notes for RWET (grad) march 7th 2019

notes-2019-03-07.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# notes 2019-03-07"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## word counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "words = open(\"./genesis.txt\").read().split()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['In',\n",
       " 'the',\n",
       " 'beginning',\n",
       " 'God',\n",
       " 'created',\n",
       " 'the',\n",
       " 'heaven',\n",
       " 'and',\n",
       " 'the',\n",
       " 'earth.']"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "words[:10]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "    {'In': 1,\n",
    "     'the': 90,\n",
    "     'beginning': 3,\n",
    "     'God': 23,\n",
    "     ...\n",
    "    }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "counts = {}\n",
    "for item in words:\n",
    "    if item in counts:\n",
    "        counts[item] += 1\n",
    "    else:\n",
    "        counts[item] = 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from collections import Counter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "count = Counter(words)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "108"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "count['the']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('the', 108),\n",
       " ('and', 63),\n",
       " ('And', 33),\n",
       " ('God', 32),\n",
       " ('of', 20),\n",
       " ('was', 17),\n",
       " ('it', 15),\n",
       " ('that', 14),\n",
       " ('in', 13),\n",
       " ('every', 12),\n",
       " ('after', 11),\n",
       " ('to', 11)]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "count.most_common(12)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('the', 108)]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "count.most_common(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'the'"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "count.most_common(10)[0][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "letter_count = Counter(open(\"./genesis.txt\").read())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[(' ', 797),\n",
       " ('e', 450),\n",
       " ('t', 339),\n",
       " ('a', 267),\n",
       " ('h', 255),\n",
       " ('n', 233),\n",
       " ('d', 232),\n",
       " ('i', 195),\n",
       " ('r', 186),\n",
       " ('o', 167),\n",
       " ('s', 128),\n",
       " ('f', 87),\n",
       " ('l', 86),\n",
       " ('g', 82),\n",
       " (',', 68),\n",
       " ('m', 65),\n",
       " ('w', 62),\n",
       " ('v', 59),\n",
       " ('u', 44),\n",
       " ('y', 42),\n",
       " ('.', 33),\n",
       " ('A', 33),\n",
       " ('G', 32),\n",
       " ('c', 31),\n",
       " ('\\n', 31),\n",
       " ('b', 29),\n",
       " ('p', 25),\n",
       " (':', 17),\n",
       " ('k', 16),\n",
       " ('L', 8),\n",
       " (';', 6),\n",
       " ('I', 3),\n",
       " ('S', 3),\n",
       " ('B', 3),\n",
       " ('D', 1),\n",
       " ('N', 1),\n",
       " ('H', 1),\n",
       " ('E', 1),\n",
       " ('x', 1)]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "letter_count.most_common()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_count = Counter([\"🐈\", \"🐈\", \"🐩\", \"🐩\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'🐈'"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_count.most_common(1)[0][0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## tracery"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: tracery in /Users/allison/anaconda/lib/python3.6/site-packages\n",
      "\u001b[33mYou are using pip version 9.0.3, however version 19.0.3 is available.\n",
      "You should consider upgrading via the 'pip install --upgrade pip' command.\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "!pip install tracery"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tracery"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Greetings, precinct!\n"
     ]
    }
   ],
   "source": [
    "rules = {\n",
    "    \"origin\": \"#greeting#, #noun#!\",\n",
    "    \"noun\": [\"galaxy\", \"world\", \"solar system\", \"dimensional plane\", \"precinct\", \"neighborhood\"],\n",
    "    \"greeting\": [\"Howdy\", \"Hello\", \"Greetings\", \"Hey\", \"Uhhhh\", \"Ummm\", \"Okay\"]\n",
    "}\n",
    "grammar = tracery.Grammar(rules)\n",
    "print(grammar.flatten(\"#origin#\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "meme generator project!\n",
    "\n",
    "    <interjection> <name>, I'm a <profession> not a <profession>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [],
   "source": [
    "from tracery.modifiers import base_english"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 149,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "You know, Robert, I've never met \"an actor\" like you.\n"
     ]
    }
   ],
   "source": [
    "rules = {\n",
    "    \"origin\": [\"#interjection.capitalize#, #name#! I'm #profession.a#, not #profession.a#\",\n",
    "               \"You know, #name#, I've never met \\\"#profession.a#\\\" like you.\"],\n",
    "    \"interjection\": [\"dammit\",\n",
    "                     \"alas\",\n",
    "                     \"oh god\",\n",
    "                     \"gee\",\n",
    "                     \"good grief\",\n",
    "                     \"hallelujah\",\n",
    "                     \"whoa\",\n",
    "                     \"rats\"],\n",
    "    \"name\": [\"Jim\", \"Robert\", \"Bernie\", \"Adam\", \"Gary\", \"Kevin\", \"Steve\"],\n",
    "    \"profession\": [\n",
    "        \"accountant\", \"actor\", \"bartender\", \"engineer\", \"farmer\", \"stripper\",\n",
