{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Aula 10 - Qui Quadrado e Regressão Logística"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "À partir da base de dados juri.xlsx faça as seguintes análises:\n",
    "\n",
    "- Considere: veredito é uma variável categórica onde 0 = não pena de morte e 1 = pena de morte\n",
    "- As variáveis independentes são escalas lineares de valores de 0 a 10."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import pingouin\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "juri = pd.read_excel('../data/juri.xlsx')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>subject</th>\n",
       "      <th>verdict</th>\n",
       "      <th>danger</th>\n",
       "      <th>rehab</th>\n",
       "      <th>punish</th>\n",
       "      <th>gendet</th>\n",
       "      <th>specdet</th>\n",
       "      <th>incap</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>8</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>10</td>\n",
       "      <td>10</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   subject  verdict  danger  rehab  punish  gendet  specdet  incap\n",
       "0        1        0       2      2       2       2        0      7\n",
       "1        2        0       0      9       0       6        8      2\n",
       "2        3        1       6      3       2      10       10      4\n",
       "3        4        1       1      3       2       3        2      1\n",
       "4        5        0       0      7       4       1        1     10"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "juri.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## PARTE 1 - Modelo de Regressão Logística Nominal\n",
    "\n",
    "Previsão do veredito à partir das 6 variáveis \n",
    "\n",
    "Responda:\n",
    "\n",
    "1. Qual a significância do modelo (Prob>ChiSq)?\n",
    "2. Considerando os coeficientes de regressão, quais variáveis são significativas como forma de prever o veredito? Quais os respectivos coeficientes e significâncias?\n",
    "3. Execute os testes de Wald para as variáveis (Triângulo vermelho ao lado de 'Nominal Logistic Fit for verdict'). Qual o Qui-quadrado (Wald ChiSquare) de 'danger'?\n",
    "4. De acordo com este modelo, qual o incremento de probabilidade do veredito de pena de morte para cada unidade de periculosidade (rehab)?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "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>names</th>\n",
       "      <th>coef</th>\n",
       "      <th>se</th>\n",
       "      <th>z</th>\n",
       "      <th>pval</th>\n",
       "      <th>CI[2.5%]</th>\n",
       "      <th>CI[97.5%]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Intercept</td>\n",
       "      <td>-1.75</td>\n",
       "      <td>0.92</td>\n",
       "      <td>-1.91</td>\n",
       "      <td>0.06</td>\n",
       "      <td>-3.55</td>\n",
       "      <td>0.05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>danger</td>\n",
       "      <td>0.29</td>\n",
       "      <td>0.09</td>\n",
       "      <td>3.16</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.11</td>\n",
       "      <td>0.48</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>rehab</td>\n",
       "      <td>-0.19</td>\n",
       "      <td>0.08</td>\n",
       "      <td>-2.31</td>\n",
       "      <td>0.02</td>\n",
       "      <td>-0.35</td>\n",
       "      <td>-0.03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>punish</td>\n",
       "      <td>0.07</td>\n",
       "      <td>0.07</td>\n",
