demo.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Copula-based conformal bounding box prediction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/lab/bcyusamu/miniconda3/envs/TBD/lib/python3.8/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "from src.reporting import UQEvalResults, SummaryReporter, GifReporter"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Uncertainty quantification results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "folds, version = 3, \"_release\", #10\n",
    "approaches = ['Bonferroni',\n",
    "              'Max additive',\n",
    "              \"Independent DE-CCP\",\n",
    "              \"Gumbel DE-CCP\",\n",
    "              'Empirical DE-CCP']\n",
    "epsilons = [0.01, 0.05, 0.1, 0.2]\n",
    "detectors = ['Correlated D.', 'Uncorrelated D.', 'YOLOv8 D.']\n",
    "filename = f\"results/UQ_experiments{version}.pkl\"\n",
    "res = UQEvalResults()\n",
    "res.load(filename)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Validity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      ">> Reporting validity ...\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1500x500 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "validity_tbls = SummaryReporter(epsilons, approaches, detectors, k_folds=folds).report(res)"
   ]
  },
  {
   "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>$1 - \\epsilon^g$</th>\n",
       "      <th>Bonferroni</th>\n",
       "      <th>Max additive</th>\n",
       "      <th>Independent DE-CCP</th>\n",
       "      <th>Gumbel DE-CCP</th>\n",
       "      <th>Empirical DE-CCP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.99</td>\n",
       "      <td>0.992±0.002</td>\n",
       "      <td>0.989±0.003</td>\n",
       "      <td>0.990±0.001</td>\n",
       "      <td>0.990±0.002</td>\n",
       "      <td>0.989±0.002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.95</td>\n",
       "      <td>0.955±0.004</td>\n",
       "      <td>0.952±0.004</td>\n",
       "      <td>0.952±0.004</td>\n",
       "      <td>0.949±0.004</td>\n",
       "      <td>0.947±0.006</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.90</td>\n",
       "      <td>0.913±0.008</td>\n",
       "      <td>0.902±0.002</td>\n",
       "      <td>0.906±0.007</td>\n",
       "      <td>0.901±0.006</td>\n",
       "      <td>0.897±0.011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.80</td>\n",
       "      <td>0.832±0.006</td>\n",
       "      <td>0.802±0.002</td>\n",
       "      <td>0.815±0.008</td>\n",
       "      <td>0.806±0.009</td>\n",
       "      <td>0.795±0.010</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   $1 - \\epsilon^g$   Bonferroni Max additive Independent DE-CCP  \\\n",
       "0              0.99  0.992±0.002  0.989±0.003        0.990±0.001   \n",
       "1              0.95  0.955±0.004  0.952±0.004        0.952±0.004   \n",
       "2              0.90  0.913±0.008  0.902±0.002        0.906±0.007   \n",
       "3              0.80  0.832±0.006  0.802±0.002        0.815±0.008   \n",
       "\n",
       "  Gumbel DE-CCP Empirical DE-CCP  \n",
       "0   0.990±0.002      0.989±0.002  \n",
       "1   0.949±0.004      0.947±0.006  \n",
       "2   0.901±0.006      0.897±0.011  \n",
       "3   0.806±0.009      0.795±0.010  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validity_tbls[0] # Experiment N°1: correlated dissimilarities"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>$1 - \\epsilon^g$</th>\n",
       "      <th>Bonferroni</th>\n",
       "      <th>Max additive</th>\n",
       "      <th>Independent DE-CCP</th>\n",
       "      <th>Gumbel DE-CCP</th>\n",
       "      <th>Empirical DE-CCP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.99</td>\n",
       "      <td>0.989±0.002</td>\n",
       "      <td>0.990±0.001</td>\n",
       "      <td>0.987±0.002</td>\n",
       "      <td>0.986±0.003</td>\n",
       "      <td>0.986±0.002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.95</td>\n",
       "      <td>0.949±0.002</td>\n",
       "      <td>0.952±0.000</td>\n",
       "      <td>0.943±0.000</td>\n",
       "      <td>0.943±0.000</td>\n",
       "      <td>0.941±0.001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.90</td>\n",
       "      <td>0.903±0.004</td>\n",
       "      <td>0.901±0.003</td>\n",
