crosswords/data/better_grid_building.ipynb

1658 lines
103 KiB
Plaintext
Raw Permalink Normal View History

2021-08-31 13:56:29 +02:00
{
"cells": [
{
"cell_type": "markdown",
"source": [
"# trying to create a better grid builging algorithm"
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 1,
"source": [
"# load stuff\n",
"import json\n",
"import random\n",
"import numpy as np\n",
"from string import digits, ascii_lowercase\n",
"import pathlib\n",
"import logging\n",
"import copy"
],
"outputs": [],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 2,
"source": [
"def get_difficulty_threshold(lang: str, difficulty: int):\n",
" return get_difficulty_threshold.thresholds[lang][difficulty]\n",
"\n",
"\n",
"get_difficulty_threshold.thresholds = {\n",
" 'de': {\n",
" 0: 12,\n",
" 1: 6,\n",
" 2: 0\n",
" },\n",
" 'en': {\n",
" 0: 200,\n",
" 1: 100,\n",
" 2: 10\n",
" }\n",
"}\n",
"\n",
"\n",
"def get_database(lang: str = \"en\") -> dict:\n",
" if lang not in get_database._dbs:\n",
" try:\n",
" file = __file__\n",
" except:\n",
" file = \"./.tmp\"\n",
" current_folder = pathlib.Path(file).parents[0]\n",
" db_file = str(current_folder / f\"{lang}.json\")\n",
"\n",
" logging.info(\"loading database: %s\", lang)\n",
"\n",
" with open(db_file, \"r\") as f:\n",
" db = json.load(f)\n",
" get_database._dbs[lang] = db\n",
"\n",
" logging.info(\"database loaded\")\n",
"\n",
" return get_database._dbs[lang]\n",
"\n",
"\n",
"get_database._dbs = {}\n",
"\n",
"def build_inverted_index(db):\n",
"\n",
" inverted_db = {}\n",
"\n",
" inverted_db['#'] = {}\n",
" number_db = inverted_db['#']\n",
"\n",
" for letter in ascii_lowercase:\n",
" inverted_db[letter] = {}\n",
"\n",
" for key, item in db.items():\n",
" try:\n",
" word = item['word']\n",
" norm_word = normalize_word(word)\n",
"\n",
" n = len(norm_word)\n",
"\n",
" if norm_word.isalnum():\n",
"\n",
" for i, letter in enumerate(norm_word):\n",
" letter_db = inverted_db[letter]\n",
" if i not in letter_db:\n",
" letter_db[i] = {}\n",
" letter_db_i = letter_db[i]\n",
" if n not in letter_db_i:\n",
" letter_db_i[n] = []\n",
" if n not in number_db:\n",
" number_db[n] = []\n",
" \n",
" letter_db_i[n].append(key)\n",
" number_db[n].append(key)\n",
" except:\n",
" pass\n",
" #print(\"error processing \" + word)\n",
" \n",
" return inverted_db\n",
"\n",
"def get_inverted_database(lang: str) -> dict:\n",
" if lang not in get_inverted_database._dbs:\n",
" get_inverted_database._dbs[lang] = build_inverted_index(get_database(lang))\n",
" return get_inverted_database._dbs[lang]\n",
"\n",
"get_inverted_database._dbs = {}\n",
" \n",
"\n",
"remove_digits = str.maketrans('', '', digits)\n",
"\n",
"def normalize_word(word: str):\n",
" word = word.translate(remove_digits)\n",
" return word.lower()\n",
"\n",
"def find_suitable_words(constraints: list, db: dict, inverted_db: dict):\n",
" sets = []\n",
"\n",
" n = len(constraints)\n",
" for i,letter in enumerate(constraints):\n",
" if letter == ' ':\n",
" continue\n",
" \n",
" letter_db = inverted_db[letter]\n",
" if i in letter_db:\n",
" i_list = letter_db[i]\n",
" \n",
" if not n in i_list:\n",
" return set()\n",
" \n",
" sets.append(set(i_list[n]))\n",
" \n",
" else:\n",
" return set()\n",
" \n",
" # at least one constraint must be set\n",
" if len(sets) == 0:\n",
" \n",
" # set first letter random and try again\n",
" if n in inverted_db['#']:\n",
" return inverted_db['#'][n]\n",
" return set()\n",
" \n",
" return set.intersection(*sets)\n",
" \n",
"\n"
],
"outputs": [],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 3,
"source": [
"find_suitable_words(list(\" \"), get_database(\"de\"), get_inverted_database(\"de\"))"
],
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"['du',\n",
" 'du',\n",
" 'er',\n",
" 'er',\n",
" 'hi',\n",
" 'hi',\n",
" 'bp',\n",
" 'bp',\n",
" 'ol',\n",
" 'ol',\n",
" 'ei',\n",
" 'ei',\n",
" 'iq',\n",
" 'iq',\n",
" 'we',\n",
" 'we',\n",
" 'cd',\n",
" 'cd',\n",
" 'am',\n",
" 'am',\n",
" 'ha',\n",
" 'ha',\n",
" 'ei0',\n",
" 'ei0',\n",
" 'hi0',\n",
" 'hi0',\n",
" 'hi1',\n",
" 'hi1',\n",
" 'es',\n",
" 'es',\n",
" 'ai',\n",
" 'ai',\n",
" 'aa',\n",
" 'aa',\n",
" 'ag',\n",
" 'ag',\n",
" 'ag0',\n",
" 'ag0',\n",
" 'db',\n",
" 'db',\n",
" 'fc',\n",
" 'fc',\n",
" 'ab',\n",
" 'ab',\n",
" 'ab0',\n",
" 'ab0',\n",
" 'hp',\n",
" 'hp',\n",
" 'ms',\n",
" 'ms',\n",
" 'pa',\n",
" 'pa',\n",
" 'eh',\n",
" 'eh',\n",
" 'eh1',\n",
" 'eh1',\n",
" 'fs',\n",
" 'fs',\n",
" 'it',\n",
" 'it',\n",
" 'ki',\n",
" 'ki',\n",
" 'pc',\n",
" 'pc',\n",
" 'pc0',\n",
" 'pc0',\n",
" 'um',\n",
" 'um',\n",
" 'um0',\n",
" 'um0',\n",
" 'hr',\n",
" 'hr',\n",
" 'in',\n",
" 'in',\n",
" 'im',\n",
" 'im',\n",
" 'ir',\n",
" 'ir',\n",
" 'hf',\n",
" 'hf',\n",
" 'cu',\n",
" 'cu',\n",
" 'ja',\n",
" 'ja',\n",
" 'ja0',\n",
" 'ja0',\n",
" 'ja1',\n",
" 'ja1',\n",
" 'aa0',\n",
" 'aa0',\n",
" 'aa2',\n",
" 'aa2',\n",
" 'dm',\n",
" 'dm',\n",
" 'zu',\n",
" 'zu',\n",
" 'zu1',\n",
" 'zu1',\n",
" 'zu2',\n",
" 'zu2',\n",
" 'zu3',\n",
" 'zu3',\n",
" 'zu4',\n",
" 'zu4',\n",
" 'an',\n",
" 'an',\n",
" 'an0',\n",
" 'an0',\n",
" 'so',\n",
" 'so',\n",
" 'so0',\n",
" 'so0',\n",
" 'so1',\n",
" 'so1',\n",
" 'so3',\n",
" 'so3',\n",
" 'af',\n",
" 'af',\n",
" 'lg',\n",
" 'lg',\n",
" 'nf',\n",
" 'nf',\n",
" 'nl',\n",
" 'nl',\n",
" 'da1',\n",
" 'da1',\n",
" 'wo',\n",
" 'wo',\n",
" 'wo0',\n",
" 'wo0',\n",
" 'wo1',\n",
" 'wo1',\n",
" 'ab1',\n",
" 'ab1',\n",
" 'ai0',\n",
" 'ai0',\n",
" 'dj',\n",
" 'dj',\n",
" 'on0',\n",
" 'on0',\n",
" 'ob0',\n",
" 'ob0',\n",
" 'am1',\n",
" 'am1',\n",
" 'ta',\n",
" 'ta',\n",
" 'to',\n",
" 'to',\n",
" 'kw',\n",
" 'kw',\n",
" 'dv',\n",
" 'dv',\n",
" 'dv0',\n",
" 'dv0',\n",
" 'mr',\n",
" 'mr',\n",
" 'zv',\n",
" 'zv',\n",
" 'kg',\n",
" 'kg',\n",
" 'ap',\n",
" 'ap',\n",
" 'ao',\n",
" 'ao',\n",
" 'av',\n",
" 'av',\n",
" 'ba',\n",
" 'ba',\n",
" 'bg',\n",
" 'bg',\n",
