fuji-nakahara/genron-sf-2018-data-analysis.ipynb

## genron-sf-2018-data-analysis.ipynb
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# データで見る ゲンロン 大森望 SF創作講座 2018"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[ゲンロン 大森望 SF創作講座 第3期](http://school.genron.co.jp/works/sf/2018/) も残すところ最終課題のみとなった。  \n",
    "最終課題は「ゲンロンSF新人賞」と題されており他とは少し毛色が違うので、通常課題はすべて出揃ったことになる。  \n",
    "明日からは[第4期の募集も始まる](https://twitter.com/genronschool/status/1110500492763762688)とのことなので、受講を迷っている方に向けてSF創作講座第3期のデータを見てみようと思う。\n",
    "\n",
    "目次は次のとおりである。\n",
    "\n",
    "- 課題提出数の推移\n",
    "- 選出・得点の機会\n",
    "- 梗概の文字数\n",
    "- 受講生勝手にランキング"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "データは、[fuji-nakahara/genron-sf-app](https://github.com/fuji-nakahara/genron-sf-app) を用いて [超・SF作家育成サイト](http://school.genron.co.jp/works/sf/) をスクレイピングしたものを用いる。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "%config InlineBackend.figure_formats = {'png', 'retina'}\n",
    "sns.set()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Connected: fuji-nakahara@genron-school-sf-app_development'"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%config SqlMagic.autopandas = True\n",
    "%config SqlMagic.feedback = False\n",
    "%load_ext sql\n",
    "%sql postgresql://fuji-nakahara@localhost/genron-school-sf-app_development"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "term_id = 2018"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2019-03-29 01:39:09.829794\n"
     ]
    }
   ],
   "source": [
    "from datetime import datetime\n",
    "print(datetime.now())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 課題提出数の推移"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "まずは、課題ごとに何編の梗概・実作が提出されているかをみてみよう。\n",
    "\n",
    "SF創作講座は1年の期間を通して月に1度のペースで開催される。  \n",
    "受講料は20万円と決して安くはないが、途中から課題を提出しなくなる受講生も意外と多い。  \n",
    "かくいう私自身も第8回の梗概を最後に、最終課題は提出できなさそうである。  \n",
    "提出数の推移から、そういった受講生がどのくらいるかがわかるだろう。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " * postgresql://fuji-nakahara@localhost/genron-school-sf-app_development\n",
      "Returning data to local variable subjects\n"
     ]
    }
   ],
   "source": [
    "%%sql subjects <<\n",
    "\n",
    "select\n",
    "    s.number\n",
    "    , s.title\n",
    "    , l.name as proposer\n",
    "    , s.synopses_count\n",
    "    , count(sy.id) as selected_synopses_count\n",
    "    , s.works_count\n",
    "from\n",
    "    subjects s\n",
    "    left join lecturers l on (s.id = l.subject_id and ('課題提示' = any (l.roles)))\n",
    "    left join synopses sy on (s.id = sy.subject_id and sy.selected = True)\n",
    "where\n",
    "    s.term_id = :term_id\n",
    "    and s.number <= 10\n",
    "group by\n",
    "    1, 2, 3, 4, 6\n",
    "order by\n",
    "    1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>number</th>\n",
       "      <th>title</th>\n",
       "      <th>proposer</th>\n",
       "      <th>synopses_count</th>\n",
       "      <th>selected_synopses_count</th>\n",
       "      <th>works_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>AIあるいは仮想通貨を題材に短編を書け</td>\n",
       "      <td>東浩紀</td>\n",
       "      <td>43</td>\n",
       "      <td>4</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>スキットがなきゃ意味がない</td>\n",
       "      <td>藤井太洋</td>\n",
       "      <td>35</td>\n",
       "      <td>3</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>生き物を作ってみよう！</td>\n",
       "      <td>新井素子</td>\n",
       "      <td>31</td>\n",
       "      <td>3</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>拘束下で書きなさい</td>\n",
       "      <td>円城塔</td>\n",
       "      <td>31</td>\n",
       "      <td>4</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>来たるべき読者のための「初めてのSF」</td>\n",
       "      <td>法月綸太郎</td>\n",
       "      <td>27</td>\n",
       "      <td>4</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>キャラクターの関係性で物語を回しなさい</td>\n",
       "      <td>長谷敏司</td>\n",
       "      <td>25</td>\n",
       "      <td>4</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>経過時間を設定してください</td>\n",
       "      <td>飛浩隆</td>\n",
       "      <td>23</td>\n",
       "      <td>3</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8</td>\n",
       "      <td>「天皇制」、または「元号」に関するSFを書きなさい。</td>\n",
       "      <td>小川哲</td>\n",
       "      <td>23</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9</td>\n",
       "      <td>小さな世界を見せてください</td>\n",
       "      <td>森岡浩之</td>\n",
       "      <td>22</td>\n",
       "      <td>4</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10</td>\n",
       "      <td>最終課題：ゲンロンSF新人賞【梗概】</td>\n",
       "      <td>None</td>\n",
       "      <td>22</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   number                       title proposer  synopses_count  \\\n",
       "0       1         AIあるいは仮想通貨を題材に短編を書け      東浩紀              43   \n",
       "1       2               スキットがなきゃ意味がない     藤井太洋              35   \n",
       "2       3                 生き物を作ってみよう！     新井素子              31   \n",
       "3       4                   拘束下で書きなさい      円城塔              31   \n",
       "4       5         来たるべき読者のための「初めてのSF」    法月綸太郎              27   \n",
       "5       6         キャラクターの関係性で物語を回しなさい     長谷敏司              25   \n",
       "6       7               経過時間を設定してください      飛浩隆              23   \n",
       "7       8  「天皇制」、または「元号」に関するSFを書きなさい。      小川哲              23   \n",
       "8       9               小さな世界を見せてください     森岡浩之              22   \n",
       "9      10          最終課題：ゲンロンSF新人賞【梗概】     None              22   \n",
       "\n",
       "   selected_synopses_count  works_count  \n",
       "0                        4            9  \n",
       "1                        3           12  \n",
       "2                        3           16  \n",
       "3                        4            9  \n",
       "4                        4           12  \n",
       "5                        4           11  \n",
       "6                        3           11  \n",
       "7                        4            5  \n",
       "8                        4            7  \n",
       "9                        0            0  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "subjects"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "上の表は、各課題の梗概提出数 (synopses_count) と実作提出数 (works_count) である。\n",
    "\n",
    "合わせて、選出された梗概の数 (selected_synopses_count) も出している。  \n",
    "梗概の選出は各課題原則3編とのことだったが、3期は4編選ばれることのほうが多かった。\n",
    "\n",
    "梗概と実作の提出数の推移をグラフにすると次のようになる。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x11f7e5240>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 269,
       "width": 376
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "subjects.plot(x='number', y=['synopses_count', 'works_count'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "梗概数は回を増すごとに単調に減少している。  \n",
    "第1回は43編が提出されていたが、第9・10回は約半数の22編である。  \n",
    "11月(第6回)に聴講生から受講生に変わった人が3名ほどいるため、実質半数を切っている。\n",
    "\n",
    "実作提出数は増えたり減ったりであるが、やはり序盤の方が少し多い。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "ちなみに、梗概・実作の提出総数は次のとおりである。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "synopses_count    282\n",
       "works_count        92\n",
       "dtype: int64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "subjects[['synopses_count', 'works_count']].sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 選出・得点機会"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "脱落してしまう理由はいろいろあると思うが、一つに徹底した実力主義があるだろう。  \n",
    "\n",
    "提出した梗概は審査され、全提出作から3または4編だけが選出される。  \n",
    "そして、選出されたとしても、また次回に実作で点数を競うことになる。\n",
    "\n",
    "講義の時間は選出作品に多く割かれ、講師の評価が低ければほとんど言及されないことも珍しくない。  \n",
    "仮に競争を意識していなかったとしても、提出した作品が講義で取り上げられないことが続くとつらいものがある。\n",
    "\n",
    "この節では、そうした梗概の選出・実作の得点機会についてみる。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " * postgresql://fuji-nakahara@localhost/genron-school-sf-app_development\n",
      "Returning data to local variable student_synopses\n"
     ]
    }
   ],
   "source": [
    "%%sql student_synopses <<\n",
    "\n",
    "select\n",
    "    name\n",
    "    , submitted_count\n",
    "    , selected_count\n",
    "    , coalesce(characters_sum / submitted_count::real, 0) as characters_ave\n",
    "    , coalesce(max_character_count, 0) as max_character_count\n",
    "    , coalesce(appeal_characters_sum / submitted_count::real, 0) as appeal_characters_ave\n",
    "    , coalesce(max_appeal_character_count, 0) as max_appeal_character_count\n",
    "from\n",
    "    (\n",
    "        select\n",
    "            s.original_id\n",
    "            , s.name\n",
    "            , count(sy.id) as submitted_count\n",
    "            , sum(case when sy.selected then 1 else 0 end) as selected_count\n",
    "            , sum(sy.character_count) as characters_sum\n",
    "            , max(sy.character_count) as max_character_count\n",
    "            , sum(sy.appeal_character_count) as appeal_characters_sum\n",
    "            , max(sy.appeal_character_count) as max_appeal_character_count\n",
    "        from\n",
    "            students s\n",
    "            join students_terms st on s.id = st.student_id\n",
    "            left join (\n",
    "                select\n",
    "                    sy.*\n",
    "                from\n",
    "                    synopses sy\n",
    "                    join subjects su on (\n",
    "                        sy.subject_id = su.id\n",
    "                        and su.term_id = :term_id\n",
    "                    )\n",
    "            ) sy on s.id = sy.student_id\n",
    "        where\n",
    "            st.term_id = :term_id\n",
    "        group by\n",
    "            1, 2\n",
    "    ) student_synopses\n",
    "order by\n",
    "    original_id"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " * postgresql://fuji-nakahara@localhost/genron-school-sf-app_development\n",
      "Returning data to local variable student_works\n"
     ]
    }
   ],
   "source": [
    "%%sql student_works <<\n",
    "\n",
    "select\n",
    "    name\n",
    "    , submitted_count\n",
    "    , submitted_count - selected_count as optional_count\n",
    "    , coalesce(score, 0) as score\n",
    "    , optional_score\n",
    "    , coalesce(characters_sum, 0) as characters_sum\n",
    "from\n",
    "    (\n",
    "        select\n",
    "            s.original_id\n",
    "            , s.name\n",
    "            , count(w.id) as submitted_count\n",
    "            , sum(case when w.selected = True then 1 else 0 end) as selected_count\n",
