{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Different stops detection methods\n",
    "\n",
    "In order to analyze traces collected by citizens using GNSS, one of the first need is to detect stops. \n",
    "The goal of this section is to presents methods existing in tracklib library to detect stops in a GPS track.\n",
    "\n",
    "Ces algorithmes suivent tous le même principe de fonctionnement. Les entrées-sorties sont représentés dans la figure suivante:\n",
    "\n",
    "<figure style='text-align:center'>\n",
    "<img src=\"stop_structure.png\"  width=\"650\" />\n",
    "<figcaption><br/>Figure 1: Input-output of stop detection algorithms</figcaption>\n",
    "</figure>\n",
    "\n",
    "Les résultats de la détection des pauses sont enregistrés dans une nouvelle trace qui contient un point par pause détectée. Ce point a une multitude d'AF qui fournit des métadonnées sur la pause comme: \n",
    "\n",
    "| Nom_AF           | Description                                         | \n",
    "| :--------------- | :-------------------------------------------------- | \n",
    "| radius           | le rayon spatial de recherche s'il existe           | \n",
    "| id_ini           | index du premier point de la pause                  |  \n",
    "| id_end           | index du dernier point de la pause                  |  \n",
    "| mean_XX          |                                                     |  \n",
    "| sigma_XX         |                                                     |  \n",
    "| duration         | la durée de la pause                                |  \n",
    "| nb_points        | le nombre de point du stop                          |  \n",
    "| rmse             | le rmse du stop                                     |  \n",
    "\n",
    "\n",
    "<div class=\"alert alert-block alert-success\">\n",
    "Les 4 méthodes peuvent s'appeler avec la fonction:<br/>\n",
    "<span style='padding-left:4em'>findStops(track, spatial, temporal, mode)\n",
    "\n",
    "appelle la méthode: <br/>\n",
    "    - findStopsLocal si mode == MODE_STOPS_LOCAL <br/>\n",
    "    - findStopsGlobal si mode == MODE_STOPS_GLOBAL <br/>\n",
    "    - findStopsLocalWithAcceleration si mode == MODE_STOPS_ACC\n",
    "</div>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Let’s start by defining our environment\n",
    "\n",
    "The first task is only useful for the online notebook"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os.path\n",
    "import sys\n",
    "\n",
    "#-------------------------------------------------------\n",
    "# Import de tracklib\n",
    "module_path = os.path.abspath(os.path.join('../../..'))\n",
    "if module_path not in sys.path:\n",
    "    sys.path.append(module_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import tracklib as trk"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Présentation de la trace\n",
    "\n",
    "Présentons tout d'abord la trace sur laquelle les algos de détection des points d'arrêt s'appliqueront. Voir le quickstart aussi qui utilise cette trace.\n",
    "\n",
    "C'est une trace d'un entrainement de course à pied autour d'une piste. Grosso modo, le coureur faisait des pauses sur place d'une durée d'environ 30 secondes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Warning: no reference point (base) provided for local projection to ENU coordinates. Arbitrarily used: [lon= 2.457019882, lat=48.830705099, hgt= 55.200]\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 576x144 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "trk.ObsTime.setReadFormat(\"4Y-2M-2DT2h:2m:2sZ\")\n",
    "tracks = trk.TrackReader.readFromFile('../../../data/gpx/activity_5807084803.gpx', trk.TrackFormat({'ext': 'GPX'}))\n",
    "trace = tracks.getTrack(0)\n",
    "\n",
    "# Transformation GEO coordinates to ENU\n",