" 'bk',\n",
" 'bk',\n",
" 'br',\n",
" 'br',\n",
" 'bt',\n",
" 'bt',\n",
" 'eg0',\n",
" 'eg0',\n",
" 'eg1',\n",
" 'eg1',\n",
" 'fg0',\n",
" 'fg0',\n",
" 'fm0',\n",
" 'fm0',\n",
" 'pd',\n",
" 'pd',\n",
" 'fw',\n",
" 'fw',\n",
" 'ra',\n",
" 'ra',\n",
" 'qm0',\n",
" 'qm0',\n",
" 'rg',\n",
" 'rg',\n",
" 'wm',\n",
" 'wm',\n",
" 'sg',\n",
" 'sg',\n",
" 'va',\n",
" 'va',\n",
" 'vg',\n",
" 'vg',\n",
" 'vz',\n",
" 'vz',\n",
" 'wd',\n",
" 'wd',\n",
" 'wp',\n",
" 'wp',\n",
" 'zh',\n",
" 'zh',\n",
" 'ct',\n",
" 'ct',\n",
" 'dg',\n",
" 'dg',\n",
" 'dh',\n",
" 'dh',\n",
" 'dt',\n",
" 'dt',\n",
" 'ep',\n",
" 'ep',\n",
" 'hk',\n",
" 'hk',\n",
" 'km',\n",
" 'km',\n",
" 'kp',\n",
" 'kp',\n",
" 'mk',\n",
" 'mk',\n",
" 'mm',\n",
" 'mm',\n",
" 'og',\n",
" 'og',\n",
" 'ot',\n",
" 'ot',\n",
" 'rh',\n",
" 'rh',\n",
" 'as0',\n",
" 'as0',\n",
" 'as1',\n",
" 'as1',\n",
" 'be',\n",
" 'be',\n",
" 'es2',\n",
" 'es2',\n",
" 'fr',\n",
" 'fr',\n",
" 'mo',\n",
" 'mo',\n",
" 'os',\n",
" 'os',\n",
" 'os0',\n",
" 'os0',\n",
" 'po',\n",
" 'po',\n",
" 'po0',\n",
" 'po0',\n",
" 'ra0',\n",
" 'ra0',\n",
" 're0',\n",
" 're0',\n",
" 'tb',\n",
" 'tb',\n",
" 'np',\n",
" 'np',\n",
" 'ps',\n",
" 'ps',\n",
" 'sv',\n",
" 'sv',\n",
" 'xl',\n",
" 'xl',\n",
" 'bw',\n",
" 'bw',\n",
" 'bh',\n",
" 'bh',\n",
" 'ss',\n",
" 'ss',\n",
" 'sw',\n",
" 'sw',\n",
" 'ac',\n",
" 'ac',\n",
" 'ak',\n",
" 'ak',\n",
" 'aw',\n",
" 'aw',\n",
" 'az',\n",
" 'az',\n",
" 'bb',\n",
" 'bb',\n",
" 'bl',\n",
" 'bl',\n",
" 'bm',\n",
" 'bm',\n",
" 'bs',\n",
" 'bs',\n",
" 'bz',\n",
" 'bz',\n",
" 'cb',\n",
" 'cb',\n",
" 'ww',\n",
" 'ww',\n",
" 'di',\n",
" 'di',\n",
" 'do0',\n",
" 'do0',\n",
" 'rg0',\n",
" 'rg0',\n",
" 'ho0',\n",
" 'ho0',\n",
" 'tv',\n",
" 'tv',\n",
" 'oh',\n",
" 'oh',\n",
" 'nt',\n",
" 'nt',\n",
" 'wc',\n",
" 'wc',\n",
" 'mp',\n",
" 'mp',\n",
" 'na',\n",
" 'na',\n",
" 'pk',\n",
" 'pk',\n",
" 'op',\n",
" 'op',\n",
" 'sp',\n",
" 'sp',\n",
" 'ka',\n",
" 'ka',\n",
" 'kp0',\n",
" 'kp0',\n",
" 'rm',\n",
" 'rm',\n",
" 'lw',\n",
" 'lw',\n",
" 'mw',\n",
" 'mw',\n",
" 'pp',\n",
" 'pp',\n",
" 'sb',\n",
" 'sb',\n",
" 'nu1',\n",
" 'nu1',\n",
" 'gz',\n",
" 'gz',\n",
" 'ae0',\n",
" 'ae0',\n",
" 'at',\n",
" 'at',\n",
" 'be0',\n",
" 'be0',\n",
" 'pi',\n",
" 'pi',\n",
" 'vn',\n",
" 'vn',\n",
" 'ss0',\n",
" 'ss0',\n",
" 'ss1',\n",
" 'ss1',\n",
" 'kp1',\n",
" 'kp1',\n",
" 'sz',\n",
" 'sz',\n",
" 'hm',\n",
" 'hm',\n",
" 'ld',\n",
" 'ld',\n",
" 'wu',\n",
" 'wu',\n",
" 'kv',\n",
" 'kv',\n",
" 'vu',\n",
" 'vu',\n",
" 'za',\n",
" 'za',\n",
" 'wg',\n",
" 'wg',\n",
" 'tg',\n",
" 'tg',\n",
" 'ja2',\n",
" 'ja2',\n",
" 'mc',\n",
" 'mc',\n",
" 'ur',\n",
" 'ur',\n",
" 'id',\n",
" 'id',\n",
" 'my',\n",
" 'my',\n",
" 'kl',\n",
" 'kl',\n",
" 'sd',\n",
" 'sd',\n",
" 'md',\n",
" 'md',\n",
" 'im0',\n",
" 'im0',\n",
" 'dw',\n",
" 'dw',\n",
" 'ny',\n",
" 'ny',\n",
" 'nv',\n",
" 'nv',\n",
" 'dz0',\n",
" 'dz0',\n",
" 'et',\n",
" 'et',\n",
" 'nn',\n",
" 'nn',\n",
" 'ff',\n",
" 'ff',\n",
" 'ff0',\n",
" 'ff0',\n",
" 'vv',\n",
" 'vv',\n",
" 'gr',\n",
" 'gr',\n",
" 'ig',\n",
" 'ig',\n",
" 'vp',\n",
" 'vp',\n",
" 'do1',\n",
" 'do1',\n",
" 'da2',\n",
" 'da2',\n",
" 'dk',\n",
" 'dk',\n",
" 'dp',\n",
" 'dp',\n",
" 'de',\n",
" 'de',\n",
" 'ec',\n",
" 'ec',\n",
" 'er2',\n",
" 'er2',\n",
" 'ga',\n",
" 'ga',\n",
" 'gd',\n",
" 'gd',\n",
" 'ug',\n",
" 'ug',\n",
" 'mg0',\n",
" 'mg0',\n",
" 'ic',\n",
" 'ic',\n",
" 'rb',\n",
" 'rb',\n",
" 'gb',\n",
" 'gb',\n",
" 'zr',\n",
" 'zr',\n",
" 'ns',\n",
" 'ns',\n",
" 'kr',\n",
" 'kr',\n",
" 'hz',\n",
" 'hz',\n",
" 'nf0',\n",
" 'nf0',\n",
" 'sm0',\n",
" 'sm0',\n",
" 'en',\n",
" 'en',\n",
" 'qi',\n",
" 'qi',\n",
" 'gv',\n",
" 'gv',\n",
" 'uz0',\n",
" 'uz0',\n",
" 'kh',\n",
" 'kh',\n",
" 'gf',\n",
" 'gf',\n",
" 'tk',\n",
" 'tk',\n",
" 'hc',\n",
" 'hc',\n",
" 'zk',\n",
" 'zk',\n",
" 'lb',\n",
" 'lb',\n",
" 'wr',\n",
" 'wr',\n",
" 'st',\n",
" 'st',\n",
" 'te',\n",
" 'te',\n",
" 'hb',\n",
" 'hb',\n",
" 'vj',\n",
" 'vj',\n",
" 'us',\n",
" 'us',\n",
" 'on1',\n",
" 'on1',\n",
" 'on2',\n",
" 'on2',\n",
" 'vr',\n",
" 'vr']"
]
},
"metadata": {},
"execution_count": 3
}
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 4,
"source": [
"class NoDataException(Exception):\n",
" pass\n",
"\n",
"\n",
"class WordInfo(object):\n",
" def __init__(self, word: str, y: int, x: int, is_vertical: bool, database: dict, opposite_prefix: str = \"opposite of\", synonym_prefix: str = \"other word for\"):\n",
" self._dictionary_database = database\n",
" self._y = y\n",
" self._x = x\n",
" self._word = word\n",
" self._hint = None\n",
" self._is_vertical = is_vertical\n",
"\n",
" self.opposite_prefix = opposite_prefix\n",
" self.synonym_prefix = synonym_prefix\n",
"\n",
" self.choose_info()\n",
"\n",
" def get_attribute(self, attr: str):\n",
" attr = self._dictionary_database[self._word][attr]\n",
" if attr is None or len(attr) == 0:\n",
" raise NoDataException\n",
" return attr\n",
"\n",
" def get_best_antonym(self) -> str:\n",
" antonyms = self.get_attribute(\"antonyms\")\n",
" return random.choice(antonyms)\n",
"\n",
" def get_best_synonym(self) -> str:\n",
" synonyms = self.get_attribute(\"synonyms\")\n",
" return random.choice(synonyms)\n",
"\n",
" def get_best_sense(self) -> str:\n",
" senses = self.get_attribute(\"senses\")\n",
" return random.choice(senses)\n",
"\n",
" def choose_info(self, n: int = 1):\n",
" assert n <= 4\n",
" # first choose antonyms, then synonyms, then senses\n",
"\n",
" hints = []\n",
"\n",
" try:\n",
" antonyms = self.get_attribute(\"antonyms\")\n",
" antonyms = [f\"{self.opposite_prefix} {w}\" for w in antonyms]\n",
" hints = hints + antonyms\n",
" except NoDataException:\n",
" pass\n",
"\n",
" try:\n",
" synonyms = self.get_attribute(\"synonyms\")\n",
" synonyms = [f\"{self.synonym_prefix} {w}\" for w in synonyms]\n",
"\n",
" hints = hints + synonyms\n",
" except NoDataException:\n",