    "            , sum(w.score) as score\n",
    "            , sum(case when w.selected != True then w.score else 0 end) as optional_score\n",
    "            , sum(w.character_count) as characters_sum\n",
    "        from\n",
    "            students s\n",
    "            join students_terms st on s.id = st.student_id\n",
    "            left join (\n",
    "                select\n",
    "                    w.*\n",
    "                    , sy.selected\n",
    "                from\n",
    "                    works w\n",
    "                    join subjects su on (\n",
    "                        w.subject_id = su.id\n",
    "                        and su.term_id = :term_id\n",
    "                    )\n",
    "                    left join synopses sy using (original_id)\n",
    "            ) w on s.id = w.student_id\n",
    "        where\n",
    "            st.term_id = :term_id\n",
    "        group by\n",
    "            1, 2\n",
    "    ) student_synopses\n",
    "order by\n",
    "    original_id"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 梗概の提出・選出回数"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "受講生1人あたりの梗概提出回数・選出回数を調べてみよう。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>submitted_count</th>\n",
       "      <th>selected_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>48.000000</td>\n",
       "      <td>48.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>5.875000</td>\n",
       "      <td>0.687500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.600384</td>\n",
       "      <td>1.113863</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>6.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>10.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>10.000000</td>\n",
       "      <td>4.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       submitted_count  selected_count\n",
       "count        48.000000       48.000000\n",
       "mean          5.875000        0.687500\n",
       "std           3.600384        1.113863\n",
       "min           0.000000        0.000000\n",
       "25%           2.000000        0.000000\n",
       "50%           6.000000        0.000000\n",
       "75%          10.000000        1.000000\n",
       "max          10.000000        4.000000"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "student_synopses[['submitted_count', 'selected_count']].describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "48人の受講生について、梗概提出回数 (submitted_count) の平均値は5.87回、中央値は6回である。  \n",
    "それに対し、選出回数 (selected_count) は平均0.69回、中央値に至っては0回であった。  \n",
    "つまり、半数以上の受講生が一度も選出されないのである。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "分布にすると次のようになる。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1218b62e8>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 254,
       "width": 389
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "student_synopses[['submitted_count', 'selected_count']].plot.hist(bins=11, alpha=0.5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "オレンジ色が選出回数の分布である。  \n",
    "1度も選出されていない受講生が32人おり、これは全体の32/48、すなわち3分の2である。  \n",
    "\n",
    "また、青色が提出回数の分布である。  \n",
    "これを見ると、10回、つまりすべての課題の梗概を提出した受講生が13人ほどいる。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 実作提出数・自主提出数"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "同じように実作についてもみてみよう。\n",
    "\n",
    "基本的には、梗概を選出された受講生が次の回に実作を書くことになっている。  \n",
    "しかし、選出されていなくても実作を提出することは許されており、これは自主提出と呼ばれている。  \n",
    "自主提出の場合は、必ずしも点数がつくわけではない。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>submitted_count</th>\n",
       "      <th>optional_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>48.000000</td>\n",
       "      <td>48.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1.916667</td>\n",
       "      <td>1.312500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.656452</td>\n",
       "      <td>2.105275</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>3.250000</td>\n",
       "      <td>2.250000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>9.000000</td>\n",
       "      <td>7.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       submitted_count  optional_count\n",
       "count        48.000000       48.000000\n",
       "mean          1.916667        1.312500\n",
       "std           2.656452        2.105275\n",
       "min           0.000000        0.000000\n",
       "25%           0.000000        0.000000\n",
       "50%           0.000000        0.000000\n",
       "75%           3.250000        2.250000\n",
       "max           9.000000        7.000000"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "student_works[['submitted_count', 'optional_count']].describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "実作提出回数の平均は1.92回、自主提出回数の平均は1.31回だった。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "提出回数の分布は次のようになる。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x121968240>"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 254,
       "width": 389
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "student_works.submitted_count.plot.hist(bins=10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "48人中26人、すなわち半数以上は1度も実作を提出していない。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "また、自主提出作品の総数は次のとおりである。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "63"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "student_works.optional_count.sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 得点した自主提出作品"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "自主提出にはどのくらいの点数がつくのか。  \n",
    "得点した自主提出作品はそれほど多くないので、すべてリストアップしてみよう。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " * postgresql://fuji-nakahara@localhost/genron-school-sf-app_development\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>number</th>\n",
       "      <th>subject_title</th>\n",
       "      <th>work_title</th>\n",
       "      <th>author</th>\n",
       "      <th>score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>AIあるいは仮想通貨を題材に短編を書け</td>\n",
       "      <td>子どもだましの森</td>\n",
       "      <td>遠山軌道</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>スキットがなきゃ意味がない</td>\n",
       "      <td>揺りかごの外から</td>\n",
       "      <td>遠山軌道</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>スキットがなきゃ意味がない</td>\n",
       "      <td>飲鴆止活（いんちんしかつ）</td>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>生き物を作ってみよう！</td>\n",
       "      <td>「蝗の王」</td>\n",
       "      <td>伊藤 元晴</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3</td>\n",
       "      <td>生き物を作ってみよう！</td>\n",
       "      <td>肉のシャイロック</td>\n",
       "      <td>国分寺崖線</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>3</td>\n",
       "      <td>生き物を作ってみよう！</td>\n",
       "      <td>イキワカレノイモウト</td>\n",
       "      <td>進藤尚典</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>5</td>\n",
       "      <td>来たるべき読者のための「初めてのSF」</td>\n",
       "      <td>ナンバー・オブ・マイ・ルート</td>\n",
       "      <td>伊藤 元晴</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>5</td>\n",
       "      <td>来たるべき読者のための「初めてのSF」</td>\n",
       "      <td>はじめましてSci-Fiさん、エイリアンより</td>\n",
       "      <td>黒田 渚</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>5</td>\n",
       "      <td>来たるべき読者のための「初めてのSF」</td>\n",
       "      <td>ギークに銃はいらない</td>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>7</td>\n",
       "      <td>経過時間を設定してください</td>\n",
       "      <td>スシュランの男</td>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>9</td>\n",
       "      <td>小さな世界を見せてください</td>\n",
       "      <td>金の網にかかった魚</td>\n",
       "      <td>甘木 零</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>9</td>\n",
       "      <td>小さな世界を見せてください</td>\n",
       "      <td>自分を食べた恋狂い</td>\n",
       "      <td>諸根 いつみ</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>9</td>\n",
       "      <td>小さな世界を見せてください</td>\n",
       "      <td>旅先の散髪屋</td>\n",
       "      <td>野咲タラ</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>9</td>\n",
       "      <td>小さな世界を見せてください</td>\n",
       "      <td>ヴァルタヴァの寫眞師</td>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    number        subject_title              work_title  author  score\n",
       "0        1  AIあるいは仮想通貨を題材に短編を書け                子どもだましの森    遠山軌道      1\n",
       "1        2        スキットがなきゃ意味がない                揺りかごの外から    遠山軌道      2\n",
       "2        2        スキットがなきゃ意味がない           飲鴆止活（いんちんしかつ）   斧田 小夜      1\n",
       "3        3          生き物を作ってみよう！                   「蝗の王」   伊藤 元晴      2\n",
       "4        3          生き物を作ってみよう！                肉のシャイロック   国分寺崖線      1\n",
       "5        3          生き物を作ってみよう！              イキワカレノイモウト    進藤尚典      2\n",
       "6        5  来たるべき読者のための「初めてのSF」          ナンバー・オブ・マイ・ルート   伊藤 元晴      1\n",
       "7        5  来たるべき読者のための「初めてのSF」  はじめましてSci-Fiさん、エイリアンより    黒田 渚      1\n",
       "8        5  来たるべき読者のための「初めてのSF」              ギークに銃はいらない   斧田 小夜      5\n",
       "9        7        経過時間を設定してください                 スシュランの男   斧田 小夜      2\n",
       "10       9        小さな世界を見せてください               金の網にかかった魚    甘木 零      3\n",
       "11       9        小さな世界を見せてください               自分を食べた恋狂い  諸根 いつみ      4\n",
       "12       9        小さな世界を見せてください                  旅先の散髪屋    野咲タラ      2\n",
       "13       9        小さな世界を見せてください              ヴァルタヴァの寫眞師   斧田 小夜      3"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%%sql\n",
    "\n",
    "select\n",
    "    su.number\n",
    "    , su.title as subject_title\n",
    "    , w.title as work_title\n",
    "    , s.name as author\n",
    "    , w.score\n",
    "from\n",
    "    works w\n",
    "    join students s on w.student_id = s.id\n",
    "    join subjects su on (\n",
    "        w.subject_id = su.id\n",
    "        and su.term_id = :term_id\n",
    "    )\n",
    "    join synopses sy on (w.original_id = sy.original_id)\n",
    "where\n",
    "    sy.selected != True\n",
    "    and w.score > 0\n",
    "order by\n",
    "    1, s.original_id"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "自主提出63作中得点したのはたった14作である。  \n",
    "14/63 = 0.22 ということで、4分の1未満の自主提出作品にしか点数はつかない。  \n",
    "また、得点の最大値も5点となっている。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 梗概の文字数"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "この節では、梗概の文字数についてみていく。\n",
    "\n",
    "SF創作講座の課題には、梗概1200字以下、アピール文400字以下というルールがある。  \n",
    "しかし、これはほとんど守られていない。  \n",
    "そして、守っていない作品も選出される。  \n",
    "むしろ、守っていない作品のほうが選出されやすいのではないか？  \n",
