay_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc8110438>,\n",
       " 'large_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8110470>,\n",
       " 'egg_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc81104a8>,\n",
       " 'factor_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81104e0>,\n",
       " 'size_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110518>,\n",
       " 'invest_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc8110550>,\n",
       " 'result_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc8110588>,\n",
       " 'make_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc81105c0>,\n",
       " 'fact_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81105f8>,\n",
       " 'russell_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110630>,\n",
       " 'control_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110668>,\n",
       " 'egg_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81106a0>,\n",
       " 'difference_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81106d8>,\n",
       " 'similar_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8110710>,\n",
       " 'journal_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110748>,\n",
       " 'october_NNP': <gensim.models.keyedvectors.Vocab at 0x1bcc8110780>,\n",
       " 'diego_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81107b8>,\n",
       " 'gil_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81107f0>,\n",
       " 'colleague_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8110828>,\n",
       " 'saint_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110860>,\n",
       " 'andrew_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8110898>,\n",
       " 'zebra_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81108d0>,\n",
       " 'finch_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8110908>,\n",
       " 'beg_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110940>,\n",
       " 'food_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110978>,\n",
       " 'fledge_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc81109b0>,\n",
       " 'develop_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc81109e8>,\n",
       " 'contain_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc8110a20>,\n",
       " 'hormone_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110a58>,\n",
       " 'lope_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110a90>,\n",
       " 'spain_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110ac8>,\n",
       " 'anders_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8110b00>,\n",
       " 'moller_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110b38>,\n",
       " 'universit_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8110b70>,\n",
       " 'pierre_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110ba8>,\n",
       " 'curie_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110be0>,\n",
       " 'france_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110c18>,\n",
       " 'show_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc8110c50>,\n",
       " 'barn_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110c88>,\n",
       " 'swallow_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc8110cc0>,\n",
       " 'take_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8110cf8>,\n",
       " 'good_JJR': <gensim.models.keyedvectors.Vocab at 0x1bcc8110d30>,\n",
       " 'care_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110d68>,\n",
       " 'chick_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8110da0>,\n",
       " 'logical_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8110dd8>,\n",
       " 'extension_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110e10>,\n",
       " 'uncover_VBN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110e48>,\n",
       " 'starter_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8110e80>,\n",
       " 'everyone_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110eb8>,\n",
       " 'want_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc8110ef0>,\n",
       " 'seem_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8110f28>,\n",
       " 'best_JJS': <gensim.models.keyedvectors.Vocab at 0x1bcc8110f60>,\n",
       " 'interest_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8110f98>,\n",
       " 'know_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc8110fd0>,\n",
       " 'make_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8114048>,\n",
       " 'carry_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8114080>,\n",
       " 'well-being_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81140b8>,\n",
       " 'challenge_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81140f0>,\n",
       " 'translate_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc8114128>,\n",
       " 'investment_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8114160>,\n",
       " 'knowledge_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8114198>,\n",
       " 'level_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81141d0>,\n",
       " 'exist_VBZ': <gensim.models.keyedvectors.Vocab at 0x1bcc8114208>,\n",
       " 'brain_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8114240>,\n",
       " 'synthesize_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc8114278>,\n",
       " 'gland_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81142b0>,\n",
       " 'extra_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81142e8>,\n",
       " 'mile_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8114320>,\n",
       " 'eat_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8114358>,\n",
       " 'classical_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8114390>,\n",
       " 'dichotomy_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81143c8>,\n",
       " 'proximal_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8114400>,\n",
       " 'distal_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8114438>,\n",
       " 'concern_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8114470>,\n",
       " 'simple_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81144a8>,\n",
       " 'invest_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc81144e0>,\n",
       " 'trait_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8114518>,\n",
       " 'enhance_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8114550>,\n",
       " 'nut_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8114588>,\n",
       " 'bolt_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc81145c0>,\n",
       " 'hormone_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc81145f8>,\n",
       " 'neural_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8114630>,\n",
       " 'pathway_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8114668>,\n",
       " 'great_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc81146a0>,\n",
       " 'mystery_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc81146d8>,\n",
       " 'amount_NN': <gensim.models.keyedvectors.Vocab at 0x1bcc8114710>,\n",
       " 'parental_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8114748>,\n",
       " 'generate_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8114780>,\n",
       " 'problem_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc81147b8>,\n",
       " 'big_JJR': <gensim.models.keyedvectors.Vocab at 0x1bcc81147f0>,\n",
       " 'raise_VBD': <gensim.models.keyedvectors.Vocab at 0x1bcc8114828>,\n",
       " 'underlie_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc8114860>,\n",
       " 'kid_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8114898>,\n",
       " 'make_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc81148d0>,\n",
       " 'sure_JJ': <gensim.models.keyedvectors.Vocab at 0x1bcc8114908>,\n",
       " 'survive_VBP': <gensim.models.keyedvectors.Vocab at 0x1bcc8114940>,\n",
       " 'researcher_NNS': <gensim.models.keyedvectors.Vocab at 0x1bcc8114978>,\n",
       " 'hatch_VBG': <gensim.models.keyedvectors.Vocab at 0x1bcc81149b0>,\n",
       " 'exist_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc81149e8>,\n",
       " 'disprove_VB': <gensim.models.keyedvectors.Vocab at 0x1bcc8114a20>,\n",
       " ...}"
      ]
     },
     "execution_count": 114,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.wv.vocab"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('system_NN', 0.7618799209594727),\n",
       " ('technology_NNS', 0.5845077633857727),\n",
       " ('scheme_NNS', 0.5730825662612915),\n",
       " ('process_NNS', 0.5695005059242249),\n",
       " ('network_NNS', 0.567191481590271),\n",
       " ('module_NNS', 0.5638443231582642),\n",
       " ('device_NNS', 0.5629462003707886),\n",
       " ('platform_NNS', 0.561886191368103),\n",
       " ('machine_NNS', 0.5435508489608765),\n",
       " ('infrastructure_NN', 0.5359182357788086)]"
      ]
     },
     "execution_count": 115,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.wv.similar_by_word(\"system_NNS\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('ecology_NN', 0.7873948812484741),\n",
       " ('genetics_NNS', 0.7804935574531555),\n",
       " ('systematics_NNS', 0.7124741077423096),\n",
       " ('organismal_JJ', 0.6865349411964417),\n",
       " ('botany_NN', 0.6813952922821045),\n",
       " ('physiology_NN', 0.6709659099578857),\n",
       " ('paleontology_NN', 0.6671159267425537),\n",
       " ('epidemiology_NN', 0.6289629936218262),\n",
       " ('biochemistry_NN', 0.6280736327171326),\n",
       " ('evolution_NN', 0.6196252107620239)]"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.wv.similar_by_word(\"biology_NN\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('elderly_JJ', 0.6808924674987793),\n",
       " ('impaired_JJ', 0.6747027039527893),\n",
       " ('caregiver_NNS', 0.6719509363174438),\n",
       " ('cooperate_VBP', 0.6619284152984619),\n",
       " ('deaf_JJ', 0.6600719690322876),\n",
       " ('abused_JJ', 0.6563312411308289),\n",
       " ('paralyzed_JJ', 0.6533416509628296),\n",
       " ('volunteer_VB', 0.6517242789268494),\n",
       " ('nurse_NNS', 0.6490663290023804),\n",
       " ('nursing_NN', 0.6450989246368408)]"
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.wv.similar_by_word(\"disabled_JJ\") # note that by giving the adjective tag JJ, we can distinguish this word from its verb usage"
   ]
  }
 ],
 "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
}