{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Valeurs manquantes :\n",
      " from Dec 2022 through Feb 2023    0\n",
      "dtype: int64\n"
     ]
    },
    {
     "ename": "KeyError",
     "evalue": "\"['2008' '12'] not in index\"",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-7-1f8634fbd95a>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     22\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     23\u001b[0m \u001b[0;31m# Conversion de l'année et du mois en un format de date standard pour faciliter l'analyse chronologique\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 24\u001b[0;31m \u001b[0mraw_data\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'date'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_datetime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mraw_data\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'2008'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'12'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0massign\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mday\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     25\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     26\u001b[0m \u001b[0;31m# Tracé de la concentration de CO₂ au fil du temps\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   2131\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mSeries\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mndarray\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mIndex\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2132\u001b[0m             \u001b[0;31m# either boolean or fancy integer index\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2133\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_getitem_array\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2134\u001b[0m         \u001b[0;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mDataFrame\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2135\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_getitem_frame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m_getitem_array\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   2175\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_take\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mindexer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconvert\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2176\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2177\u001b[0;31m             \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_convert_to_indexer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2178\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_take\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mindexer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconvert\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2179\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/indexing.py\u001b[0m in \u001b[0;36m_convert_to_indexer\u001b[0;34m(self, obj, axis, is_setter)\u001b[0m\n\u001b[1;32m   1267\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0mmask\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0many\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1268\u001b[0m                     raise KeyError('{mask} not in index'\n\u001b[0;32m-> 1269\u001b[0;31m                                    .format(mask=objarr[mask]))\n\u001b[0m\u001b[1;32m   1270\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1271\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0m_values_from_object\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mindexer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyError\u001b[0m: \"['2008' '12'] not in index\""
     ]
    }
   ],
   "source": [
    "# Analyse des données de CO₂ de l'observatoire Mauna Loa\n",
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "\n",
    "# URL des données de concentration de CO₂ en format CSV depuis le site de Scripps CO₂ Program\n",
    "data_url = \"https://scrippsco2.ucsd.edu/assets/data/atmospheric/stations/in_situ_co2/monthly/monthly_in_situ_co2_mlo.csv\"\n",
    "\n",
    "# Chargement des données et ignorer les lignes de commentaires en début de fichier\n",
    "# (Lignes de commentaires de 0 à 56 incluses, donc on saute les 57 premières lignes)\n",
    "raw_data = pd.read_csv(data_url, sep=';', skiprows=57)\n",
    "\n",
    "# Affichage des premières lignes du jeu de données pour comprendre sa structure\n",
    "raw_data.head()\n",
    "\n",
    "# Vérification des valeurs manquantes\n",
    "print(\"Valeurs manquantes :\")\n",
    "print(raw_data.isnull().sum())\n",
    "\n",
    "# Suppression des lignes avec des valeurs manquantes\n",
    "data = raw_data.dropna()\n",
    "\n",
    "# Conversion de l'année et du mois en un format de date standard pour faciliter l'analyse chronologique\n",
    "raw_data['date'] = pd.to_datetime(raw_data[['2008', '12']].assign(day=1))\n",
    "\n",
    "# Tracé de la concentration de CO₂ au fil du temps\n",
    "plt.figure(figsize=(12, 6))\n",
    "plt.plot(data['date'], data['average'], label='Concentration moyenne de CO₂ (ppm)', color='black')\n",
    "plt.xlabel('Année')\n",
    "plt.ylabel('Concentration de CO₂ (ppm)')\n",
    "plt.title('Concentration mensuelle moyenne de CO₂ à Mauna Loa (1958 - présent)')\n",
    "plt.legend()\n",
    "plt.show()\n",
    "\n",
    "# Analyse des tendances avec une moyenne annuelle glissante pour observer la tendance à long terme\n",
    "data['yearly_avg'] = data['average'].rolling(window=12).mean()\n",
    "\n",
    "plt.figure(figsize=(12, 6))\n",
    "plt.plot(data['date'], data['average'], label='CO₂ mensuel', color='grey')\n",
    "plt.plot(data['date'], data['yearly_avg'], label='Moyenne annuelle glissante', color='blue')\n",
    "plt.xlabel('Année')\n",
    "plt.ylabel('Concentration de CO₂ (ppm)')\n",
    "plt.title('Tendance de la concentration de CO₂ à Mauna Loa')\n",
    "plt.legend()\n",
    "plt.show()\n",
    "\n",
    "# Étude de l'incidence annuelle\n",
    "# Extraction de l'année pour faciliter le regroupement annuel\n",
    "data['year'] = data['date'].dt.year\n",
    "\n",
    "# Calcul de la concentration annuelle moyenne\n",
    "yearly_co2 = data.groupby('year')['average'].mean()\n",
    "\n",
    "# Visualisation de l'évolution annuelle\n",
    "plt.figure(figsize=(12, 6))\n",
    "yearly_co2.plot(style='*', color='green')\n",
    "plt.xlabel(\"Année\")\n",
    "plt.ylabel(\"Concentration annuelle moyenne de CO₂ (ppm)\")\n",
    "plt.title(\"Évolution de la concentration annuelle moyenne de CO₂ à Mauna Loa\")\n",
    "plt.show()\n",
    "\n",
    "# Distribution des concentrations annuelles de CO₂ pour évaluer les années avec les concentrations les plus élevées\n",
    "df_yearly_co2 = yearly_co2.sort_values().reset_index()\n",
    "df_yearly_co2.columns = ['Année', 'Concentration moyenne de CO₂ (ppm)']\n",
    "df_yearly_co2\n",
    "\n",
    "# Histogramme de la distribution annuelle de CO₂\n",
    "yearly_co2.hist(xrot=20, color='skyblue')\n",
    "plt.xlabel(\"Concentration annuelle moyenne de CO₂ (ppm)\")\n",
    "plt.ylabel(\"Nombre d'années\")\n",
    "plt.title(\"Distribution de la concentration annuelle moyenne de CO₂ à Mauna Loa\")\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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
}