    "多くの受講生が疑問思っているであろうこの問いに答えてみたい。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " * postgresql://fuji-nakahara@localhost/genron-school-sf-app_development\n",
      "Returning data to local variable synopses_character_counts\n"
     ]
    }
   ],
   "source": [
    "%%sql synopses_character_counts <<\n",
    "\n",
    "select\n",
    "    s.number\n",
    "    , sy.title\n",
    "    , st.name as author\n",
    "    , sy.character_count\n",
    "    , sy.appeal_character_count\n",
    "    , sy.selected\n",
    "from\n",
    "    subjects s\n",
    "    join synopses sy on s.id = sy.subject_id\n",
    "    join students st on sy.student_id = st.id\n",
    "where\n",
    "    s.term_id = :term_id\n",
    "    and s.number <= 9\n",
    "order by\n",
    "    1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "selected_synopses_character_counts = synopses_character_counts[synopses_character_counts.selected]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 各種文字数の統計量"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "全梗概の文字数、全梗概のアピール文文字数、選出梗概の文字数、選出梗概のアピール文文字数のそれぞれについて平均や分散などの統計量をみる。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "character_counts_with_selected = pd.DataFrame(\n",
    "    {\n",
    "        'character_count': synopses_character_counts.character_count,\n",
    "        'selected_character_count': selected_synopses_character_counts.character_count,\n",
    "        'appeal_character_count': synopses_character_counts.appeal_character_count.fillna(0),\n",
    "        'selected_appeal_character_count': selected_synopses_character_counts.appeal_character_count.fillna(0)\n",
    "    }\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>character_count</th>\n",
       "      <th>selected_character_count</th>\n",
       "      <th>appeal_character_count</th>\n",
       "      <th>selected_appeal_character_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>260.000000</td>\n",
       "      <td>33.000000</td>\n",
       "      <td>260.000000</td>\n",
       "      <td>33.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1433.761538</td>\n",
       "      <td>1580.969697</td>\n",
       "      <td>328.976923</td>\n",
       "      <td>340.575758</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>408.257088</td>\n",
       "      <td>525.927781</td>\n",
       "      <td>230.630158</td>\n",
       "      <td>173.437494</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>310.000000</td>\n",
       "      <td>1087.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1196.750000</td>\n",
       "      <td>1198.000000</td>\n",
       "      <td>184.750000</td>\n",
       "      <td>255.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1268.500000</td>\n",
       "      <td>1417.000000</td>\n",
       "      <td>319.500000</td>\n",
       "      <td>323.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1599.250000</td>\n",
       "      <td>1798.000000</td>\n",
       "      <td>398.000000</td>\n",
       "      <td>400.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>3714.000000</td>\n",
       "      <td>3714.000000</td>\n",
       "      <td>1967.000000</td>\n",
       "      <td>1035.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       character_count  selected_character_count  appeal_character_count  \\\n",
       "count       260.000000                 33.000000              260.000000   \n",
       "mean       1433.761538               1580.969697              328.976923   \n",
       "std         408.257088                525.927781              230.630158   \n",
       "min         310.000000               1087.000000                0.000000   \n",
       "25%        1196.750000               1198.000000              184.750000   \n",
       "50%        1268.500000               1417.000000              319.500000   \n",
       "75%        1599.250000               1798.000000              398.000000   \n",
       "max        3714.000000               3714.000000             1967.000000   \n",
       "\n",
       "       selected_appeal_character_count  \n",
       "count                        33.000000  \n",
       "mean                        340.575758  \n",
       "std                         173.437494  \n",
       "min                           0.000000  \n",
       "25%                         255.000000  \n",
       "50%                         323.000000  \n",
       "75%                         400.000000  \n",
       "max                        1035.000000  "
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "character_counts_with_selected.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "梗概の文字数 (character_count) の平均は1434字であるのに対し、選出梗概の文字数 (selected_character_count) の平均は1581字と約150字も多かった。  \n",
    "アピール文についても、329字に対し、341字と10字ほど多い。  \n",
    "もちろん、選出梗概のサンプル数が少なく、標準偏差も大きいため有意差はない。  \n",
    "とはいえ、選出梗概の方が文字数が多いのではないか、という感覚が間違いではなさそうだ。\n",
    "\n",
    "本文文字数の25パーセンタイルを見ると、1197字（選出梗概で1198字）となっており、約1/4の作品しか本文の文字数制約を守っていないことがわかる。\n",
    "また、アピール文に関しては75パーセンタイルが400字ということで、約3/4がルールを守っている。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "本文とアピール文の文字数の分布はそれぞれ次のようになる。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x121fb18d0>"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 254,
       "width": 391
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "bins = list(range(0, character_counts_with_selected.character_count.max() + 300, 300))\n",
    "character_counts_with_selected[['character_count', 'selected_character_count']].plot.hist(bins=bins)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1221bf518>"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 254,
       "width": 389
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "bins = list(range(0, int(character_counts_with_selected.appeal_character_count.max()) + 100, 100))\n",
    "character_counts_with_selected[['appeal_character_count', 'selected_appeal_character_count']].plot.hist(bins=bins)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 文字数順の選出梗概"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "選出梗概はそもそも33編しかないので、一覧しても大した量ではない。  \n",
    "せっかくなので、本文文字数の少ない順に並べておく。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>number</th>\n",
       "      <th>title</th>\n",
       "      <th>author</th>\n",
       "      <th>character_count</th>\n",
       "      <th>appeal_character_count</th>\n",
       "      <th>selected</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>251</th>\n",
       "      <td>9</td>\n",
       "      <td>最古にして最新の弔い作法</td>\n",
       "      <td>小野 十郎</td>\n",
       "      <td>1087</td>\n",
       "      <td>224.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>234</th>\n",
       "      <td>8</td>\n",
       "      <td>酔来酔去</td>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>1126</td>\n",
       "      <td>255.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>180</th>\n",
       "      <td>6</td>\n",
       "      <td>フィオナの空、ロアの海</td>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>1148</td>\n",
       "      <td>340.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>83</th>\n",
       "      <td>3</td>\n",
       "      <td>死者の裔</td>\n",
       "      <td>武見 倉森</td>\n",
       "      <td>1154</td>\n",
       "      <td>248.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1</td>\n",
       "      <td>これからの祈りについて</td>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>1168</td>\n",
       "      <td>327.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1</td>\n",
       "      <td>AI、無人島を脱出できず</td>\n",
       "      <td>進藤尚典</td>\n",
       "      <td>1179</td>\n",
       "      <td>289.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>103</th>\n",
       "      <td>3</td>\n",
       "      <td>流星雨があがったら</td>\n",
       "      <td>揚羽はな</td>\n",
       "      <td>1196</td>\n",
       "      <td>296.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>155</th>\n",
       "      <td>5</td>\n",
       "      <td>暴走ロケットに乗れ！</td>\n",
       "      <td>揚羽はな</td>\n",
       "      <td>1198</td>\n",
       "      <td>276.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>涜神のスティグマ</td>\n",
       "      <td>維嶋津/いしましん</td>\n",
       "      <td>1198</td>\n",
       "      <td>393.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41</th>\n",
       "      <td>1</td>\n",
       "      <td>暗点</td>\n",
       "      <td>国分寺崖線</td>\n",
       "      <td>1200</td>\n",
       "      <td>394.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>256</th>\n",
       "      <td>9</td>\n",
       "      <td>ちいさな夜警</td>\n",
       "      <td>琴柱遥</td>\n",
       "      <td>1229</td>\n",
       "      <td>453.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>138</th>\n",
       "      <td>4</td>\n",
       "      <td>10文字以内で述べなさい。（ただし、句読点は含みません）</td>\n",
       "      <td>進藤尚典</td>\n",
       "      <td>1236</td>\n",
       "      <td>263.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>156</th>\n",
       "      <td>5</td>\n",
       "      <td>拝啓、摩天の龍より指先の君へ</td>\n",
       "      <td>維嶋津/いしましん</td>\n",
       "      <td>1298</td>\n",
       "      <td>253.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>121</th>\n",
       "      <td>4</td>\n",
       "      <td>自己をめぐる嗣焼（つぐやき）梨子（りこ）の奔走</td>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>1343</td>\n",
       "      <td>520.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>233</th>\n",
       "      <td>8</td>\n",
       "      <td>天は廻（めぐ）る、皇（すめらぎ）と共に</td>\n",
       "      <td>維嶋津/いしましん</td>\n",
       "      <td>1363</td>\n",
       "      <td>344.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>142</th>\n",
       "      <td>5</td>\n",
       "      <td>殻の内側に住む子供たちは</td>\n",
       "      <td>武見 倉森</td>\n",
       "      <td>1402</td>\n",
       "      <td>302.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>230</th>\n",
       "      <td>8</td>\n",
       "      <td>式年遷皇</td>\n",
       "      <td>フジ・ナカハラ</td>\n",
       "      <td>1417</td>\n",
       "      <td>400.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>240</th>\n",
       "      <td>9</td>\n",
       "      <td>小さな家</td>\n",
       "      <td>宿禰</td>\n",
       "      <td>1498</td>\n",
       "      <td>224.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>190</th>\n",
       "      <td>6</td>\n",
       "      <td>子羊たち</td>\n",
       "      <td>琴柱遥</td>\n",
       "      <td>1558</td>\n",