       "      <td>0.893±0.003</td>\n",
       "      <td>0.893±0.002</td>\n",
       "      <td>0.890±0.003</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.80</td>\n",
       "      <td>0.811±0.005</td>\n",
       "      <td>0.798±0.005</td>\n",
       "      <td>0.795±0.004</td>\n",
       "      <td>0.788±0.009</td>\n",
       "      <td>0.665±0.181</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   $1 - \\epsilon^g$   Bonferroni Max additive Independent DE-CCP  \\\n",
       "0              0.99  0.989±0.002  0.990±0.001        0.987±0.002   \n",
       "1              0.95  0.949±0.002  0.952±0.000        0.943±0.000   \n",
       "2              0.90  0.903±0.004  0.901±0.003        0.893±0.003   \n",
       "3              0.80  0.811±0.005  0.798±0.005        0.795±0.004   \n",
       "\n",
       "  Gumbel DE-CCP Empirical DE-CCP  \n",
       "0   0.986±0.003      0.986±0.002  \n",
       "1   0.943±0.000      0.941±0.001  \n",
       "2   0.893±0.002      0.890±0.003  \n",
       "3   0.788±0.009      0.665±0.181  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validity_tbls[1] # Experiment N°2: independent dissimilarities"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>$1 - \\epsilon^g$</th>\n",
       "      <th>Bonferroni</th>\n",
       "      <th>Max additive</th>\n",
       "      <th>Independent DE-CCP</th>\n",
       "      <th>Gumbel DE-CCP</th>\n",
       "      <th>Empirical DE-CCP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.99</td>\n",
       "      <td>0.992±0.003</td>\n",
       "      <td>0.990±0.003</td>\n",
       "      <td>0.988±0.001</td>\n",
       "      <td>0.987±0.003</td>\n",
       "      <td>0.981±0.004</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.95</td>\n",
       "      <td>0.965±0.007</td>\n",
       "      <td>0.944±0.009</td>\n",
       "      <td>0.961±0.006</td>\n",
       "      <td>0.957±0.008</td>\n",
       "      <td>0.937±0.010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.90</td>\n",
       "      <td>0.943±0.009</td>\n",
       "      <td>0.889±0.021</td>\n",
       "      <td>0.922±0.017</td>\n",
       "      <td>0.913±0.018</td>\n",
       "      <td>0.882±0.025</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.80</td>\n",
       "      <td>0.893±0.014</td>\n",
       "      <td>0.795±0.024</td>\n",
       "      <td>0.868±0.022</td>\n",
       "      <td>0.854±0.032</td>\n",
       "      <td>0.776±0.023</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   $1 - \\epsilon^g$   Bonferroni Max additive Independent DE-CCP  \\\n",
       "0              0.99  0.992±0.003  0.990±0.003        0.988±0.001   \n",
       "1              0.95  0.965±0.007  0.944±0.009        0.961±0.006   \n",
       "2              0.90  0.943±0.009  0.889±0.021        0.922±0.017   \n",
       "3              0.80  0.893±0.014  0.795±0.024        0.868±0.022   \n",
       "\n",
       "  Gumbel DE-CCP Empirical DE-CCP  \n",
       "0   0.987±0.003      0.981±0.004  \n",
       "1   0.957±0.008      0.937±0.010  \n",
       "2   0.913±0.018      0.882±0.025  \n",
       "3   0.854±0.032      0.776±0.023  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validity_tbls[2] # Experiment N°3: YOLOv8's dissimilarities"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Efficiency"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      ">> Reporting efficiency ...\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1500x500 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "efficiency_tbls = SummaryReporter(epsilons, approaches, detectors, k_folds=folds, summarize_validity=False).report(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>$1 - \\epsilon^g$</th>\n",
       "      <th>Bonferroni</th>\n",
       "      <th>Max additive</th>\n",
       "      <th>Independent DE-CCP</th>\n",
       "      <th>Gumbel DE-CCP</th>\n",
       "      <th>Empirical DE-CCP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.99</td>\n",
       "      <td>1.24e+04±9.50e+02</td>\n",
       "      <td>1.56e+05±2.38e+04</td>\n",
       "      <td>1.15e+04±6.75e+02</td>\n",
       "      <td>1.12e+04±7.20e+02</td>\n",
       "      <td>1.11e+04±8.15e+02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.95</td>\n",
       "      <td>5.34e+03±2.05e+02</td>\n",
       "      <td>5.53e+04±3.38e+03</td>\n",