" pass\n",
"\n",
" try:\n",
" senses = self.get_attribute(\"senses\")\n",
" hints = hints + senses\n",
" except NoDataException:\n",
" pass\n",
"\n",
" final_hints = []\n",
" for i in range(n):\n",
" choice = random.choice(hints)\n",
" hints.remove(choice)\n",
" final_hints.append(choice)\n",
"\n",
" if n == 1:\n",
" self._hint = final_hints[0]\n",
" return\n",
"\n",
" hint_symbols = ['a)', 'b)', 'c)', 'd)']\n",
"\n",
" self._hint = \"\"\n",
" for i in range(n):\n",
" self._hint += hint_symbols[i] + \" \" + final_hints[i] + \". \"\n",
"\n",
" def get_hint(self) -> str:\n",
" return self._hint\n",
"\n",
" def get_hint_location(self):\n",
" x = self._x if self._is_vertical else self._x - 1\n",
" y = self._y - 1 if self._is_vertical else self._y\n",
" return (y, x)\n",
"\n",
" def is_vertical(self):\n",
" return self._is_vertical\n"
],
"outputs": [],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 64,
"source": [
"def create_base_grid(n:int, min_word_length: int = 4, max_word_length: int = 15, filter_length: int = 2):\n",
" w = n\n",
" h = n\n",
" horizontal_grid = np.full(shape=(h,w), dtype=np.bool, fill_value=False)\n",
" vertical_grid = np.full(shape=(h,w), dtype=np.bool, fill_value=False)\n",
"\n",
"\n",
" for y in range(h):\n",
" x = 0\n",
" while x < w:\n",
" rand_max = random.randint(min_word_length, max_word_length)\n",
" rand_length = random.randint(min_word_length, rand_max)#\n",
"\n",
" x_next = min(x + rand_length, w)\n",
" horizontal_grid[y,x:x_next] = True\n",
" x = x_next + 1\n",
" \n",
" for x in range(w):\n",
" y = 0\n",
" while y < h:\n",
" rand_max = random.randint(min_word_length, max_word_length)\n",
" rand_length = random.randint(min_word_length, rand_max)\n",
" y_next = min(y + rand_length, h)\n",
" vertical_grid[y:y_next, x] = True\n",
" y = y_next + 1\n",
" \n",
"\n",
" \n",
" for y in range(0,h,2):\n",
" horizontal_grid[y,0] = False\n",
" horizontal_grid[y,-1] = False\n",
"\n",
" \n",
" \n",
" for x in range(2,w,2):\n",
" vertical_grid[0,x] = False\n",
" vertical_grid[-1,x] = False\n",
"\n",
" for y in range(2,h,2):\n",
" for x in range(2,w,2):\n",
" if random.randint(0,3) == 0:\n",
" horizontal_grid[y,x] = False\n",
"\n",
"\n",
"\n",
" combined = np.logical_and(horizontal_grid, vertical_grid)\n",
"\n",
" #combined = np.logical_and(horizontal_grid, horizontal_grid.transpose())\n",
" \n",
"\n",
"\n",
" # clean up areas that are to small\n",
" old_combined = combined.copy()\n",
" first_try = True\n",
"\n",
" while np.sum(old_combined.astype(int)) != np.sum(combined.astype(int)) or first_try:\n",
"\n",
" first_try = False\n",
"\n",
" count_x = np.full(shape=(h,w), dtype=np.int, fill_value=0)\n",
" count_y = np.full(shape=(h,w), dtype=np.int, fill_value=0)\n",
"\n",
" for x in range(w):\n",
" last_y = 0\n",
" for y in range(h):\n",
" if not combined[y,x] and last_y != y: \n",
" count_y[last_y:y,x] = y - last_y\n",
" last_y = y + 1\n",
" \n",
" if last_y < h:\n",
" count_y[last_y:h,x] = h - last_y\n",
" \n",
" for y in range(h):\n",
" last_x = 0\n",
" for x in range(w):\n",
" if not combined[y,x] and last_x != x: \n",
" count_x[y,last_x:x] = x - last_x\n",
" last_x = x + 1\n",
" \n",
" if last_x < w:\n",
" count_x[y, last_x:w] = w - last_x\n",
"\n",
" count_mask = np.logical_and(count_x < filter_length, count_y < filter_length)\n",
" old_combined = combined.copy()\n",
" combined[count_mask] = False\n",
"\n",
"\n",
" # clean up areas that are too small\n",
"\n",
" reachable = np.full(shape=(h,w), dtype=np.bool, fill_value=False)\n",
"\n",
" old_reachable = reachable.copy()\n",
"\n",
" reachable[1,0] = True\n",
" reachable[0,1] = True\n",
"\n",
" \n",
" i = 0\n",
" while np.sum(old_reachable.astype(int)) != np.sum(reachable.astype(int)):\n",
" old_reachable = reachable.copy()\n",
" i += 1\n",
" for y in range(h):\n",
" for x in range(w):\n",
" if x > 0 and (reachable[y,x-1] and combined[y,x-1]) or x < w-1 and (reachable[y,x+1] and combined[y,x+1]):\n",
" reachable[y,x] = True\n",
" continue\n",
" if y > 0 and (reachable[y-1,x] and combined[y-1,x]) or y < h-1 and (reachable[y+1,x] and combined[y+1,x]):\n",
" reachable[y,x] = True\n",
" \n",
" #print(\"flooded after \" + str(i) + \" iterations\")\n",
" \n",
" combined = np.logical_and(combined, reachable)\n",
"\n",
" return combined\n"
],
"outputs": [],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 6,
"source": [
"def create_base_grid(n: int):\n",
" grid = np.full(shape=(n,n), dtype=np.bool, fill_value=True)\n",
" for y in range(n):\n",
" for x in range(n):\n",
" if y % 2 == 1 and x % 2 == 1 and not random.randint(0,8) == 0:\n",
" grid[y,x] = False\n",
" \n",
" else:\n",
" if y % 2 != x % 2:\n",
" if random.randint(0,3) == 0:\n",
" grid[y,x] = False\n",
" else:\n",
" if random.randint(0,8) == 0:\n",
" pass\n",
" #grid[y,x] = False\n",
"\n",
" return grid\n",
" #return np.logical_and(grid, grid.transpose())\n",
"\n",
" "
],
"outputs": [],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 65,
"source": [
"%%prun\n",
"import matplotlib.pyplot as plt\n",
"\n",
"base_grid = create_base_grid(20)"
],
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" "
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" 2317 function calls in 0.008 seconds\n",
"\n",
" Ordered by: internal time\n",
"\n",
" ncalls tottime percall cumtime percall filename:lineno(function)\n",
" 1 0.006 0.006 0.008 0.008 <ipython-input-64-c07db7426ad7>:1(create_base_grid)\n",
" 18 0.001 0.000 0.001 0.000 {method 'copy' of 'numpy.ndarray' objects}\n",
" 311 0.000 0.000 0.001 0.000 random.py:291(randrange)\n",
" 311 0.000 0.000 0.000 0.000 random.py:238(_randbelow_with_getrandbits)\n",
" 36 0.000 0.000 0.000 0.000 {method 'astype' of 'numpy.ndarray' objects}\n",
" 36 0.000 0.000 0.000 0.000 {method 'reduce' of 'numpy.ufunc' objects}\n",
