{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "078900c6-d71d-44f0-9e76-cc5ce66f0ca9",
   "metadata": {},
   "source": [
    "# Logistic regression: using general fit\n",
    "\n",
    "Exploring different fitting techniques and using MLE asymptotic approx of parameter distribution to estimate model CI intervals.\n",
    "\n",
    "Using Logistic regression class."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e18cec5e",
   "metadata": {},
   "source": [
    "## Common"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "3b351af7",
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import scipy\n",
    "\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import os\n",
    "\n",
    "# our libs\n",
    "import data_utils\n",
    "import logit_gen\n",
    "\n",
    "np.set_printoptions(precision=16)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e0de7f02-942b-42ff-874c-3c0e2ac1e0dc",
   "metadata": {},
   "source": [
    "## Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "3373f87f",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "results_path = \"./results\"\n",
    "if not os.path.exists(results_path): os.makedirs(results_path)\n",
    "\n",
    "data_path = \"../../data/\"\n",
    "suv_filename = os.path.join(data_path, \"suv_percentilesSLOthenUWM.mat\")\n",
    "flags_filename = os.path.join(data_path,\"flags_combined.mat\")\n",
    "normal_range_filename = os.path.join(data_path, \"normal_range.mat\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "811d990d",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "\"\"\"\n",
    "Loading all data\n",
    "\"\"\"\n",
    "suv_dict = scipy.io.loadmat(suv_filename)\n",
    "flags_dict = scipy.io.loadmat(flags_filename)\n",
    "normal_range_dict = scipy.io.loadmat(normal_range_filename)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "4a292c31",
   "metadata": {},
   "outputs": [],
   "source": [
    "# get data\n",
    "perc = 95\n",
    "organ = \"lung\"\n",
    "\n",
    "x0, y = data_utils.get_data(organ, perc, suv_dict, flags_dict)\n",
    "\n",
    "scales = [\"plain\", \"log\"]\n",
    "xs = [x0, np.log(x0)]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "35e9bb7b-5a50-4cae-9af4-261c11453dd4",
   "metadata": {},
   "source": [
    "## Fit\n",
    "\n",
    "Ref: logistic regression documentation\n",
    "* https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
    "* https://stats.stackexchange.com/questions/186830/what-is-scikit-learns-logisticregression-minimizing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "239ae789",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "application/vnd.microsoft.datawrangler.viewer.v0+json": {
       "columns": [
        {
         "name": "scale",
         "rawType": "object",
         "type": "string"
        },
        {
         "name": "pars",
         "rawType": "object",
         "type": "unknown"
        },
        {
         "name": "cost",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "success",
         "rawType": "bool",
         "type": "boolean"
        }
       ],
       "ref": "88c239ca-37ff-4998-a26d-0ae21cd0770b",
       "rows": [
        [
         "plain",
         "[-24.95282468101097     0.7197035437687624  -1.375610632716079\n   4.742670263605188 ]",
         "6.958343476437389",
         "True"
        ],
        [
         "log",
         "[-2.2050224224507048e+01 -6.4876272607921720e-07  9.0151787252668498e+00\n -8.5482037800709261e+00]",
         "5.608180093799169",
         "True"
        ]
       ],
       "shape": {
        "columns": 3,
        "rows": 2
       }
      },
      "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>pars</th>\n",
       "      <th>cost</th>\n",
       "      <th>success</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>scale</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>plain</th>\n",
       "      <td>[-24.95282468101097, 0.7197035437687624, -1.37...</td>\n",
       "      <td>6.958343</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log</th>\n",
       "      <td>[-22.050224224507048, -6.487627260792172e-07, ...</td>\n",
       "      <td>5.608180</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                    pars      cost  success\n",
       "scale                                                                      \n",
       "plain  [-24.95282468101097, 0.7197035437687624, -1.37...  6.958343     True\n",
       "log    [-22.050224224507048, -6.487627260792172e-07, ...  5.608180     True"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# fits\n",
    "lg = logit_gen.LogisticPolyRegression(3, mono = True, lam = (0, 1e-3))\n",
    "ress = [lg.fit(x, y, method=\"diff_evol\") for x in xs]\n",
    "\n",
    "pd.DataFrame(ress, index = pd.Index(scales, name = 'scale'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "d9044f0b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "pars:\n"
     ]
    },
    {
     "data": {
      "application/vnd.microsoft.datawrangler.viewer.v0+json": {
       "columns": [
        {
         "name": "scale",
         "rawType": "object",
         "type": "string"
        },
        {
         "name": "0",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "1",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "2",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "3",
         "rawType": "float64",
         "type": "float"
        }
       ],
       "ref": "e469a0ea-5cb7-430d-84bc-9a18e7408802",
       "rows": [
        [
         "plain",
         "-24.95282468101097",
         "0.7197035437687624",
         "-1.375610632716079",
         "4.742670263605188"
        ],
        [
         "log",
         "-22.050224224507048",
         "-6.487627260792172e-07",
         "9.01517872526685",
         "-8.548203780070926"
        ]
       ],
       "shape": {
        "columns": 4,
        "rows": 2
       }
      },
      "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>scale</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>plain</th>\n",
       "      <td>-24.952825</td>\n",
       "      <td>7.197035e-01</td>\n",
       "      <td>-1.375611</td>\n",
       "      <td>4.742670</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log</th>\n",
       "      <td>-22.050224</td>\n",