       "      <td>431.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>189</th>\n",
       "      <td>6</td>\n",
       "      <td>透明な血のつながり</td>\n",
       "      <td>フジ・ナカハラ</td>\n",
       "      <td>1570</td>\n",
       "      <td>471.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>201</th>\n",
       "      <td>7</td>\n",
       "      <td>天体環レース</td>\n",
       "      <td>甘木 零</td>\n",
       "      <td>1596</td>\n",
       "      <td>1035.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>68</th>\n",
       "      <td>2</td>\n",
       "      <td>いずれ助詞系女子</td>\n",
       "      <td>伊藤 元晴</td>\n",
       "      <td>1600</td>\n",
       "      <td>315.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>92</th>\n",
       "      <td>3</td>\n",
       "      <td>空を織る虫</td>\n",
       "      <td>やまね</td>\n",
       "      <td>1606</td>\n",
       "      <td>NaN</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>225</th>\n",
       "      <td>8</td>\n",
       "      <td>与えられた三〇年</td>\n",
       "      <td>伊藤 元晴</td>\n",
       "      <td>1746</td>\n",
       "      <td>155.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45</th>\n",
       "      <td>2</td>\n",
       "      <td>リアル・サイボーグ</td>\n",
       "      <td>フジ・ナカハラ</td>\n",
       "      <td>1798</td>\n",
       "      <td>400.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>139</th>\n",
       "      <td>4</td>\n",
       "      <td>吾輩は鬼である</td>\n",
       "      <td>谷 美里</td>\n",
       "      <td>1814</td>\n",
       "      <td>320.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>194</th>\n",
       "      <td>7</td>\n",
       "      <td>四国狸の化して恐竜となる話</td>\n",
       "      <td>琴柱遥</td>\n",
       "      <td>1857</td>\n",
       "      <td>356.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>141</th>\n",
       "      <td>5</td>\n",
       "      <td>手ぶくろをはめたチェリスト</td>\n",
       "      <td>谷 美里</td>\n",
       "      <td>1990</td>\n",
       "      <td>542.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>188</th>\n",
       "      <td>6</td>\n",
       "      <td>夕焼けのグライダー</td>\n",
       "      <td>小野 十郎</td>\n",
       "      <td>2096</td>\n",
       "      <td>475.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>250</th>\n",
       "      <td>9</td>\n",
       "      <td>鬼のいる理想郷</td>\n",
       "      <td>遠山軌道</td>\n",
       "      <td>2168</td>\n",
       "      <td>35.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>193</th>\n",
       "      <td>7</td>\n",
       "      <td>マリオネット俳優</td>\n",
       "      <td>国分寺崖線</td>\n",
       "      <td>2201</td>\n",
       "      <td>393.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>72</th>\n",
       "      <td>2</td>\n",
       "      <td>おむかえの距離</td>\n",
       "      <td>小野 十郎</td>\n",
       "      <td>2418</td>\n",
       "      <td>187.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>110</th>\n",
       "      <td>4</td>\n",
       "      <td>オペレーション・パトリオット</td>\n",
       "      <td>茶里 裕治</td>\n",
       "      <td>3714</td>\n",
       "      <td>323.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     number                         title     author  character_count  \\\n",
       "251       9                  最古にして最新の弔い作法      小野 十郎             1087   \n",
       "234       8                          酔来酔去      斧田 小夜             1126   \n",
       "180       6                   フィオナの空、ロアの海      斧田 小夜             1148   \n",
       "83        3                          死者の裔      武見 倉森             1154   \n",
       "10        1                   これからの祈りについて      斧田 小夜             1168   \n",
       "7         1                  AI、無人島を脱出できず       進藤尚典             1179   \n",
       "103       3                     流星雨があがったら       揚羽はな             1196   \n",
       "155       5                    暴走ロケットに乗れ！       揚羽はな             1198   \n",
       "9         1                      涜神のスティグマ  維嶋津/いしましん             1198   \n",
       "41        1                            暗点      国分寺崖線             1200   \n",
       "256       9                        ちいさな夜警        琴柱遥             1229   \n",
       "138       4  10文字以内で述べなさい。（ただし、句読点は含みません）       進藤尚典             1236   \n",
       "156       5                拝啓、摩天の龍より指先の君へ  維嶋津/いしましん             1298   \n",
       "121       4       自己をめぐる嗣焼（つぐやき）梨子（りこ）の奔走      斧田 小夜             1343   \n",
       "233       8           天は廻（めぐ）る、皇（すめらぎ）と共に  維嶋津/いしましん             1363   \n",
       "142       5                  殻の内側に住む子供たちは      武見 倉森             1402   \n",
       "230       8                          式年遷皇    フジ・ナカハラ             1417   \n",
       "240       9                          小さな家         宿禰             1498   \n",
       "190       6                          子羊たち        琴柱遥             1558   \n",
       "189       6                     透明な血のつながり    フジ・ナカハラ             1570   \n",
       "201       7                        天体環レース       甘木 零             1596   \n",
       "68        2                      いずれ助詞系女子      伊藤 元晴             1600   \n",
       "92        3                         空を織る虫        やまね             1606   \n",
       "225       8                      与えられた三〇年      伊藤 元晴             1746   \n",
       "45        2                     リアル・サイボーグ    フジ・ナカハラ             1798   \n",
       "139       4                       吾輩は鬼である       谷 美里             1814   \n",
       "194       7                 四国狸の化して恐竜となる話        琴柱遥             1857   \n",
       "141       5                 手ぶくろをはめたチェリスト       谷 美里             1990   \n",
       "188       6                     夕焼けのグライダー      小野 十郎             2096   \n",
       "250       9                       鬼のいる理想郷       遠山軌道             2168   \n",
       "193       7                      マリオネット俳優      国分寺崖線             2201   \n",
       "72        2                       おむかえの距離      小野 十郎             2418   \n",
       "110       4                オペレーション・パトリオット      茶里 裕治             3714   \n",
       "\n",
       "     appeal_character_count  selected  \n",
       "251                   224.0      True  \n",
       "234                   255.0      True  \n",
       "180                   340.0      True  \n",
       "83                    248.0      True  \n",
       "10                    327.0      True  \n",
       "7                     289.0      True  \n",
       "103                   296.0      True  \n",
       "155                   276.0      True  \n",
       "9                     393.0      True  \n",
       "41                    394.0      True  \n",
       "256                   453.0      True  \n",
       "138                   263.0      True  \n",
       "156                   253.0      True  \n",
       "121                   520.0      True  \n",
       "233                   344.0      True  \n",
       "142                   302.0      True  \n",
       "230                   400.0      True  \n",
       "240                   224.0      True  \n",
       "190                   431.0      True  \n",
       "189                   471.0      True  \n",
       "201                  1035.0      True  \n",
       "68                    315.0      True  \n",
       "92                      NaN      True  \n",
       "225                   155.0      True  \n",
       "45                    400.0      True  \n",
       "139                   320.0      True  \n",
       "194                   356.0      True  \n",
       "141                   542.0      True  \n",
       "188                   475.0      True  \n",
       "250                    35.0      True  \n",
       "193                   393.0      True  \n",
       "72                    187.0      True  \n",
       "110                   323.0      True  "
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_synopses_character_counts.sort_values(by='character_count')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 課題ごとの梗概文字数"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "次に、課題ごとの梗概文字数の分布を見ておこう。  \n",
    "もしかすると、1200字のルールを守ったものしか選出しないゲスト講師がいるかも知れない。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x122428358>"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 269,
       "width": 401
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.scatterplot(x='number', y='character_count', hue='selected', data=synopses_character_counts)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "横軸が課題の番号、縦軸が文字数で、ひとつひとつの作品がドットでプロットされている。  \n",
    "選出された梗概はドットがオレンジ色になっている。\n",
    "\n",
    "ただ、これではドットの重なりが多くわかりにくいので、重なった部分を横に広げたのが下の図である。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x122601780>"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 269,
       "width": 401
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.swarmplot(x='number', y='character_count', hue='selected', data=synopses_character_counts)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "すべての選出作が1200字を下回ったのは第1回だけだった。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 受講生勝手にランキング"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "ここからは趣向を変えて、3期のようすを知っている人向けのデータを紹介する。  \n",
    "SF創作講座では得点が絶対唯一の指標であるが、ここではそれ以外の数値について受講生を勝手にランキングしていこうと思う。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 梗概"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "まずは、梗概に関するランキングである。  \n",
    "データとして以下の表を用いる。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>submitted_count</th>\n",
       "      <th>selected_count</th>\n",
       "      <th>characters_ave</th>\n",
       "      <th>max_character_count</th>\n",
       "      <th>appeal_characters_ave</th>\n",
       "      <th>max_appeal_character_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>伊藤 元晴</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1431.000000</td>\n",
       "      <td>1746</td>\n",
       "      <td>194.500000</td>\n",
       "      <td>383</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>亜月</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1161.333333</td>\n",
       "      <td>1716</td>\n",
       "      <td>241.833333</td>\n",
       "      <td>352</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>甘木 零</td>\n",
       "      <td>9</td>\n",
       "      <td>1</td>\n",
       "      <td>1490.333333</td>\n",
       "      <td>1860</td>\n",
       "      <td>582.333333</td>\n",
       "      <td>1035</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>茶里 裕治</td>\n",
       "      <td>10</td>\n",
       "      <td>1</td>\n",
