{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "hideCode": false,
    "hidePrompt": false
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import datetime"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "hideCode": false,
    "hidePrompt": false
   },
   "source": [
    "# Analyse de la concentration de CO2 dans l'atmosphère depuis 1958\n",
    "# 1. Chargement des données"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "hideCode": false,
    "hidePrompt": false
   },
   "source": [
    "Récupérons directement les données sur le site [officiel](https://scrippsco2.ucsd.edu/)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {
    "hideCode": false,
    "hidePrompt": false
   },
   "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>Yr</th>\n",
       "      <th>Mn</th>\n",
       "      <th>Date Excel</th>\n",
       "      <th>Date</th>\n",
       "      <th>CO2 [ppm]</th>\n",
       "      <th>seasonally adjusted [ppm]</th>\n",
       "      <th>fit [ppm]</th>\n",
       "      <th>seasonally adjusted fit [ppm]</th>\n",
       "      <th>CO2 filled [ppm]</th>\n",
       "      <th>seasonally adjusted filled [ppm]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1958</td>\n",
       "      <td>1</td>\n",
       "      <td>21200</td>\n",
       "      <td>1958-01-01</td>\n",
       "      <td>-99.99</td>\n",
       "      <td>-99.99</td>\n",
       "      <td>-99.99</td>\n",
       "      <td>-99.99</td>\n",
       "      <td>-99.99</td>\n",
       "      <td>-99.99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1958</td>\n",
       "      <td>2</td>\n",
       "      <td>21231</td>\n",
       "      <td>1958-02-01</td>\n",
       "      <td>-99.99</td>\n",
       "      <td>-99.99</td>\n",
       "      <td>-99.99</td>\n",
       "      <td>-99.99</td>\n",
       "      <td>-99.99</td>\n",
       "      <td>-99.99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1958</td>\n",
       "      <td>3</td>\n",
       "      <td>21259</td>\n",
       "      <td>1958-03-01</td>\n",
       "      <td>315.71</td>\n",
       "      <td>314.43</td>\n",
       "      <td>316.20</td>\n",
       "      <td>314.90</td>\n",
       "      <td>315.71</td>\n",
       "      <td>314.43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1958</td>\n",
       "      <td>4</td>\n",
       "      <td>21290</td>\n",
       "      <td>1958-04-01</td>\n",
       "      <td>317.45</td>\n",
       "      <td>315.15</td>\n",
       "      <td>317.30</td>\n",
       "      <td>314.98</td>\n",
       "      <td>317.45</td>\n",
       "      <td>315.15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1958</td>\n",
       "      <td>5</td>\n",
       "      <td>21320</td>\n",
       "      <td>1958-05-01</td>\n",
       "      <td>317.51</td>\n",
       "      <td>314.69</td>\n",
       "      <td>317.88</td>\n",
       "      <td>315.06</td>\n",
       "      <td>317.51</td>\n",
       "      <td>314.69</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>1958</td>\n",
       "      <td>6</td>\n",
       "      <td>21351</td>\n",
       "      <td>1958-06-01</td>\n",
       "      <td>-99.99</td>\n",
       "      <td>-99.99</td>\n",
       "      <td>317.27</td>\n",
       "      <td>315.14</td>\n",
       "      <td>317.27</td>\n",
       "      <td>315.14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>1958</td>\n",
       "      <td>7</td>\n",
       "      <td>21381</td>\n",
       "      <td>1958-07-01</td>\n",
       "      <td>315.87</td>\n",
       "      <td>315.20</td>\n",
       "      <td>315.85</td>\n",
       "      <td>315.21</td>\n",
       "      <td>315.87</td>\n",
       "      <td>315.20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1958</td>\n",
       "      <td>8</td>\n",
       "      <td>21412</td>\n",
       "      <td>1958-08-01</td>\n",
       "      <td>314.93</td>\n",
       "      <td>316.23</td>\n",
       "      <td>313.95</td>\n",
       "      <td>315.28</td>\n",
       "      <td>314.93</td>\n",
       "      <td>316.23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>1958</td>\n",
       "      <td>9</td>\n",
       "      <td>21443</td>\n",
       "      <td>1958-09-01</td>\n",
       "      <td>313.21</td>\n",
       "      <td>316.12</td>\n",
       "      <td>312.42</td>\n",
       "      <td>315.35</td>\n",
       "      <td>313.21</td>\n",
       "      <td>316.12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1958</td>\n",
       "      <td>10</td>\n",
       "      <td>21473</td>\n",
       "      <td>1958-10-01</td>\n",
       "      <td>-99.99</td>\n",
       "      <td>-99.99</td>\n",
       "      <td>312.41</td>\n",
       "      <td>315.40</td>\n",
       "      <td>312.41</td>\n",
       "      <td>315.40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1958</td>\n",
       "      <td>11</td>\n",
       "      <td>21504</td>\n",
       "      <td>1958-11-01</td>\n",
       "      <td>313.33</td>\n",
       "      <td>315.21</td>\n",
       "      <td>313.60</td>\n",
       "      <td>315.46</td>\n",
       "      <td>313.33</td>\n",
       "      <td>315.21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>1958</td>\n",
       "      <td>12</td>\n",
       "      <td>21534</td>\n",
       "      <td>1958-12-01</td>\n",
       "      <td>314.67</td>\n",
       "      <td>315.43</td>\n",