    "trace.toENUCoords()\n",
    "\n",
    "# speed\n",
    "trace.estimate_speed()\n",
    "\n",
    "# ---------------------------------------------------------\n",
    "# Graphics\n",
    "plt.figure(figsize=(8, 2))\n",
    "plt.subplots_adjust(top=1.3, wspace=0.2, hspace=0.2)\n",
    "\n",
    "ax1 = plt.subplot2grid((1, 2), (0, 0))\n",
    "trace.plot(append=ax1)\n",
    "\n",
    "ax2 = plt.subplot2grid((1, 2), (0, 1))\n",
    "ax2.boxplot(trace.getAnalyticalFeature('speed'))\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Méthode 1: segmentation avec la vitesse maximale durant une période minimale\n",
    "\n",
    "This algorithm take maximal speed during stop and minimal stop duration (in seconds) into account.\n",
    "\n",
    "This algorithm of stop detection is based on geographical moving distance in time windows.\n",
    "\n",
    "\n",
    "2 paramètres nécessaires: \n",
    "- duration: minimal stop duration (in seconds)\n",
    "- speed: maximal speed during stop (in ground units / sec)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of stops:  10\n",
      "['radius', 'mean_x', 'mean_y', 'mean_z', 'id_ini', 'id_end', 'sigma_x', 'sigma_y', 'sigma_z', 'duration', 'nb_points', 'rmse']\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 460.8x345.6 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "stops = trk.findStopsLocal(trace, speed=2, duration=15)\n",
    "print ('Number of stops: ', stops.size())\n",
    "print (stops.getListAnalyticalFeatures())\n",
    "# print (stops['nb_points', 0], stops['duration', 0])\n",
    "\n",
    "# --------------------------------------------------------------------------\n",
    "#  On ajoute une AF pour marquer les stops\n",
    "trace['stop_m1'] = 0\n",
    "for i in range(stops.size()):\n",
    "    id_ini = int(stops['id_ini', i])\n",
    "    id_fin = int(stops['id_end', i])\n",
    "    for k in range(id_ini, id_fin+1):\n",
    "        trace['stop_m1', k] = 1\n",
    "\n",
    "trace.plot(type='POINT', af_name='stop_m1', append = False, color='red', pointsize=3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Méthode 2: take into account acceleration\n",
    "\n",
    "Méthod: findStopsLocalWithAcceleration(track, ????)\n",
    "\n",
    "This algorithm detect stop point, knowing that a point is a stop when speed is null or very low and acceleration is negative."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of stops:  2\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 460.8x345.6 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "stops = trk.findStopsLocalWithAcceleration(trace, diameter=50, duration=15)\n",
    "print ('Number of stops: ', stops.size())\n",
    "# print (stops.getListAnalyticalFeatures())\n",
    "# print (stops['nb_points', 0], stops['duration', 0])\n",
    "\n",
    "# --------------------------------------------------------------------------\n",
    "#  On ajoute une AF pour marquer les stops\n",
    "trace['stop_m2'] = 0\n",
    "for i in range(stops.size()):\n",
    "    id_ini = int(stops['id_ini', i])\n",
    "    id_fin = int(stops['id_end', i])\n",
    "    for k in range(id_ini, id_fin+1):\n",
    "        trace['stop_m2', k] = 1\n",
    "\n",
    "# On prépare la barre de couleur: gris clair: pas de pause, rouge est stop\n",
    "trace.plot(type='POINT', af_name='stop_m2', append = False, color='red', pointsize=3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Méthode 3: méthode des cercles englobants\n",
    "\n",
    "Méthode: findStopsGlobal(track, diameter=20, duration=60)\n",
    "\n",
    "This algorithm find stop points in a track based on two parameters: the maximal size of a stop (as the diameter of enclosing circle, in ground units) and minimal time duration (in seconds).\n",
    "\n",
    "La fonction findStopsGlobal: Find stop points in a track based on two parameters:\n",