       "      <td>1803.100000</td>\n",
       "      <td>3714</td>\n",
       "      <td>239.500000</td>\n",
       "      <td>375</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>遠山軌道</td>\n",
       "      <td>9</td>\n",
       "      <td>1</td>\n",
       "      <td>1502.888889</td>\n",
       "      <td>2168</td>\n",
       "      <td>241.222222</td>\n",
       "      <td>688</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>篠田 航平</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>1487.125000</td>\n",
       "      <td>1876</td>\n",
       "      <td>338.875000</td>\n",
       "      <td>544</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>夢想 真</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>1346.900000</td>\n",
       "      <td>1531</td>\n",
       "      <td>211.400000</td>\n",
       "      <td>507</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>フジ・ナカハラ</td>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>1472.333333</td>\n",
       "      <td>2239</td>\n",
       "      <td>410.666667</td>\n",
       "      <td>471</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>宿禰</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>1946.666667</td>\n",
       "      <td>3517</td>\n",
       "      <td>289.000000</td>\n",
       "      <td>371</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>灰田 頼人</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>1545.600000</td>\n",
       "      <td>2566</td>\n",
       "      <td>208.600000</td>\n",
       "      <td>382</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>菊地 和広</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>1326.000000</td>\n",
       "      <td>1713</td>\n",
       "      <td>483.200000</td>\n",
       "      <td>639</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>広木 素数一</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1351.000000</td>\n",
       "      <td>1516</td>\n",
       "      <td>203.500000</td>\n",
       "      <td>216</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>結城 イケ</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1361.500000</td>\n",
       "      <td>1373</td>\n",
       "      <td>170.500000</td>\n",
       "      <td>178</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>今井 曖昧</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>906.500000</td>\n",
       "      <td>1098</td>\n",
       "      <td>15.000000</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>縞里 若菜</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1375.666667</td>\n",
       "      <td>1537</td>\n",
       "      <td>69.333333</td>\n",
       "      <td>117</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>安岐 いぬこ</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1153.500000</td>\n",
       "      <td>1189</td>\n",
       "      <td>220.000000</td>\n",
       "      <td>337</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>維嶋津/いしましん</td>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "      <td>1445.222222</td>\n",
       "      <td>2865</td>\n",
       "      <td>341.555556</td>\n",
       "      <td>774</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>伊藤屋 イトウ</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>カケヒマサヒデ</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1168.333333</td>\n",
       "      <td>1194</td>\n",
       "      <td>306.333333</td>\n",
       "      <td>378</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>武見 倉森</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1433.400000</td>\n",
       "      <td>1840</td>\n",
       "      <td>340.600000</td>\n",
       "      <td>660</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>生田目 ケイ</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>1595.333333</td>\n",
       "      <td>2290</td>\n",
       "      <td>442.444444</td>\n",
       "      <td>595</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>国分寺崖線</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1933.200000</td>\n",
       "      <td>2504</td>\n",
       "      <td>527.300000</td>\n",
       "      <td>1178</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>茶瓶</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>1471.600000</td>\n",
       "      <td>1881</td>\n",
       "      <td>401.200000</td>\n",
       "      <td>438</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>_</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1778.000000</td>\n",
       "      <td>1778</td>\n",
       "      <td>1967.000000</td>\n",
       "      <td>1967</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>黒田 渚</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>1396.200000</td>\n",
       "      <td>1626</td>\n",
       "      <td>532.200000</td>\n",
       "      <td>779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>谷 美里</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>2002.800000</td>\n",
       "      <td>2209</td>\n",
       "      <td>590.600000</td>\n",
       "      <td>1359</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>moimasa5</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1195.000000</td>\n",
       "      <td>1195</td>\n",
       "      <td>397.000000</td>\n",
       "      <td>397</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>諸根 いつみ</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>1210.700000</td>\n",
       "      <td>1240</td>\n",
       "      <td>269.200000</td>\n",
       "      <td>395</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>夏川 智樹</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1434.000000</td>\n",
       "      <td>1434</td>\n",
       "      <td>327.000000</td>\n",
       "      <td>327</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>小野 十郎</td>\n",
       "      <td>8</td>\n",
       "      <td>3</td>\n",
       "      <td>1679.000000</td>\n",
       "      <td>2467</td>\n",
       "      <td>466.625000</td>\n",
       "      <td>1428</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>やまね</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>1430.500000</td>\n",
       "      <td>2365</td>\n",
       "      <td>60.833333</td>\n",
       "      <td>199</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>薮　ゆき</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1044.000000</td>\n",
       "      <td>1044</td>\n",
       "      <td>160.000000</td>\n",
       "      <td>160</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>中外中</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1204.000000</td>\n",
       "      <td>1204</td>\n",
       "      <td>220.000000</td>\n",
       "      <td>220</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>伊吹</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1112.000000</td>\n",
       "      <td>1112</td>\n",
       "      <td>281.000000</td>\n",
       "      <td>281</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>進藤尚典</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1354.500000</td>\n",
       "      <td>1666</td>\n",
       "      <td>186.500000</td>\n",
       "      <td>379</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>右手 新土</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>1677.250000</td>\n",
       "      <td>2236</td>\n",
       "      <td>627.750000</td>\n",
       "      <td>1443</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>shgee</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>げんなり</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>1140.555556</td>\n",
       "      <td>1328</td>\n",
       "      <td>154.666667</td>\n",
       "      <td>289</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38</th>\n",
       "      <td>不二 拓/tack</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>1176.750000</td>\n",
       "      <td>1241</td>\n",
       "      <td>306.000000</td>\n",
       "      <td>554</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>野咲タラ</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>1139.500000</td>\n",
       "      <td>1665</td>\n",
       "      <td>420.400000</td>\n",
       "      <td>822</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40</th>\n",
       "      <td>俵野 道生</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>1189.250000</td>\n",
       "      <td>1296</td>\n",
       "      <td>108.000000</td>\n",
       "      <td>216</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41</th>\n",
       "      <td>安藤 タカシ</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>1291.000000</td>\n",
       "      <td>2011</td>\n",
       "      <td>276.000000</td>\n",
       "      <td>424</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42</th>\n",
       "      <td>瓜田 流</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1197.500000</td>\n",
       "      <td>1198</td>\n",
       "      <td>312.000000</td>\n",
       "      <td>381</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>10</td>\n",
       "      <td>4</td>\n",
       "      <td>1253.100000</td>\n",
       "      <td>1640</td>\n",
       "      <td>311.600000</td>\n",
       "      <td>520</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>揚羽はな</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>1197.600000</td>\n",
       "      <td>1200</td>\n",
       "      <td>305.500000</td>\n",
       "      <td>373</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45</th>\n",
       "      <td>ヤナギサワ　カズキ</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>1699.777778</td>\n",
       "      <td>2226</td>\n",
       "      <td>346.111111</td>\n",
       "      <td>449</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46</th>\n",
       "      <td>足立 佑</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>1300.750000</td>\n",
       "      <td>1549</td>\n",
       "      <td>272.500000</td>\n",
       "      <td>341</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47</th>\n",
       "      <td>琴柱遥</td>\n",
       "      <td>10</td>\n",
       "      <td>3</td>\n",
       "      <td>1518.900000</td>\n",
       "      <td>1857</td>\n",
       "      <td>407.000000</td>\n",
       "      <td>566</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         name  submitted_count  selected_count  characters_ave  \\\n",
       "0       伊藤 元晴               10               2     1431.000000   \n",
       "1          亜月                6               0     1161.333333   \n",
       "2        甘木 零                9               1     1490.333333   \n",