       "      <td>-6.487627e-07</td>\n",
       "      <td>9.015179</td>\n",
       "      <td>-8.548204</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               0             1         2         3\n",
       "scale                                             \n",
       "plain -24.952825  7.197035e-01 -1.375611  4.742670\n",
       "log   -22.050224 -6.487627e-07  9.015179 -8.548204"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "parss = np.array([r[\"pars\"] for r in ress])\n",
    "\n",
    "print(\"pars:\")\n",
    "pd.DataFrame(parss, index = pd.Index(scales, name = 'scale'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "9a99322a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "------------------------\n",
      "pars=[np.float64(-24.95282468101097), np.float64(0.7197035437687624), np.float64(-1.375610632716079), np.float64(4.742670263605188)]\n",
      "beta=[np.float64(-24.95282468101097), np.float64(23.01089442019822), np.float64(-6.524067642081666), np.float64(0.6307682042805105)]\n",
      "nllf = 6.310796817843079, jac = [np.float64(0.049905820100136666), np.float64(-0.001439122217907679), np.float64(0.0027524581445015905), np.float64(-0.009483619507843766)]\n",
      "------------------------\n",
      "pars=[np.float64(-22.050224224507048), np.float64(-6.487627260792172e-07), np.float64(9.01517872526685), np.float64(-8.548203780070926)]\n",
      "beta=[np.float64(-22.050224224507048), np.float64(73.0717878656193), np.float64(-77.06358485734108), np.float64(27.091149149501344)]\n",
      "nllf = 4.967622470134009, jac = [np.float64(0.04410050178479885), np.float64(-5.942272603936023e-08), np.float64(-0.018030250005959293), np.float64(0.017096399653879296)]\n"
     ]
    }
   ],
   "source": [
    "for x, pars in zip(xs, parss): \n",
    "    r = lg.get_nllf(x, y, pars, jac = True)\n",
    "    beta = lg.get_beta(pars)\n",
    "    print(\"------------------------\")\n",
    "    print(f\"pars={list(pars)}\")\n",
    "    print(f\"beta={list(beta)}\")\n",
    "    print(f\"nllf = {r[0]}, jac = {list(r[1])}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "9cf6fec1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "cov_pars = array([[ 3.7011408751970407e+02, -5.5275274011364877e+00,\n",
      "         3.0236311799020555e+01, -5.2846325842595704e+01],\n",
      "       [-5.5275274011148117e+00,  6.0129442912447262e+00,\n",
      "        -1.4488804385876226e+00,  3.3732862043891326e-01],\n",
      "       [ 3.0236311799016239e+01, -1.4488804385893441e+00,\n",
      "         2.8241043319591674e+00, -4.3946706511078730e+00],\n",
      "       [-5.2846325842596791e+01,  3.3732862044203366e-01,\n",
      "        -4.3946706511085809e+00,  7.7094728942172042e+00]])\n",
      "cov_pars = array([[ 4.4630805323192696e+01, -6.8539122151507012e-06,\n",
      "        -1.1803149245747390e+01,  9.4618054754664147e+00],\n",
      "       [-6.8539122181012422e-06,  1.0684453870708955e+01,\n",
      "         8.0745911105747215e-07, -2.4825789051200138e-06],\n",
      "       [-1.1803149245746660e+01,  8.0745911316225257e-07,\n",
      "         6.2368113611918439e+00, -3.3220285138687586e+00],\n",
      "       [ 9.4618054754662140e+00, -2.4825789074935547e-06,\n",
      "        -3.3220285138688466e+00,  2.2332146827532942e+00]])\n"
     ]
    }
   ],
   "source": [
    "# asymptotic covariance matrix of parameters\n",
    "cov_parss = np.array([lg.get_cov(x, y, pars) for x, pars in zip(xs, parss)])\n",
    "\n",
    "for cov_pars in cov_parss: print(f\"{cov_pars = }\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "cbc4c71e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[3.8022151330933002e+02 6.1326745130114517e+00 3.0465641739904520e-01\n",
      " 1.7647973847460007e-03]\n",
      "[5.0063827282275831e+01 3.0263623402922155e+00 1.0641744570845628e-02\n",
      " 1.0684453870707888e+01]\n"
     ]
    }
   ],
   "source": [
    "# check eigenvalues\n",
    "for cov_pars in cov_parss: print(np.linalg.eigvals(cov_pars))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "2359d3c1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# defining two-sided confidence intervals\n",
    "alpha = 0.05   # significance level\n",
    "probs = [alpha/2, 1 - alpha/2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "4ba4d5d4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "pars_CI = array([[-62.65929662106028  ,  -4.086384042401973 ,  -4.66934415207751  ,\n",
      "         -0.6993535008038725],\n",
      "       [ 12.75364725903832  ,   5.525791129939497 ,   1.9181228866453512,\n",
      "         10.184694028014247 ]])\n",
      "pars_CI = array([[-35.14401667678996  ,  -6.406551168811283 ,   4.1204413455440365,\n",
      "        -11.477163022116859 ],\n",
      "       [ -8.956431772224137 ,   6.406549871285828 ,  13.909916104989662 ,\n",
      "         -5.619244538024995 ]])\n"
     ]
    }
   ],
   "source": [
    "# CI of params (assuming asymptotic distr of parameters) : Wald approximation\n",
    "pars_CIs = np.array([lg.get_pars_quantiles_normal(probs, pars, cov_pars) for pars, cov_pars in zip(parss, cov_parss)])\n",
    "\n",
    "for pars_CI in pars_CIs: print(f\"{pars_CI = }\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "96acc3ab",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.microsoft.datawrangler.viewer.v0+json": {
       "columns": [
        {
         "name": "index",
         "rawType": "int64",
         "type": "integer"
        },
        {
         "name": "scale",
         "rawType": "object",
         "type": "string"
        },
        {
         "name": "coef",
         "rawType": "object",
         "type": "string"
        },
        {
         "name": "value",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "LCL",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "UCL",
         "rawType": "float64",
         "type": "float"
        }
       ],
       "ref": "ac4418d7-e493-4bd3-a17d-778c4e6ef6f1",
       "rows": [
        [
         "0",
         "plain",
         "p0",
         "-24.95282468101097",
         "-62.65929662106028",
         "12.75364725903832"
        ],
        [
         "1",
         "plain",
         "p1",
         "0.7197035437687624",
         "-4.086384042401973",