       "      <td>5.15e+03±2.46e+02</td>\n",
       "      <td>4.97e+03±2.28e+02</td>\n",
       "      <td>4.87e+03±2.40e+02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.90</td>\n",
       "      <td>3.40e+03±1.36e+02</td>\n",
       "      <td>2.73e+04±7.77e+02</td>\n",
       "      <td>3.22e+03±8.89e+01</td>\n",
       "      <td>3.10e+03±7.91e+01</td>\n",
       "      <td>2.99e+03±1.09e+02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.80</td>\n",
       "      <td>1.98e+03±3.69e+01</td>\n",
       "      <td>1.00e+04±1.35e+02</td>\n",
       "      <td>1.81e+03±4.52e+01</td>\n",
       "      <td>1.72e+03±4.56e+01</td>\n",
       "      <td>1.62e+03±5.00e+01</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   $1 - \\epsilon^g$         Bonferroni       Max additive Independent DE-CCP  \\\n",
       "0              0.99  1.24e+04±9.50e+02  1.56e+05±2.38e+04  1.15e+04±6.75e+02   \n",
       "1              0.95  5.34e+03±2.05e+02  5.53e+04±3.38e+03  5.15e+03±2.46e+02   \n",
       "2              0.90  3.40e+03±1.36e+02  2.73e+04±7.77e+02  3.22e+03±8.89e+01   \n",
       "3              0.80  1.98e+03±3.69e+01  1.00e+04±1.35e+02  1.81e+03±4.52e+01   \n",
       "\n",
       "       Gumbel DE-CCP   Empirical DE-CCP  \n",
       "0  1.12e+04±7.20e+02  1.11e+04±8.15e+02  \n",
       "1  4.97e+03±2.28e+02  4.87e+03±2.40e+02  \n",
       "2  3.10e+03±7.91e+01  2.99e+03±1.09e+02  \n",
       "3  1.72e+03±4.56e+01  1.62e+03±5.00e+01  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "efficiency_tbls[0] # Experiment N°1: correlated dissimilarities"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>$1 - \\epsilon^g$</th>\n",
       "      <th>Bonferroni</th>\n",
       "      <th>Max additive</th>\n",
       "      <th>Independent DE-CCP</th>\n",
       "      <th>Gumbel DE-CCP</th>\n",
       "      <th>Empirical DE-CCP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.99</td>\n",
       "      <td>2.22e+03±3.14e+00</td>\n",
       "      <td>6.29e+04±3.18e+02</td>\n",
       "      <td>2.21e+03±5.30e+00</td>\n",
       "      <td>2.21e+03±3.76e+00</td>\n",
       "      <td>2.21e+03±4.99e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.95</td>\n",
       "      <td>2.13e+03±4.52e+00</td>\n",
       "      <td>5.33e+04±4.51e+02</td>\n",
       "      <td>2.11e+03±3.16e+00</td>\n",
       "      <td>2.11e+03±3.00e+00</td>\n",
       "      <td>2.11e+03±3.51e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.90</td>\n",
       "      <td>2.02e+03±6.73e+00</td>\n",
       "      <td>4.29e+04±3.76e+02</td>\n",
       "      <td>2.00e+03±3.35e+00</td>\n",
       "      <td>2.00e+03±3.67e+00</td>\n",
       "      <td>1.99e+03±8.02e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.80</td>\n",
       "      <td>1.81e+03±7.62e+00</td>\n",
       "      <td>2.68e+04±6.45e+01</td>\n",
       "      <td>1.77e+03±8.94e+00</td>\n",
       "      <td>1.77e+03±8.84e+00</td>\n",
       "      <td>1.48e+03±4.08e+02</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   $1 - \\epsilon^g$         Bonferroni       Max additive Independent DE-CCP  \\\n",
       "0              0.99  2.22e+03±3.14e+00  6.29e+04±3.18e+02  2.21e+03±5.30e+00   \n",
       "1              0.95  2.13e+03±4.52e+00  5.33e+04±4.51e+02  2.11e+03±3.16e+00   \n",
       "2              0.90  2.02e+03±6.73e+00  4.29e+04±3.76e+02  2.00e+03±3.35e+00   \n",
       "3              0.80  1.81e+03±7.62e+00  2.68e+04±6.45e+01  1.77e+03±8.94e+00   \n",
       "\n",
       "       Gumbel DE-CCP   Empirical DE-CCP  \n",
       "0  2.21e+03±3.76e+00  2.21e+03±4.99e+00  \n",
       "1  2.11e+03±3.00e+00  2.11e+03±3.51e+00  \n",
       "2  2.00e+03±3.67e+00  1.99e+03±8.02e+00  \n",
       "3  1.77e+03±8.84e+00  1.48e+03±4.08e+02  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "efficiency_tbls[1] # Experiment N°2: independent dissimilarities"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>$1 - \\epsilon^g$</th>\n",
       "      <th>Bonferroni</th>\n",
       "      <th>Max additive</th>\n",
       "      <th>Independent DE-CCP</th>\n",
       "      <th>Gumbel DE-CCP</th>\n",
       "      <th>Empirical DE-CCP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.99</td>\n",
       "      <td>8.99e+10±3.89e+10</td>\n",
       "      <td>1.92e+12±1.20e+12</td>\n",
       "      <td>5.62e+10±1.57e+10</td>\n",