" 311 0.000 0.000 0.001 0.000 random.py:335(randint)\n",
" 36 0.000 0.000 0.000 0.000 fromnumeric.py:70(_wrapreduction)\n",
" 1 0.000 0.000 0.008 0.008 {built-in method builtins.exec}\n",
" 36 0.000 0.000 0.000 0.000 fromnumeric.py:2105(sum)\n",
" 43 0.000 0.000 0.001 0.000 {built-in method numpy.core._multiarray_umath.implement_array_function}\n",
" 541 0.000 0.000 0.000 0.000 {method 'getrandbits' of '_random.Random' objects}\n",
" 36 0.000 0.000 0.001 0.000 <__array_function__ internals>:2(sum)\n",
" 115 0.000 0.000 0.000 0.000 {built-in method builtins.min}\n",
" 311 0.000 0.000 0.000 0.000 {method 'bit_length' of 'int' objects}\n",
" 36 0.000 0.000 0.000 0.000 fromnumeric.py:71(<dictcomp>)\n",
" 7 0.000 0.000 0.000 0.000 numeric.py:268(full)\n",
" 7 0.000 0.000 0.000 0.000 {built-in method numpy.empty}\n",
" 7 0.000 0.000 0.000 0.000 <__array_function__ internals>:2(copyto)\n",
" 1 0.000 0.000 0.008 0.008 <string>:1(<module>)\n",
" 36 0.000 0.000 0.000 0.000 {built-in method builtins.isinstance}\n",
" 36 0.000 0.000 0.000 0.000 fromnumeric.py:2100(_sum_dispatcher)\n",
" 36 0.000 0.000 0.000 0.000 {method 'items' of 'dict' objects}\n",
" 7 0.000 0.000 0.000 0.000 multiarray.py:1043(copyto)\n",
" 1 0.000 0.000 0.000 0.000 {method 'disable' of '_lsprof.Profiler' objects}"
]
}
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 66,
"source": [
"\n",
"\n",
"\n",
"plt.imshow(base_grid)\n",
"plt.colorbar()\n",
"plt.show()\n"
],
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 432x288 with 2 Axes>"
],
"image/svg+xml": "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n<!-- Created with matplotlib (https://matplotlib.org/) -->\n<svg height=\"252.317344pt\" version=\"1.1\" viewBox=\"0 0 311.62075 252.317344\" width=\"311.62075pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n <metadata>\n <rdf:RDF xmlns:cc=\"http://creativecommons.org/ns#\" xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\">\n <cc:Work>\n <dc:type rdf:resource=\"http://purl.org/dc/dcmitype/StillImage\"/>\n <dc:date>2021-08-23T14:04:57.641931</dc:date>\n <dc:format>image/svg+xml</dc:format>\n <dc:creator>\n <cc:Agent>\n <dc:title>Matplotlib v3.3.4, https://matplotlib.org/</dc:title>\n </cc:Agent>\n </dc:creator>\n </cc:Work>\n </rdf:RDF>\n </metadata>\n <defs>\n <style type=\"text/css\">*{stroke-linecap:butt;stroke-linejoin:round;}</style>\n </defs>\n <g id=\"figure_1\">\n <g id=\"patch_1\">\n <path d=\"M 0 252.317344 \nL 311.62075 252.317344 \nL 311.62075 0 \nL 0 0 \nz\n\" style=\"fill:none;\"/>\n </g>\n <g id=\"axes_1\">\n <g id=\"patch_2\">\n <path d=\"M 36.465625 228.439219 \nL 253.905625 228.439219 \nL 253.905625 10.999219 \nL 36.465625 10.999219 \nz\n\" style=\"fill:#ffffff;\"/>\n </g>\n <g clip-path=\"url(#p68de2f1ea0)\">\n <image height=\"218\" id=\"imagee93f9e6ce7\" transform=\"scale(1 -1)translate(0 -218)\" width=\"218\" x=\"36.465625\" xlink:href=\"data:image/png;base64,\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\" y=\"-10.439219\"/>\n </g>\n <g id=\"matplotlib.axis_1\">\n <g id=\"xtick_1\">\n <g id=\"line2d_1\">\n <defs>\n <path d=\"M 0 0 \nL 0 3.5 \n\" id=\"ma462419da4\" style=\"stroke:#000000;stroke-width:0.8;\"/>\n </defs>\n <g>\n <use style=\"stroke:#000000;stroke-width:0.8;\" x=\"41.901625\" xlink:href=\"#ma462419da4\" y=\"228.439219\"/>\n </g>\n </g>\n <g id=\"text_1\">\n <!-- 0 -->\n <g transform=\"translate(38.720375 243.037656)scale(0.1 -0.1)\">\n <defs>\n <path d=\"M 31.78125 66.40625 \nQ 24.171875 66.40625 20.328125 58.90625 \nQ 16.5 51.421875 16.5 36.375 \nQ 16.5 21.390625 20.328125 13.890625 \nQ 24.171875 6.390625 31.78125 6.390625 \nQ 39.453125 6.390625 43.28125 13.890625 \nQ 47.125 21.390625 47.125 36.375 \nQ 47.125 51.421875 43.28125 58.90625 \nQ 39.453125 66.40625 31.78125 66.40625 \nz\nM 31.78125 74.21875 \nQ 44.046875 74.21875 50.515625 64.515625 \nQ 56.984375 54.828125 56.984375 36.375 \nQ 56.984375 17.96875 50.515625 8.265625 \nQ 44.046875 -1.421875 31.781
"image/png": "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
},
"metadata": {
"needs_background": "light"
}
}
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 112,
"source": [
"class GridWord(object):\n",
"\n",
" @classmethod\n",
" def from_base_grid(cls, base_grid: np.ndarray, min_word_length = 2) -> list:\n",
"\n",
" grid_words = []\n",
" # a word starts after each non-letter field, and at the beginning if there is\n",
" # a letter field at the beginning of a row/column\n",
" h, w = base_grid.shape\n",
"\n",
" # first get all horizontal words\n",
" for y in range(h):\n",
" word_start = 0\n",
" for x in range(w):\n",
" if not base_grid[y, x]:\n",
" if word_start < x:\n",
" word = GridWord(\n",
" y=y,\n",
" x=word_start,\n",
" is_vertical=False,\n",
" length=x - word_start\n",
" )\n",
" if word.length >= min_word_length:\n",
" grid_words.append(word)\n",
" \n",
" word_start = x + 1\n",
"\n",
" if word_start < w:\n",
" word = GridWord(\n",
" y=y,\n",
" x=word_start,\n",
" is_vertical=False,\n",
" length=w - word_start\n",
" )\n",
" if word.length >= min_word_length:\n",
" grid_words.append(word)\n",
" \n",
" # then get all vertical word slots\n",
" for x in range(w):\n",
" word_start = 0\n",
" for y in range(h):\n",
" if not base_grid[y, x]:\n",
" if word_start < y:\n",
" word = GridWord(\n",
" y=word_start,\n",
" x=x,\n",
" is_vertical=True,\n",
" length=y - word_start\n",
" )\n",
"\n",
" if word.length >= min_word_length:\n",
" grid_words.append(word)\n",
" \n",
" word_start = y + 1\n",
"\n",
" if word_start < h:\n",
" word = GridWord(\n",
" y=word_start,\n",
" x=x,\n",
" is_vertical=True,\n",
" length=h - word_start\n",
" )\n",
" if word.length >= min_word_length:\n",
" grid_words.append(word)\n",
" \n",
" for i in range(len(grid_words)):\n",
" grid_words[i].id = i\n",
" for j in range(i):\n",
" word_a = grid_words[i]\n",
" word_b = grid_words[j]\n",