    "        \"new media artist\", \"therapist\", \"sous chef\", \"zoologist\"\n",
    "    ]\n",
    "}\n",
    "grammar = tracery.Grammar(rules)\n",
    "grammar.add_modifiers(base_english)\n",
    "print(grammar.flatten(\"#origin#\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'a': <function tracery.modifiers.a>,\n",
       " 'capitalize': <function tracery.modifiers.capitalize_>,\n",
       " 'capitalizeAll': <function tracery.modifiers.capitalizeAll>,\n",
       " 'ed': <function tracery.modifiers.ed>,\n",
       " 'firstS': <function tracery.modifiers.firstS>,\n",
       " 'lowercase': <function tracery.modifiers.lowercase>,\n",
       " 'replace': <function tracery.modifiers.replace>,\n",
       " 's': <function tracery.modifiers.s>,\n",
       " 'uppercase': <function tracery.modifiers.uppercase>}"
      ]
     },
     "execution_count": 124,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "base_english"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 151,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 152,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = json.load(open(\"./occupations.json\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 154,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict"
      ]
     },
     "execution_count": 154,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 155,
   "metadata": {},
   "outputs": [],
   "source": [
    "occupations = data['occupations']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 156,
   "metadata": {},
   "outputs": [],
   "source": [
    "import random"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'floor layer'"
      ]
     },
     "execution_count": 168,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "random.choice(occupations)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 177,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Gee, Bernie! I'm a curator, not a textile worker\n",
      "Oh god, Jim! I'm a highway maintenance worker, not a clinical psychologist\n",
      "Gee, Gary! I'm a conservation worker, not an ambulance dispatcher\n",
      "You know, Robert, I've never met \"a blending machine operator\" like you.\n",
      "You know, Gary, I've never met \"a cutting machine operator\" like you.\n",
      "Gee, Robert! I'm a title searcher, not a physical therapist\n",
      "Hallelujah, Kevin! I'm a diagnostic medical sonographer, not an operations research analyst\n",
      "Oh god, Gary! I'm a stationary engineer, not a travel guide\n",
      "You know, Steve, I've never met \"a respiratory therapist\" like you.\n",
      "Alas, Robert! I'm a drier operator, not a prosthetist\n",
      "You know, Steve, I've never met \"a religion teacher\" like you.\n",
      "You know, Robert, I've never met \"a museum technician\" like you.\n"
     ]
    }
   ],
   "source": [
    "rules = {\n",
    "    \"origin\": [\"#interjection.capitalize#, #name#! I'm #profession.a#, not #profession.a#\",\n",
    "               \"You know, #name#, I've never met \\\"#profession.a#\\\" like you.\"],\n",
    "    \"interjection\": [\"dammit\",\n",
    "                     \"alas\",\n",
    "                     \"oh god\",\n",
    "                     \"gee\",\n",
    "                     \"good grief\",\n",
    "                     \"hallelujah\",\n",
    "                     \"whoa\",\n",
    "                     \"rats\"],\n",
    "    \"name\": [\"Jim\", \"Robert\", \"Bernie\", \"Adam\", \"Gary\", \"Kevin\", \"Steve\"],\n",
    "    \"profession\": occupations\n",
    "}\n",
    "grammar = tracery.Grammar(rules)\n",
    "grammar.add_modifiers(base_english)\n",
    "for i in range(12):\n",
    "    print(grammar.flatten(\"#origin#\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 206,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Oh cheesewheel cheesewheel\n",
      "cheesewheel baseball climatologists\n",
      "cheesewheel banana\n"
     ]
    }
   ],
   "source": [
    "interjection = random.choice([\"Oh\", \"Rats\", \"Gee\"])\n",
    "rules = {\n",
    "    \"origin\": \"#five#\\n#seven#\\n#five#\",\n",
    "    \"five\": [\"#twosyl# #threesyl#\", \"#threesyl# #twosyl#\", interjection + \" #twosyl# #twosyl#\"],\n",
    "    \"seven\": [\"#twosyl# #twosyl# #fivesyl#\"],\n",
    "    \"twosyl\": [\"cheesewheel\", \"parrot\", \"baseball\"],\n",
    "    \"threesyl\": [\"abacus\", \"mastodon\", \"banana\"],\n",
    "    \"fivesyl\": ['climatologists',\n",
    " 'augustyniak',\n",
    " 'recalculation',\n",
    " 'illusionism',\n",
    " 'exhilarating']\n",
    "}\n",
    "grammar = tracery.Grammar(rules)\n",
    "grammar.add_modifiers(base_english)\n",
    "haiku = grammar.flatten(\"#origin#\")\n",
    "print(haiku)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 191,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Geecheesewheel baseball\n",
      "cheesewheel cheesewheel recalculation\n",
      "banana baseball\n"
     ]
    }
   ],
   "source": [
    "print(haiku)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 178,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pronouncing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 180,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['climatologists',\n",
       " 'augustyniak',\n",
       " 'recalculation',\n",
       " 'illusionism',\n",
       " 'exhilarating']"
      ]
     },
     "execution_count": 180,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "random.sample(pronouncing.search_stresses(\"^.....$\"), 5)"
   ]
  }
 ],
 "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}