first commit

.gitignore

@@ -0,0 +1 @@
+data/*

middleschool-cardlist.ipynb

@@ -0,0 +1,238 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# middleschool-cardlist\n",
+    "\n",
+    "## Prepare the data\n",
+    "\n",
+    "Download raw data from [MTGJSON](https://mtgjson.com/) (uncomment and run only once)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# !cd data\n",
+    "# !wget \"https://mtgjson.com/api/v5/AllPrintings.json.bz2\"\n",
+    "# !bunzip2 AllPrintings.json.bz2\n",
+    "# !cd -\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The Raw data is very large, so let's make JSON files for all relevant sets\n",
+    "\n",
+    "Note: this cell can take a couple minutes to run\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "setlist = ['4ED', 'ICE', 'CHR', 'HML', 'ALL', 'MIR', 'VIS', '5ED',\n",
+    "           'WTH', 'POR', 'TMP', 'STH', 'EXO', 'P02', 'USG', 'ULG',\n",
+    "           '6ED', 'UDS', 'PTK', 'S99', 'MMQ', 'NEM', 'PCY', 'S00',\n",
+    "           'INV', 'PLS', '7ED', 'APC', 'ODY', 'TOR', 'JUD', 'ONS',\n",
+    "           'LGN', 'SCG', 'PDRC', 'PHPR']\n",
+    "for set in setlist:\n",
+    "    command = 'cat data/AllPrintings.json | jq \\'.data.\\\"' + \\\n",
+    "        set + '\\\".cards\\' > data/set_' + set + '.json'\n",
+    "    !{command}\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Concatenate all set files into `middleschool.json`\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "command = \"jq -s add data/set_* > data/middleschool.json\"\n",
+    "!{command}\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create a list with each card's oracle ID, English name, and Japanese name\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "5793 cards found\n",
+      "                              oracle_id               name    name_ja\n",
+      "0  8adbba6e-03ef-4278-aec5-8a4496b377a8       Abandon Hope         断念\n",
+      "0  5a70ccfa-d12d-4e62-a1a4-f05cda2fd442  Abandoned Outpost  見捨てられた前哨地\n",
+      "0  c208b959-d0e4-4a9a-8255-2c7cc7596767    Abbey Gargoyles  修道院のガーゴイル\n",
+      "0  62e3f285-886c-414e-b4ff-403a7c01c23a       Abbey Matron       None\n",
+      "0  d0e1904e-1a37-41f6-8582-b9ea794bb886          Abduction         誘拐\n",
+      "                              oracle_id                      name    name_ja\n",
+      "0  ae8773a3-05f2-4074-9a53-033b0c127235  Zuo Ci, the Mocking Sage  嘲笑する仙人 左慈\n",
+      "0  c6eaa147-3566-43a9-999a-d58b877496f5            Zur's Weirding   ズアーの運命支配\n",
+      "0  ee0f883f-d7c9-4acf-a78f-f733b6f268d3           Zuran Enchanter       None\n",
+      "0  08cb8a30-9cb4-4517-bee5-8848aa60d1a2                 Zuran Orb       None\n",
+      "0  bc7b90b1-3517-4e5d-9bd8-68b4d8a259fd         Zuran Spellcaster       None\n"
+     ]
+    }
+   ],
+   "source": [
+    "import json\n",
+    "import pandas as pd\n",
+    "\n",
+    "with open(\"data/middleschool.json\") as json_data:\n",
+    "    cards = json.loads(json_data.read())\n",
+    "\n",
+    "column_names = ['oracle_id', 'name', 'name_ja']\n",
+    "middleschool_df = pd.DataFrame(columns=column_names)\n",
+    "for card in cards:\n",
+    "    oracle_id = card['identifiers']['scryfallOracleId']\n",
+    "    name = card['name']\n",
+    "    lang_ja = [lang for lang in card['foreignData']\n",
+    "               if lang['language'] == 'Japanese']\n",
+    "    if (len(lang_ja) > 0):\n",
+    "        name_ja = lang_ja[0]['name']\n",
+    "    else:\n",
+    "        name_ja = None\n",
+    "    temporary_df = pd.DataFrame({\n",
+    "        'oracle_id': [oracle_id],\n",
+    "        'name':      [name],\n",
+    "        'name_ja':   [name_ja]\n",
+    "    })\n",
+    "    middleschool_df = pd.concat([middleschool_df, temporary_df])\n",
+    "\n",
+    "middleschool_df = middleschool_df.drop_duplicates(subset=['oracle_id'])\n",
+    "middleschool_df = middleschool_df.sort_values(by='name')\n",
+    "print(middleschool_df.shape[0], 'cards found')\n",
+    "print(middleschool_df.head())\n",
+    "print(middleschool_df.tail())\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Exclude all cards banned in Middle School\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Cards legal by set: 5793\n",
+      "Banned cards: 26\n",
+      "Cards legal by set and not banned: 5767\n"
+     ]
+    }
+   ],
+   "source": [
+    "banlist = [\"Amulet of Quoz\",\n",
+    "           \"Balance\",\n",
+    "           \"Brainstorm\",\n",
+    "           \"Bronze Tablet\",\n",
+    "           \"Channel\",\n",
+    "           \"Dark Ritual\",\n",
+    "           \"Demonic Consultation\",\n",
+    "           \"Flash\",\n",
+    "           \"Goblin Recruiter\",\n",
+    "           \"Imperial Seal\",\n",
+    "           \"Jeweled Bird\",\n",
+    "           \"Lion's Eye Diamond\",\n",
+    "           \"Mana Crypt\",\n",
+    "           \"Mana Vault\",\n",
+    "           \"Memory Jar\",\n",
+    "           \"Mind's Desire\",\n",
+    "           \"Mind Twist\",\n",
+    "           \"Rebirth\",\n",
+    "           \"Strip Mine\",\n",
+    "           \"Tempest Efreet\",\n",
+    "           \"Timmerian Fiends\",\n",
+    "           \"Tolarian Academy\",\n",
+    "           \"Vampiric Tutor\",\n",
+    "           \"Windfall\",\n",
+    "           \"Yawgmoth's Bargain\",\n",
+    "           \"Yawgmoth's Will\"]\n",
+    "print('Cards legal by set:', middleschool_df.shape[0])\n",
+    "banned_df = middleschool_df[pd.DataFrame(\n",
+    "    middleschool_df.name.tolist()).isin(banlist).any(1).values]\n",
+    "print('Banned cards:', banned_df.shape[0])\n",
+    "middleschool_df = pd.concat(\n",
+    "    [middleschool_df, banned_df]).drop_duplicates(keep=False)\n",
+    "print('Cards legal by set and not banned:', middleschool_df.shape[0])\n",
+    "middleschool_df = middleschool_df.reset_index(drop=True)\n",
+    "middleschool_df = middleschool_df[['oracle_id', 'name', 'name_ja']]\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Save the list to a CSV file and a JSON file\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "middleschool_df.to_csv('output/middleschool.csv')\n",
+    "middleschool_df.to_json('output/middleschool.json')\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.9.12 64-bit",
+   "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": "3.9.12"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "b0fa6594d8f4cbf19f97940f81e996739fb7646882a419484c72d19e05852a7e"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}