    "- Maximal size of a stop (as the diameter of enclosing circle, in ground units) \n",
    "- and minimal time duration (in seconds)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[38;2;255;0;0m  0%\u001b[39m \u001b[38;2;255;0;0m(0 of 188)\u001b[39m |                        | Elapsed Time: 0:00:00 ETA:  --:--:--"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Minimal enclosing circles computation:\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[38;2;0;255;0m100%\u001b[39m \u001b[38;2;0;255;0m(188 of 188)\u001b[39m |######################| Elapsed Time: 0:00:00 Time:  0:00:000:00\n",
      "\u001b[38;2;255;0;0m  0%\u001b[39m \u001b[38;2;255;0;0m(0 of 187)\u001b[39m |                        | Elapsed Time: 0:00:00 ETA:  --:--:--"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Optimal split search:\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[38;2;0;255;0m100%\u001b[39m \u001b[38;2;0;255;0m(187 of 187)\u001b[39m |######################| Elapsed Time: 0:00:00 Time:  0:00:000:00\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "9\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "stops = trk.findStopsGlobal(trace, downsampling=1, diameter=30, duration=15)\n",
    "print (len(stops))\n",
    "plt.plot(trace[\"x\"], trace[\"y\"], '+', color=\"teal\", markersize=3)\n",
    "\n",
    "# --------------------------------------------------------------------------\n",
    "#  On ajoute une AF pour marquer les stops\n",
    "trace['stop_m3'] = 0\n",
    "for i in range(stops.size()):\n",
    "    subset = trace[stops[\"id_ini\", i]:stops[\"id_end\", i]]\n",
    "    plt.plot(subset[\"x\"], subset[\"y\"], 'r+')\n",
    "    trk.minCircle(subset).plot('r-')\n",
    "    \n",
    "    id_ini = int(stops['id_ini', i])\n",
    "    id_fin = int(stops['id_end', i])\n",
    "    for k in range(id_ini, id_fin+1):\n",
    "        trace['stop_m3', k] = 1\n",
    "    \n",
    "plt.axis('equal')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Méthode 4: st-dbscan\n",
    "\n",
    "<div class=\"alert alert-block alert-info\">\n",
    "<b>Reference:</b> <br/>\n",
    "Birant, D., & Kut, A. (2007). ST-DBSCAN: An algorithm for clustering\n",
    "spatial–temporal data. Data & Knowledge Engineering, 60(1), 208-221.\n",
    "</div>\n",
    "\n",
    "DBSCAN algorithm with three important directions:\n",
    "1. First, unlike the existing density-based clustering algorithms, our algorithm can cluster spatial–temporal data according to its non-spatial, spatial and temporal attributes. \n",
    "2. Second, DBSCAN cannot detect some noise points when clusters of diﬀerent densities exist. Our algorithm solves this problem by assigning to each cluster a density factor.\n",
    "3. Third, the values of border objects in a cluster may be very diﬀerent than the values of border objects in opposite side, if the non-spatial values of neighbor objects have little diﬀerences and the clusters are adjacent to each other. Our algorithm solves this problem by comparing the average value of a cluster with new coming value.\n",
    "\n",
    "\n",
    "Méthode: stdbscan(track, af_name, eps1, eps2, minPts, deltaAF)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "New analytical features:  ['speed', 'stop_m1', 'acceleration', 'stop_m2', 'stop_m3', 'stdbscan', 'noise']\n"
     ]
    }
   ],
   "source": [
    "# Quels paramètres choisir ?\n",
    "# af_name : t for timestamp\n",
    "# eps1 = to measure the closeness of two points geographically\n",
    "# eps2 = to measure the similarity of timestamp values i.e. the proximity timestamp\n",
    "# MinPts = minimum number of points (a threshold) clustered together\n",
    "# deltaAF = to prevent the discovering of combined clusters\n",
    "\n",
    "trk.stdbscan(trace, 't', 15, 30, 5, 1)\n",
    "\n",
