{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 第7章『適合度検定』"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## p.137"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-04-14T17:28:12.645564Z",
     "start_time": "2019-04-14T17:28:12.351168Z"
    }
   },
   "outputs": [],
   "source": [
    "\"\"\" Pythonでは累乗計算では ** または pow を用います。 \"\"\"\n",
    "\"\"\" Pythonでは配列の要素ごとの演算は numpy を用います。 \"\"\"\n",
    "\"\"\" Pythonでは検定には scipy.stats が便利です。 \"\"\"\n",
    "# https://ryamada.hatenadiary.jp/entry/20150101/1419899280\n",
    "\n",
    "import numpy as np\n",
    "import scipy.stats\n",
    "\n",
    "def HWE_test(o1, o2, o3):\n",
    "    n = o1 + o2 + o3\n",
    "    p = (2*o1 + o2)/(2*n)\n",
    "    ob = np.array([o1,o2,o3])\n",
    "    ex = np.array([n*p**2, 2*n*p*(1-p), n*(1-p)**2])\n",
    "    X = np.sum((ob-ex)**2/ex)\n",
    "    p_value = 1 - scipy.stats.chi2.cdf(X, 1)\n",
    "    print(p_value)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-04-14T17:28:16.188314Z",
     "start_time": "2019-04-14T17:28:16.183829Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.002701152959209474\n"
     ]
    }
   ],
   "source": [
    "HWE_test(50, 120, 30)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## p.139"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-04-14T17:28:31.937454Z",
     "start_time": "2019-04-14T17:28:31.932703Z"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import scipy.stats\n",
    "# https://docs.scipy.org/doc/scipy-0.15.1/reference/generated/scipy.stats.chi2_contingency.html\n",
    "\n",
    "def Association_test(n10, n11, n12, n20, n21, n22):\n",
    "    case = np.array([2*n10+n11,n11+2*n12])\n",
    "    ctrl = np.array([2*n20+n21,n21+2*n22])\n",
    "    matrix = np.array([case, ctrl])\n",
    "    result = scipy.stats.chi2_contingency(matrix, correction=False)\n",
    "    print(result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-04-14T17:28:50.801685Z",
     "start_time": "2019-04-14T17:28:50.797960Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(9.603841536614647, 0.0019417073371168674, 1, array([[196., 204.],\n",
      "       [294., 306.]]))\n"
     ]
    }
   ],
   "source": [
    "Association_test(50, 120, 30, 60, 150, 90)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-04-14T17:28:53.034914Z",
     "start_time": "2019-04-14T17:28:53.030032Z"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import scipy.stats\n",
    "# https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.fisher_exact.html\n",
    "\n",
    "def Association_test_fisher(n10, n11, n12, n20, n21, n22):\n",
    "    case = np.array([2*n10+n11, n11+2*n12])\n",
    "    ctrl = np.array([2*n20+n21, n21+2*n22])\n",
    "    matrix = np.array([case, ctrl])\n",
    "    result = scipy.stats.fisher_exact(matrix)\n",
    "    print(result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-04-14T17:28:58.367014Z",
     "start_time": "2019-04-14T17:28:58.341849Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1.4938271604938271, 0.0023904276302564188)\n"
     ]
    }
   ],
   "source": [
    "Association_test_fisher(50, 120, 30, 60, 150, 90)"
   ]
  }
 ],
 "metadata": {
  "hide_input": false,
  "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": "3.7.6"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": false,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": true,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": true
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}