{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Analyse de données liées au journal de bord"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np \n",
    "from datetime import datetime\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.dates as mdates\n",
    "import re"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "La première étape consiste à importer puis corriger les données."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([(6088001, '\"NICE\"', '20250801', 0., 20.8, 26.5, 24.1),\n",
       "       (6088001, '\"NICE\"', '20250802', 0., 20.2, 27.8, 24.2),\n",
       "       (6088001, '\"NICE\"', '20250803', 0., 21. , 27.4, 24.5),\n",
       "       (6088001, '\"NICE\"', '20250804', 0., 22. , 27.2, 24.6),\n",
       "       (6088001, '\"NICE\"', '20250805', 0., 21.7, 27.1, 24.6)],\n",
       "      dtype=[('NUM_POSTE', '<i8'), ('NOM_USUEL', '<U10'), ('AAAAMMJJ', '<U10'), ('RR', '<f8'), ('TN', '<f8'), ('TX', '<f8'), ('TM', '<f8')])"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Importer donnees\n",
    "data = np.genfromtxt('Q_06_latest-2024-2025_RR-T-Vent_filtered_Nice_20250801-26.csv', delimiter=';', names = True,\n",
    "                     dtype=[('NUM_POSTE', '<i8'), ('NOM_USUEL', '<U10'), ('AAAAMMJJ', '<U10'), ('RR', '<f8'), ('TN', '<f8'), ('TX', '<f8'), ('TM', '<f8')])\n",
    "data[:5,]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([(6088001, 'NICE', '2025-08-01', 0., 20.8, 26.5, 24.1),\n",
       "       (6088001, 'NICE', '2025-08-02', 0., 20.2, 27.8, 24.2),\n",
       "       (6088001, 'NICE', '2025-08-03', 0., 21. , 27.4, 24.5),\n",
       "       (6088001, 'NICE', '2025-08-04', 0., 22. , 27.2, 24.6),\n",
       "       (6088001, 'NICE', '2025-08-05', 0., 21.7, 27.1, 24.6)],\n",
       "      dtype=[('NUM_POSTE', '<i8'), ('NOM_USUEL', '<U10'), ('AAAAMMJJ', '<U10'), ('RR', '<f8'), ('TN', '<f8'), ('TX', '<f8'), ('TM', '<f8')])"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Corriger colonne NOM_USUEL\n",
    "data['NOM_USUEL'] = [re.sub(\"\\\"\", \"\", x) for x in data['NOM_USUEL']]\n",
    "# Convertir colonne en date\n",
    "data['AAAAMMJJ'] = [datetime.strptime(x, '%Y%m%d') for x in data['AAAAMMJJ']]\n",
    "data[:5,]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Il est temps de faire quelques statistiques de bases à partir de ces données."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Moyenne des températures minimales sur le mois d'août à NICE : 23.4 °C.\n",
      "Ecart-type = 2.81\n",
      "Moyenne des températures maximales sur le mois d'août à NICE : 29.9 °C.\n",
      "Ecart-type = 3.09\n",
      "Moyenne des précipitations sur le mois d'août à NICE : 0.6 mm.\n",
      "Ecart-type = 2.67\n",
      "Plus fort taux de précipitations pour le mois d'août à NICE : 13.0 mm.\n",
      "Plus fort taux de précipitations le 2025-08-20 .\n"
     ]
    }
   ],
   "source": [
    "print(\"Moyenne des températures minimales sur le mois d'août à\", data['NOM_USUEL'][0], \":\", round(np.mean(data['TN']), 1), \"°C.\")\n",
    "print(\"Ecart-type =\", round(np.std(data['TN'], ddof=1), 2))\n",
    "print(\"Moyenne des températures maximales sur le mois d'août à\", data['NOM_USUEL'][0], \":\", round(np.mean(data['TX']), 1), \"°C.\")\n",
    "print(\"Ecart-type =\", round(np.std(data['TX'], ddof=1), 2))\n",
    "print(\"Moyenne des précipitations sur le mois d'août à\", data['NOM_USUEL'][0], \":\", round(np.mean(data['RR']), 1), \"mm.\")\n",
    "print(\"Ecart-type =\", round(np.std(data['RR'], ddof=1), 2))\n",
    "print(\"Plus fort taux de précipitations pour le mois d'août à\", data['NOM_USUEL'][0], \":\", data['RR'].max(), \"mm.\")\n",
    "indices = np.where(data['RR'] == data['RR'].max())\n",
    "print(\"Plus fort taux de précipitations le\", data[indices]['AAAAMMJJ'][0], \".\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Maintenant nous allons pouvoir visualiser ces données météo."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Avec Q1 = 27.35 , Q2 = 28.7 , Q3 = 31.95\n"
     ]
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "plt.style.use('seaborn-whitegrid')\n",
    "plt.boxplot(data['TX'])\n",
    "plt.title(\"Températures maximales du mois d'août à \" + data['NOM_USUEL'][0])\n",
    "plt.xticks([])\n",
    "plt.show()\n",
    "print(\"Avec Q1 =\", round(np.quantile(data['TX'], 0.25), 2), \", Q2 =\", round(np.quantile(data['TX'], 0.5), 2), \", Q3 =\", round(np.quantile(data['TX'], 0.75), 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "fig, ax = plt.subplots(figsize = (7,5))\n",
    "l1 = ax.plot(data['AAAAMMJJ'], data['TN'], color = 'blue', linewidth = 2, label = 'Minimales') \n",
    "l2 = ax.plot(data['AAAAMMJJ'], data['TX'], color = 'red', linewidth = 2, label = 'Maximales')\n",
    "l3 = ax.plot(data['AAAAMMJJ'], data['TM'], color = 'black', linewidth = 2, label = 'Moyennes')\n",
    "ax.tick_params(axis = 'x', labelrotation = 75)\n",
    "ax.set_ylabel('Température (°C)')\n",
    "ax.legend()\n",
    "plt.title(\"Suivi des températures pour le mois d'août à \" + data['NOM_USUEL'][0])\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}