       "3       茶里 裕治               10               1     1803.100000   \n",
       "4        遠山軌道                9               1     1502.888889   \n",
       "5       篠田 航平                8               0     1487.125000   \n",
       "6        夢想 真               10               0     1346.900000   \n",
       "7     フジ・ナカハラ                6               3     1472.333333   \n",
       "8          宿禰                6               1     1946.666667   \n",
       "9       灰田 頼人                5               0     1545.600000   \n",
       "10      菊地 和広                5               0     1326.000000   \n",
       "11     広木 素数一                2               0     1351.000000   \n",
       "12      結城 イケ                2               0     1361.500000   \n",
       "13      今井 曖昧                2               0      906.500000   \n",
       "14      縞里 若菜                3               0     1375.666667   \n",
       "15     安岐 いぬこ                2               0     1153.500000   \n",
       "16  維嶋津/いしましん                9               3     1445.222222   \n",
       "17    伊藤屋 イトウ                0               0        0.000000   \n",
       "18    カケヒマサヒデ                3               0     1168.333333   \n",
       "19      武見 倉森               10               2     1433.400000   \n",
       "20     生田目 ケイ                9               0     1595.333333   \n",
       "21      国分寺崖線               10               2     1933.200000   \n",
       "22         茶瓶                5               0     1471.600000   \n",
       "23          _                1               0     1778.000000   \n",
       "24       黒田 渚                5               0     1396.200000   \n",
       "25       谷 美里               10               2     2002.800000   \n",
       "26   moimasa5                1               0     1195.000000   \n",
       "27     諸根 いつみ               10               0     1210.700000   \n",
       "28      夏川 智樹                1               0     1434.000000   \n",
       "29      小野 十郎                8               3     1679.000000   \n",
       "30        やまね                6               1     1430.500000   \n",
       "31       薮　ゆき                1               0     1044.000000   \n",
       "32        中外中                1               0     1204.000000   \n",
       "33         伊吹                1               0     1112.000000   \n",
       "34       進藤尚典               10               2     1354.500000   \n",
       "35      右手 新土                4               0     1677.250000   \n",
       "36      shgee                0               0        0.000000   \n",
       "37       げんなり                9               0     1140.555556   \n",
       "38  不二 拓/tack                4               0     1176.750000   \n",
       "39       野咲タラ               10               0     1139.500000   \n",
       "40      俵野 道生                4               0     1189.250000   \n",
       "41     安藤 タカシ               10               0     1291.000000   \n",
       "42       瓜田 流                2               0     1197.500000   \n",
       "43      斧田 小夜               10               4     1253.100000   \n",
       "44       揚羽はな               10               2     1197.600000   \n",
       "45  ヤナギサワ　カズキ                9               0     1699.777778   \n",
       "46       足立 佑                4               0     1300.750000   \n",
       "47        琴柱遥               10               3     1518.900000   \n",
       "\n",
       "    max_character_count  appeal_characters_ave  max_appeal_character_count  \n",
       "0                  1746             194.500000                         383  \n",
       "1                  1716             241.833333                         352  \n",
       "2                  1860             582.333333                        1035  \n",
       "3                  3714             239.500000                         375  \n",
       "4                  2168             241.222222                         688  \n",
       "5                  1876             338.875000                         544  \n",
       "6                  1531             211.400000                         507  \n",
       "7                  2239             410.666667                         471  \n",
       "8                  3517             289.000000                         371  \n",
       "9                  2566             208.600000                         382  \n",
       "10                 1713             483.200000                         639  \n",
       "11                 1516             203.500000                         216  \n",
       "12                 1373             170.500000                         178  \n",
       "13                 1098              15.000000                          16  \n",
       "14                 1537              69.333333                         117  \n",
       "15                 1189             220.000000                         337  \n",
       "16                 2865             341.555556                         774  \n",
       "17                    0               0.000000                           0  \n",
       "18                 1194             306.333333                         378  \n",
       "19                 1840             340.600000                         660  \n",
       "20                 2290             442.444444                         595  \n",
       "21                 2504             527.300000                        1178  \n",
       "22                 1881             401.200000                         438  \n",
       "23                 1778            1967.000000                        1967  \n",
       "24                 1626             532.200000                         779  \n",
       "25                 2209             590.600000                        1359  \n",
       "26                 1195             397.000000                         397  \n",
       "27                 1240             269.200000                         395  \n",
       "28                 1434             327.000000                         327  \n",
       "29                 2467             466.625000                        1428  \n",
       "30                 2365              60.833333                         199  \n",
       "31                 1044             160.000000                         160  \n",
       "32                 1204             220.000000                         220  \n",
       "33                 1112             281.000000                         281  \n",
       "34                 1666             186.500000                         379  \n",
       "35                 2236             627.750000                        1443  \n",
       "36                    0               0.000000                           0  \n",
       "37                 1328             154.666667                         289  \n",
       "38                 1241             306.000000                         554  \n",
       "39                 1665             420.400000                         822  \n",
       "40                 1296             108.000000                         216  \n",
       "41                 2011             276.000000                         424  \n",
       "42                 1198             312.000000                         381  \n",
       "43                 1640             311.600000                         520  \n",
       "44                 1200             305.500000                         373  \n",
       "45                 2226             346.111111                         449  \n",
       "46                 1549             272.500000                         341  \n",
       "47                 1857             407.000000                         566  "
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "student_synopses"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 梗概提出皆勤賞"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "全10回すべての梗概を提出した13名は次のとおりである。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>submitted_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>伊藤 元晴</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>茶里 裕治</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>夢想 真</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>武見 倉森</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>国分寺崖線</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>谷 美里</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>諸根 いつみ</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>進藤尚典</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>野咲タラ</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41</th>\n",
       "      <td>安藤 タカシ</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>揚羽はな</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47</th>\n",
       "      <td>琴柱遥</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      name  submitted_count\n",
       "0    伊藤 元晴               10\n",
       "3    茶里 裕治               10\n",
       "6     夢想 真               10\n",
       "19   武見 倉森               10\n",
       "21   国分寺崖線               10\n",
       "25    谷 美里               10\n",
       "27  諸根 いつみ               10\n",
       "34    進藤尚典               10\n",
       "39    野咲タラ               10\n",
       "41  安藤 タカシ               10\n",
       "43   斧田 小夜               10\n",
       "44    揚羽はな               10\n",
       "47     琴柱遥               10"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "student_synopses[student_synopses.submitted_count == 10][['name', 'submitted_count']]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 文字数遵守"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "10回すべての梗概を提出しながらも、梗概とアピール文の文字数制限をすべて守った受講生が、なんと一人だけいた。  \n",
    "揚羽はなさんである。\n",
    "\n",
    "ちなみに梗概を4回以上提出した人に範囲を広げてもただ1人である。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>submitted_count</th>\n",
       "      <th>max_character_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>揚羽はな</td>\n",
       "      <td>10</td>\n",
       "      <td>1200</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    name  submitted_count  max_character_count\n",
       "44  揚羽はな               10                 1200"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "student_synopses \\\n",
    "    [(student_synopses.max_character_count <= 1200) & (student_synopses.submitted_count >= 4)] \\\n",