"\n",
" if word_a.check_connected(word_b):\n",
" word_a.connect_word(word_b)\n",
" word_b.connect_word(word_a)\n",
"\n",
" return grid_words\n",
"\n",
" def __init__(self, y: int, x: int, is_vertical: bool, length: int, id: int = None) -> None:\n",
" self.x = x\n",
" self.y = y\n",
" self.is_vertical = is_vertical\n",
" self.length = length\n",
" self.word_key = None\n",
" self.connected_words = []\n",
" self.id = id\n",
"\n",
" self.candidate_cache = []\n",
" self.candidate_cache_key = \"\"\n",
" \n",
" \n",
" def get_letters(self, letter_grid: np.ndarray) -> list:\n",
" if self.is_vertical:\n",
" return letter_grid[self.y:self.y+self.length, self.x].flatten()\n",
" return letter_grid[self.y, self.x: self.x + self.length].flatten()\n",
" \n",
" def set_letters(self, letters, letter_grid: np.ndarray):\n",
" if self.is_vertical:\n",
" letter_grid[self.y:self.y + self.length, self.x] = letters\n",
" else:\n",
" letter_grid[self.y, self.x: self.x + self.length] = letters\n",
" \n",
" def set_word_key(self, word_key:str):\n",
" self.word_key = word_key\n",
" \n",
" def connect_word(self, grid_word):\n",
" self.connected_words.append(grid_word)\n",
" \n",
" \n",
" \n",
" def check_connected(self, grid_word):\n",
" if self.is_vertical == grid_word.is_vertical:\n",
" return False\n",
" \n",
" if self.is_vertical:\n",
" if self.y > grid_word.y:\n",
" return False\n",
" if self.y + self.length <= grid_word.y:\n",
" return False\n",
" \n",
" if self.x >= grid_word.x + grid_word.length:\n",
" return False\n",
" \n",
" if self.x < grid_word.x:\n",
" return False\n",
" \n",
" else:\n",
" if self.x > grid_word.x:\n",
" return False\n",
" if self.x + self.length <= grid_word.x:\n",
" return False\n",
" if self.y >= grid_word.y + grid_word.length:\n",
" return False\n",
" if self.y < grid_word.y:\n",
" return False\n",
" \n",
" return True\n",
" \n",
" def get_candidates(self, letter_grid, db, inverted_db):\n",
" letters = self.get_letters(letter_grid)\n",
" word = \"\".join(letters) \n",
" if word == self.candidate_cache_key:\n",
" return self.candidate_cache\n",
" self.candidate_cache = find_suitable_words(letters, db, inverted_db)\n",
" self.candidate_cache_key = word\n",
" return self.candidate_cache\n",
" \n",
" def get_connected_words(self):\n",
" return self.connected_words\n",
"\n",
" \n",
"\n",
"\n",
"class GridCreationState(object):\n",
" def __init__(self, base_grid, db, inverted_db, letter_grid = None, grid_words = None, final_grid_words = None, used_ids = None) -> None:\n",
" self.base_grid = base_grid\n",
" self.shape = base_grid.shape\n",
" self.db = db\n",
" self.inverted_db = inverted_db\n",
" \n",
"\n",
" if letter_grid is None:\n",
" self.letter_grid = np.full(shape = self.shape, fill_value=' ', dtype=np.unicode)\n",
" else:\n",
" self.letter_grid = letter_grid\n",
" \n",
" if grid_words is None:\n",
" self.grid_words = GridWord.from_base_grid(base_grid=base_grid)\n",
" else:\n",
" self.grid_words = grid_words\n",
"\n",
" \n",
" if final_grid_words is None:\n",
" self.final_grid_words = []\n",
" else:\n",
" self.final_grid_words = final_grid_words\n",
" \n",
" if used_ids is None:\n",
" self.used_ids = [[False]] * len(self.grid_words)\n",
" else:\n",
" self.used_ids = used_ids\n",
" \n",
"\n",
"\n",
" def copy(self):\n",
" return GridCreationState(self.base_grid, self.db, self.inverted_db, self.letter_grid.copy(), self.grid_words.copy(), self.final_grid_words.copy(), self.used_ids.copy())\n",
" \n",
"\n",
" def set_random_word(self, last_word = None, n_retries = 1, max_preselected = 10):\n",
" # choose random word\n",
"\n",
" preselected_id = None\n",
" preselected_candidates = []\n",
"\n",
" for word in self.final_grid_words:\n",
" connected_words = word.get_connected_words()\n",
" #random.shuffle(connected_words)\n",
" for connected_word in connected_words:\n",
" if not self.used_ids[connected_word.id]:\n",
" preselected_id = connected_word.id\n",
" for i in range(preselected_id):\n",
" if self.used_ids[i]:\n",
" preselected_id -= 1\n",
" preselected_candidates.append(preselected_id)\n",
" \n",
" \n",
" if len(preselected_candidates) > 0:\n",
" random.shuffle(preselected_candidates)\n",
" break\n",
" \n",
" \n",
"\n",
"\n",
" n_tries = 1\n",
" if preselected_id is not None:\n",
" n_tries = min(len(preselected_candidates), max_preselected)\n",
" else:\n",
" random_index = random.randint(0, len(self.grid_words) - 1)\n",
" \n",
" for i in range(n_tries):\n",
" if preselected_id is not None:\n",
" random_index = preselected_candidates[i]\n",
" grid_word = self.grid_words[random_index]\n",
" \n",
" candidates_raw = list(grid_word.get_candidates(self.letter_grid, self.db, self.inverted_db))\n",
" \n",
" \n",
" if len(candidates_raw) > 0:\n",
" for j in range(min(n_retries, len(candidates_raw))):\n",
" word_key = candidates_raw[j]\n",
" word = normalize_word(self.db[word_key]['word'])\n",
"\n",
" new_grid = self.letter_grid.copy()\n",
"\n",
" grid_word.set_letters(list(word), new_grid)\n",
"\n",
" for word in grid_word.get_connected_words():\n",
" if word.id not in self.used_ids:\n",
" n_cands = len(word.get_candidates(new_grid, self.db, self.inverted_db))\n",
" if n_cands == 0:\n",
" return None\n",
"\n",
"\n",
" self.letter_grid = new_grid\n",
" grid_word.set_word_key(word_key)\n",
" self.used_ids[grid_word.id] = True\n",
" self.final_grid_words.append(grid_word)\n",
" del(self.grid_words[random_index])\n",
"\n",
" return grid_word\n",
" \n",
" return None\n",
" \n",
" \n",
" def fill(self, depth = 0, last_word = None):\n",
" if depth % 5 == 0:\n",
" print(\"depth\", depth)\n",
"\n",
" n_retries = 100 if depth == 0 else 2\n",
" if len(self.grid_words) == 0:\n",
" return self\n",
"\n",
"\n",
" \n",
" state_copy = self.copy()\n",
" grid_word = None\n",
" for _ in range(n_retries):\n",
" \n",