       "      <td>314.76</td>\n",
       "      <td>315.51</td>\n",
       "      <td>314.67</td>\n",
       "      <td>315.43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>1959</td>\n",
       "      <td>1</td>\n",
       "      <td>21565</td>\n",
       "      <td>1959-01-01</td>\n",
       "      <td>315.58</td>\n",
       "      <td>315.52</td>\n",
       "      <td>315.63</td>\n",
       "      <td>315.57</td>\n",
       "      <td>315.58</td>\n",
       "      <td>315.52</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>1959</td>\n",
       "      <td>2</td>\n",
       "      <td>21596</td>\n",
       "      <td>1959-02-01</td>\n",
       "      <td>316.49</td>\n",
       "      <td>315.84</td>\n",
       "      <td>316.29</td>\n",
       "      <td>315.63</td>\n",
       "      <td>316.49</td>\n",
       "      <td>315.84</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>1959</td>\n",
       "      <td>3</td>\n",
       "      <td>21624</td>\n",
       "      <td>1959-03-01</td>\n",
       "      <td>316.65</td>\n",
       "      <td>315.37</td>\n",
       "      <td>316.99</td>\n",
       "      <td>315.69</td>\n",
       "      <td>316.65</td>\n",
       "      <td>315.37</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Yr  Mn  Date Excel        Date  CO2 [ppm]  seasonally adjusted [ppm]  \\\n",
       "0   1958   1       21200  1958-01-01     -99.99                     -99.99   \n",
       "1   1958   2       21231  1958-02-01     -99.99                     -99.99   \n",
       "2   1958   3       21259  1958-03-01     315.71                     314.43   \n",
       "3   1958   4       21290  1958-04-01     317.45                     315.15   \n",
       "4   1958   5       21320  1958-05-01     317.51                     314.69   \n",
       "5   1958   6       21351  1958-06-01     -99.99                     -99.99   \n",
       "6   1958   7       21381  1958-07-01     315.87                     315.20   \n",
       "7   1958   8       21412  1958-08-01     314.93                     316.23   \n",
       "8   1958   9       21443  1958-09-01     313.21                     316.12   \n",
       "9   1958  10       21473  1958-10-01     -99.99                     -99.99   \n",
       "10  1958  11       21504  1958-11-01     313.33                     315.21   \n",
       "11  1958  12       21534  1958-12-01     314.67                     315.43   \n",
       "12  1959   1       21565  1959-01-01     315.58                     315.52   \n",
       "13  1959   2       21596  1959-02-01     316.49                     315.84   \n",
       "14  1959   3       21624  1959-03-01     316.65                     315.37   \n",
       "\n",
       "    fit [ppm]  seasonally adjusted fit [ppm]  CO2 filled [ppm]  \\\n",
       "0      -99.99                         -99.99            -99.99   \n",
       "1      -99.99                         -99.99            -99.99   \n",
       "2      316.20                         314.90            315.71   \n",
       "3      317.30                         314.98            317.45   \n",
       "4      317.88                         315.06            317.51   \n",
       "5      317.27                         315.14            317.27   \n",
       "6      315.85                         315.21            315.87   \n",
       "7      313.95                         315.28            314.93   \n",
       "8      312.42                         315.35            313.21   \n",
       "9      312.41                         315.40            312.41   \n",
       "10     313.60                         315.46            313.33   \n",
       "11     314.76                         315.51            314.67   \n",
       "12     315.63                         315.57            315.58   \n",
       "13     316.29                         315.63            316.49   \n",
       "14     316.99                         315.69            316.65   \n",
       "\n",
       "    seasonally adjusted filled [ppm]  \n",
       "0                             -99.99  \n",
       "1                             -99.99  \n",
       "2                             314.43  \n",
       "3                             315.15  \n",
       "4                             314.69  \n",
       "5                             315.14  \n",
       "6                             315.20  \n",
       "7                             316.23  \n",
       "8                             316.12  \n",
       "9                             315.40  \n",
       "10                            315.21  \n",
       "11                            315.43  \n",
       "12                            315.52  \n",
       "13                            315.84  \n",
       "14                            315.37  "
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Step 0: Load the raw data without the readme info.\n",
    "data_url = \"https://scrippsco2.ucsd.edu/assets/data/atmospheric/stations/in_situ_co2/monthly/monthly_in_situ_co2_mlo.csv\"\n",
    "df = pd.read_csv(data_url, skiprows=60).reset_index()\n",
    "\n",
    "# Step 1: Concatenate the first three rows to form the header\n",
    "header = df.iloc[:3].astype(str).agg(' '.join).str.strip().tolist()\n",
    "\n",
    "# Step 2: Create a new DataFrame with the correct header\n",
    "df.columns = header\n",