       "      <td>5.01e+10±1.66e+10</td>\n",
       "      <td>3.10e+10±1.28e+10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.95</td>\n",
       "      <td>5.00e+09±3.22e+09</td>\n",
       "      <td>8.60e+09±5.99e+09</td>\n",
       "      <td>3.72e+09±2.52e+09</td>\n",
       "      <td>2.52e+09±1.57e+09</td>\n",
       "      <td>6.14e+08±4.44e+08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.90</td>\n",
       "      <td>9.41e+08±5.04e+08</td>\n",
       "      <td>3.99e+07±3.60e+07</td>\n",
       "      <td>4.63e+08±2.90e+08</td>\n",
       "      <td>2.38e+08±1.37e+08</td>\n",
       "      <td>1.47e+07±1.19e+07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.80</td>\n",
       "      <td>5.23e+07±2.94e+07</td>\n",
       "      <td>7.05e+05±1.95e+05</td>\n",
       "      <td>1.39e+07±1.12e+07</td>\n",
       "      <td>4.69e+06±3.42e+06</td>\n",
       "      <td>3.57e+05±5.63e+04</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   $1 - \\epsilon^g$         Bonferroni       Max additive Independent DE-CCP  \\\n",
       "0              0.99  8.99e+10±3.89e+10  1.92e+12±1.20e+12  5.62e+10±1.57e+10   \n",
       "1              0.95  5.00e+09±3.22e+09  8.60e+09±5.99e+09  3.72e+09±2.52e+09   \n",
       "2              0.90  9.41e+08±5.04e+08  3.99e+07±3.60e+07  4.63e+08±2.90e+08   \n",
       "3              0.80  5.23e+07±2.94e+07  7.05e+05±1.95e+05  1.39e+07±1.12e+07   \n",
       "\n",
       "       Gumbel DE-CCP   Empirical DE-CCP  \n",
       "0  5.01e+10±1.66e+10  3.10e+10±1.28e+10  \n",
       "1  2.52e+09±1.57e+09  6.14e+08±4.44e+08  \n",
       "2  2.38e+08±1.37e+08  1.47e+07±1.19e+07  \n",
       "3  4.69e+06±3.42e+06  3.57e+05±5.63e+04  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "efficiency_tbls[2] # Experiment N°3: YOLOv8's dissimilarities"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Object detection results"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Examples"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "__init__() missing 1 required positional argument: 'num_frames'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[11], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m giffer \u001b[38;5;241m=\u001b[39m \u001b[43mGifReporter\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdest\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mMax_additive_vs_Empiricial_DE-CPP.gif\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m      2\u001b[0m giffer\u001b[38;5;241m.\u001b[39mreport(res, save\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n",
      "\u001b[0;31mTypeError\u001b[0m: __init__() missing 1 required positional argument: 'num_frames'"
     ]
    }
   ],
   "source": [
    "giffer = GifReporter(dest=\"Max_additive_vs_Empiricial_DE-CPP.gif\")\n",
    "giffer.report(res, save=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## DELETE ME"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[(3007, 16), (2756, 16), (744, 16)]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "[res.logs[approaches[0], det, 0, epsilons[0]][\"cal_res\"].shape for det in detectors]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[(9781, 16), (9674, 16), (2740, 16)]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "[res.logs[approaches[0], det, 0, epsilons[0]][\"test_res\"].shape for det in detectors]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>object's fields</th>\n",
       "      <th>x_min</th>\n",
       "      <th>y_min</th>\n",
       "      <th>x_max</th>\n",
       "      <th>y_max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>Bounds</th>\n",
       "      <th>Exact value</th>\n",
       "      <th>Exact value</th>\n",
       "      <th>Exact value</th>\n",
       "      <th>Exact value</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>images</th>\n",
       "      <th>objects</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>003376.png</th>\n",
       "      <th>0</th>\n",
       "      <td>1.200721</td>\n",
       "      <td>1.618175</td>\n",
       "      <td>0.60282</td>\n",
       "      <td>1.009003</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>002951.png</th>\n",
       "      <th>0</th>\n",
       "      <td>1.183542</td>\n",
       "      <td>0.131589</td>\n",
       "      <td>0.249822</td>\n",