         "5.525791129939497"
        ],
        [
         "2",
         "plain",
         "p2",
         "-1.375610632716079",
         "-4.66934415207751",
         "1.9181228866453512"
        ],
        [
         "3",
         "plain",
         "p3",
         "4.742670263605188",
         "-0.6993535008038725",
         "10.184694028014247"
        ],
        [
         "4",
         "log",
         "p0",
         "-22.050224224507048",
         "-35.14401667678996",
         "-8.956431772224137"
        ],
        [
         "5",
         "log",
         "p1",
         "-6.487627260792172e-07",
         "-6.406551168811283",
         "6.406549871285828"
        ],
        [
         "6",
         "log",
         "p2",
         "9.01517872526685",
         "4.1204413455440365",
         "13.909916104989662"
        ],
        [
         "7",
         "log",
         "p3",
         "-8.548203780070926",
         "-11.477163022116859",
         "-5.619244538024995"
        ]
       ],
       "shape": {
        "columns": 5,
        "rows": 8
       }
      },
      "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>scale</th>\n",
       "      <th>coef</th>\n",
       "      <th>value</th>\n",
       "      <th>LCL</th>\n",
       "      <th>UCL</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>plain</td>\n",
       "      <td>p0</td>\n",
       "      <td>-2.495282e+01</td>\n",
       "      <td>-62.659297</td>\n",
       "      <td>12.753647</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>plain</td>\n",
       "      <td>p1</td>\n",
       "      <td>7.197035e-01</td>\n",
       "      <td>-4.086384</td>\n",
       "      <td>5.525791</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>plain</td>\n",
       "      <td>p2</td>\n",
       "      <td>-1.375611e+00</td>\n",
       "      <td>-4.669344</td>\n",
       "      <td>1.918123</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>plain</td>\n",
       "      <td>p3</td>\n",
       "      <td>4.742670e+00</td>\n",
       "      <td>-0.699354</td>\n",
       "      <td>10.184694</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>log</td>\n",
       "      <td>p0</td>\n",
       "      <td>-2.205022e+01</td>\n",
       "      <td>-35.144017</td>\n",
       "      <td>-8.956432</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>log</td>\n",
       "      <td>p1</td>\n",
       "      <td>-6.487627e-07</td>\n",
       "      <td>-6.406551</td>\n",
       "      <td>6.406550</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>log</td>\n",
       "      <td>p2</td>\n",
       "      <td>9.015179e+00</td>\n",
       "      <td>4.120441</td>\n",
       "      <td>13.909916</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>log</td>\n",
       "      <td>p3</td>\n",
       "      <td>-8.548204e+00</td>\n",
       "      <td>-11.477163</td>\n",
       "      <td>-5.619245</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   scale coef         value        LCL        UCL\n",
       "0  plain   p0 -2.495282e+01 -62.659297  12.753647\n",
       "1  plain   p1  7.197035e-01  -4.086384   5.525791\n",
       "2  plain   p2 -1.375611e+00  -4.669344   1.918123\n",
       "3  plain   p3  4.742670e+00  -0.699354  10.184694\n",
       "4    log   p0 -2.205022e+01 -35.144017  -8.956432\n",
       "5    log   p1 -6.487627e-07  -6.406551   6.406550\n",
       "6    log   p2  9.015179e+00   4.120441  13.909916\n",
       "7    log   p3 -8.548204e+00 -11.477163  -5.619245"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# nr of parameters\n",
    "d = parss.shape[-1]\n",
    "\n",
    "# present table of results\n",
    "df_pars_CI_wald = pd.DataFrame({\n",
    "    \"scale\" :[lab for lab in scales for _ in range(d)],\n",
    "    \"coef\" : [ f\"p{i}\" for _ in scales for i in range(d)],\n",
    "    \"value\" : parss.flatten(), \n",
    "    \"LCL\" : pars_CIs[:,0].flatten(), \n",
    "    \"UCL\": pars_CIs[:,1].flatten()\n",
    "})\n",
    "\n",
    "df_pars_CI_wald"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "6ef6f46b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.microsoft.datawrangler.viewer.v0+json": {
       "columns": [
        {
         "name": "scale",
         "rawType": "object",
         "type": "string"
        },
        {
         "name": "LLF",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "AIC",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "BIC",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "A",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "chi2",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "p-value(chi2)",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "n",
         "rawType": "int64",
         "type": "integer"
        },
        {
         "name": "k",
         "rawType": "int64",
         "type": "integer"
        },
        {
         "name": "dof",
         "rawType": "int64",
         "type": "integer"
        }
       ],
       "ref": "41392858-3a0d-4d16-a0e5-74d9d2d1b909",
       "rows": [
        [
         "plain",
         "-6.310796817843079",
         "20.62159363568616",
         "28.863365677871833",
         "0.9655172413793104",
         "13.812460233264728",
         "0.9999999944452566",
         "58",
         "4",
         "54"
        ],
        [
         "log",
         "-4.967622470134009",
         "17.935244940268017",
         "26.177016982453694",
         "0.9655172413793104",
         "8.60216748552471",
         "0.9999999999998123",
         "58",
         "4",
         "54"
        ]
       ],
       "shape": {
        "columns": 9,
        "rows": 2
       }
      },
      "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>LLF</th>\n",
       "      <th>AIC</th>\n",
       "      <th>BIC</th>\n",
       "      <th>A</th>\n",
       "      <th>chi2</th>\n",
       "      <th>p-value(chi2)</th>\n",
       "      <th>n</th>\n",
       "      <th>k</th>\n",
       "      <th>dof</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>scale</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>plain</th>\n",
       "      <td>-6.310797</td>\n",
       "      <td>20.621594</td>\n",
       "      <td>28.863366</td>\n",
       "      <td>0.965517</td>\n",
       "      <td>13.812460</td>\n",
