{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "Collapsed": "false"
   },
   "outputs": [],
   "source": [
    "from szyfrow.support.language_models import *\n",
    "from szyfrow.support.utilities import *\n",
    "import collections"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "Collapsed": "false"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "14843"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "words8 = [w for w in keywords if len(w) == 8]\n",
    "len(words8)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "Collapsed": "false"
   },
   "outputs": [],
   "source": [
    "anags8 = collections.defaultdict(list)\n",
    "for w in words8:\n",
    "    anags8[cat(sorted(w))] += [w]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "Collapsed": "false"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['aegilnrt', 'aeginrst', 'deeinrst', 'ceeprsst', 'aeinrrst']"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cands = [w for w in anags8 if len(anags8[w]) >= 5]\n",
    "cands"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "Collapsed": "false"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "aegilnrt ['alerting', 'altering', 'integral', 'relating', 'triangle']\n",
      "aeginrst ['angriest', 'gantries', 'granites', 'ingrates', 'rangiest', 'tangiers']\n",
      "deeinrst ['dniester', 'inserted', 'nerdiest', 'resident', 'trendies']\n",
      "ceeprsst ['respects', 'scepters', 'sceptres', 'specters', 'spectres']\n",
      "aeinrrst ['restrain', 'retrains', 'strainer', 'terrains', 'trainers']\n"
     ]
    }
   ],
   "source": [
    "for c in cands:\n",
    "    print(c, anags8[c])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "Collapsed": "false"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"alerting', 'altering', 'integral', 'relating', 'triangle', 'angriest', 'gantries', 'granites', 'ingrates', 'rangiest', 'tangiers', 'dniester', 'inserted', 'nerdiest', 'resident', 'trendies', 'respects', 'scepters', 'sceptres', 'specters', 'spectres', 'restrain', 'retrains', 'strainer', 'terrains', 'trainers\""
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"', '\".join(w for c in cands for w in anags8[c])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "Collapsed": "false"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}