Bonus, comments

middleschool-cardlist.ipynb

@@ -44,6 +44,7 @@
     "           'INV', 'PLS', '7ED', 'APC', 'ODY', 'TOR', 'JUD', 'ONS',\n",
     "           'LGN', 'SCG', 'PDRC', 'PHPR', 'ATH', 'BRB', 'BTD', 'DKM']\n",
     "for set in setlist:\n",
+    "    # Write a separate JSON document for each Middle School legal set\n",
     "    command = 'cat data/AllPrintings.json | jq \\'.data.\\\"' + \\\n",
     "        set + '\\\".cards\\' > data/set_' + set + '.json'\n",
     "    !{command}\n"
@@ -75,19 +76,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 56,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "                              oracle_id           name name_ja\n",
-      "0  5acc8b39-3c3e-4012-8cfd-ac3c2c4ca982  Arc Lightning   弧状の稲妻\n",
-      "0  5acc8b39-3c3e-4012-8cfd-ac3c2c4ca982  Arc Lightning    None\n",
-      "                              oracle_id           name name_ja\n",
-      "0  5acc8b39-3c3e-4012-8cfd-ac3c2c4ca982  Arc Lightning   弧状の稲妻\n",
       "5800 cards found\n",
+      "These are the first and last 5 cards\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",
@@ -110,6 +107,7 @@
     "with open(\"data/middleschool.json\") as json_data:\n",
     "    cards = json.loads(json_data.read())\n",
     "\n",
+    "# Create a pandas DataFrame with all cards from all legal sets\n",
     "column_names = ['oracle_id', 'name', 'name_ja']\n",
     "middleschool_df = pd.DataFrame(columns=column_names)\n",
     "for card in cards:\n",
@@ -117,6 +115,7 @@
     "    name = card['name']\n",
     "    lang_ja = [lang for lang in card['foreignData']\n",
     "               if lang['language'] == 'Japanese']\n",
+    "    # Some cards do not have a Japanese name\n",
     "    if (len(lang_ja) > 0):\n",
     "        name_ja = lang_ja[0]['name']\n",
     "    else:\n",
@@ -128,20 +127,22 @@
     "    })\n",
     "    middleschool_df = pd.concat([middleschool_df, temporary_df])\n",
     "\n",
+    "# For cards with multiple occurrences, put the rows that have the Japanese name on top\n",
     "middleschool_df = middleschool_df.sort_values(by=['name', 'name_ja'])\n",
-    "print(middleschool_df[middleschool_df['name'] == 'Arc Lightning'])\n",
+    "# For cards with multiple occurrences, delete all rows except for the top one\n",
     "middleschool_df = middleschool_df.drop_duplicates(subset=['oracle_id'])\n",
-    "print(middleschool_df[middleschool_df['name'] == 'Arc Lightning'])\n",
     "print(middleschool_df.shape[0], 'cards found')\n",
+    "print('These are the first and last 5 cards')\n",
     "print(middleschool_df.head())\n",
     "print(middleschool_df.tail())\n"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Exclude all cards banned in Middle School\n"
+    "Find Japanese names for cards that were not released in Japanese in Middle School legal sets"
    ]
   },
   {
@@ -169,11 +170,16 @@
     "def find_japanese_name(name):\n",
     "    url = 'http://whisper.wisdom-guild.net/search.php?q=' + name\n",
     "    r = session.get(url)\n",
+    "    # Find the text on the <title> element in the HTML document\n",
     "    title = r.html.find('title')[0].text\n",
+    "    # Find the position of the English card name within the title\n",
     "    idx = title.find(name)\n",
+    "    # The Japanese name should be before the English name, \n",
+    "    # so if idx is 0, there is no Japanese name\n",
     "    if idx == 0:\n",
     "        return None\n",
     "    else:\n",
+    "        # Take only the Japanese name from the title\n",
     "        name_ja = title[0:idx - 1]\n",
     "        return name_ja\n",
     "\n",
@@ -192,6 +198,14 @@
     "print(name, '→', find_japanese_name(name))\n"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Exclude all cards banned in Middle School"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 19,
@@ -235,9 +249,13 @@
     "           \"Yawgmoth's Bargain\",\n",
     "           \"Yawgmoth's Will\"]\n",
     "print('Cards legal by set:', middleschool_df.shape[0])\n",
+    "# Find the rows with the banned cards\n",
     "banned_df = middleschool_df[pd.DataFrame(\n",
     "    middleschool_df.name.tolist()).isin(banlist).any(axis=1).values]\n",
     "print('Banned cards:', banned_df.shape[0])\n",
+    "# Append the banned cards to the main Middle School DataFrame,\n",
+    "# then remove any rows that appear twice,\n",
+    "# effectively leaving only the legal cards\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",