       "      <td>1.0</td>\n",
       "      <td>58</td>\n",
       "      <td>4</td>\n",
       "      <td>54</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>log</th>\n",
       "      <td>-4.967622</td>\n",
       "      <td>17.935245</td>\n",
       "      <td>26.177017</td>\n",
       "      <td>0.965517</td>\n",
       "      <td>8.602167</td>\n",
       "      <td>1.0</td>\n",
       "      <td>58</td>\n",
       "      <td>4</td>\n",
       "      <td>54</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            LLF        AIC        BIC         A       chi2  p-value(chi2)   n  \\\n",
       "scale                                                                           \n",
       "plain -6.310797  20.621594  28.863366  0.965517  13.812460            1.0  58   \n",
       "log   -4.967622  17.935245  26.177017  0.965517   8.602167            1.0  58   \n",
       "\n",
       "       k  dof  \n",
       "scale          \n",
       "plain  4   54  \n",
       "log    4   54  "
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# goodness of fit measures\n",
    "pd.DataFrame(\n",
    "    [lg.goodness_of_fit(x, y, pars) for x, pars in zip(xs, parss)], \n",
    "    index = pd.Index(scales, name = 'scale')\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "54f463d0",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plotting results\n",
    "fig, axs = plt.subplots(ncols = len(scales), figsize = (6*len(scales), 5))\n",
    "\n",
    "for ax, scale, x, pars, cov_pars in zip(axs, scales, xs, parss, cov_parss):\n",
    "\n",
    "    ax.set_title(f\"cond. prob. for AE: scale {scale}\")\n",
    "\n",
    "    if scale == \"plain\":\n",
    "        xlab = r\"$x = max_{visit} SUV(visit, p)$\"\n",
    "    else:\n",
    "        xlab = r\"$x = log(max_{visit} SUV(visit, p))$\"\n",
    "    \n",
    "    ax.set_xlabel(xlab)\n",
    "    ax.set_ylabel(\"P(AE|X = x)\")\n",
    "\n",
    "    # plotting data points\n",
    "    for i, lab in enumerate([\"NC\", \"AE\"]): ax.scatter(x[y == i], y[y == i], label = lab)  \n",
    "\n",
    "    # plotting fitted model \n",
    "    #xp = np.linspace(min(x), max(x), 100)\n",
    "    xp = np.linspace(min(x), max(x)+1, 100)\n",
    "    yp = lg.model(xp, pars)\n",
    "\n",
    "    ax.plot(xp, yp, label = \"logistic reg\")\n",
    "\n",
    "    for lab, c in zip([\"normal\", \"delta\"], [\"red\", \"green\"]):\n",
    "        \n",
    "        # define quantile model\n",
    "        fname = f\"lg.get_model_quantiles_{lab}\"\n",
    "        \n",
    "        # get result of model quantiles at probs\n",
    "        # pars and cov_pars are obtained via MLE method\n",
    "        res = eval(fname)(xp, probs, pars, cov_pars)\n",
    "\n",
    "        # make plot of quantiles\n",
    "        ax.fill_between(xp, *res, color = c, alpha = 0.5, label = f\"CI:{lab}\")\n",
    "\n",
    "handles, labels = ax.get_legend_handles_labels()\n",
    "fig.legend(handles, labels, bbox_to_anchor=(1.02, 0.5), loc='center right')\n",
    "\n",
    "plt.savefig(os.path.join(results_path, \"logit_fit.pdf\"))\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "67fa2c6c",
   "metadata": {},
   "source": [
    "##  Model CI"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "92080804",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "model CI:scale:plain,method:normal\n",
      "model CI:scale:plain,method:delta\n",
      "model CI:scale:plain,boots-method:normal\n",
      "model CI:scale:plain,boots-method:nonparam_boots\n",
      "model CI:scale:plain,boots-method:nonparam_stratified_boots\n",
      "model CI:scale:plain,boots-method:parametric_boots\n",
      "model CI:scale:log,method:normal\n",
      "model CI:scale:log,method:delta\n",
      "model CI:scale:log,boots-method:normal\n",
      "model CI:scale:log,boots-method:nonparam_boots\n",
      "model CI:scale:log,boots-method:nonparam_stratified_boots\n",
      "model CI:scale:log,boots-method:parametric_boots\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plotting results\n",
    "fig, axs = plt.subplots(ncols = len(scales), figsize = (6*len(scales), 5))\n",
    "\n",
    "boots_pars_results = dict()\n",
    "\n",
    "for ax, scale, x, pars, cov_pars in zip(axs, scales, xs, parss, cov_parss):\n",
    "\n",
    "    ax.set_title(f\"cond. prob. for AE: scale {scale}\")\n",
    "    \n",
    "    if scale == \"plain\":\n",
    "        xlab = r\"$x = max_{visit} SUV(visit, p)$\"\n",
    "    else:\n",
    "        xlab = r\"$x = log(max_{visit} SUV(visit, p))$\"\n",
    "    \n",
    "    ax.set_xlabel(xlab)\n",
    "    ax.set_ylabel(\"P(AE|X = x)\")\n",
    "\n",
    "    # plotting data points\n",
    "    for i, lab in enumerate([\"NC\", \"AE\"]): \n",
    "        ax.scatter(x[y == i], y[y == i], label = lab)  \n",
    "\n",
    "    # plotting fitted model\n",
    "    dx = max(x) - min(x)\n",
    "    xp = np.linspace(min(x) - 0.1*dx, max(x) + 0.1*dx, 100)\n",
    "    yp = lg.model(xp, pars)\n",
    "\n",
    "    ax.plot(xp, yp, label = \"logistic reg\")\n",
    "\n",
    "    for method, c in zip([\"normal\", \"delta\"], [\"red\", \"green\"]):\n",
    "        \n",
    "        print(f\"model CI:scale:{scale},method:{method}\")\n",
    "\n",
    "        # define quantile model\n",
    "        fname = f\"lg.get_model_quantiles_{method}\"\n",
    "        \n",
    "        # get result of model quantiles at probs\n",
    "        # pars and cov_pars are obtained via MLE method\n",
    "        res = eval(fname)(xp, probs, pars, cov_pars)\n",
    "\n",
    "        # make plot of quantiles\n",
    "        ax.fill_between(xp, *res, color = c, alpha = 0.5, label = f\"CI:{method}\")\n",
    "\n",
    "    # plot quantiles of models at bootstapped parameters\n",
    "    for method, c in zip(\n",
    "        [\"normal\", \"nonparam_boots\", \"nonparam_stratified_boots\", \"parametric_boots\"],\n",
    "        [\"orange\", \"pink\", \"purple\", \"cyan\"]):\n",
    "    \n",
    "        print(f\"model CI:scale:{scale},boots-method:{method}\")\n",
    "\n",
    "        # generate boostrapped parameters\n",
    "        m = 10000\n",
    "        fname = f\"lg.get_{method}_pars\"\n",
    "        bpars = eval(fname)(x, y, m)\n",