       "      <td>0.868971</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">004841.png</th>\n",
       "      <th>0</th>\n",
       "      <td>1.349661</td>\n",
       "      <td>0.108609</td>\n",
       "      <td>2.74664</td>\n",
       "      <td>0.430694</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.368448</td>\n",
       "      <td>0.181865</td>\n",
       "      <td>6.553336</td>\n",
       "      <td>0.226106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.251093</td>\n",
       "      <td>1.076803</td>\n",
       "      <td>0.405844</td>\n",
       "      <td>0.796615</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">007185.png</th>\n",
       "      <th>4</th>\n",
       "      <td>0.368892</td>\n",
       "      <td>1.610726</td>\n",
       "      <td>4.355884</td>\n",
       "      <td>1.175854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2.40559</td>\n",
       "      <td>2.31434</td>\n",
       "      <td>5.357407</td>\n",
       "      <td>2.114428</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.600206</td>\n",
       "      <td>0.674551</td>\n",
       "      <td>0.134777</td>\n",
       "      <td>1.303734</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.762522</td>\n",
       "      <td>1.00335</td>\n",
       "      <td>5.031397</td>\n",
       "      <td>0.84098</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.882511</td>\n",
       "      <td>0.862197</td>\n",
       "      <td>1.890616</td>\n",
       "      <td>1.328757</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3007 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "object's fields          x_min       y_min       x_max       y_max\n",
       "Bounds             Exact value Exact value Exact value Exact value\n",
       "images     objects                                                \n",
       "003376.png 0          1.200721    1.618175     0.60282    1.009003\n",
       "002951.png 0          1.183542    0.131589    0.249822    0.868971\n",
       "004841.png 0          1.349661    0.108609     2.74664    0.430694\n",
       "           1          0.368448    0.181865    6.553336    0.226106\n",
       "           2          0.251093    1.076803    0.405844    0.796615\n",
       "...                        ...         ...         ...         ...\n",
       "007185.png 4          0.368892    1.610726    4.355884    1.175854\n",
       "           5           2.40559     2.31434    5.357407    2.114428\n",
       "           6          0.600206    0.674551    0.134777    1.303734\n",
       "           7          0.762522     1.00335    5.031397     0.84098\n",
       "           8          0.882511    0.862197    1.890616    1.328757\n",
       "\n",
       "[3007 rows x 4 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "res.logs[approaches[0], detectors[0], 0, epsilons[0]][\"cal_dissims\"]"
   ]
  },
  {
   "cell_type": "raw",
   "metadata": {
    "vscode": {
     "languageId": "raw"
    }
   },
   "source": [
    "from pandas import DataFrame\n",
    "from PIL import Image, ImageDraw\n",
    "from typing import List, Any\n",
    "\n",
    "\n",
    "log_idx, mode = -1, \"cal_res\"\n",
    "method = res.logs[log_idx][\"cfmz_name\"]\n",
    "fname, _ = res.logs[log_idx][mode].iloc[0].name\n",
    "gt_bboxes = res.logs[log_idx][mode][\"Ground truths\"].loc[fname]\n",
    "conf_intevals = res.logs[log_idx][mode][method].loc[fname]\n",
    "inner_bboxes = conf_intevals.xs(\"Lower bound\", level=\"Bounds\", axis=1)\n",
    "outer_bboxes = conf_intevals.xs(\"Upper bound\", level=\"Bounds\", axis=1)\n",
    "bboxes = zip(gt_bboxes.iterrows(), inner_bboxes.iterrows(), outer_bboxes.iterrows())\n",
    "\n",
    "\"\"\"\n",
    "frames = [{\"name\": fname, \n",
    "          \"Ground truths\": gt_bboxes,\n",
    "          method1: conf_intevals1,\n",
    "          method2: conf_intevals2\n",
    "          }]\n",
    "\"\"\"\n",
    "\n",
    "src = \"datasets/FilteredKitti/raw/training/image_2\"\n",
    "img = Image.open(f'{src}/{fname}')\n",
    "canvas = ImageDraw.Draw(img)\n",
    "\n",
    "for item in zip(bboxes):\n",
    "    gt, inner, outer = item[0]\n",
    "    canvas.rectangle(gt[1], fill=None, outline=\"green\")\n",
    "    canvas.rectangle(inner[1], fill=None, outline=\"red\")\n",
    "    canvas.rectangle(outer[1], fill=None, outline=\"blue\")\n",