       "      <td>0.99</td>\n",
       "      <td>0.32</td>\n",
       "      <td>-0.07</td>\n",
       "      <td>0.21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>gendet</td>\n",
       "      <td>0.19</td>\n",
       "      <td>0.08</td>\n",
       "      <td>2.40</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.34</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>specdet</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.08</td>\n",
       "      <td>0.08</td>\n",
       "      <td>0.94</td>\n",
       "      <td>-0.15</td>\n",
       "      <td>0.16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>incap</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.08</td>\n",
       "      <td>0.05</td>\n",
       "      <td>0.96</td>\n",
       "      <td>-0.15</td>\n",
       "      <td>0.15</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       names  coef    se     z  pval  CI[2.5%]  CI[97.5%]\n",
       "0  Intercept -1.75  0.92 -1.91  0.06     -3.55       0.05\n",
       "1     danger  0.29  0.09  3.16  0.00      0.11       0.48\n",
       "2      rehab -0.19  0.08 -2.31  0.02     -0.35      -0.03\n",
       "3     punish  0.07  0.07  0.99  0.32     -0.07       0.21\n",
       "4     gendet  0.19  0.08  2.40  0.02      0.03       0.34\n",
       "5    specdet  0.01  0.08  0.08  0.94     -0.15       0.16\n",
       "6      incap  0.00  0.08  0.05  0.96     -0.15       0.15"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Regressão Logística Múltipla Binária\n",
    "X = juri[['danger', 'rehab', 'punish', 'gendet', 'specdet', 'incap']] # Variáveis preditoras\n",
    "y = juri['verdict'] # Variável dependente binária [0, 1]\n",
    "lom = pingouin.logistic_regression(X, y, remove_na=True)\n",
    "lom.round(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot: >"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAh8AAAGdCAYAAACyzRGfAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjYuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy89olMNAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAr90lEQVR4nO3deXQUVd7/8U8nZE8nEAxJwBBQ2URENICAbCMSncEB59FHEUdQ1JFFQY4LOCOKiHFFHpHBHRFBUcHlJ64giBsIYREQEghbhkVQIRtkIX1/fzg0tgmQmMrtdHi/zulzqKrbVd+6qer+UHW722WMMQIAALAkyN8FAACAUwvhAwAAWEX4AAAAVhE+AACAVYQPAABgFeEDAABYRfgAAABWET4AAIBV9fxdwO95PB7t3r1bbrdbLpfL3+UAAIBKMMYoPz9fjRs3VlDQia9t1LrwsXv3biUnJ/u7DAAA8Afk5OTo9NNPP2GbWhc+3G63pF+Lj4mJ8XM1AACgMvLy8pScnOx9Hz+RWhc+jt5qiYmJIXwAABBgKjNkggGnAADAKsIHAACwivABAACsInwAAACrCB8AAMAqwgcAALCK8AEAAKwifAAAAKsIHwAAwKoqh4+lS5fq8ssvV+PGjeVyufTuu+/6LDfGaPz48UpKSlJERIT69OmjzZs3O1UvAAAIcFUOH4WFhWrfvr2mTZtW4fLHHntMTz/9tJ599lktX75cUVFRSktLU1FRUbWLBQAAga/Kv+1y2WWX6bLLLqtwmTFGU6ZM0b/+9S/1799fkvTqq68qISFB7777rq655prqVeuAK6d/oz251QtC+/OLVeYxkqTgIJfi3WF/eF1JseF6e1jXatXjL9XtSyf7UQrcvqxtx6REX3J+c347pbYdk1Lt6EtHf1hu27Zt2rt3r/r06eOdFxsbq86dO+vbb7+tMHwUFxeruLjYO52Xl+dkSeXsyS3SroOHHVtfWZlxdH2BxMm+pB85Jp1AXzqH89sZHJMVc3TA6d69eyVJCQkJPvMTEhK8y34vPT1dsbGx3kdycrKTJQEAgFrG0Ssff8S4ceM0ZswY73ReXl6NBpCk2PBqr2NvbpHKzH8vgblcSqzGOp2ox1+qW7uT/ehEPf5S245Jp2ryh9rWl4HajxLnt1Nq2zHpVE3V5Wj4SExMlCT9+OOPSkpK8s7/8ccfdd5551X4nLCwMIWFVe/+VVU4cZ+r2yOfey97JcaG6+uxf6r2OgNRdfuSfvwVx6Rz6EvncH47g2OyYo7edmnevLkSExO1aNEi77y8vDwtX75cXbp0cXJTAAAgQFX5ykdBQYG2bNnind62bZvWrFmjuLg4NW3aVKNHj9ZDDz2kFi1aqHnz5rrvvvvUuHFjDRgwwMm6AQBAgKpy+Fi5cqV69+7tnT46XmPw4MF65ZVXdPfdd6uwsFC33HKLDh48qIsuukgff/yxwsP9f48JAAD4X5XDR69evWT+O/ClIi6XSw8++KAefPDBahUGAADqJn7bBQAAWEX4AAAAVhE+AACAVYQPAABgFeEDAABYRfgAAABWET4AAIBVhA8AAGAV4QMAAFhF+AAAAFYRPgAAgFWEDwAAYBXhAwAAWEX4AAAAVhE+AACAVYQPAABgFeEDAABYRfgAAABWET4AAIBVhA8AAGAV4QMAAFhF+AAAAFYRPgAAgFWEDwAAYBXhAwAAWEX4AAAAVhE+AACAVYQPAABgFeEDAABYRfgAAABWET4AAIBVhA8AAGAV4QMAAFhF+AAAAFYRPgAAgFWEDwAAYBXhAwAAWEX4AAAAVhE+AACAVYQPAABgFeEDAABYRfgAAABWET4AAIBVhA8AAGAV4QMAAFhF+AAAAFYRPgAAgFWEDwAAYBXhAwAAWEX4AAAAVhE+AACAVYQPAABgFeEDAABYRfgAAABWET4AAIBVhA8AAGAV4QMAAFjlePgoKyvTfffdp+bNmysiIkJnnnmmJk6cKGOM05sCAAABqJ7TK3z00Uc1ffp0zZw5U23bttXKlSt1ww03KDY2VrfffrvTmwMAAAHG8fDxzTffqH///vrLX/4iSWrWrJlef/11fffdd05vCgAABCDHb7t07dpVixYtUlZWliRp7dq1+uqrr3TZZZdV2L64uFh5eXk+DwAAUHc5fuVj7NixysvLU+vWrRUcHKyysjJNmjRJgwYNqrB9enq6JkyY4HQZAACglnL8ysebb76p2bNna86cOVq1apVmzpypJ554QjNnzqyw/bhx45Sbm+t95OTkOF0SAACoRRy/8nHXXXdp7NixuuaaayRJ7dq1044dO5Senq7BgweXax8WFqawsDCnywAAALWU41c+Dh06pKAg39UGBwfL4/E4vSkAABCAHL/ycfnll2vSpElq2rSp2rZtq9WrV2vy5Mm68cYbnd4UAAAIQI6Hj6lTp+q+++7T8OHDtW/fPjVu3Fj/+Mc/NH78eKc3BQAAApDj4cPtdmvKlCmaMmWK06sGAAB1AL/tAgAArCJ8AAAAqwgfAADAKsIHAACwivABAACsInwAAACrCB8AAMAqwgcAALCK8AEAAKwifAAAAKsIHwAAwCrCBwAAsIrwAQAArCJ8AAAAqwgfAADAKsIHAACwivABAACsInwAAACrCB8AAMAqwgcAALCK8AEAAKwifAAAAKsIHwAAwCrCBwAAsIrwAQAArCJ8AAAAqwgfAADAKsIHAACwivABAACsInwAAACrCB8AAMAqwgcAALCK8AEAAKwifAAAAKsIHwAAwCrCBwAAsIrwAQAArCJ8AAAAqwgfAADAKsIHAACwivABAACsInwAAACrCB8AAMAqwgcAALCK8AEAAKwifAAAAKsIHwAAwCrCBwAAsIrwAQAArCJ8AAAAqwgfAADAKsIHAACwivABAACsInwAAACrCB8AAMAqwgcAALCqRsLHrl27dN1116lhw4aKiIhQu3bttHLlyprYFAAACDD1nF7hgQMH1K1bN/Xu3VsfffSR4uPjtXnzZjVo0MDpTQEAgADkePh49NFHlZycrBkzZnjnNW/e3OnNAACAAOX4bZf3339fqampuuqqq9SoUSN16NBBL7zwwnHbFxcXKy8vz+cBAADqLsfDx9atWzV9+nS1aNFCn3zyiYYNG6bbb79dM2fOrLB9enq6YmNjvY/k5GSnSwIAALWI4+HD4/Ho/PPP18MPP6wOHTrolltu0c0336xnn322wvbjxo1Tbm6u95GTk+N0SQAAoBZxPHwkJSXp7LPP9pnXpk0b7dy5s8L2YWFhiomJ8XkAAIC6y/Hw0a1bN2VmZvrMy8rKUkpKitObAgAAAcjx8HHHHXdo2bJlevjhh7VlyxbNmTNHzz//vEaMGOH0pgAAQAByPHx07NhR77zzjl5//XWdc845mjhxoqZMmaJBgwY5vSkAABCAHP+eD0nq16+f+vXrVxOrBgAAAY7fdgEAAFYRPgAAgFWEDwAAYBXhAwAAWEX4AAAAVhE+AACAVYQPAABgFeEDAABYRfgAAABWET4AAIBVhA8AAGAV4QMAAFhF+AAAAFYRPgAAgFWEDwD4rzKPUUmZxzttjPFjNUDdRfgAcMrzeIxe/mqbej6+WPvzi73zd+cW6Z63v9ePeUV+rA6oe+r5uwAA8Kcyj9HouWv0/9burnD53JU5+iJrv+b+40KlNIyyXB1QN3HlA8Ap7bml2ccNHkftzSvSLa9myOPhNgzgBMIHgFNWyRGPXv5qe6XaZv6Yry8276/ZgoBTBOEDwCnrqy379VNB8ckb/tf8VbtqsBrg1EH4AHDK2nWwagNJdx88XEOVAKcWwgeAU1ZYvaq9BFa1PYCKcSYBAS6vqFSFxUe804XFR5R7qNSPFQWO1JQGVWvfLK6GKgFOLYQPIEB5PEZTFmap86RFOnj4WNg4eLhUndMX6olPMvl0xkmcER+tbmc1rFTb4CCXBnZKruGKgGNKyzz6f2t3+4xL+qmgWO+t2aWSI54TPLP2I3zAL9bvytWBQyXe6R/zivTM55t9vuAJx2eM0fj312vKws06XFpWbnlRqUfPLN6isfO/51s6T+LeP7dRREjwSduN6H2WkmIjLFQESPvyijRg2te67fXVKv5N0Cg+4tGoN9bor898pT25gTsGifABqzweo4kf/KB+U7/SoZJjb5pHPEZPfJqlno8v1mc//OjHCgPDF1n79dqynSdt9+bK/9CfJ9G2caxm3thJcVGhFS53uaQRvc/UHX1aWK4Mp6pDJUf095e+04bdecdts2lvvq57cbkKfnPLNZAQPmDVE59m6qWvth13+aGSMg2fnaHvtv1isarAM/Ob7ZVu++q3O2qukDqiU/M4Lb27tx4acI5Cg4+9LEaH1dOiMT11V1pruVwuP1aIU8ncFTnK/DH/pO2y9xdq9rLAPL8JH7BmT+5hPbd060nblZYZTfpwo4WKAlPxkTJ9kVX5L7v6astPPgNSUbHosHq67sIUxbvDvPNiI0J0Rny0H6vCqWj28pNf1Txqznc7A/LWKuED1rzxXY7KKjkAcm3OQa3flVvDFQWmgqIjquo40vwiwgfsMcao5Mix26oFxaXK+eWQHysKHAXFR7RlX0Gl2+/4+ZAOBOCn2wgfsGZ1zsEabX+qiA6vp+Cgyt8CcLmkmAh+QxJ2ZOz4RZdO+VL7C44NKM89fEQ9Hl+sYa9l6JfCkhM8G6V/4FMspWWB98kXwgesOVLFE+SPnISngrB6werZMr7S7S866zRFhhI+UPOWbf1ZA19YXuF4BWOkj9bv1f8+960OHiKAHE9MRIhiwit/vkaFBh93sHRtRviANckNIqvWPq5q7U8lg7s2q3Tb67tUvi3wRxUfKdPtr68+6fdPbNlXoEkLGNN1PMFBLv3t/NMr3X5AhyYKCQ68t/LAqxgB68rUyp9Qp0WHVel/96eaHi1O0/VdUk7abmCnZPVp08hCRTjVfbRur/ZV8nt63lu7m9svJ3BDt2YKDzn523NovSDd0K25hYqcR/iANakpDSr9ddY3dW+uUH5H47hcLpcm/LWt7uzbUlGh5b8gKzI0WKMubqFJA9rxEVFY8cmGvZVuW3LEoyWZ+2qwmsCW0jBK/x50/gl/Syg0OEhTB3bQWY0C89NYvLrDGpfLpX9fd77OjI86YbsrLzhdt3Q/w1JVgcvlcmnkn1po+T/7qH5kiHd+/cgQLbv3Yt1xSUsFVWFgKlAdB6o4jiMQP6Fh059aJ2jesK76c7vEcsvS