    "    \n",
    "        boots_pars_results[(scale, method)] = bpars\n",
    "\n",
    "        # quantiles\n",
    "        quant = np.quantile([lg.model(xp, p) for p in bpars], probs, axis = 0)\n",
    "\n",
    "        # make plot of quantiles\n",
    "        ax.fill_between(xp, *quant, color = c, alpha = 0.5, label = f\"CI:boots, {method}\")\n",
    "\n",
    "handles, labels = ax.get_legend_handles_labels()\n",
    "fig.legend(handles, labels, bbox_to_anchor=(1.17, 0.5), loc='center right')\n",
    "\n",
    "plt.savefig(os.path.join(results_path, \"logit_fit.pdf\"))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5ce16edf",
   "metadata": {},
   "source": [
    "## Parameter CI"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "18dce684",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "pars CI:scale:['plain', 'log'],method:Wald/delta\n",
      "model CI:scale:plain,boots-method:normal\n",
      "model CI:scale:plain,boots-method:nonparam_boots\n",
      "model CI:scale:plain,boots-method:nonparam_stratified_boots\n",
      "model CI:scale:plain,boots-method:parametric_boots\n",
      "model CI:scale:log,boots-method:normal\n",
      "model CI:scale:log,boots-method:nonparam_boots\n",
      "model CI:scale:log,boots-method:nonparam_stratified_boots\n",
      "model CI:scale:log,boots-method:parametric_boots\n"
     ]
    },
    {
     "data": {
      "application/vnd.microsoft.datawrangler.viewer.v0+json": {
       "columns": [
        {
         "name": "index",
         "rawType": "int64",
         "type": "integer"
        },
        {
         "name": "scale",
         "rawType": "object",
         "type": "string"
        },
        {
         "name": "coef",
         "rawType": "object",
         "type": "string"
        },
        {
         "name": "value",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "LCL",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "UCL",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "method",
         "rawType": "object",
         "type": "string"
        }
       ],
       "ref": "4dd7d8a5-8068-48a7-ab13-8e52a82e4578",
       "rows": [
        [
         "0",
         "plain",
         "p0",
         "-24.95282468101097",
         "-62.65929662106028",
         "12.75364725903832",
         "Wald/delta"
        ],
        [
         "1",
         "plain",
         "p1",
         "0.7197035437687624",
         "-4.086384042401973",
         "5.525791129939497",
         "Wald/delta"
        ],
        [
         "2",
         "plain",
         "p2",
         "-1.375610632716079",
         "-4.66934415207751",
         "1.9181228866453512",
         "Wald/delta"
        ],
        [
         "3",
         "plain",
         "p3",
         "4.742670263605188",
         "-0.6993535008038725",
         "10.184694028014247",
         "Wald/delta"
        ],
        [
         "4",
         "log",
         "p0",
         "-22.050224224507048",
         "-35.14401667678996",
         "-8.956431772224137",
         "Wald/delta"
        ],
        [
         "5",
         "log",
         "p1",
         "-6.487627260792172e-07",
         "-6.406551168811283",
         "6.406549871285828",
         "Wald/delta"
        ],
        [
         "6",
         "log",
         "p2",
         "9.01517872526685",
         "4.1204413455440365",
         "13.909916104989662",
         "Wald/delta"
        ],
        [
         "7",
         "log",
         "p3",
         "-8.548203780070926",
         "-11.477163022116859",
         "-5.619244538024995",
         "Wald/delta"
        ],
        [
         "8",
         "plain",
         "p0",
         "-24.95282468101097",
         "-62.48418243189562",
         "14.080803206494007",
         "normal"
        ],
        [
         "9",
         "plain",
         "p1",
         "0.7197035437687624",
         "-5.629421970938108",
         "3.9920853464629764",
         "normal"
        ],
        [
         "10",
         "plain",
         "p2",
         "-1.375610632716079",
         "-1.9616557392414524",
         "4.640407308941415",
         "normal"
        ],
        [
         "11",
         "plain",
         "p3",
         "4.742670263605188",
         "-10.166627341599623",
         "0.8589864899667288",
         "normal"
        ],
        [
         "12",
         "plain",
         "p0",
         "-24.95282468101097",
         "-33.24828168561239",
         "-8.590177152498258",
         "nonparam_boots"
        ],
        [
         "13",
         "plain",
         "p1",
         "0.7197035437687624",
         "-2.361954777043074",
         "2.321501825027682e-06",
         "nonparam_boots"
        ],
        [
         "14",
         "plain",
         "p2",
         "-1.375610632716079",
         "-6.183687527350962",
         "3.6526945787990175",
         "nonparam_boots"
        ],
        [
         "15",
         "plain",
         "p3",
         "4.742670263605188",
         "-5.980641050872779",
         "5.728435596276336",
         "nonparam_boots"
        ],
        [
         "16",
         "plain",
         "p0",
         "-24.95282468101097",
         "-31.06046516182461",
         "-9.148854129963828",
         "nonparam_stratified_boots"
        ],
        [
         "17",
         "plain",
         "p1",
         "0.7197035437687624",
         "-2.4286788567484003",
         "2.1171387289805523e-06",
         "nonparam_stratified_boots"
        ],
        [
         "18",
         "plain",
         "p2",
         "-1.375610632716079",
         "-6.232918893947502",
         "3.6895714169844807",
         "nonparam_stratified_boots"
        ],
        [
         "19",
         "plain",
         "p3",
         "4.742670263605188",
         "-5.791672336706236",
         "5.312949558889721",
         "nonparam_stratified_boots"
        ],
        [
         "20",
         "plain",
         "p0",
         "-24.95282468101097",
         "-24.952829285018712",
         "-5.272372005113529",
         "parametric_boots"
        ],
        [
         "21",
         "plain",
         "p1",
         "0.7197035437687624",
         "-2.4324037145418713",
         "8.527363090120753e-06",
         "parametric_boots"
        ],
        [
         "22",
         "plain",
         "p2",
         "-1.375610632716079",
         "-3.6390436098117953",
         "3.8443296465901664",
         "parametric_boots"
        ],
        [
         "23",
         "plain",
         "p3",
         "4.742670263605188",
         "-4.953010521219558",
         "4.334531706584803",
         "parametric_boots"
        ],
        [
         "24",
         "log",
         "p0",
         "-22.050224224507048",
         "-34.990843611825134",
         "-8.512875306978525",
         "normal"
        ],
        [
         "25",
         "log",
         "p1",
         "-6.487627260792172e-07",
         "-6.48536332911137",
         "6.295197839796865",
         "normal"
        ],
        [
         "26",
         "log",
         "p2",
         "9.01517872526685",
         "4.102838470588292",
         "13.870836743716684",
         "normal"
        ],
        [
         "27",
         "log",
         "p3",
         "-8.548203780070926",
         "-11.44743062958081",
         "-5.557754240166658",
         "normal"
        ],
        [
         "28",
         "log",
         "p0",
         "-22.050224224507048",
         "-24.082834491327173",
         "-5.874216158163668",
         "nonparam_boots"
        ],
        [
         "29",
         "log",
         "p1",
         "-6.487627260792172e-07",
         "-4.993212678989062",
         "1.3161050620444058e-06",
         "nonparam_boots"
        ],
        [
         "30",
         "log",
         "p2",
         "9.01517872526685",
         "-15.348282764698276",
         "9.264464931477292",
         "nonparam_boots"
        ],
        [
         "31",
         "log",
         "p3",
         "-8.548203780070926",
         "-8.514071479220375",
         "9.109778182216045",
         "nonparam_boots"
        ],
        [
         "32",
         "log",
         "p0",
         "-22.050224224507048",
         "-23.836877345328144",
         "-5.857158731894141",
         "nonparam_stratified_boots"
        ],
        [
         "33",
         "log",
         "p1",
         "-6.487627260792172e-07",
         "-5.030267636389803",
         "1.6966288892473271e-06",
         "nonparam_stratified_boots"
        ],
        [
         "34",
         "log",
         "p2",
         "9.01517872526685",
         "-15.433352476917266",
         "9.335537364241295",
         "nonparam_stratified_boots"
        ],
        [
         "35",
         "log",
         "p3",
         "-8.548203780070926",
         "-8.648010086502335",
         "8.90436720568199",
         "nonparam_stratified_boots"
        ],
        [
         "36",
         "log",
         "p0",
         "-22.050224224507048",
         "-20.864131079562082",
         "-5.809523544377692",
         "parametric_boots"
        ],
        [
         "37",
         "log",
         "p1",
         "-6.487627260792172e-07",
         "-3.992735327374158",
         "9.048899462517914e-06",
         "parametric_boots"
        ],
        [
         "38",
         "log",
         "p2",
         "9.01517872526685",
         "-14.548704352260241",
         "7.667585597515155",
         "parametric_boots"
        ],
        [
         "39",
         "log",
         "p3",
         "-8.548203780070926",
         "-7.867576107275356",
         "7.849861829187226",
         "parametric_boots"
        ]
       ],
       "shape": {
        "columns": 6,
        "rows": 40
       }
      },
      "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>scale</th>\n",
       "      <th>coef</th>\n",
       "      <th>value</th>\n",
       "      <th>LCL</th>\n",
       "      <th>UCL</th>\n",
       "      <th>method</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>plain</td>\n",
       "      <td>p0</td>\n",
       "      <td>-2.495282e+01</td>\n",
       "      <td>-62.659297</td>\n",
       "      <td>12.753647</td>\n",
       "      <td>Wald/delta</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>plain</td>\n",
       "      <td>p1</td>\n",
       "      <td>7.197035e-01</td>\n",
       "      <td>-4.086384</td>\n",
       "      <td>5.525791</td>\n",
       "      <td>Wald/delta</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>plain</td>\n",
       "      <td>p2</td>\n",
       "      <td>-1.375611e+00</td>\n",
       "      <td>-4.669344</td>\n",
       "      <td>1.918123</td>\n",
       "      <td>Wald/delta</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>plain</td>\n",
       "      <td>p3</td>\n",
       "      <td>4.742670e+00</td>\n",
       "      <td>-0.699354</td>\n",
       "      <td>10.184694</td>\n",
       "      <td>Wald/delta</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>log</td>\n",
       "      <td>p0</td>\n",
       "      <td>-2.205022e+01</td>\n",
       "      <td>-35.144017</td>\n",
       "      <td>-8.956432</td>\n",
       "      <td>Wald/delta</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>log</td>\n",
       "      <td>p1</td>\n",
       "      <td>-6.487627e-07</td>\n",
       "      <td>-6.406551</td>\n",
       "      <td>6.406550</td>\n",
       "      <td>Wald/delta</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>log</td>\n",
       "      <td>p2</td>\n",
       "      <td>9.015179e+00</td>\n",
       "      <td>4.120441</td>\n",
       "      <td>13.909916</td>\n",
       "      <td>Wald/delta</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>log</td>\n",
       "      <td>p3</td>\n",
       "      <td>-8.548204e+00</td>\n",
       "      <td>-11.477163</td>\n",
       "      <td>-5.619245</td>\n",
       "      <td>Wald/delta</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>plain</td>\n",
       "      <td>p0</td>\n",
       "      <td>-2.495282e+01</td>\n",
       "      <td>-62.484182</td>\n",
       "      <td>14.080803</td>\n",
       "      <td>normal</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>plain</td>\n",
       "      <td>p1</td>\n",
       "      <td>7.197035e-01</td>\n",
       "      <td>-5.629422</td>\n",
       "      <td>3.992085</td>\n",
       "      <td>normal</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>plain</td>\n",
       "      <td>p2</td>\n",
       "      <td>-1.375611e+00</td>\n",
       "      <td>-1.961656</td>\n",