" \n",
" grid_word = state_copy.set_random_word(last_word = last_word, n_retries=20, max_preselected = 2)\n",
" if grid_word is not None:\n",
" \n",
" final_state = state_copy.fill(\n",
" depth = depth + 1,\n",
" last_word = grid_word)\n",
" if final_state is not None:\n",
" return final_state\n",
" return None\n",
"\n",
" \n",
" \n",
"\n",
"\n",
"\n",
" \n"
],
"outputs": [],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 114,
"source": [
"%%prun\n",
"base_grid = create_base_grid(14, min_word_length=3, max_word_length=12)\n",
"\n",
"db = get_database(\"de\")\n",
"inverted_db = get_inverted_database(\"de\")\n",
"\n",
"grid_state = GridCreationState(base_grid, db, inverted_db)\n",
"\n",
"final_state = grid_state.fill()\n",
"\n",
"print(final_state is not None)"
],
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"depth 0\n",
"True\n",
" "
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" 1490 function calls (1488 primitive calls) in 0.004 seconds\n",
"\n",
" Ordered by: internal time\n",
"\n",
" ncalls tottime percall cumtime percall filename:lineno(function)\n",
" 1 0.002 0.002 0.003 0.003 <ipython-input-64-c07db7426ad7>:1(create_base_grid)\n",
" 14 0.000 0.000 0.000 0.000 {method 'astype' of 'numpy.ndarray' objects}\n",
" 14 0.000 0.000 0.000 0.000 {method 'reduce' of 'numpy.ufunc' objects}\n",
" 1 0.000 0.000 0.000 0.000 <ipython-input-112-58b0ffc6eba3>:3(from_base_grid)\n",
" 184 0.000 0.000 0.000 0.000 random.py:238(_randbelow_with_getrandbits)\n",
" 184 0.000 0.000 0.000 0.000 random.py:291(randrange)\n",
" 2 0.000 0.000 0.000 0.000 <ipython-input-112-58b0ffc6eba3>:188(set_random_word)\n",
" 2 0.000 0.000 0.000 0.000 <ipython-input-2-026304d5612b>:92(find_suitable_words)\n",
" 1 0.000 0.000 0.004 0.004 {built-in method builtins.exec}\n",
" 7 0.000 0.000 0.000 0.000 socket.py:438(send)\n",
" 11 0.000 0.000 0.000 0.000 {method 'copy' of 'numpy.ndarray' objects}\n",
" 3/1 0.000 0.000 0.001 0.001 <ipython-input-112-58b0ffc6eba3>:254(fill)\n",
" 184 0.000 0.000 0.000 0.000 random.py:335(randint)\n",
" 22 0.000 0.000 0.000 0.000 {built-in method numpy.core._multiarray_umath.implement_array_function}\n",
" 14 0.000 0.000 0.000 0.000 fromnumeric.py:70(_wrapreduction)\n",
" 14 0.000 0.000 0.000 0.000 fromnumeric.py:2105(sum)\n",
" 3 0.000 0.000 0.000 0.000 {method 'join' of 'str' objects}\n",
" 315 0.000 0.000 0.000 0.000 {method 'getrandbits' of '_random.Random' objects}\n",
" 7 0.000 0.000 0.000 0.000 iostream.py:195(schedule)\n",
" 14 0.000 0.000 0.000 0.000 <__array_function__ internals>:2(sum)\n",
" 1 0.000 0.000 0.004 0.004 <string>:1(<module>)\n",
" 6 0.000 0.000 0.000 0.000 iostream.py:384(write)\n",
" 75 0.000 0.000 0.000 0.000 {built-in method builtins.min}\n",
" 3 0.000 0.000 0.000 0.000 <ipython-input-112-58b0ffc6eba3>:154(__init__)\n",
" 3 0.000 0.000 0.000 0.000 <ipython-input-112-58b0ffc6eba3>:138(get_candidates)\n",
" 8 0.000 0.000 0.000 0.000 numeric.py:268(full)\n",
" 8 0.000 0.000 0.000 0.000 {built-in method numpy.empty}\n",
" 1 0.000 0.000 0.000 0.000 {method 'intersection' of 'set' objects}\n",
" 184 0.000 0.000 0.000 0.000 {method 'bit_length' of 'int' objects}\n",
" 8 0.000 0.000 0.000 0.000 <__array_function__ internals>:2(copyto)\n",
" 3 0.000 0.000 0.000 0.000 {method 'flatten' of 'numpy.ndarray' objects}\n",
" 2 0.000 0.000 0.000 0.000 <ipython-input-112-58b0ffc6eba3>:96(set_letters)\n",
" 2 0.000 0.000 0.000 0.000 {built-in method builtins.print}\n",
" 14 0.000 0.000 0.000 0.000 fromnumeric.py:71(<dictcomp>)\n",
" 3 0.000 0.000 0.000 0.000 <ipython-input-112-58b0ffc6eba3>:91(get_letters)\n",
" 7 0.000 0.000 0.000 0.000 <ipython-input-112-58b0ffc6eba3>:78(__init__)\n",
" 7 0.000 0.000 0.000 0.000 threading.py:1093(is_alive)\n",
" 2 0.000 0.000 0.000 0.000 <ipython-input-112-58b0ffc6eba3>:184(copy)\n",
" 6 0.000 0.000 0.000 0.000 iostream.py:308(_is_master_process)\n",
" 20 0.000 0.000 0.000 0.000 {built-in method builtins.isinstance}\n",
" 7 0.000 0.000 0.000 0.000 iostream.py:91(_event_pipe)\n",
" 7 0.000 0.000 0.000 0.000 threading.py:1039(_wait_for_tstate_lock)\n",
" 2 0.000 0.000 0.000 0.000 <ipython-input-2-026304d5612b>:88(normalize_word)\n",
" 7 0.000 0.000 0.000 0.000 {method 'acquire' of '_thread.lock' objects}\n",
" 14 0.000 0.000 0.000 0.000 fromnumeric.py:2100(_sum_dispatcher)\n",
" 1 0.000 0.000 0.000 0.000 <ipython-input-2-026304d5612b>:19(get_database)\n",
" 2 0.000 0.000 0.000 0.000 {method 'translate' of 'str' objects}\n",
" 6 0.000 0.000 0.000 0.000 {built-in method posix.getpid}\n",
" 17 0.000 0.000 0.000 0.000 {built-in method builtins.len}\n",
" 14 0.000 0.000 0.000 0.000 {method 'items' of 'dict' objects}\n",
" 6 0.000 0.000 0.000 0.000 iostream.py:321(_schedule_flush)\n",
" 8 0.000 0.000 0.000 0.000 multiarray.py:1043(copyto)\n",
" 7 0.000 0.000 0.000 0.000 {method 'append' of 'list' objects}\n",
" 6 0.000 0.000 0.000 0.000 {method 'copy' of 'list' objects}\n",
" 7 0.000 0.000 0.000 0.000 threading.py:529(is_set)\n",
" 1 0.000 0.000 0.000 0.000 <ipython-input-2-026304d5612b>:78(get_inverted_database)\n",
" 2 0.000 0.000 0.000 0.000 <ipython-input-112-58b0ffc6eba3>:105(connect_word)\n",
" 3 0.000 0.000 0.000 0.000 <ipython-input-112-58b0ffc6eba3>:147(get_connected_words)\n",
" 1 0.000 0.000 0.000 0.000 <ipython-input-112-58b0ffc6eba3>:110(check_connected)\n",
" 2 0.000 0.000 0.000 0.000 {method 'lower' of 'str' objects}\n",
" 7 0.000 0.000 0.000 0.000 {method 'append' of 'collections.deque' objects}\n",
" 2 0.000 0.000 0.000 0.000 <ipython-input-112-58b0ffc6eba3>:102(set_word_key)\n",
" 1 0.000 0.000 0.000 0.000 {method 'disable' of '_lsprof.Profiler' objects}"
]
}
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 115,
"source": [
"\n",
"plt.imshow(base_grid)\n",
"plt.show()\n",
"print(final_state.letter_grid)\n",