    "    [['name', 'submitted_count', 'max_character_count']] \\\n",
    "    .sort_values(by='max_character_count').head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 5回以上の提出で平均文字数1200字以下"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "毎回守ったわけではないが、過半数の課題を提出したうえで、それらの文字数を平均すると1200字以下になる受講生は次のとおりである。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>submitted_count</th>\n",
       "      <th>characters_ave</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>野咲タラ</td>\n",
       "      <td>10</td>\n",
       "      <td>1139.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>げんなり</td>\n",
       "      <td>9</td>\n",
       "      <td>1140.555556</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>亜月</td>\n",
       "      <td>6</td>\n",
       "      <td>1161.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>揚羽はな</td>\n",
       "      <td>10</td>\n",
       "      <td>1197.600000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    name  submitted_count  characters_ave\n",
       "39  野咲タラ               10     1139.500000\n",
       "37  げんなり                9     1140.555556\n",
       "1     亜月                6     1161.333333\n",
       "44  揚羽はな               10     1197.600000"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "student_synopses \\\n",
    "    [(student_synopses.characters_ave <= 1200) & (student_synopses.submitted_count >= 5)] \\\n",
    "    [['name', 'submitted_count', 'characters_ave']] \\\n",
    "    .sort_values(by='characters_ave')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 文字数超過ワースト5"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "逆に、文字数制限を一切守る気のない、平均文字数のもっとも大きい人たちは次のとおりである。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>submitted_count</th>\n",
       "      <th>characters_ave</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>谷 美里</td>\n",
       "      <td>10</td>\n",
       "      <td>2002.800000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>宿禰</td>\n",
       "      <td>6</td>\n",
       "      <td>1946.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>国分寺崖線</td>\n",
       "      <td>10</td>\n",
       "      <td>1933.200000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>茶里 裕治</td>\n",
       "      <td>10</td>\n",
       "      <td>1803.100000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45</th>\n",
       "      <td>ヤナギサワ　カズキ</td>\n",
       "      <td>9</td>\n",
       "      <td>1699.777778</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         name  submitted_count  characters_ave\n",
       "25       谷 美里               10     2002.800000\n",
       "8          宿禰                6     1946.666667\n",
       "21      国分寺崖線               10     1933.200000\n",
       "3       茶里 裕治               10     1803.100000\n",
       "45  ヤナギサワ　カズキ                9     1699.777778"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "student_synopses[student_synopses.submitted_count >= 2][['name', 'submitted_count', 'characters_ave']] \\\n",
    "    .sort_values(by='characters_ave', ascending=False).head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 梗概選出回数"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "3回以上梗概を選出されたのは5人、うち4回選出されたのは斧田 小夜さん1人だった。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>selected_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>フジ・ナカハラ</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>維嶋津/いしましん</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>小野 十郎</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47</th>\n",
       "      <td>琴柱遥</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         name  selected_count\n",
       "43      斧田 小夜               4\n",
       "7     フジ・ナカハラ               3\n",
       "16  維嶋津/いしましん               3\n",
       "29      小野 十郎               3\n",
       "47        琴柱遥               3"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "student_synopses[student_synopses.selected_count >= 3][['name', 'selected_count']] \\\n",
    "    .sort_values(by='selected_count', ascending=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 梗概選出率"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "しかし、梗概選出回数を提出回数で割った「梗概選出率」でみると、1位は私になる。  \n",
    "「受講生勝手にランキング」などと言いながら、これがやりたかっただけである。  \n",
    "ちなみに、選出実作1編あたりの得点でランキングをつくった場合は、私がワースト1位になってしまう。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>submitted_count</th>\n",
       "      <th>selected_count</th>\n",
       "      <th>selected_rate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>フジ・ナカハラ</td>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>0.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>10</td>\n",
       "      <td>4</td>\n",
       "      <td>0.400000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>小野 十郎</td>\n",
       "      <td>8</td>\n",
       "      <td>3</td>\n",
       "      <td>0.375000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>維嶋津/いしましん</td>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "      <td>0.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47</th>\n",
       "      <td>琴柱遥</td>\n",
       "      <td>10</td>\n",
       "      <td>3</td>\n",
       "      <td>0.300000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         name  submitted_count  selected_count  selected_rate\n",
       "7     フジ・ナカハラ                6               3       0.500000\n",
       "43      斧田 小夜               10               4       0.400000\n",
       "29      小野 十郎                8               3       0.375000\n",
       "16  維嶋津/いしましん                9               3       0.333333\n",
       "47        琴柱遥               10               3       0.300000"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_rate = (student_synopses.selected_count / student_synopses.submitted_count).fillna(0)\n",
    "selected_rate.name = 'selected_rate'\n",
    "pd.concat([student_synopses, selected_rate], axis=1)\\\n",
    "    [['name', 'submitted_count', 'selected_count', 'selected_rate']] \\\n",
    "    .sort_values(by='selected_rate', ascending=False).head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 実作"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "つぎは、実作に関するランキングをみていこう。  \n",
    "データとして用いるのは以下の表である。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>submitted_count</th>\n",
       "      <th>optional_count</th>\n",
       "      <th>score</th>\n",
       "      <th>optional_score</th>\n",
       "      <th>characters_sum</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>伊藤 元晴</td>\n",
       "      <td>7</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>3</td>\n",
       "      <td>119855</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>亜月</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>甘木 零</td>\n",
       "      <td>7</td>\n",
       "      <td>6</td>\n",
       "      <td>8</td>\n",
       "      <td>3</td>\n",
       "      <td>101547</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>茶里 裕治</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>54</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>遠山軌道</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>83332</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>篠田 航平</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>夢想 真</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>フジ・ナカハラ</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>33434</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>宿禰</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>11</td>\n",
       "      <td>0</td>\n",
       "      <td>43795</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>灰田 頼人</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>菊地 和広</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>広木 素数一</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>結城 イケ</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>今井 曖昧</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>縞里 若菜</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>安岐 いぬこ</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>維嶋津/いしましん</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>19</td>\n",
       "      <td>0</td>\n",
       "      <td>50007</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>伊藤屋 イトウ</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>カケヒマサヒデ</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>武見 倉森</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>17274</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>生田目 ケイ</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>21564</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>国分寺崖線</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>12</td>\n",
       "      <td>1</td>\n",
       "      <td>96056</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>茶瓶</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>_</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>黒田 渚</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>48259</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>谷 美里</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>14</td>\n",
       "      <td>0</td>\n",
       "      <td>73029</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>moimasa5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>諸根 いつみ</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>91385</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>夏川 智樹</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>小野 十郎</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>89182</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>やまね</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>14985</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>薮　ゆき</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>中外中</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>伊吹</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>進藤尚典</td>\n",
       "      <td>8</td>\n",
       "      <td>6</td>\n",
       "      <td>12</td>\n",
       "      <td>2</td>\n",
       "      <td>103795</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>右手 新土</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>shgee</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>げんなり</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38</th>\n",
       "      <td>不二 拓/tack</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>野咲タラ</td>\n",
       "      <td>7</td>\n",