2ibo7WFdlNa2/LJAQfiAVY3c4Zo/rJv+0eMM/f4/5K0S3Hr0f9rp8SvP5U2zCqLD6inqNwNKo0LrKSY85ATPAJznruIxV5VBlaeqc5rE6t+DLlBSbLh3XlJsuJ77e6rOPb2+/wpzAOED1sVGhmjcn9v4nFAJ7jB9PLq7ru7YlNsEQACqytiiekEu9WBMV6UF/eY1MaiOvD4SPuA3Lh07ieoFBxE6gAD21/ZNfG7/ncil5yQqISb85A1RZxE+AADVFhEarMevbH/SL8BrHBuu+/qdbakq1FaEDwCAIy45O0EvXp+qxONc1ejUPE5vD+vKVQ8QPgAAzundupG+vKe3z7duRofV0we3XaQ3/9FFjetH+LE61BaEDwCAo0KCgxQRcuz7Z2IjQnROk1g/VoTahvABAACsInwAAACrCB8AAMAqwgcAALCK8AEAAKwifAAAAKsIH1VUfKRMRaVl3ukyY/xYDQAAgYfwUUmlZR499VmWuqR/rp8Lj/109N7cIt06K0M7fz7kx+oAAAgc/KZxJZSWeXTLqyu1OHN/hcs/3rBX323/RW/ccqFaJrgtVwcAQGDhykclTF20+bjB46hfCkt0y6srdaTMY6kqAAACE+HjJIpKy/Tqsh2Varv950NatGlfDVcEAEBgI3ycxNKs/Tp4qLTS7d9bs6sGqwEAIPARPk7ix/ziKrXfm1tUQ5UAAFA3ED5O4re/zFgZkaGM4QUA4ERqPHw88sgjcrlcGj16dE1vqkZ0bh4nl6vy7buc2bDmigEAoA6o0fCxYsUKPffcczr33HNrcjM1KjkuUr1axleqbUiwS/+bmlzDFQEAENhqLHwUFBRo0KBBeuGFF9SgQYOa2owV//zL2YoJP/ntlLvTWiveHWahIgAAAleNhY8RI0boL3/5i/r06XPCdsXFxcrLy/N51DZnNYrWnJsvVJP6ERUurxfk0r1/bq2buje3XBkAAIGnRkZHvvHGG1q1apVWrFhx0rbp6emaMGFCTZThqHOaxGrxnb308Ya9uvvttSoq/fXLxGLC6+mzMT2VEBPu5woBAAgMjl/5yMnJ0ahRozR79myFh5/8DXncuHHKzc31PnJycpwuyTGh9YL01/aN1TDq2K0Vd3gIwQMAgCpw/MpHRkaG9u3bp/PPP987r6ysTEuXLtUzzzyj4uJiBQcf+/hqWFiYwsIYJwEAwKnC8fBx8cUXa926dT7zbrjhBrVu3Vr33HOPT/AAAACnHsfDh9vt1jnnnOMzLyoqSg0bNiw3HwAAnHr4hlMAAGCVle8CX7JkiY3NAACAAMCVDwAAYBXhAwAAWEX4AAAAVhE+AACAVYQPAABgFeEDAABYRfgAAABWET4AAIBVhA8AAGAV4QMAAFhF+AAAAFYRPgAAgFWEDwAAYBXhAwAAWEX4AAAAVhE+AACAVYQPAABgFeEDAABYRfgAAABWET4AAIBVhA8AAGAV4QMAAFhF+AAAAFYRPgAAgFWEDwAAYBXhAwAAWEX4AAAAVhE+AACAVYQPAABgFeEDAABYRfgAAABWET4AAIBVhA8AAGAV4QMAAFhF+AAAAFYRPgAAgFWEDwAAYBXhAwAAWEX4AAAAVhE+AACAVYQPAABgFeEDAABYRfgAAABWET4AAIBVhA8AAGAV4QMAAFhF+AAAAFYRPgAAgFWEDwAAYBXhAwAAWEX4AAAAVhE+AACAVYQPAABgFeEDAABYRfgAAABWET4AAIBVjoeP9PR0dezYUW63W40aNdKAAQOUmZnp9GYAAECAcjx8fPHFFxoxYoSWLVumzz77TKWlperbt68KCwud3hQAAAhA9Zxe4ccff+wz/corr6hRo0bKyMhQjx49nN4cAAAIMI6Hj9/Lzc2VJMXFxVW4vLi4WMXFxd7pvLy8mi4JAAD4UY0OOPV4PBo9erS6deumc845p8I26enpio2N9T6Sk5NrsiQAAOBnNRo+RowYofXr1+uNN944bptx48YpNzfX+8jJyanJkgAAgJ/V2G2XkSNH6oMPPtDSpUt1+umnH7ddWFiYwsLCaqoMAABQyzgePowxuu222/TOO+9oyZIlat68udObAAAAAczx8DFixAjNmTNH7733ntxut/bu3StJio2NVUREhNObAwAAAcbxMR/Tp09Xbm6uevXqpaSkJO9j7ty5Tm8KAAAEoBq57QIAAHA8/LYLAACwivABAACsInwAAACrCB8AAMAqwgcAALCK8AEAAKwifAAAAKsIHwAAwCrCBwAAsIrwAQAArCJ8AAAAqwgfAADAKsIHAACwivABAACsInwAAACrCB8AAMAqwgcAALCK8AEAAKwifAAAAKsIHwAAwCrCBwAAsIrwAQAArCJ8AAAAqwgfAADAKsIHAACwivABAACsInwAAACrCB8AAMAqwgcAALCK8AEAAKwifAAAAKsIHwAAwCrCBwAAsIrwAQAArCJ8AAAAqwgfAADAKsIHAACwivABAACsInwAAACrCB8AAMAqwgcAALCK8AEAAKwifAAAAKsIHwAAwCrCBwAAsIrwAQAArCJ8AAAAqwgfAADAKsIHAACwivABAACsInwAAACrCB8AAMAqwgcAALCK8AEAAKwifAAAAKsIHwAAwKoaCx/Tpk1Ts2bNFB4ers6dO+u7776rqU0BAIAAUiPhY+7cuRozZozuv/9+rVq1Su3bt1daWpr27dtXE5sDAAABxGWMMU6vtHPnzurYsaOeeeYZSZLH41FycrJuu+02jR079oTPzcvLU2xsrHJzcxUTE+N0abpy+jfak1tUrXXszS1S2X+7LdjlUmJs+B9eV1JsuN4e1rVa9fhLdfvSyX6UArcva9sxKdGXnN+c306pbcekVHN9WZX373pOb7ykpEQZGRkaN26cd15QUJD69Omjb7/9tlz74uJiFRcXe6fz8vKcLsnHntwi7Tp42LH1lRnj6PoCiZN9ST9yTDqBvnQO57czOCYr5vhtl59++kllZWVKSEjwmZ+QkKC9e/eWa5+enq7Y2FjvIzk52emSAABALeL4lY+qGjdunMaMGeOdzsvLq9EAklTNy1WStD+/WGWe/14CC3Ip3h3m13r8pbq1O9mPTtTjL7XtmHSqJn+obX0ZqP0ocX47pbYdk07VVF2Oj/koKSlRZGSk3n77bQ0YMMA7f/DgwTp48KDee++9Ez6/psd8AAAA51Xl/dvx2y6hoaG64IILtGjRIu88j8ejRYsWqUuXLk5vDgAABJgaue0yZswYDR48WKmpqerUqZOmTJmiwsJC3XDDDTWxOQAAEEBqJHxcffXV2r9/v8aPH6+9e/fqvPPO08cff1xuECoAADj11Mj3fFQHYz4AAAg8fh3zAQAAcCKEDwAAYBXhAwAAWEX4AAAAVhE+AACAVYQPAABgFeEDAABYRfgAAABWET4AAIBVNfL16tVx9AtX8/Ly/FwJAACorKPv25X54vRaFz7y8/MlScnJyX6uBAAAVFV+fr5iY2NP2KbW/baLx+PR7t275Xa75XK5/F3OceXl5Sk5OVk5OTn8Bk010I/OoS+dQ186g350TiD0pTFG+fn5aty4sYKCTjyqo9