    "print ('New analytical features: ', trace.getListAnalyticalFeatures())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# visualisation des noises\n",
    "fig = plt.figure(figsize=(10, 4))\n",
    "\n",
    "ax1 = fig.add_subplot(121)\n",
    "for i in range(len(trace)):\n",
    "    o = trace[i]\n",
    "    if trace.getObsAnalyticalFeature('noise', i) > 0:\n",
    "        ax1.plot([o.position.getX()], [o.position.getY()], 'ro', markersize=2)\n",
    "    else:\n",
    "        ax1.plot([o.position.getX()], [o.position.getY()], 'ko', markersize=2)\n",
    "\n",
    "\n",
    "# Dans la zone des pauses\n",
    "ll = trk.ENUCoords(-40, -40)\n",
    "ur = trk.ENUCoords(15, 30)\n",
    "bbox = trk.Rectangle(ll, ur)\n",
    "ax2 = fig.add_subplot(122)\n",
    "for i in range(len(trace)):\n",
    "    o = trace[i]\n",
    "    if trace.getObsAnalyticalFeature('noise', i) > 0 and bbox.contains(o.position):\n",
    "        ax2.plot([o.position.getX()], [o.position.getY()], 'ro', markersize=4)\n",
    "    elif bbox.contains(o.position):\n",
    "        ax2.plot([o.position.getX()], [o.position.getY()], 'ko', markersize=4)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Analyse des clusters pour la méthode st-dbscan"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAD4CAYAAAAEhuazAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAAAs4UlEQVR4nO3dfXRjd3ng8e+j60ywW5qXjoG8jJuIGSRLY0iZwYVtd5k2gaQ0amBbeggLhNKeuLFT2m5pm5c9FNpOlpduN0vxpM5CNrSlyYEtLBEFhoRlYHdLYiYF4pEtkbGSScKkZKaEt8pkIunZP+6VLWskWbJ1Jd2r53OOjqR7peufrKtHP/1enp+oKsYYYwZLpNcFMMYY030W/I0xZgBZ8DfGmAFkwd8YYwaQBX9jjBlAQ70uQKu2b9+uF110Ua+LYULqwQcfPKmqo93+u3ZeGz89+OCD3we+oqpX1O4LTPC/6KKLOHz4cK+LYUJKRI714u/aeW38JCIP1wv8YM0+xhgzkCz4G2PMALLgb4wxA8iCvzFtEpHniMi8iHxDRDIi8m5v+7kicq+IPOxdn9PrshrTiAV/Y9r3DPALqvoS4BLgChF5OXAD8AVV3QV8wbtvTF+y4G9Mm9T1Q+/uGd5FgauAj3jbPwK8tvulM6Y1FvyN2QQRcUTk68BTwL2q+gDwfFV9EsC7fl6D514rIodF5PCJEydO25/P50kmkwwNDZFMJsnn8/69EDOwLPj30MzMDENDQ8zMzPS6KKZNqlpS1UuAC4FJEdndxnNvV9W9qrp3dPT0eWWpVIpsNkupVCKbzZJKpTpXcGM8vgd/r4b0NRH5tHffOsU8c3NzlEol5ubmel0Us0mq+l3gEHAF8G0ROQ/Au35qM8fM5XKUy2UAyuUyuVyuI2U1plo3av6/AyxV3bdOMc/U1BSO4zA1NdXropg2iMioiJzt3R4GLgOywD3ANd7DrgE+tZnjx2IxIhH3oxmJRIjFYlstsjGn8TX4i8iFwC8BH6raHPpOsVabc2ZnZ5mammJubs6afoLlPOCLIvIQ8FXcNv9PA+8BXiUiDwOv8u63LZ1OE4/HcRyHeDxOOp3uWMGNqRA/l3EUkf8J/GfgucA7VPVKEfmuqp5d9ZinVXXDpp+9e/dqUHKgDA0NUSqVcByHYrG4pcfOzMwwNzfH1NQUs7OzfhV54InIg6q6t9t/N0jntQmeZue1bzV/EbkSeEpVH9zCMZqOiuhX7TTn1Hts9S8H6xcwxvhCVX254Nb4nwAeBf4ZKAB/C+SA87zHnAfkWjnenj17tB9NT0+r4zg6PT3dscc6jqPA6mPrPaedv2s2BhxWnz4LzS79el6bcGh2XnflBAf2AZ/2br8fuMG7fQPwvlaO0a8fkupAXW16elpFRIHVAN3osbVaCeytHsu0xoK/CaNm53Uvxvl3pFOsXzRq4pmbm6t88a022bTaHDQ7O0uxWGzaxm8jhYwxW9LoW6HfLkGrIdWr+Xfzb1uTUHuwmr8JoWbntc3w7ZDa4Z2zs7OUy2VUteujdKyT2BizEQv+HdJPAdeahIwxG7Hgv0m1Nf1+Crit9BkYYwabr5O8OqnfJsO0M5HL9D+b5GXCqCeTvMKun2r6G6n+lWKZRI0xYDX/lszMzHDgwAFEhOuuuy4wzSmVGcKVjmfHcQDsF0sdVvM3YWQ1/y2qdOKqal906Laq0gldCfzj4+OrqYKD8IvFGOMfC/4tqARKEQlU0Kw0TU1PT1MsFllaWlr9IgjKrxdjjD8s+Neo1yY+OzuLqlIulwMVNGtH/QSpn8IY4y8L/jUqTSUHDhwgEomEpmPUUkMbsPWBzRrr8K0xMTHBkSNHVu+HpWPUhqY2Nygdvslkkmw2S7lcJhKJEI/HyWQyXfv7prusw7cNS0tL6+6XSqVQ1P6tyceArQ9s1ljwr1HdSVoZGhmkET6N2KxfA7Y+sFljwb9GdZC02rIJG1sf2FRY8KfxgutWWzZhE41GyWQyFItFMpkM0Wi010UyPWLBn/7KyGmMMd1gwR/rDDXGDB4L/ljzDjRu+jLGhNNAB38LeGus6cuYweJr8BeRHSLyRRFZEpGMiPyOt/1cEblXRB72rs/xsxyNWMBbY01fxgwWv2v+ReD3VXUceDkwIyIJ4AbgC6q6C/iCd7/rLOCtsaav1vV7pcaYVvga/FX1SVX9J+/2D4Al4ALgKuAj3sM+ArzWz3I0YgHPbFJfV2qMaUXX2vxF5CLgp4EHgOer6pPgfkEAz+tWOYzZqn6v1BjTiq4EfxH5ceDvgd9V1e+38bxrReSwiBw+ceKEfwU06zTqCLcO8tNZpcYEle9ZPUXkDODTwEFV/QtvWw7Yp6pPish5wCFVbZpkxJa7655GGUDDnBl0M1k9vUrNl4D9qvoJEfmuqp5dtf9pVT2t3V9ErgWuBRgbG9tz7NixrRXemAZ6ltVTRAT4MLBUCfyee4BrvNvXAJ/ysxymPePj4+uuK6yDfI1Xqfl74KOq+glv87e9ygze9VP1nquqt6vqXlXdOzo62p0Ct6hT+f5t3YAAUFXfLsDPAQo8BHzdu7wG+EncDrGHvetzNzrWnj171HSH4zgKqOM4Oj09vXodZsBhbf28FuCvgVtrtr8fuMG7fQPwvo2O1W/ndSKR0EgkooBGIhFNJBI9PY7Zmmbnta/Bv5OXzXxIBiVwdVr1