"for grid_word in final_state.final_grid_words:\n",
" connected = []\n",
" for word in grid_word.connected_words:\n",
" connected.append(word.word_key)\n",
" print(grid_word.word_key, connected)"
],
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
],
"image/svg+xml": "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n<!-- Created with matplotlib (https://matplotlib.org/) -->\n<svg height=\"248.518125pt\" version=\"1.1\" viewBox=\"0 0 251.565 248.518125\" width=\"251.565pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n <metadata>\n <rdf:RDF xmlns:cc=\"http://creativecommons.org/ns#\" xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\">\n <cc:Work>\n <dc:type rdf:resource=\"http://purl.org/dc/dcmitype/StillImage\"/>\n <dc:date>2021-08-23T14:20:12.832599</dc:date>\n <dc:format>image/svg+xml</dc:format>\n <dc:creator>\n <cc:Agent>\n <dc:title>Matplotlib v3.3.4, https://matplotlib.org/</dc:title>\n </cc:Agent>\n </dc:creator>\n </cc:Work>\n </rdf:RDF>\n </metadata>\n <defs>\n <style type=\"text/css\">*{stroke-linecap:butt;stroke-linejoin:round;}</style>\n </defs>\n <g id=\"figure_1\">\n <g id=\"patch_1\">\n <path d=\"M 0 248.518125 \nL 251.565 248.518125 \nL 251.565 0 \nL 0 0 \nz\n\" style=\"fill:none;\"/>\n </g>\n <g id=\"axes_1\">\n <g id=\"patch_2\">\n <path d=\"M 26.925 224.64 \nL 244.365 224.64 \nL 244.365 7.2 \nL 26.925 7.2 \nz\n\" style=\"fill:#ffffff;\"/>\n </g>\n <g clip-path=\"url(#p0cc632ace9)\">\n <image height=\"218\" id=\"image6dc259e393\" transform=\"scale(1 -1)translate(0 -218)\" width=\"218\" x=\"26.925\" xlink:href=\"data:image/png;base64,\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\" y=\"-6.64\"/>\n </g>\n <g id=\"matplotlib.axis_1\">\n <g id=\"xtick_1\">\n <g id=\"line2d_1\">\n <defs>\n <path d=\"M 0 0 \nL 0 3.5 \n\" id=\"m004dfe69e3\" style=\"stroke:#000000;stroke-width:0.8;\"/>\n </defs>\n <g>\n <use style=\"stroke:#000000;stroke-width:0.8;\" x=\"34.690714\" xlink:href=\"#m004dfe69e3\" y=\"224.64\"/>\n </g>\n </g>\n <g id=\"text_1\">\n <!-- 0 -->\n <g transform=\"translate(31.509464 239.238437)scale(0.1 -0.1)\">\n <defs>\n <path d=\"M 31.78125 66.40625 \nQ 24.171875 66.40625 20.328125 58.90625 \nQ 16.5 51.421875 16.5 36.375 \nQ 16.5 21.390625 20.328125 13.890625 \nQ 24.171875 6.390625 31.78125 6.390625 \nQ 39.453125 6.390625 43.28125 13.890625 \nQ 47.125 21.390625 47.125 36.375 \nQ 47.125 51.421875 43.28125 58.90625 \nQ 39.453125 66.40625 31.78125 66.40625 \nz\nM 31.78125 74.21875 \nQ 44.046875 74.21875 50.515625 64.515625 \nQ 56.984375 54.828125 56.984375 36.375 \nQ 56.984375 17.96875 50.515625 8.265625 \nQ 44.046875 -1.421875 31.78125 -1.421875 \nQ 19.53125 -1.421875 13.0625 8.265625 \nQ 6.59375 17.96875 6.59375 36.375 \nQ 6.59375 54.828125 13.0625 64.515625 \nQ 19.53125 74.21875 31.78125 74.21875 \nz\n\" id=\"DejaVuSans-48\"/>\n </defs>\n <use xlink:href=\"#DejaVuSans-48\"/>\n </g>\n </g>\n </g>\n <g id=\"xtick_2\">\n <g id=\"line2d_2\">\n <g>\n <use style=\"stroke:#000000;stroke-width:0.8;\" x=\"65.753571\" xlink:href=\"#m004dfe69e3\" y=\"224.6
"image/png": "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"
},
"metadata": {
"needs_background": "light"
}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"[[' ' 'm' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ']\n",
" ['a' 'a' 'c' 'h' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ']\n",
" [' ' 'i' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ']\n",
" [' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ']\n",
" [' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ']\n",
" [' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ']\n",
" [' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ']\n",
" [' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ']\n",
" [' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ']\n",
" [' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ']\n",
" [' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ']\n",
" [' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ']\n",
" [' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ']\n",
" [' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ' ']]\n",
"mai ['aach0']\n",
"aach0 ['mai']\n"
]
}
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": null,
"source": [
"grid_word"
],
"outputs": [],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 292,
"source": [
"def create_word_grid(w: int, h: int, lang_code: str = \"en\", target_density: float = 0.5, difficulty: int = 0):\n",
" np.full()\n",
"\n"
],
"outputs": [],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 85,
"source": [
"w = 5\n",
"h = 5\n",
"\n",
"hh_index = np.zeros(shape=(h,w), dtype = int)\n",
"vv_index = np.zeros(shape=(w,h), dtype = int)\n",
"\n",
"\n",
"h_index = w - np.arange(w)\n",
"v_index = h - np.arange(h)\n",
"\n",
"hh_index[:] = h_index\n",
"vv_index[:] = v_index\n",
"vv_index = vv_index.transpose()\n",
"\n",
"\n",
"horizontal_starting_points = np.full(shape=(h, w), dtype=int, fill_value=-1)\n",
"horizontal_starting_points[::2,::2] = 0\n",
"horizontal_starting_points[horizontal_starting_points == 0] = hh_index[horizontal_starting_points == 0]\n",
"\n",
"vertical_starting_points = np.full(shape=(h, w), dtype=int, fill_value=-1)\n",
"vertical_starting_points[::2,::2] = 0\n",
"vertical_starting_points[vertical_starting_points == 0] = vv_index[vertical_starting_points == 0]\n",
"\n",
"vertical_starting_points"
],
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([[ 5, -1, 5, -1, 5],\n",
" [-1, -1, -1, -1, -1],\n",
" [ 3, -1, 3, -1, 3],\n",
" [-1, -1, -1, -1, -1],\n",
" [ 1, -1, 1, -1, 1]])"
]
},
"metadata": {},
"execution_count": 85
}
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": null,
"source": [],
"outputs": [],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 82,
"source": [
"w = 10\n",
"h = 5\n",
"\n",