Zd+QgKCtLpp5/u7zIqLSYmptYeCIGEfnQOfekc+tIZ9KNzantfnuyKx1EMOAUAAFYRPgAAgFWEjz8oLCxM999/v8LCwvxdSkCjH51DXzqHvnQG/eicutaXtW7AKQAAqNu48gEAAKwifAAAAKsIHwAAwKpTMnz06tVLo0eP9ncZpxwn+v2VV15R/fr1HamnrqtKX9GvVTNkyBANGDDA32XUOXW1X3nPKe+UDB/AqeDqq69WVlaWv8uApCVLlsjlcungwYP+LqVOCZR+nT9/viZOnOjvMmqVWvcNpzimtLRUISEh/i6jUkpKShQaGurvMvAbERERioiI8HcZwCkvLi7O3yXUOnX+ykdhYaGuv/56RUdHKykpSU8++aTP8lmzZik1NVVut1uJiYm69tprtW/fPu/yo8l60aJFSk1NVWRkpLp27arMzEyf9Tz00ENq1KiR3G63brrpJo0dO1bnnXeeT5sXX3xRbdq0UXh4uFq3bq1///vf3mXbt2+Xy+XS3Llz1bNnT4WHh2v27NnOd4hDevXqpZEjR2r06NE67bTTlJaWpvXr1+uyyy5TdHS0EhIS9Pe//10//fSTz/M8Ho/uvvtuxcXFKTExUQ888IDP8smTJ6tdu3aKiopScnKyhg8froKCgnLbf/fdd9WiRQuFh4crLS1NOTk5Nbm7jjvafyNHjlRsbKxOO+003Xfffd5fg3S5XHr33Xd9nlO/fn298sorko4dL/Pnz1fv3r0VGRmp9u3b69tvv/W2//2tlLVr16p3795yu92KiYnRBRdcoJUrV/ps45NPPlGbNm0UHR2tSy+9VHv27KmR/XdKfn6+Bg0apKioKCUlJempp57yucRdXFysO++8U02aNFFUVJQ6d+6sJUuWeJ9/tI9OtN9lZWUaM2aM6tevr4YNG+ruu+8u96udHo9H6enpat68uSIiItS+fXu9/fbbkn79W/Xu3VuS1KBBA7lcLg0ZMqRG+6Wy3n77bbVr104RERFq2LCh+vTpo8LCQu/tjwkTJig+Pl4xMTG69dZbVVJS4n3uifb5qA0bNqhfv36KiYmR2+1W9+7dlZ2dLalu9+vv/faYbNasmR5++GHdeOONcrvdatq0qZ5//nmf9v/5z380cOBAxcXFKSoqSqmpqVq+fLkkKTs7W/3791dCQoKio6PVsWNHLVy40Of5zZo108SJEzVw4EBFRUWpSZMmmjZtmpV9rTRTxw0bNsw0bdrULFy40Hz//femX79+xu12m1GjRhljjHnppZfMhx9+aLKzs823335runTpYi677DLv8xcvXmwkmc6dO5slS5aYDRs2mO7du5uuXbt627z22msmPDzcvPzyyyYzM9NMmDDBxMTEmPbt2/u0SUpKMvPmzTNbt2418+bNM3FxceaVV14xxhizbds2I8k0a9bM22b37t1W+uiP6Nmzp4mOjjZ33XWX2bRpk1m2bJmJj48348aNMxs3bjSrVq0yl1xyiendu7fPc2JiYswDDzxgsrKyzMyZM43L5TKffvqpt81TTz1lPv/8c7Nt2zazaNEi06pVKzNs2DDv8hkzZpiQkBCTmppqvvnmG7Ny5UrTqVMnn79HIDjaf6NGjTKbNm0yr732momMjDTPP/+8McYYSeadd97xeU5sbKyZMWOGMebY8dK6dWvzwQcfmMzMTHPllVealJQUU1paaoz5ta9iY2O9z2/btq257rrrzMaNG01WVpZ58803zZo1a7xtQ0JCTJ8+fcyKFStMRkaGadOmjbn22mtrvC+q46abbjIpKSlm4cKFZt26deaKK67wOb9vuukm07VrV7N06VKzZcsW8/jjj5uwsDCTlZVljKncfj/66KOmQYMGZt68eeaHH34wQ4cONW632/Tv39/b5qGHHjKtW7c2H3/8scnOzjYzZswwYWFhZsmSJebIkSNm3rx5RpLJzMw0e/bsMQcPHrTZTRXavXu3qVevnpk8ebLZtm2b+f777820adNMfn6+GTx4sImOjjZXX321Wb9+vfnggw9MfHy8uffee73PP9E+G2PMf/7zHxMXF2f+9re/mRUrVpjMzEzz8ssvm02bNhlj6m6/VqRnz57eYzIlJcXExcWZadOmmc2bN5v09HQTFBTk7Zf8/HxzxhlnmO7du5svv/zSbN682cydO9d88803xhhj1qxZY5599lmzbt06k5WVZf71r3+Z8PBws2PHDu/2UlJSjNvtNunp6SYzM9M8/fTTJjg42Oe11t/qdPjIz883oaGh5s033/TO+/nnn01ERIT3QPi9FStWGEkmPz/fGHMsfCxcuNDbZsGCBUaSOXz4sDHGmM6dO5sRI0b4rKdbt24+4ePMM880c+bM8WkzceJE06VLF2PMsTeTKVOm/OH9talnz56mQ4cO3umJEyeavn37+rTJycnxvjAcfc5FF13k06Zjx47mnnvuOe523nrrLdOwYUPv9IwZM4wks2zZMu+8jRs3Gklm+fLl1donm3r27GnatGljPB6Pd94999xj2rRpY4ypfPh48cUXvcs3bNhgJJmNGzcaY8qHD7fb7Q27v3e0X7ds2eKdN23aNJOQkFCd3axReXl5JiQkxLz11lveeQcPHjSRkZFm1KhRZseOHSY4ONjs2rXL53kXX3yxGTdunDGmcvudlJRkHnvsMe90aWmpOf30071vkkVFRSYyMtL75nDU0KFDzcCBA40xx15HDhw44Mi+OyEjI8NIMtu3by+3bPDgwSYuLs4UFhZ6502fPt1ER0ebsrKySu3zuHHjTPPmzU1JSUmF26+r/VqR34eP6667zrvM4/GYRo0amenTpxtjjHnuueeM2+02P//8c6XX37ZtWzN16lTvdEpKirn00kt92lx99dU+/7H2tzo95iM7O1slJSXq3Lmzd15cXJxatWrlnc7IyNADDzygtWvX6sCBA/J4PJKknTt36uyzz/a2O/fcc73/TkpKkiTt27dPTZs2VWZmpoYPH+6z7U6dOunzzz+X9Outn+zsbA0dOlQ333yzt82RI0fK/QJgampqdXfbmgsuuMD777Vr12rx4sWKjo4u1y47O1stW7aU5NuP0q99+dvbXAsXLlR6ero2bdqkvLw8HTlyREVFRTp06JAiIyMlSfXq1VPHjh29z2ndurXq16+vjRs3qlOnTo7uY0268MIL5XK5vNNdunTRk08+qbKyskqv43jHZevWrcu1HTNmjG666SbNmjVLffr00VVXXaUzzzzTuzwyMtJn+vd/m9pm69atKi0t9fmbx8bGes/vdevWqayszHvsHVVcXKyGDRt6p0+037m5udqzZ4/Pa0i9evWUmprqvUWwZcsWHTp0SJdcconPdkpKStShQweH9tZ57du318UXX6x27dopLS1Nffv21ZVXXqkGDRp4lx8956Rfj8+CggLl5OSooKDgpPu8Zs0ade/evcJxa3W5Xyvjt+ety+VSYmKi95hbs2aNOnTocNxxIgUFBXrggQe0YMEC7dmzR0eOHNHhw4e1c+dOn3ZdunQpNz1lyhRnd6Qa6nT4OJnCwkKlpaUpLS1Ns2fPVnx8vHbu3Km0tDSfe5uSfE6go28YR4PKyRwds/DCCy/4nGySFBwc7DMdFRVV5f3wl9/WWlBQoMsvv1yPPvpouXZH3xQllXshcrlc3n7cvn27+vXrp2HDhmnSpEmKi4vTV199paFDh6qkpMTnhbCuc7lc5e5/l5aWlmtXlePygQce0LXXXqsFCxboo48+0v3336833nhDV1xxRbl1Ha+GQFJQUKDg4GBlZGSUO89+G5Kru99Hz+8FCxaoSZMmPstq8+9wBAcH67PPPtM333yjTz/9VFOnTtU///lP79iCE6nMPld3sHOg9mtlnOh18GT9duedd+qzzz7TE088obPOOksRERG68sory71n1XZ1OnyceeaZCgkJ0fLly9W0aVNJ0oEDB5SVlaWePXtq06ZN+vnnn/XII48oOTlZksoNwKuMVq1aacWKFbr++uu981asWOH9d0JCgho3bqytW7dq0KBB1dyr2un888/XvHnz1KxZM9Wr98cOq4yMDHk8Hj355JMKCvp1LPSbb75Zrt2RI0e0cuVK7/94MzMzdfDgQbVp0+aP74Af/P5FftmyZWrRooWCg4MVHx/vM+hx8+bNOnToULW32bJlS7Vs2VJ33HGHBg4cqBkzZnjDR6A544wzFBISohUrVnjP79zcXGVlZalHjx7q0KGDysrKtG/fPnXv3v0PbSM2NlZJSUlavny5evToIenX4y8jI0Pnn3++JOnss89WWFiYdu7cqZ49e1a4nqOfBKvKVS0bXC6XunXrpm7dumn8+PFKSUnRO++8I+nXq5mHDx/2vhkuW7ZM0dHRSk5OVlxc3En3+dxzz9XMmTMr/NReXe/X6jj33HP14osv6pdffqnw6sfXX3+tIUOGeM/bgoICbd++vVy7ZcuWlZuuTa+RdfrTLtHR0Ro6dKjuuusuff7551q/fr2GDBnifWNr2rSpQkNDNXXqVG3dulXvv//+H/os9m233aaXXnpJM2fO1ObNm/XQQw/p+++/97mkPmHCBKWnp+vpp59WVlaW1q1bpxkzZmjy5MmO7a8/jRgxQr/88osGDhyoFStWKDs7W5988oluuOGGSr8wnHXWWSotLfX+PWbNmqVnn322XLuQkBDddtttWr58uTIyMjRkyBBdeOGFAXXLRfr11t6YMWOUmZmp119/XVOnTtWoUaMkSX/605/0zDPPaPXq1Vq5cqVuvfXWan3s+vDhwxo5cqSWLFmiHTt26Ouvv9aKFStq1YtRVbndbg0ePFh33XWXFi9erA0bNmjo0KEKCgqSy+VSy5YtNWjQIF1//fWaP3++tm3bpu+++07p6elasGBBpbczatQoPfLII3r33Xe1adMmDR8+3Od7Jdxut+68807dcccdmjlzprKzs7Vq1SpNnTpVM2fOlCSlpKTI5XLpgw8+0P79+yv8BJdty5cv18MPP6yVK1dq586dmj9/vvbv3+89JkpKSjR06FD98MMP+vDDD3X//fdr5MiRCgoKqtQ+jxw5Unl5ebrmmmu0cuVKbd68WbNmzfJ+UrCu9mt1DRw4UImJiRowYIC+/vprbd26VfPmzfN+kq1FixaaP3++1qxZo7Vr1+raa6+t8Grn119/rccee0xZWVmaNm2a3nrrLe/rS63g1xEnFuTn55vrrrvOREZGmoSEBPPYY4/5DP6ZM2eOadasmQkLCzNdunQx77//vpFkVq9ebYypeEDT6tWrjSSzbds277wHH3zQnHbaaSY6OtrceOON5vbbbzcXXnihTy2zZ8825513ngkNDTUNGjQwPXr0MPPnzzfGHBtAeHS7td1v+/CorKwsc8UVV5j69eubiIgI07p1azN69GjvoMqKntO/f38zePBg7/TkyZNNUlKSiYiIMGlpaebVV1/16f+jgyjnzZtnzjjjDBMWFmb69OnjM9I7EPTs2dMMHz7c3HrrrSYmJsY0aNDA3Hvvvd6+2rVrl+nbt6+JiooyLVq0MB9++GGFA05/e7wcOHDASDKLFy82xvgOOC0uLjbXXHONSU5ONqGhoaZx48Zm5MiR3kHTvx+caowx77zzjqntLxF5eXnm2muvNZGRkSYxMdFMnjzZdOrUyYwdO9YYY0xJSYkZP368adasmQkJCTFJSUnmiiuuMN9//70xpnL7XVpaakaNGmViYmJM/fr1zZgxY8z111/v86kMj8djpkyZYlq1amVCQkJMfHy8SUtLM1988YW3zYMPPmgSExONy+XyOeb95YcffjBpaWkmPj7ehIWFmZYtW3oHLQ4ePNj079/fjB8/3jRs2NBER0ebm2++2RQVFXmfX5l9Xrt2renbt6+JjIw0brfbdO/e3WRnZxtj6m6/VuT3A06feuopn+Xt27c3999/v3d6+/bt5n/+539MTEyMiYyMNKmpqd4B9du2bTO9e/c2ERERJjk52TzzzDPlXltTUlLMhAkTzFVXXeU9N/7v//6vhveyalzGBPBN3VrskksuUWJiombNmuXvUlAL9erVS+edd16tGgBWFxQWFqpJkyZ68sknNXToUH+XE7CGDBmigwcPlvuuGQSGZs2aafTo0bX6K93r9JgPWw4dOqRnn31WaWlpCg4O1uuvv66FCxfqs88+83dpQJ22evVqbdq0SZ06dVJubq4efPBBSVL//v39XBmAEyF8OMDlcunDDz/UpEmTVFRUpFatWmnevHnq06ePv0sD6rwnnnhCmZmZCg0N1QUXXKAvv/xSp512mr/LAnAC3HYBAABW1elPuwAAgNqH8AEAAKwifAAAAKsIHwAAwCrCBwAAsIrwAQAArCJ8AAAAqwgfAADAKsIHAACw6v8DX5QZKChlrUkAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.pointplot(\n",
    "    data=juri[['danger', 'rehab', 'punish', 'gendet', 'specdet', 'incap']],\n",
    "    errorbar=(\"pi\", 100), capsize=.4, join=False,)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                 test    lambda       chi2   dof      pval    cramer     power\n",
      "0             pearson  1.000000  18.923347  10.0  0.041247  0.435010  0.868967\n",
      "1        cressie-read  0.666667  19.633344  10.0  0.032918  0.443095  0.883531\n",
      "2      log-likelihood  0.000000  23.423537  10.0  0.009287  0.483979  0.940215\n",
      "3       freeman-tukey -0.500000        NaN  10.0       NaN       NaN       NaN\n",
      "4  mod-log-likelihood -1.000000        inf  10.0  0.000000       inf  1.000000\n",