/636i6DZ44KuzeAf2kpN5f2uXOq97908jtmagQ3+zQKXaU2zAB+m/287wb+Tl34L/lbzD5dm53Wo0ztYG/XWfe97P0mp9A1uu+0DJJNQ3XRb+f/+xOteh3PoEGd+6UsMHTpEcn6e/MpKz8psNm92dpahoSHA7eDf7BwYWzeg/9kavqYpkQwQBxwiEYjHoXrJ1+T8PNlCgXLVcyJAfGSEzORkdwu7BYOyhu9GbI3fcLE1fM2mibiBH6BchtolX3M1gR+g7G03wWNr/A4OC/6mqfFxt8YPEIlA7ZKvsZGRtZNIgVtvhUsv5cc+YCkzgqjVNX5tKGfwhTL4z8zMICJEIhGbjbpF6bTb1OM47nVt0216YoL4yAiUgGfFfUC5zPfvv5/k/Lz1AQRMq231qVSKbDZLqVQim82SSqW6XFKzVaFs86/MRAUQkdWfsWZjMzMzzM3NMTU11VZn39AQuP/yGWAO7vh7IhefRZlg9AFYm397qj9jQChnfYfBwLX5V4/uCcqXW79oZY2D/MrKabX6WAyveWiWSKQIY2et9gWUgcVCwX4BhEirzUOmf4Uy+M/OzrJ7926A1WvTmlaGx6YWFsgWCpRwg/oLH3iAU3PzRH92ZbV5aOeZI6edXNlCgdTCgq/lN93R6aGc1ofQfaFs9oFwJyHrtaFDh1j9wX/rrW47fypF4qabVpt28isrpBYWWKwZ9eMAxX37ulja1lizT2/ZEFN/DFyzD9gELz+tjvBRVjt4SafXDe+MDg+TmZwkUTUaKOI915haNsS0+0Ib/G2VLn/MzMywdNXvwVteCo+OwJUpt7H/yhTO8dMDe2U0kIPb6ZuemOh+oU1H+dFEY30I3RfaZh/jD7c57RtAHM47BfsXYKwAj40QeecEpceHe13ETbFmn9b50USTz+dJpVLkcjlisRjpdJpoNNqhEg+uZuf1ULcLY4JtamqKAwdigANPDsPb3Db+SuoHE361TTTf/36W+fkkhUKOkZEYExNphofbC9zRaNTa+LsstM0+xh+zs7Ps3FlbZ1DKO/6VxZvv58wvfYlDTz/dk7KZ7qhtonnve4coFLJAiUIhy8JCZyZ85fOQTLpzSGqTCpqts+Bvtu4j83DnV+H8H3FKlcsfeqjuw2wN4HCoHeZ5/vklqJrVUSh0prM2lYJs1p08mM269yvsi2HrLPibtj3ySM2GHesnbp0qa90P5YEDByiVShw4cMD/QhrfVJpoisUimUyGkZEYVI3pcu9vXS7nDiSD05MKNvtiMK2x4G/atjab17suytpOBZ4VSs9bYfEP5nnhI2uzgN0lnVm9NuEwMZFmZMTN/joyEmdiojO5+2vPs+oBQM2+GExrLPibllWabV760pl1yd4+esGL2VYJ6M8K/OGL3VFAOwrgwOIPC1z+4ALXXXcdjuPwxjf+J/vJHiLDw1EmJzPs21dkcjLTdmdvI82SCjb7YjCtsaGepmWtzJpOJt2f4eXPH6osA+AqgV66b/1jytRdIKYXbKhnsOTzblNPLucG/nQabGTo6fpyhq+IXCEiORE5KiI3dOKY1qHor1ZmTafTMDQ0AY89CiXvd3kJeHxtApj9ZDdbFY26FYZvfjMPJHnRiywnULt6UvMXEQf4JvAq4Angq8DVqrrY6Dmt1JAsn09/EBE47zzYfwuMXQSPj7Dzjgke/rI7Acxq/mus5r81lhOouX6s+U8CR1U1r6qngLuBq7Z6UMvn0x+2/eIvwre/DW//R3j1K9n2J7s5eKcb+GdmZshmd3HWWccbLhBjzEbyT+dJHkiyuLRoOYE2qVc1/18FrlDV3/Tuvxn4GVW9vuZx1wLXAoyNje05duxY18tq2rcu6ydrmTzzeXjhCzNw3k/B/q/hXFwiNjLC7K5dzDz8MLlCgZiX/yc63N00EVbzD5bkgSTZk1nKHyzDSUCxmn8d/VjzrzfW77RvIVW9XVX3qure0dHRLhTLdEKsQSbPVApExmH/IoyVKOHm+L/8oYdW1wewnP+9E6Sc+rmTOcpahquB7YDQdF2BlfwK88l5Dg0dYj45z0reFhXqVfB/AthRdf9C4HiPymI6rFEmz2wWVCNuIjhvJFAZOKW6btWvXM0aAKY7grQub2x7jIhE4FyIXB8h8cEEmUymYTK4hdQChWwBSlDIFlhIWQWjV4ndvgrsEpGLgW8BbwDe2KOymA6r5PKvNTQEp04Bj42sfgFEgCERit4XgOX8750g5dRPX50mdVeK3Mkcse0x0lc37zgq5ArVGSjc+wOuJzV/VS0C1wMHgSXgY6q6qYY6G94ZHKvrfd884X4BlNxfBgdf/OLA5fwXkTtE5CkROVK17VwRuVdEHvauz+llGdsVpJz60XOiZKYzFN9ZJDOdIXpO80H+I7GR6gwU7v1Bp6qBuOzZs0frcRxHAXUcp+5+0x3T09PqOI5OT083fEwioRqJqIJ7nUh0sYAbAA5rG+cj8O+AlwJHqra9D7jBu30D8N6NjtPovO6F5eVlTSQS6jiOJhIJXV5e7nWROqawXNAHEg/oF50v6gOJBzT3xYImEqqO456HIXqp6zQ7r3se1Fu9NPqQtBJ0jP9a+RJeXta+/cC1G/zdp3BRTfDPAed5t88Dchsdo5+C/yDp54pIJzU7rwOf28eWa+wPrcyxqMzKLBbd6xBOx3++qj4J4F0/r96DRORaETksIodPnDjR1QL2i16nZLZZ5pbYzXRIK1/C1j/jUhvCvGFKZr+HnVpiOAv+povm5uYolUrMzc2RX1khOT/P0KG1lM8h8G0ROQ/Au36qx+XpW81q3iv5FS4bv4ylxSXfhp02yxg6KAIf/Cu1yYmJCatV9rnqpqHUwkIYJ3bdA1zj3b4G+FQPy9LXmtW8F1ILHDt1DPXmffox7HQAmiA3FPjgX6lNHjlyZLVWafpTddNQrlAI9MQuEbkL+AoQE5EnROQ3gPcArxKRh3GTFr6nl2XsZ81q3oVcgR3sQLxEAIL09bDToAp88K/UJnfv3m1J3QKkUQqIoFDVq1X1PFU9Q1UvVNUPq+q/qOqlqrrLu/5Or8vZr5rVvEdiI9witzDGGBEijJ1xPh//uA3o6LTAB//Z2VmmpqZYWlpifHycubk5a/oJgNmzJxg67k70Gjo+wuzZ/T+xy7RvMx23E+kJLrgI7ox8mC/81Ie480744Q/tM91poVjJq5LHv8Ly+fe/fsvpb1k9/bHZfPuHDg1BTW7YffvsM92ufszq2TEzMzOr+UjOPfdcAMbHx3tZJNOC2tEei4s2DDSMNpsvaGQkRnU+Bve+6aTAB/+5uTlUFcdx+N73vgfA0tJSj0tlatWO8a8d7QFz1mEfQpvNFzQxkWZkJA44jIzEmZgYwLGYPgt88K8ePmgrefWv6jH+cPpojze9yd67MEqn08TjcRzHqZtvf2Ulz/x8kkOHhpifT7Ky4vYJDA9HmZzMsG9fkcnJDMPDAzgW02ehaPM3/W9mZoa5uTmmpqb6MhWHtfn3xvx8kkIhC15C75GROJOTthJXp4S6zd8EQzs5mCwNxOAoFHJUJ9p375tusOBv+k5tE5EJL+vY7R0L/qbvWN/N4LCO3d7p1TKOxjQ0Ozvbl/0CpvMqHbum+6zmb/qe9QEMtl7n/g8rC/6m71kfQDjln86TPJBk6E+GSB5Ikn+6flSvzv2/uAjj4/5+Afi9lkC/8C34i8j7RSQrIg+JyCdF5OyqfTeKyFERyYnI5X6VwYSD9QGEU+quFNmTWUpaInsyS+qu+jn7q2eDA5w6dfriLx0tVypFNpv1bS2BfuFnzf9eYLeqvhj4JnAjgIgkgDcASeAK4ICIOD6WwwRYv88PMJuXO5mjrF7qBy2TO1l/mGe9ScF+LrtYyUUEbkqKbDbr3x/rId+Cv6p+XlUrmZjuBy70bl8F3K2qz6jqI8BRYLLTf9/aicPBmnzCK7Y9RkS81A8SIba9/jDPdBq2bVu7L+LvsotDQ0NN74dFt9r83wZ81rt9AfB41b4nvG2n2cpC1xY0wmFqagoRoVQqMTMzY1/qIZK+Ok18exxHHOLb46Svrj/MMxqFpSVIJNx0IOPj9ZddbLUPYSPVGYLr3Q8NVd30BbgPOFLnclXVY24GPslaKolZ4E1V+z8M/MpGf2vPnj3ajunpaXUcR6enp9t6nuk/juMooI7jrLvdScBh3cJnYbOXds/rIFheXtZEIqGO42gikdDl5eWu/N3EbEIj744o70Ij745oYjaxueMkEhqJRBTQSCSiicTmjtMPmp3XW6r5q+plqrq7zuVTACJyDXAl8B+8goBb099RdZgLgeNbKUc97aQTMP2tusO3kq7b0nb3r151mLbah7CRjZLRhYVvid1E5ArgL4BXquqJqu1J4O9w2/nPB74A7FLVpr+tBj0BlnFVFu7p9II9ltitc3q1uFLyQJLsySxlLRORCPHtcTLTGVbyKyykFijkCozERphITzAcHfa9PP2gV4ndPgg8F7hXRL4uIn8FoKoZ4GPAIvA5YGajwG9MhQ377H+bzeG/VY36EBZSCxSyBShBIVtgIbXQlfL0Oz9H++xU1R2qeol3+a2qfftV9YWqGlPVzzY7jjGNWOdvf+pVs0n0nCiZ6QzFdxbJTGeInhNlZSVPIfuD6sShFHKFjvy9RmsRBIXl8zeBUt3sA3SsCciafcJpfj5J4df+AB7bAeqAlBkZ/3EmM1sfXR6EtQgsn7/HaorBZ52/ppF8Ps+uXbsQEUSEXbt2cfRoFm65CcYeg0gJxh5jIj3Rkb8X9LUIBqrm71dnoemNTr6fVvMPvmQyyeLi4rptF1+8jTvuKOJH7dxq/gFinYXhYu+nqZark/PhscdKvq0XEPi1CBpNAOi3S6cmw9jkr2Da6H3b6vtKByd54easyuGmLrmh2WPDOMmrVxKJhALrLkGeoNUJzc7rngf1Vi+d+pD4NUPU+Guj922r72ungj/gAMtAFNgGfANINHq8Bf/OWV5e1p07d3qBX/SMM8Y1ElnWREJ1s5OMezVbuVOandcD1ewD1lQQVBu9b330vk4CR1U1r6qngLtxkxkan0WjUR5++GFUlUSiTKm0SLkcJZvdfAroMKd3HqgO31qWLthUdKrDV0R+FbhCVX/Tu/9m4GdU9fqqx1wLXAswNja259ixY1v9s6bG0JC7+EuF48BmxgT0arZyp1iHbwOVzJ8HDhywIaCmU6TOtnU1LFW9XVX3qure0dHRLhVrsMRi4E0yJhLZfAroXs1W7oaBDv5nnXXW6m1L/2w6pCuJC01z6TTE426NPx6vnwK6teOEN8lbOFcpaNF3vvOd1dt90l5sgu+rwC4RuRj4Fu6qdW/sbZEGTzQKmQ4MuY9Go2Q6caA+NNA1/927d69eW/pn0wnqrl53PXAQWAI+pm4yQxNQtYvEHPraYySTbr9CMtl8MfmV/ArzyXkODR1iPjnPSn6lewXfwEDX/BcWLLuf6TxV/QzwmV6Xw3RGZaH5spbJnsxy+WtOUXzKXVS+MpKo0Y+D1Yyi5bWMop3IK9QJAx38jTFmI7WLxJz69kWrXfjlcvPF5Au5gi8ZRTthoJt9jDFmI7ULzW97/qMtjyQaiY2sRdmId79PWPA3gWfZWo2faheJOfiZbS2PJJpITzASHwEHRuIjHcso2gkDPcnLhEMnsntaVk8TRjbJy4RaH6V2MCFUO9on/3SwVuxqxIK/CbzZ2dmGQ3WtSchsVWW0T0lLZE9mSd0Vjvw+vgd/EXmHiKiIbK/adqOIHBWRnIhc7ncZNsOCRjhUUnjY7G2zWbWjfXIng7ViVyO+Bn8R2QG8CnisalsCd9ZjEjfv+QERcfwsx2ZY0AgHaxIKh3w+TzKZZGhoiGQySb7ZzKoOqx3tE9sejvw+ftf8/yvwh6xPbHUVcLeqPqOqj+AueNEfsx6qWNAIh2ZNQiY4eplauXa0T/rqcOT38W2Sl4j8MvAtVf2GyLpEhxcA91fdf8LbVu8Y1alvfSppfbOzsxYwjOkTuVyOctlreimX6y7Z6JfoOVEy0+HL0LGl4C8i9wEvqLPrZuAm4NX1nlZnW93xpqp6O3A7uEPiNllMY0zAxWIxstks5XI5dKmVe2VLwV9VL6u3XUQmgIuBSq3/QuCfRGQSS3lrjGlTOp0mlUqRy+WIxWKhSq3cK760+avqgqo+T1UvUtWLcAP+S1X1n4F7gDeIyJle2ttdwLwf5ei4fJ6W0/kZYzqmklq5WCySyWSIRqO9LlLgdX2cv5fe9mPAIvA5YEZVS82f1ScuvxwWF9314RYX3fumr9mQXWPq60pWT6/2X31/P7C/G3+7o44ebX7f9J3qpToB68Q3xmMzfLdAITRTvcOqeqiuzdkwZo0F/3bs3Lk6LEmBo+cSmqneYTU7O8v09LTN2TAt6+WEsm6y4N+OgwdZHIWiwOIoXP4md+q3tSv3N5voZdrRywll3WQpnduUPJBcXdItIhHi2+Pk3p7bckph01uW0tlUVFKEVwT5c20pnTuo3lRvSwVhTHjEYjEi3lJdYZ5QZsG/TZWp3sV3FslMZ4ieE+XP//z3+cd/jPH6188xP59kZSWcbYRBZk1zplXpdJp4PI7jOMTj8aYTylbyK8wn5zk0dIj55Dwr+ZUulnRrrNmnA+bnkxQKWdyVmiOMjMSZnFzLBbKSX2EhtUAhV2Ak5i7lNhwd7ll5B9FGq31Zs4/ZjPnkPIVsofLRZyQ+wmSmf/JUWrOPzwqFHO67D1Cm8IPsuprAQmrBPUFKUMgWWEgt9LK4A8ma5owfCrlC9UffvR8QFvw7YGQkxuq/sizw+I51gT7IJ0hY2Igf44eR2MhaFI149wPCgv8WreRXKL/jz+DRHVCKwGNjcNMt7k4v0NeeIOJIINsIjTHrTaQnGImPgOM2+UykJ3pdpJZ1Jb1DmC2kFvhR9hz4P3e6gX1I0KLXj+LVBCbSE6u/AMQR9FkFXftl0E9thMaY1g1HhwP7+bWa/1bk8yQXf41Xli/lZbyV55SPU3q2xKPlRylLebUmUDlB9hX3oSVdW73AmoACR0ReLyIZESmLyN6afX2/NrUxFRb8t+DUay5nmMcQygzzGBPcxHE9jqI0GkUV5DZCA8AR4N8DX67eGJS1qY2psODfrqqc/mfkjhLxqvERlGEe56yzzmKMMRwcfrD4Az6/9/PA2njgQraADEkg2wgNqOqSqtZbQzAQa1MbU2HBv12pFGSzbk5/1lpwSgJLo2We+8Pn4uBwK7fyal7NHU/fAbA23LMMWlRGYu54YBvvHxoXAI9X3W+6NrWIHBaRwydOnOhK4Yw/8k/nSR5IMvQnQyQPJAOV5deCf7tyOfAWkq4sRlwUyG6H/3j9ztVmnTRpypT5NJ/mzb/5Zl6x+ApuLd/qPsHa+n23lRm9InKfiBypc7mq2dPqbGu4NrWq7lXVvaOjo22Xz/SP1F0psiezlLRE9mQ2UFl+Lfi3KxYDL++HRiIsv2Abz3mXw6+9K8Ftv32QifQEx593nCu5EoAyZf72w39LmTJpvGni1tbvu8oiLpvJ4a+ql6nq7jqXTzV5mq1NPYByJ3OU1a0MlrVM7mS9FsH+ZMG/Xek0xOPgOEg8zs7/t7Quz89wdJi3XPcW7nnXPevrggLOhMPxnzxubf1d0IMZvcFdm9psWmx7jIh4SeAkQmx7cJLAWfBvVzQKmQwUi+51nYWkV0+IvXAxcOQ58CzwtSef5UMzN1lbfxf4NaNXRF4nIk8ArwD+QUQOQsDXpjabVi/Lb62+XRxGVX27AL8N5IAM8L6q7TfijobIAZe3cqw9e/ZoX1leVk0kVB3HvV5eXtv1nWVNzCbUebejR0bRoqCKe31klB4WevBMT0+r4zg6PT3d9HHAYfXxs9Do0nfn9YBaXl7WRCKhjuNoIpHQ5arP81YlEgmNRCIKaCQS0UQi0bFjb6TZee1bVk8R+XngZuCXVPUZEXmeqj7ljYe+C3cY3PnAfcCLdINaUt9lP0wm3VE/5bLbBxCPu78EahQjwlDVv7goMFQORibVMNgom2eFZfUcbMlkkmw2S7lcJhKJEI/HydT5PG9GLxeH6VVWz+uA96jqMwCq+pS3PRTjobVq1A/lsnu/Vj5PKVI1HBR45PlnrHtIkPOBB4Fl8zStyOVylL3Pc7lcJlfv87xJ/bo4jJ/B/0XAvxWRB0TkSyLyMm97KMZDrzhjlL0e3TJCoXTh6YE7lWKbCoL7BVB0YOra89eNCbZ0z/6ybJ6mFX4G6HYWh+mmLQX/DcZDDwHnAC8H/gD4mIgIIRkP/VDxz1hhDCXCCmMssJ+Fyx9c/6BcDvGaeATYVoK/vO0YY/+yNibY0j37w1buMu3wM0BHo1EymQzFYpFMJkO0ziCRXthSVk9VvazRPhG5DviE1+kwLyJlYDshGQ8die/kq4v/g3XfZUefWf+gWGytX8B7ZPwkLM7CULnMDyLfJVc6zo843zuojf/vlOpx/lbrNxupBOhB4mezz/8CfgFARF4EbANOEpLx0BPpCYRnqW7RH1nXmsXanIAqjsKZJRhSOKv0JBPchHrHsPH/nWNt/cY052fwvwOIisgR4G7gGm/0USjGQw9Hh5nc+WeMcIxK4J/Yecf6B1XmBCQSa7OCWfutEEEZ4XHE22Lj/zvH2vqNac634K+qp1T1TepOi3+pqv7vqn37VfWFqhpT1c/6VQa/DR+8k0ti+/m5yGX82Oiv89o3P1k/sVP1rOBt26h805URCutawIwxg6gXE8Fshu9WRKP89Nu3ceYfR9g9A/eRr5/YqXpW8NISj7xgG+XVjuJbUJTn7HxO98sfUtbZa4ImlUqRzWYplUpks1lSKf8TxFnw36K2EztFo0QWl9j37p/l46Pv4l8jz+eM2Bm85OBLulDawbCVpG7G9IKf8wwaseC/RZtJ7BQ9J8qX3/ll3vrUW7m0dCnnf+V89n5ubyBzgvcj6+w1QdOLiWAW/LeolcROjWbxVpon9v7F3sDmBO9H1tlrgqYXE8G2NM7fuLX4zPT68cH5p922/9zJHLHtMeY+MEfx4aI7iStbYH58Hi0pLyu9jE/ySZ783JPwILAXyr8UrJzgxpit68U8A6v5+6B6dZ/FE4s8881n1s3i1VMKJRiTMW7hFjfwK3A4eDnBjTHBZMHfB9WdwACPbX+Mkpw+lSGiES5yLuJNb3uT+07spWHTkTHGdJIFfx9UdwID3Hz1zatfALJNqmd5MRIb4W8+9DdoSdF5XV0RzGyeDfU0ZmO+5fPvtCDlPa+0+S+eWFzdFpEI8e1xDl9x2M3kmSswEnPTOdis3s5qNYd/Ncvnb8KoV/n8B1alE3j57cskRhPrRgINR4eZzEyyr7jP0jl0WKXGPz4+bkM9TSh1ciaw1fxNaGymxl9hNX8TBO2uOGY1fxNqVuM3g6KTM4Et+AeAdWA2V0nnsLS0ZJO7TKh1ciawBf8AsFw1zVk6BzMoOjkT2IJ/AExNTSEilEolq/3XYekczKDo5JKQFvwDYHZ2dvWnntX+jTGdYME/IKxpoz7rDzGDotMLvthQTxNoWxneWa3VoZ4i8n4gBZwCloFfV9XvevtuBH4DKAFvV9WDGx3PzmvTqnaHeYIN9Qwlq/G6/4PKsLcu/iK6F9itqi8GvgncCCAiCeANQBK4AjggIk63CmXCr9MLvvgW/EXkEhG5X0S+LiKHRWSyat+NInJURHIicrlfZQgzGwHk/g9UFcdxutbZq6qfV9XKT4z7gQu921cBd6vqM6r6CHAUmKx3DGM2o9MLvvhZ838f8G5VvQR4p3ffakgdYn0AffE/eBvwWe/2BcDjVfue8LadRkSu9SpEh0+cOOFzEU1YdHrBFz+DvwI/4d0+Czju3bYaUgfY8Eb//gcicp+IHKlzuarqMTcDReCjlU11DlW3Q01Vb1fVvaq6d3R0tKNlN+FVPcwznU6TSqW21Pnr50pevwscFJE/x/2S+Tfe9gtwfy5XNK0hAdcCjI2N+VZQY6qp6mXN9ovINcCVwKW6NmLiCWBH1cMuZK3CY0xHpVKp1c7fbDZLKpVqeyWwLdX8N6ghXQf8nqruAH4P+HDlaXUOZTUkEwgicgXwR8Avq2qhatc9wBtE5EwRuRjYBcz3oowm/DrR+bul4K+ql6nq7jqXTwHXAJ/wHvpx1pp2rIZkWlZvVFOPRzp9EHgucK83mOGvAFQ1A3wMWAQ+B8yo6unLtxnTAR3p/FVVXy7AErDPu30p8KB3Owl8AzgTuBjIA85Gx9uzZ4+a001PT6vjODo9Pd3rovhCRBRQEVnd5jiOAuo4Tsf+DnBYffosNLvYeW02Y3l5WROJhDqOo4lEQpeXl+s+rtl57dskLxH5OeC/4fYr/AiYVtUHvX03446UKAK/q6qfbXggj02Gqa9Tk5z6lchaK2H1yJ65uTmmpqY61tlr+fxNGPVkkpeq/l9V3aOqL1HVn6kEfm/fflV9oarGWgn8prE+GO7oq+npaRzHWU1sNzc3ZyOdjOkAm+EbcNWBMCyzfqtfR+X1XXfddaH+kjOm2yy3T4iEpQmoF6/Dmn1MGFlunwERhiagmZkZSqUSIhLo12FMv7PgHyL12sKD1hRUyVUUiURC1ZRlTL+x4B9yQUsAV/vrJWjlNyYoLPiHXCWYjo+P92UNurZmX/vrJQxNWcb0Iwv+AyKTyfRlDbpRzb7ypQDYsE5jfGDBP+QqwVW9vPf99gugUc3emnuM8ZcF/5CrBNfp6WmKxSJLS0t9FVQbTdiy5h5j/GXj/AfMxMQER44cYffu3SwsLPS6OH3DxvmbMLJx/mbV0tLSumtjzGCy4D9grDnFGAMW/AdObRu7TaIyZjBZ8B9w7Y6qsS8LY8LBgv+Aa7UZqBL0b7vttnVfFvZlYEwwWfAfcK3mxq+dL9Bq+gX7cjCmP1nwNy2pnS/QavoFm6xlTH+y4G9a0qijGGi4mIylZzamf9kkL7Mp9RZcqd0WpMVlbJKXCaJ8Pk8qlSKXyxGLxUin00Sj0dX9vk3yEpHXi0hGRMoisrdm340iclREciJyedX2PSKy4O37gFSv0G0Co1620NomIJtTYIy/UqkU2WyWUqlENpsllUq1/Nwt1fxFZBwoA3PAO1T1sLc9AdwFTALnA/cBL1LVkojMA78D3A98BvhAK4u4Ww2pPwWpdt+M1fxNEFU+fxW1n0Pfav6quqSquTq7rgLuVtVnVPUR4CgwKSLnAT+hql9R91vnr4HXbqUMpresdm9M78RiMSIRN4xHIhFisVjLz/Wrw/cC4PGq+0942y7wbtdur0tErhWRwyJy+MSJE74U1GxNq0NFjTGdl06nicfjOI5DPB4nnU63/NyhjR4gIvcBL6iz62ZV/VSjp9XZpk2216WqtwO3g/vzeIOiGmPMQIlGo2QymU09d8Pgr6qXbeK4TwA7qu5fCBz3tl9YZ7sxgSAif4rbrFkGngLeqqrHvX03Ar8BlIC3q+rBnhXUmA341exzD/AGETlTRC4GdgHzqvok8AMRebk3yuctQKNfD8b0o/er6otV9RLg08A7YXWQwxuAJHAFcEBEnJ6V0pgNbHWo5+tE5AngFcA/iMhBAFXNAB8DFoHPATOqWumSvg74EG4n8DKw4UgfY