03_rank_test_chi2.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "b9b044ba-d751-48ec-b727-437d7c0e708d",
   "metadata": {},
   "source": [
    "# About\n",
    "\n",
    "順位の適合度検定をする"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "8818179d-9fd4-4cca-a8bb-36ffc4e650b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import collections\n",
    "import scipy\n",
    "\n",
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "sns.set(font_scale=1.5)\n",
    "c_list = sns.color_palette().as_hex()\n",
    "color_num = len(c_list)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "94d695c6-a015-422e-b32c-6044001773ae",
   "metadata": {},
   "outputs": [],
   "source": [
    "dct_player = {\n",
    "    \"さくま\": \"sakuma\", \"ようきひ\":\"yohkihi\", \"ガキ\": \"gaki\"\n",
    "}\n",
    "\n",
    "s = \"\"\"\n",
    "さくま:ガキ:ようきひ\n",
    "さくま:ようきひ:ガキ\n",
    "ガキ:ようきひ:さくま\n",
    "ようきひ:ガキ:さくま\n",
    "ようきひ:さくま:ガキ\n",
    "ようきひ:ガキ:さくま\n",
    "ようきひ:ガキ:さくま\n",
    "ようきひ:さくま:ガキ\n",
    "ようきひ:さくま:ガキ\n",
    "さくま:ガキ:ようきひ\n",
    "ガキ:さくま:ようきひ\n",
    "ようきひ:さくま:ガキ\n",
    "ようきひ:さくま:ガキ\n",
    "ようきひ:さくま:ガキ\n",
    "さくま:ようきひ:ガキ\n",
    "さくま:ガキ:ようきひ\n",
    "さくま:ようきひ:ガキ\n",
    "さくま:ガキ:ようきひ\n",
    "ようきひ:ガキ:さくま\n",
    "ようきひ:さくま:ガキ\n",
    "ようきひ:さくま:ガキ\n",
    "ようきひ:さくま:ガキ\n",
    "ようきひ:さくま:ガキ\n",
    "ようきひ:さくま:ガキ\n",
    "ようきひ:さくま:ガキ\n",
    "ようきひ:さくま:ガキ\n",
    "ようきひ:さくま:ガキ\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "323959d8-0d9b-40f7-955e-5e9f89acbd73",
   "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>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>さくま</td>\n",
       "      <td>ガキ</td>\n",
       "      <td>ようきひ</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>さくま</td>\n",
       "      <td>ようきひ</td>\n",
       "      <td>ガキ</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ガキ</td>\n",
       "      <td>ようきひ</td>\n",
       "      <td>さくま</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ようきひ</td>\n",
       "      <td>ガキ</td>\n",
       "      <td>さくま</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ようきひ</td>\n",
       "      <td>さくま</td>\n",
       "      <td>ガキ</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      1     2     3\n",
       "0   さくま    ガキ  ようきひ\n",
       "1   さくま  ようきひ    ガキ\n",
       "2    ガキ  ようきひ   さくま\n",
       "3  ようきひ    ガキ   さくま\n",
       "4  ようきひ   さくま    ガキ"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lst_rank = []\n",
    "for t in s.strip().split(\"\\n\"):\n",
    "    rank = t.split(\":\")\n",
    "    lst_rank.append({1:rank[0], 2:rank[1], 3:rank[2]})\n",
    "df_rank = pd.DataFrame(lst_rank)\n",
    "df_rank.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "1f566143-7d7d-4da6-8673-9848e19022ea",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Counter({'さくま': 7, 'ガキ': 2, 'ようきひ': 18})"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cnt_top = collections.Counter(df_rank[1])\n",
    "cnt_top"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4b6a8c5e-65ee-4b38-9e23-fbac78e04992",
   "metadata": {},
   "source": [
    "# 適合度検定"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1c61b3ee-51c8-48eb-ab53-2a352adb4718",
   "metadata": {},
   "source": [
    "## 3人の勝率の当確率性"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "50069a12-3406-4075-bf4c-75360bb1cc20",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[7, 2, 18]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "top_cnt = list(cnt_top.values())\n",
    "top_cnt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "6b8d1ae9-41df-4e78-9539-b20eb68db40c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([9., 9., 9.])"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "exp = np.ones(3)/3 * sum(top_cnt)\n",
    "exp"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "7cb0224a-8608-44d3-8fee-cace1f1fa4b0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Power_divergenceResult(statistic=14.88888888888889, pvalue=0.0005846808328765149)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scipy.stats.chisquare(top_cnt, f_exp=exp)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "76383dae-624d-45fa-9b4a-94ed7f4af9df",
   "metadata": {},
   "source": [
    "## さくまとようきひの勝率"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "a62d2729-f441-42a9-a205-b4785de02f18",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'さくま': 7, 'ようきひ': 18}"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "[7, 18]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "array([12.5, 12.5])"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "targets = [\"さくま\", \"ようきひ\"]\n",
    "dct_top_cnt = {k:v for k, v in cnt_top.items() if (k in targets)}\n",
    "top_cnt = list(dct_top_cnt.values())\n",
    "exp = (np.ones(len(targets)) / len(targets)) * sum(top_cnt)\n",
    "\n",
    "display(dct_top_cnt)\n",
    "display(top_cnt)\n",
    "display(exp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "3ebafe9e-36f1-4444-8e5c-daca06babae6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Power_divergenceResult(statistic=4.84, pvalue=0.027806895026997226)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scipy.stats.chisquare(top_cnt, f_exp=exp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "051f8640-ff7a-4931-b4ce-52743127d19c",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}