      "5              neyman -2.000000        NaN  10.0       NaN       NaN       NaN\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/marianne/code/Analise_Estatistica/venv/lib/python3.10/site-packages/pingouin/contingency.py:150: UserWarning: Low count on observed frequencies.\n",
      "  warnings.warn(\"Low count on {} frequencies.\".format(name))\n",
      "/home/marianne/code/Analise_Estatistica/venv/lib/python3.10/site-packages/pingouin/contingency.py:150: UserWarning: Low count on expected frequencies.\n",
      "  warnings.warn(\"Low count on {} frequencies.\".format(name))\n",
      "/home/marianne/code/Analise_Estatistica/venv/lib/python3.10/site-packages/scipy/stats/_stats_py.py:7169: RuntimeWarning: divide by zero encountered in power\n",
      "  terms = f_obs * ((f_obs / f_exp)**lambda_ - 1)\n",
      "/home/marianne/code/Analise_Estatistica/venv/lib/python3.10/site-packages/scipy/stats/_stats_py.py:7169: RuntimeWarning: invalid value encountered in multiply\n",
      "  terms = f_obs * ((f_obs / f_exp)**lambda_ - 1)\n",
      "/home/marianne/code/Analise_Estatistica/venv/lib/python3.10/site-packages/scipy/stats/_stats_py.py:7166: RuntimeWarning: divide by zero encountered in divide\n",
      "  terms = 2.0 * special.xlogy(f_exp, f_exp / f_obs)\n"
     ]
    }
   ],
   "source": [
    "# Teste de independência Chi-quadrado: A variável x independe de y?\n",
    "expected, observed, stats = pingouin.chi2_independence(data=juri, x='verdict',\n",
    "y='danger', correction=False)\n",
    "print(stats)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot: xlabel='verdict'>"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Visualização exploratoria de proporções - gráfico de barras 100% empilhadas\n",
    "props = juri.groupby('verdict')['danger'].value_counts(normalize=True)\n",
    "wide_props = props.unstack()\n",
    "wide_props.plot(kind=\"bar\", stacked=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot: xlabel='danger'>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Visualização exploratoria de proporções - gráfico de barras 100% empilhadas\n",
    "props = juri.groupby('danger')['verdict'].value_counts(normalize=True)\n",
    "wide_props = props.unstack()\n",
    "wide_props.plot(kind=\"bar\", stacked=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "      test  lambda       chi2   dof      pval   cramer     power\n",
      "0  pearson     1.0  18.923347  10.0  0.041247  0.43501  0.868967\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/marianne/code/Analise_Estatistica/venv/lib/python3.10/site-packages/pingouin/contingency.py:150: UserWarning: Low count on observed frequencies.\n",
      "  warnings.warn(\"Low count on {} frequencies.\".format(name))\n",
      "/home/marianne/code/Analise_Estatistica/venv/lib/python3.10/site-packages/pingouin/contingency.py:150: UserWarning: Low count on expected frequencies.\n",
      "  warnings.warn(\"Low count on {} frequencies.\".format(name))\n",
      "/home/marianne/code/Analise_Estatistica/venv/lib/python3.10/site-packages/scipy/stats/_stats_py.py:7169: RuntimeWarning: divide by zero encountered in power\n",
      "  terms = f_obs * ((f_obs / f_exp)**lambda_ - 1)\n",
      "/home/marianne/code/Analise_Estatistica/venv/lib/python3.10/site-packages/scipy/stats/_stats_py.py:7169: RuntimeWarning: invalid value encountered in multiply\n",
      "  terms = f_obs * ((f_obs / f_exp)**lambda_ - 1)\n",
      "/home/marianne/code/Analise_Estatistica/venv/lib/python3.10/site-packages/scipy/stats/_stats_py.py:7166: RuntimeWarning: divide by zero encountered in divide\n",