       "      <td>4.640407</td>\n",
       "      <td>normal</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>plain</td>\n",
       "      <td>p3</td>\n",
       "      <td>4.742670e+00</td>\n",
       "      <td>-10.166627</td>\n",
       "      <td>0.858986</td>\n",
       "      <td>normal</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>plain</td>\n",
       "      <td>p0</td>\n",
       "      <td>-2.495282e+01</td>\n",
       "      <td>-33.248282</td>\n",
       "      <td>-8.590177</td>\n",
       "      <td>nonparam_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>plain</td>\n",
       "      <td>p1</td>\n",
       "      <td>7.197035e-01</td>\n",
       "      <td>-2.361955</td>\n",
       "      <td>0.000002</td>\n",
       "      <td>nonparam_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>plain</td>\n",
       "      <td>p2</td>\n",
       "      <td>-1.375611e+00</td>\n",
       "      <td>-6.183688</td>\n",
       "      <td>3.652695</td>\n",
       "      <td>nonparam_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>plain</td>\n",
       "      <td>p3</td>\n",
       "      <td>4.742670e+00</td>\n",
       "      <td>-5.980641</td>\n",
       "      <td>5.728436</td>\n",
       "      <td>nonparam_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>plain</td>\n",
       "      <td>p0</td>\n",
       "      <td>-2.495282e+01</td>\n",
       "      <td>-31.060465</td>\n",
       "      <td>-9.148854</td>\n",
       "      <td>nonparam_stratified_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>plain</td>\n",
       "      <td>p1</td>\n",
       "      <td>7.197035e-01</td>\n",
       "      <td>-2.428679</td>\n",
       "      <td>0.000002</td>\n",
       "      <td>nonparam_stratified_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>plain</td>\n",
       "      <td>p2</td>\n",
       "      <td>-1.375611e+00</td>\n",
       "      <td>-6.232919</td>\n",
       "      <td>3.689571</td>\n",
       "      <td>nonparam_stratified_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>plain</td>\n",
       "      <td>p3</td>\n",
       "      <td>4.742670e+00</td>\n",
       "      <td>-5.791672</td>\n",
       "      <td>5.312950</td>\n",
       "      <td>nonparam_stratified_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>plain</td>\n",
       "      <td>p0</td>\n",
       "      <td>-2.495282e+01</td>\n",
       "      <td>-24.952829</td>\n",
       "      <td>-5.272372</td>\n",
       "      <td>parametric_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>plain</td>\n",
       "      <td>p1</td>\n",
       "      <td>7.197035e-01</td>\n",
       "      <td>-2.432404</td>\n",
       "      <td>0.000009</td>\n",
       "      <td>parametric_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>plain</td>\n",
       "      <td>p2</td>\n",
       "      <td>-1.375611e+00</td>\n",
       "      <td>-3.639044</td>\n",
       "      <td>3.844330</td>\n",
       "      <td>parametric_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>plain</td>\n",
       "      <td>p3</td>\n",
       "      <td>4.742670e+00</td>\n",
       "      <td>-4.953011</td>\n",
       "      <td>4.334532</td>\n",
       "      <td>parametric_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>log</td>\n",
       "      <td>p0</td>\n",
       "      <td>-2.205022e+01</td>\n",
       "      <td>-34.990844</td>\n",
       "      <td>-8.512875</td>\n",
       "      <td>normal</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>log</td>\n",
       "      <td>p1</td>\n",
       "      <td>-6.487627e-07</td>\n",
       "      <td>-6.485363</td>\n",
       "      <td>6.295198</td>\n",
       "      <td>normal</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>log</td>\n",
       "      <td>p2</td>\n",
       "      <td>9.015179e+00</td>\n",
       "      <td>4.102838</td>\n",
       "      <td>13.870837</td>\n",
       "      <td>normal</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>log</td>\n",
       "      <td>p3</td>\n",
       "      <td>-8.548204e+00</td>\n",
       "      <td>-11.447431</td>\n",
       "      <td>-5.557754</td>\n",
       "      <td>normal</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>log</td>\n",
       "      <td>p0</td>\n",
       "      <td>-2.205022e+01</td>\n",
       "      <td>-24.082834</td>\n",
       "      <td>-5.874216</td>\n",
       "      <td>nonparam_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>log</td>\n",
       "      <td>p1</td>\n",
       "      <td>-6.487627e-07</td>\n",
       "      <td>-4.993213</td>\n",
       "      <td>0.000001</td>\n",
       "      <td>nonparam_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>log</td>\n",
       "      <td>p2</td>\n",
       "      <td>9.015179e+00</td>\n",
       "      <td>-15.348283</td>\n",
       "      <td>9.264465</td>\n",
       "      <td>nonparam_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>log</td>\n",
       "      <td>p3</td>\n",
       "      <td>-8.548204e+00</td>\n",
       "      <td>-8.514071</td>\n",
       "      <td>9.109778</td>\n",
       "      <td>nonparam_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>log</td>\n",
       "      <td>p0</td>\n",
       "      <td>-2.205022e+01</td>\n",
       "      <td>-23.836877</td>\n",
       "      <td>-5.857159</td>\n",
       "      <td>nonparam_stratified_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>log</td>\n",
       "      <td>p1</td>\n",
       "      <td>-6.487627e-07</td>\n",
       "      <td>-5.030268</td>\n",
       "      <td>0.000002</td>\n",
       "      <td>nonparam_stratified_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>log</td>\n",
       "      <td>p2</td>\n",
       "      <td>9.015179e+00</td>\n",
       "      <td>-15.433352</td>\n",
       "      <td>9.335537</td>\n",
       "      <td>nonparam_stratified_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>log</td>\n",
       "      <td>p3</td>\n",
       "      <td>-8.548204e+00</td>\n",
       "      <td>-8.648010</td>\n",
       "      <td>8.904367</td>\n",
       "      <td>nonparam_stratified_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>log</td>\n",
       "      <td>p0</td>\n",
       "      <td>-2.205022e+01</td>\n",
       "      <td>-20.864131</td>\n",