/qFqn6/6u6PsdZsWXeQQ7fLZ0yrNmz2aUZVPwl8ssG+/cD+OtsPA7u38neN6SUR2Y/7q/V7wM97my/AHb5c0XAwg4hcC1wLMDY25l9BjWnC0jsYU0NE7hORI3UuVwGo6s2qugP4KHB95Wl1DlV3kIKq3q6qe1V17+joqD8vwpgNbKnmb0wYtTHI4e+AfwD+mMaDHIzpS4HJ7SMiJ4BjbTxlO3DSp+J0W5heC/Tn6/kpVd2wGi4iu1T1Ye/2bwOvVNVfFZEk7pdBZVb7F4BdVX1djY7X7nndD/rx/fNbUF/zLuArqnpF7Y7A1Pxb+WBWE5HDvZiu74cwvRYI/Ot5j4jEcId6HgN+C9xBDiJSGeRQZP0gh4baPa/7QcDfv00J42sOTPA3ph+o6q802Vd3kIMx/cg6fI0xZgCFOfjf3usCdFCYXguE7/UMmkF8/0L3mgPT4WuMMaZzwlzzN8YY04AFf2OMGUCBD/5hXkpSRN4lIt8Ska97l9dU7av72vqZiFzhlfeoiNzQ6/KY9ojI+0UkKyIPicgnReTsqn2BOx9bEepzVlUDfQHGgRhwCNhbtT0BfAM4E7gYN4mc4+2bx01GJ7iJ5X6x16+jwWt7F+7ymLXbG762fr0AjlfOKLDNK3+i1+WyS1vv4auBIe/2e4H3ercDdz62+HpDfc4Gvuavg7mUZBAzSE4CR1U1r6qngLtxX4cJCFX9vKpWFoi9n7W1OYJ4PrYi1Ods4IN/Ex1ZSrIPXO/9zL5DRM7xtjV6bf0siGU2jb2NtXTsYX1vw/q6gIDM8O3lUpJ+a/bagNuAP8Ut358C/wX3Q9dXr6FFQSzzwGnlsyYiN+OmsPho5Wl1Hh+G9zasrwsISPDXEC8l2eprE5H/jrtyFAQzg2QQyzxwNjofReQa4ErgUq/ZFML73ob1dQHhbvYJ/FKSXv9ExeuAI97tuq+t2+Vr01eBXSJysYhsw13y8J4el8m0QUSuAP4I+GVVLVTtCuL52IpQn7OBqPk3IyKvA/4SGMVdSvLrqnq5Ns+yeB1wJzCM227Zr0tJvk9ELsH9qfkoMAWbzyDZS6paFJHrgYO4oyjuUHe5TxMcH8Qd0XOvNzr6flX9rSCej60I+zlr6R2MMWYAhbnZxxhjTAMW/I0xZgBZ8DfGmAFkwd8YYwaQBX9jjBlAFvyNMWYAWfA3xpgB9P8Bf1AtcMAWzRUAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = plt.figure(figsize=(6, 4))\n",
    "COLORS = ['ro','go','bo','yo','mo','co']\n",
    "\n",
    "trace['stop_m4'] = 0\n",
    "\n",
    "ax1 = fig.add_subplot(121)\n",
    "for i in range(len(trace)):\n",
    "    o = trace[i]\n",
    "    cluster = trace.getObsAnalyticalFeature('stdbscan', i)\n",
    "    if cluster > 0:\n",
    "        #print (cluster)\n",
    "        trace['stop_m4', i] = 1\n",
    "        color = COLORS[cluster%6]\n",
    "        ax1.plot([o.position.getX()], [o.position.getY()], color, markersize=4)\n",
    "    else:\n",
    "        ax1.plot([o.position.getX()], [o.position.getY()], 'ko', markersize=2)\n",
    "\n",
    "ax2 = fig.add_subplot(122)\n",
    "cpt = 0\n",
    "clusterOld = -1\n",
    "d=dict()\n",
    "for i in range(len(trace)):\n",
    "    o = trace[i]\n",
    "    cluster = trace.getObsAnalyticalFeature('stdbscan', i)\n",
    "    if cluster > 0 and bbox.contains(o.position):\n",
    "        if cluster != clusterOld:\n",
    "            cpt += 1\n",
    "            d[COLORS[cpt%6]] = []\n",
    "        color = COLORS[cpt%6]\n",
    "        ax2.plot([o.position.getX()], [o.position.getY()], color, markersize=4)\n",
    "        d[color].append(i)\n",
    "        #ax2.text(o.position.getX()+0.1, o.position.getY()+0.1, str(i))\n",
    "        clusterOld = cluster\n",
    "    elif bbox.contains(o.position):\n",
    "        ax2.plot([o.position.getX()], [o.position.getY()], 'ko', markersize=4)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Détail des clusters dans la figure de droite:\n",
      "go [29, 30, 32, 34, 35, 36]\n",
      "bo [67, 68, 69, 70, 71, 72, 73, 74]\n",
      "yo [109, 110, 112, 113, 114]\n",
      "mo [147, 149, 150, 151, 152]\n"
     ]
    }
   ],
   "source": [
    "print ('Détail des clusters dans la figure de droite:')\n",
    "for k in d:\n",
    "    print (k, d[k])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Graphic Abstract\n",
    "\n",
    "Visualisation des stops points par rapport au profil de vitesse"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "tags": [
     "nbsphinx-thumbnail"
    ]
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 288x216 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(4, 3))\n",
    "\n",
    "# -----------------------------------------------------------------------------\n",
    "# # On dessine\n",
    "TAB_AFS = ['stop_m1', 'stop_m3', 'stop_m4']\n",
    "trace.plotProfil('SPATIAL_SPEED_PROFIL', TAB_AFS, append=True)"
   ]
  }
 ],
 "metadata": {
  "celltoolbar": "Tags",
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}