"hh_index = np.zeros(shape=(h,w), dtype = int)\n",
"vv_index = np.zeros(shape=(w,h), dtype = int)\n",
"\n",
"\n",
"h_index = w - 1 - np.arange(w)\n",
"v_index = h - 1 - np.arange(h)\n",
"\n",
"hh_index[:] = h_index\n",
"vv_index[:] = v_index\n",
"vv_index = vv_index.transpose()\n",
"\n",
"hh_index\n"
],
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([[9, 8, 7, 6, 5, 4, 3, 2, 1, 0],\n",
" [9, 8, 7, 6, 5, 4, 3, 2, 1, 0],\n",
" [9, 8, 7, 6, 5, 4, 3, 2, 1, 0],\n",
" [9, 8, 7, 6, 5, 4, 3, 2, 1, 0],\n",
" [9, 8, 7, 6, 5, 4, 3, 2, 1, 0]])"
]
},
"metadata": {},
"execution_count": 82
}
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 87,
"source": [
"l = [[1,2],[2,3]]\n",
"\n",
"[1,3] in l"
],
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"False"
]
},
"metadata": {},
"execution_count": 87
}
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 53,
"source": [
"import pprint\n",
"\n",
"grid, hints, solution = create_word_grid(10,20)\n",
"\n",
"pprint.pprint(grid)"
],
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"100\n",
"200\n",
"300\n",
"400\n",
"500\n",
"600\n",
"700\n",
"800\n",
"900\n",
"1000\n",
"1100\n",
"1200\n"
]
},
{
"output_type": "error",
"ename": "RecursionError",
"evalue": "maximum recursion depth exceeded while calling a Python object",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mRecursionError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-53-d31de1543123>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mpprint\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0mgrid\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mhints\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msolution\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcreate_word_grid\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m20\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 4\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mpprint\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mgrid\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m<ipython-input-52-64ae6dfdecba>\u001b[0m in \u001b[0;36mcreate_word_grid\u001b[0;34m(w, h, lang_code, target_density, difficulty)\u001b[0m\n\u001b[1;32m 279\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 280\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 281\u001b[0;31m \u001b[0msolution_word_locations\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_solution_word\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 282\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 283\u001b[0m \u001b[0mlogging\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minfo\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"crossword generation done after %s iterations\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m<ipython-input-52-64ae6dfdecba>\u001b[0m in \u001b[0;36mget_solution_word\u001b[0;34m(min_length, max_length)\u001b[0m\n\u001b[1;32m 173\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mchar\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mlocations_cpy\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlocations_cpy\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mchar\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 174\u001b[0m \u001b[0;31m# next try:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 175\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mget_solution_word\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmin_length\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmin_length\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmax_length\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmax_length\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 176\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 177\u001b[0m \u001b[0mlocation_candidates\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlocations_cpy\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mchar\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"... last 1 frames repeated, from the frame below ...\n",
"\u001b[0;32m<ipython-input-52-64ae6dfdecba>\u001b[0m in \u001b[0;36mget_solution_word\u001b[0;34m(min_length, max_length)\u001b[0m\n\u001b[1;32m 173\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mchar\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mlocations_cpy\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlocations_cpy\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mchar\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 174\u001b[0m \u001b[0;31m# next try:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 175\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mget_solution_word\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmin_length\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmin_length\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmax_length\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmax_length\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 176\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 177\u001b[0m \u001b[0mlocation_candidates\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlocations_cpy\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mchar\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mRecursionError\u001b[0m: maximum recursion depth exceeded while calling a Python object"
]
}
],
"metadata": {}
}
],
"metadata": {
"orig_nbformat": 4,
"language_info": {
"name": "python",
"version": "3.9.5",
"mimetype": "text/x-python",
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"pygments_lexer": "ipython3",
"nbconvert_exporter": "python",
"file_extension": ".py"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3.9.5 64-bit"
},
"interpreter": {
"hash": "916dbcbb3f70747c44a77c7bcd40155683ae19c65e1c03b4aa3499c5328201f1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}