       "      <td>-5.809524</td>\n",
       "      <td>parametric_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>log</td>\n",
       "      <td>p1</td>\n",
       "      <td>-6.487627e-07</td>\n",
       "      <td>-3.992735</td>\n",
       "      <td>0.000009</td>\n",
       "      <td>parametric_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>38</th>\n",
       "      <td>log</td>\n",
       "      <td>p2</td>\n",
       "      <td>9.015179e+00</td>\n",
       "      <td>-14.548704</td>\n",
       "      <td>7.667586</td>\n",
       "      <td>parametric_boots</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39</th>\n",
       "      <td>log</td>\n",
       "      <td>p3</td>\n",
       "      <td>-8.548204e+00</td>\n",
       "      <td>-7.867576</td>\n",
       "      <td>7.849862</td>\n",
       "      <td>parametric_boots</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    scale coef         value        LCL        UCL                     method\n",
       "0   plain   p0 -2.495282e+01 -62.659297  12.753647                 Wald/delta\n",
       "1   plain   p1  7.197035e-01  -4.086384   5.525791                 Wald/delta\n",
       "2   plain   p2 -1.375611e+00  -4.669344   1.918123                 Wald/delta\n",
       "3   plain   p3  4.742670e+00  -0.699354  10.184694                 Wald/delta\n",
       "4     log   p0 -2.205022e+01 -35.144017  -8.956432                 Wald/delta\n",
       "5     log   p1 -6.487627e-07  -6.406551   6.406550                 Wald/delta\n",
       "6     log   p2  9.015179e+00   4.120441  13.909916                 Wald/delta\n",
       "7     log   p3 -8.548204e+00 -11.477163  -5.619245                 Wald/delta\n",
       "8   plain   p0 -2.495282e+01 -62.484182  14.080803                     normal\n",
       "9   plain   p1  7.197035e-01  -5.629422   3.992085                     normal\n",
       "10  plain   p2 -1.375611e+00  -1.961656   4.640407                     normal\n",
       "11  plain   p3  4.742670e+00 -10.166627   0.858986                     normal\n",
       "12  plain   p0 -2.495282e+01 -33.248282  -8.590177             nonparam_boots\n",
       "13  plain   p1  7.197035e-01  -2.361955   0.000002             nonparam_boots\n",
       "14  plain   p2 -1.375611e+00  -6.183688   3.652695             nonparam_boots\n",
       "15  plain   p3  4.742670e+00  -5.980641   5.728436             nonparam_boots\n",
       "16  plain   p0 -2.495282e+01 -31.060465  -9.148854  nonparam_stratified_boots\n",
       "17  plain   p1  7.197035e-01  -2.428679   0.000002  nonparam_stratified_boots\n",
       "18  plain   p2 -1.375611e+00  -6.232919   3.689571  nonparam_stratified_boots\n",
       "19  plain   p3  4.742670e+00  -5.791672   5.312950  nonparam_stratified_boots\n",
       "20  plain   p0 -2.495282e+01 -24.952829  -5.272372           parametric_boots\n",
       "21  plain   p1  7.197035e-01  -2.432404   0.000009           parametric_boots\n",
       "22  plain   p2 -1.375611e+00  -3.639044   3.844330           parametric_boots\n",
       "23  plain   p3  4.742670e+00  -4.953011   4.334532           parametric_boots\n",
       "24    log   p0 -2.205022e+01 -34.990844  -8.512875                     normal\n",
       "25    log   p1 -6.487627e-07  -6.485363   6.295198                     normal\n",
       "26    log   p2  9.015179e+00   4.102838  13.870837                     normal\n",
       "27    log   p3 -8.548204e+00 -11.447431  -5.557754                     normal\n",
       "28    log   p0 -2.205022e+01 -24.082834  -5.874216             nonparam_boots\n",
       "29    log   p1 -6.487627e-07  -4.993213   0.000001             nonparam_boots\n",
       "30    log   p2  9.015179e+00 -15.348283   9.264465             nonparam_boots\n",
       "31    log   p3 -8.548204e+00  -8.514071   9.109778             nonparam_boots\n",
       "32    log   p0 -2.205022e+01 -23.836877  -5.857159  nonparam_stratified_boots\n",
       "33    log   p1 -6.487627e-07  -5.030268   0.000002  nonparam_stratified_boots\n",
       "34    log   p2  9.015179e+00 -15.433352   9.335537  nonparam_stratified_boots\n",
       "35    log   p3 -8.548204e+00  -8.648010   8.904367  nonparam_stratified_boots\n",
       "36    log   p0 -2.205022e+01 -20.864131  -5.809524           parametric_boots\n",
       "37    log   p1 -6.487627e-07  -3.992735   0.000009           parametric_boots\n",
       "38    log   p2  9.015179e+00 -14.548704   7.667586           parametric_boots\n",
       "39    log   p3 -8.548204e+00  -7.867576   7.849862           parametric_boots"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# nr of parameters\n",
    "d = parss.shape[-1]\n",
    "\n",
    "# CI of params:\n",
    "#   - using Wald approximation \n",
    "#   - assuming asymptotic MLE distr of parameters \n",
    "#   - cov = hessian(nllf)^{-1}\n",
    "#   - this could be considered as delta method\n",
    "\n",
    "print(f\"pars CI:scale:{scales},method:Wald/delta\")\n",
    "lst_pars_CI = [df_pars_CI_wald.assign(method= \"Wald/delta\")]\n",
    "\n",
    "for scale, x, pars, cov_pars in zip(scales, xs, parss, cov_parss):\n",
    "\n",
    "    # plot quantiles of models at bootstapped parameters\n",
    "    for method in [\"normal\", \"nonparam_boots\", \"nonparam_stratified_boots\", \"parametric_boots\"]:\n",
    "    \n",
    "        print(f\"model CI:scale:{scale},boots-method:{method}\")\n",
    "\n",
    "        # get boostrapped parameters\n",
    "        bpars = boots_pars_results[(scale, method)]\n",
    "    \n",
    "        # quantiles\n",
    "        quant = np.quantile(bpars, probs, axis = 0)\n",
    "\n",
    "        df_tmp = pd.DataFrame({\n",
    "            \"method\": f\"{method}\",\n",
    "            \"scale\" : scale,\n",
    "            \"coef\" : [f\"p{i}\" for i in range(d)],\n",
    "            \"value\" : pars, \n",
    "            \"LCL\" : quant[0], \n",
    "            \"UCL\": quant[1]\n",
    "        })\n",
    "        \n",
    "        lst_pars_CI.append(df_tmp)\n",
    "\n",
    "df_pars_CI = pd.concat(lst_pars_CI, ignore_index=True)\n",
    "df_pars_CI"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base (3.12.3)",
   "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}