      "  terms = 2.0 * special.xlogy(f_exp, f_exp / f_obs)\n"
     ]
    }
   ],
   "source": [
    "# Teste de dupla independência Chi-quadrado: As variáveis x e y são independentes entre si?\n",
    "expected, observed, stats = pingouin.chi2_independence(data=juri, x='verdict', y='danger')\n",
    "print(stats[stats['test'] == 'pearson'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## PARTE 2: Modelo de Regressão Logística Nominal\n",
    "\n",
    "Previsão do veredito à partir das variáveis periculosidade (danger), reabilitação (rehab) e dissuasão geral (gendet)\n",
    "\n",
    "Responda:\n",
    "1. Qual a significância do modelo (Prob>ChiSq)?\n",
    "2. Considerando os coeficientes de regressão, quais os coeficientes e significâncias das variáveis? São iguais ou diferentes do modelo anterior? Porquê?\n",
    "3. De acordo com este modelo, qual o incremento de probabilidade do veredito de pena de morte para cada unidade de periculosidade (rehab)?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "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>names</th>\n",
       "      <th>coef</th>\n",
       "      <th>se</th>\n",
       "      <th>z</th>\n",
       "      <th>pval</th>\n",
       "      <th>CI[2.5%]</th>\n",
       "      <th>CI[97.5%]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Intercept</td>\n",
       "      <td>-1.35</td>\n",
       "      <td>0.68</td>\n",
       "      <td>-1.97</td>\n",
       "      <td>0.05</td>\n",
       "      <td>-2.69</td>\n",
       "      <td>-0.01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>danger</td>\n",
       "      <td>0.28</td>\n",
       "      <td>0.09</td>\n",
       "      <td>3.15</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.11</td>\n",
       "      <td>0.45</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>rehab</td>\n",
       "      <td>-0.18</td>\n",
       "      <td>0.08</td>\n",
       "      <td>-2.24</td>\n",
       "      <td>0.02</td>\n",
       "      <td>-0.34</td>\n",
       "      <td>-0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>gendet</td>\n",
       "      <td>0.19</td>\n",
       "      <td>0.08</td>\n",
       "      <td>2.46</td>\n",
       "      <td>0.01</td>\n",
       "      <td>0.04</td>\n",
       "      <td>0.34</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       names  coef    se     z  pval  CI[2.5%]  CI[97.5%]\n",
       "0  Intercept -1.35  0.68 -1.97  0.05     -2.69      -0.01\n",
       "1     danger  0.28  0.09  3.15  0.00      0.11       0.45\n",
       "2      rehab -0.18  0.08 -2.24  0.02     -0.34      -0.02\n",
       "3     gendet  0.19  0.08  2.46  0.01      0.04       0.34"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Regressão Logística Múltipla Binária\n",
    "X = juri[['danger', 'rehab', 'gendet']] # Variáveis preditoras\n",
    "y = juri['verdict'] # Variável dependente binária [0, 1]\n",
    "lom = pingouin.logistic_regression(X, y, remove_na=True)\n",
    "lom.round(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "https://medium.com/@ginoasuncion/visualizing-logistic-regression-results-using-a-forest-plot-in-python-bc7ba65b55bb"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.10.6 ('venv': venv)",
   "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": "3.10.6"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "17a21100134af3592d09988eee871935e79466d45670c914d929fa5f969b25f9"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}