    "df.columns = [\" \".join(col.split()) for col in df.columns]\n",
    "\n",
    "# Step 3: Drop the first three rows (now redundant)\n",
    "df = df.iloc[3:, :-1].reset_index(drop=True).apply(pd.to_numeric)\n",
    "df['Date'] = df.apply(lambda row: datetime.date(int(row.Yr),int(row.Mn),1), axis=1)\n",
    "\n",
    "# Display the updated DataFrame\n",
    "df.head(15)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "hideCode": false,
    "hidePrompt": false
   },
   "source": [
    "## 2. Analyse des données manquantes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "hideCode": false,
    "hidePrompt": false
   },
   "source": [
    "Affichage du nombre de données manquantes par colonne. Les données manquantes sont remplacées par la valeur -99.99."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {
    "hideCode": false,
    "hidePrompt": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Yr                                   0\n",
       "Mn                                   0\n",
       "Date Excel                           0\n",
       "Date                                 0\n",
       "CO2 [ppm]                           17\n",
       "seasonally adjusted [ppm]           17\n",
       "fit [ppm]                           13\n",
       "seasonally adjusted fit [ppm]       13\n",
       "CO2 filled [ppm]                    12\n",
       "seasonally adjusted filled [ppm]    12\n",
       "dtype: int64"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(df==-99.99).sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "hideCode": false,
    "hidePrompt": false
   },
   "source": [
    "Keep only the non missing data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {
    "hideCode": false,
    "hidePrompt": false
   },
   "outputs": [],
   "source": [
    "df = df.loc[(df!=-99.99).all(1)].reset_index(drop=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Nous pouvons voir si tous les mois sont représentés de la même façon:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Mn\n",
       "1     67\n",
       "2     65\n",
       "3     66\n",
       "4     66\n",
       "5     67\n",
       "6     66\n",
       "7     67\n",
       "8     67\n",
       "9     67\n",
       "10    66\n",
       "11    67\n",
       "12    67\n",
       "Name: Yr, dtype: int64"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby(\"Mn\").count()[\"Yr\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "hideCode": false,
    "hidePrompt": false
   },
   "source": [
    "## 3. Caractérisation des phénomènes périodiques sous-jacents"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Affichons les tendances annuelles, qui sont relativements courtes, comparativement à la tendance globale."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "metadata": {
    "hideCode": false,
    "hidePrompt": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "CO2 = df.iloc[:,4].values\n",
    "dates = df.loc[:,'Date'].values\n",
    "df_yearly_mean = df.groupby(\"Yr\").mean()\n",
    "CO2_yearly = df_yearly_mean.loc[:,\"CO2 [ppm]\"].values\n",
    "dates_yearly_f = df_yearly_mean.index.values\n",
    "dates_yearly = [datetime.date(int(d), 7, 1) for d in dates_yearly_f]\n",
    "\n",
    "plt.plot(dates, CO2, label=\"Évolution globale\")\n",
    "plt.plot(dates_yearly, CO2_yearly, label=\"Annuel\")\n",
    "plt.ylabel(\"CO2 (PPM)\")\n",
    "plt.xlabel(\"Année\")\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Affichons maintenant la tendance sur une année. Moyennons pour chaque mois sur toutes les années."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df_mn = df.groupby('Mn').mean()\n",
    "CO2 = df_mn.iloc[:,4].values\n",
    "months = df_mn.index.values\n",
    "\n",
    "plt.plot(months, CO2)\n",
    "plt.ylabel(\"CO2 (PPM)\")\n",
    "plt.xlabel(\"Mois\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "On observe une tendance annuelle dû aux saisons. On a également observé une tendance globale à la hausse."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4. Prédiction pour les années futures"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Nous proposons une régression linéaire simple pour estimer les valeurs pour les prochaines années."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {},
   "outputs": [],
   "source": [
    "pente = ((CO2_yearly-CO2_yearly.mean())*(dates_yearly_f-dates_yearly_f.mean())).sum()/((dates_yearly_f-dates_yearly_f.mean())**2).sum()\n",
    "origine = CO2_yearly.mean() - pente * dates_yearly_f.mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-2930.5194959134415"
      ]
     },
     "execution_count": 129,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "origine"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x7fe92d60e400>"
      ]
     },
     "execution_count": 137,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(dates_yearly, CO2_yearly, label=\"Annuel\")\n",
    "plt.plot(dates_yearly, pente*dates_yearly_f+origine, label=\"Modèle\")\n",
    "\n",
    "dates_yearly_pred_f = np.arange(2025,2031)\n",
    "dates_yearly_pred = [datetime.date(int(d), 7, 1) for d in dates_yearly_pred_f]\n",
    "plt.plot(dates_yearly_pred, pente*dates_yearly_pred_f+origine, label=\"Prédictions\")\n",
    "\n",
    "plt.legend()"
   ]
  }
 ],
 "metadata": {
  "hide_code_all_hidden": false,
  "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
}