{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "e1b17564-0abb-41c5-8cf4-7200b014550f",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package wordnet to /home/sy/nltk_data...\n",
      "[nltk_data]   Package wordnet is already up-to-date!\n",
      "[nltk_data] Downloading package words to /home/sy/nltk_data...\n",
      "[nltk_data]   Package words is already up-to-date!\n"
     ]
    }
   ],
   "source": [
    "import json\n",
    "import nltk\n",
    "from nltk.corpus import wordnet as wn\n",
    "from nltk.stem.wordnet import WordNetLemmatizer\n",
    "nltk.download('wordnet')\n",
    "from nltk.corpus import words\n",
    "nltk.download('words')\n",
    "ww = words.words()\n",
    "import pandas as pd \n",
    "import string"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "27488c82-1e9b-4873-9e6b-e0b5937fc51d",
   "metadata": {},
   "outputs": [],
   "source": [
    "def format(s):\n",
    "    return ' '.join(s.split('_'))\n",
    "from collections import defaultdict\n",
    "lexnames = set()\n",
    "lexname_blacklist = {\n",
    "    'noun.plant',\n",
    "    'noun.animal',\n",
    "    'noun.person',\n",
    "    'noun.state',\n",
    "    'noun.body',\n",
    "    #'noun.location',\n",
    "    #'noun.group',\n",
    "}\n",
    "def is_proper(w):\n",
    "    return w[0] in string.ascii_uppercase\n",
    "def groups_for_pos(pos='as'):\n",
    "    dsynonyms = []\n",
    "    for word in wn.words():\n",
    "        if is_proper(word):\n",
    "            continue\n",
    "        synsets = wn.synsets(word)\n",
    "        synonymss = wn.synonyms(word)\n",
    "        syns = set()\n",
    "        for synset, synonyms in zip(synsets, synonymss):\n",
    "            if synset.lexname() in lexname_blacklist:\n",
    "                continue\n",
    "            if synset.pos() in pos:\n",
    "                syns |= set(syn for syn in synonyms if not is_proper(syn))\n",
    "        if len(syns) >= 4:\n",
    "            clues = [format(clue) for clue in syns]\n",
    "            clues.append(format(word))\n",
    "            dsynonyms.append(dict(answer=word, hint=f'synonyms for {format(word)}', clues=clues))\n",
    "    return dsynonyms"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "445789e7-3808-4a28-9df5-9a69313cb4c2",
   "metadata": {},
   "outputs": [],
   "source": [
    "dadj = groups_for_pos('as')\n",
    "dverb = groups_for_pos('v')\n",
    "dnoun = groups_for_pos('n')\n",
    "dadverb = groups_for_pos('r')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "64ccaf3d-9743-49ed-b10b-d7b3e70e0235",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('LADECv1-2019.csv', index_col=0)\n",
    "df = df.drop(df[df.correctParse == 'no'].index)\n",
    "df = df.drop(df[df.isCommonstim == 0].index)\n",
    "prefixes = df.groupby('c1').groups\n",
    "suffixes = df.groupby('c2').groups\n",
    "dprefix = []\n",
    "for prefix, ids in prefixes.items():\n",
    "    if len(ids) >= 4:\n",
    "        dprefix.append(dict(answer=prefix, hint=f'{prefix} _', clues=list(df.loc[list(ids)].c2)))\n",
    "dsuffix = []\n",
    "for suffix, ids in suffixes.items():\n",
    "    if len(ids) >= 4:\n",
    "        dsuffix.append(dict(answer=suffix, hint=f'_ {suffix}', clues=list(df.loc[list(ids)].c1)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "def43999-d789-4e5c-bb27-4fd29074c875",
   "metadata": {},
   "outputs": [],
   "source": [
    "from Levenshtein import ratio\n",
    "def similar(a, b):\n",
    "    a, b = a.lower(), b.lower()\n",
    "    if len(a) > len(b):\n",
    "        a, b = b, a\n",
    "    if a + 's' == b or a + 'es' == b or a + 'ing' == b or a + 'ly' == b:\n",
    "        return True\n",
    "    r = ratio(a, b)\n",
    "    if .8 <= r <= .9:\n",
    "        pass\n",
    "        #print(a, b, r)\n",
    "    return r >= .85\n",
    "def filter_duplicates(group):\n",
    "    if not group:\n",
    "        return []\n",
    "    ok = [group[0]]\n",
    "    for i in range(1, len(group)):\n",
    "        for word in ok:\n",
    "            if similar(word, group[i]):\n",
    "                break\n",
    "        else:\n",
    "            ok.append(group[i])\n",
    "    return ok"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "1c8175f2-817e-45ab-af0b-5ea7ee7a5dc9",
   "metadata": {},
   "outputs": [],
   "source": [
    "blacklist = ['man', 'men', 'woman', 'women']\n",
    "def process_groups(groups):\n",
    "    new = []\n",
    "    for group in groups:\n",
    "        clues = group['clues']\n",
    "        clues = [clue for clue in clues if clue not in blacklist]\n",
    "        clues = filter_duplicates(clues)\n",
    "        if len(clues) < 4:\n",
    "            continue\n",
    "        new.append(dict(answer=group['answer'], hint=group['hint'], clues=clues))\n",
    "    return new\n",
    "corpus = [\n",
    "    dict(name='suffixes', groups=process_groups(dsuffix), portion=.9),\n",
    "    dict(name='prefixes', groups=process_groups(dprefix), portion=.8),\n",
    "    dict(name='verbs', groups=process_groups(dverb), portion=.6),\n",
    "    dict(name='adverbs', groups=process_groups(dadverb), portion=.54),\n",
    "    dict(name='nouns', groups=process_groups(dnoun), portion=.2),\n",
    "    dict(name='adjectives', groups=process_groups(dadj), portion=0),\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "1f2cca38-5d1a-421e-9bcc-09d68880c6f1",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('../static/corpus.js', 'w') as f:\n",
    "    f.write('var corpus = ')\n",
    "    json.dump(corpus, f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "589f6645-3a52-40ad-9899-717ea7614d00",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'noun.group'"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wn.synsets('Islamic_jihad')[0].lexname()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "8faeb5ee-e1ff-4571-91bf-178cdc7d29f7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'ABCDEFGHIJKLMNOPQRSTUVWXYZ'"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "    string.ascii_uppercase"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b8d12e1a-757f-4d87-9374-e7eb656f30d4",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "68f254d5-7a96-488a-b1a8-6a82dce44271",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "091e0422-99be-4b20-a20d-17ac296990b6",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ff46e8c4-b806-43f6-8cf9-d4260bad1ba8",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "668b25f4-6992-41a3-881c-3a6a72ba0d77",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1a0ae159-2a40-4ca5-915a-6ca40df3080f",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}