       "      <td>7</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>91901</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40</th>\n",
       "      <td>俵野 道生</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8122</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41</th>\n",
       "      <td>安藤 タカシ</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>50014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42</th>\n",
       "      <td>瓜田 流</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>9</td>\n",
       "      <td>5</td>\n",
       "      <td>41</td>\n",
       "      <td>11</td>\n",
       "      <td>194215</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>揚羽はな</td>\n",
       "      <td>6</td>\n",
       "      <td>4</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>84768</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45</th>\n",
       "      <td>ヤナギサワ　カズキ</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46</th>\n",
       "      <td>足立 佑</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47</th>\n",
       "      <td>琴柱遥</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>46</td>\n",
       "      <td>0</td>\n",
       "      <td>100798</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         name  submitted_count  optional_count  score  optional_score  \\\n",
       "0       伊藤 元晴                7               5     22               3   \n",
       "1          亜月                0               0      0               0   \n",
       "2        甘木 零                7               6      8               3   \n",
       "3       茶里 裕治                1               0      7               0   \n",
       "4        遠山軌道                4               4      3               3   \n",
       "5       篠田 航平                0               0      0               0   \n",
       "6        夢想 真                0               0      0               0   \n",
       "7     フジ・ナカハラ                2               0      2               0   \n",
       "8          宿禰                3               2     11               0   \n",
       "9       灰田 頼人                0               0      0               0   \n",
       "10      菊地 和広                0               0      0               0   \n",
       "11     広木 素数一                0               0      0               0   \n",
       "12      結城 イケ                0               0      0               0   \n",
       "13      今井 曖昧                0               0      0               0   \n",
       "14      縞里 若菜                0               0      0               0   \n",
       "15     安岐 いぬこ                0               0      0               0   \n",
       "16  維嶋津/いしましん                3               0     19               0   \n",
       "17    伊藤屋 イトウ                0               0      0               0   \n",
       "18    カケヒマサヒデ                0               0      0               0   \n",
       "19      武見 倉森                1               0      6               0   \n",
       "20     生田目 ケイ                2               2      0               0   \n",
       "21      国分寺崖線                5               3     12               1   \n",
       "22         茶瓶                0               0      0               0   \n",
       "23          _                0               0      0               0   \n",
       "24       黒田 渚                3               3      1               1   \n",
       "25       谷 美里                5               3     14               0   \n",
       "26   moimasa5                0               0      0               0   \n",
       "27     諸根 いつみ                5               5      4               4   \n",
       "28      夏川 智樹                0               0      0               0   \n",
       "29      小野 十郎                3               1     12               0   \n",
       "30        やまね                1               0      6               0   \n",
       "31       薮　ゆき                0               0      0               0   \n",
       "32        中外中                0               0      0               0   \n",
       "33         伊吹                0               0      0               0   \n",
       "34       進藤尚典                8               6     12               2   \n",
       "35      右手 新土                0               0      0               0   \n",
       "36      shgee                0               0      0               0   \n",
       "37       げんなり                0               0      0               0   \n",
       "38  不二 拓/tack                0               0      0               0   \n",
       "39       野咲タラ                7               7      2               2   \n",
       "40      俵野 道生                1               1      0               0   \n",
       "41     安藤 タカシ                5               5      0               0   \n",
       "42       瓜田 流                0               0      0               0   \n",
       "43      斧田 小夜                9               5     41              11   \n",
       "44       揚羽はな                6               4     10               0   \n",
       "45  ヤナギサワ　カズキ                0               0      0               0   \n",
       "46       足立 佑                0               0      0               0   \n",
       "47        琴柱遥                4               1     46               0   \n",
       "\n",
       "    characters_sum  \n",
       "0           119855  \n",
       "1                0  \n",
       "2           101547  \n",
       "3               54  \n",
       "4            83332  \n",
       "5                0  \n",
       "6                0  \n",
       "7            33434  \n",
       "8            43795  \n",
       "9                0  \n",
       "10               0  \n",
       "11               0  \n",
       "12               0  \n",
       "13               0  \n",
       "14               0  \n",
       "15               0  \n",
       "16           50007  \n",
       "17               0  \n",
       "18               0  \n",
       "19           17274  \n",
       "20           21564  \n",
       "21           96056  \n",
       "22               0  \n",
       "23               0  \n",
       "24           48259  \n",
       "25           73029  \n",
       "26               0  \n",
       "27           91385  \n",
       "28               0  \n",
       "29           89182  \n",
       "30           14985  \n",
       "31               0  \n",
       "32               0  \n",
       "33               0  \n",
       "34          103795  \n",
       "35               0  \n",
       "36               0  \n",
       "37               0  \n",
       "38               0  \n",
       "39           91901  \n",
       "40            8122  \n",
       "41           50014  \n",
       "42               0  \n",
       "43          194215  \n",
       "44           84768  \n",
       "45               0  \n",
       "46               0  \n",
       "47          100798  "
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "student_works"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 実作提出回数"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "実作提出回数トップ5は次のとおりである。  \n",
    "斧田さんは実作も皆勤賞だった。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>submitted_count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>進藤尚典</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>伊藤 元晴</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>甘木 零</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>野咲タラ</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     name  submitted_count\n",
       "43  斧田 小夜                9\n",
       "34   進藤尚典                8\n",
       "0   伊藤 元晴                7\n",
       "2    甘木 零                7\n",
       "39   野咲タラ                7"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "student_works[student_works.submitted_count >= 7][['name', 'submitted_count']] \\\n",
    "    .sort_values(by='submitted_count', ascending=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 自主提出得点"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "点数の入りにくい自主提出の得点だけでランキングすると、トップ5は次のようになる。  \n",
    "ここでも斧田さんが1位。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>optional_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>諸根 いつみ</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>伊藤 元晴</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>甘木 零</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>遠山軌道</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      name  optional_score\n",
       "43   斧田 小夜              11\n",
       "27  諸根 いつみ               4\n",
       "0    伊藤 元晴               3\n",
       "2     甘木 零               3\n",
       "4     遠山軌道               3"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "student_works[student_works.optional_score >= 3][['name', 'optional_score']] \\\n",
    "    .sort_values(by='optional_score', ascending=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 実作総文字数"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "最後に、実作の総文字数トップ5である。  \n",
    "当然斧田さんが1位。だんとつの20万字である。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>characters_sum</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>斧田 小夜</td>\n",
       "      <td>194215</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>伊藤 元晴</td>\n",
       "      <td>119855</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>進藤尚典</td>\n",
       "      <td>103795</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>甘木 零</td>\n",
       "      <td>101547</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47</th>\n",
       "      <td>琴柱遥</td>\n",
       "      <td>100798</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     name  characters_sum\n",
       "43  斧田 小夜          194215\n",
       "0   伊藤 元晴          119855\n",
       "34   進藤尚典          103795\n",
       "2    甘木 零          101547\n",
       "47    琴柱遥          100798"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "student_works[['name', 'characters_sum']].sort_values(by='characters_sum', ascending=False).head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "実作に関する数字は斧田さんが圧倒的であった。  \n",
    "それでも、総得点は琴柱遥さんが1位である。  \n",
    "星新一賞の一般部門優秀賞を受賞し、ただひとり文字数を遵守した揚羽さんにも注目したい。\n",
    "\n",
    "はたして、ゲンロンSF新人賞は誰の手に渡るのか。"
   ]
  }
 ],
 "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": "3.7.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}