From d003eb70236b65eb8ef0e07685ccc8707dd9fa3a Mon Sep 17 00:00:00 2001
From: 720d0853c18a70320e63c05851c89be9
 <720d0853c18a70320e63c05851c89be9@app-learninglab.inria.fr>
Date: Tue, 23 Feb 2021 10:52:59 +0000
Subject: [PATCH] complete report

---
 module3/exo3/exercice.ipynb | 224 ++++++++++++++++++++++++++----------
 1 file changed, 161 insertions(+), 63 deletions(-)

diff --git a/module3/exo3/exercice.ipynb b/module3/exo3/exercice.ipynb
index 5100670..2d37a00 100644
--- a/module3/exo3/exercice.ipynb
+++ b/module3/exo3/exercice.ipynb
@@ -19,7 +19,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 1,
    "metadata": {
     "hideCode": false,
     "hidePrompt": false
@@ -45,7 +45,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {
     "hideCode": false,
     "hidePrompt": false
@@ -57,7 +57,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {
     "hideCode": false,
     "hidePrompt": false
@@ -90,54 +90,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "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>Unnamed: 0</th>\n",
-       "      <th>date</th>\n",
-       "      <th>CO2</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "Empty DataFrame\n",
-       "Columns: [Unnamed: 0, date, CO2]\n",
-       "Index: []"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "raw_data[raw_data.isnull().any(axis=1)]\n",
     "data = raw_data.dropna().copy()"
@@ -155,7 +113,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 5,
    "metadata": {
     "hideCode": false,
     "hidePrompt": false
@@ -174,12 +132,12 @@
     "hidePrompt": false
    },
    "source": [
-    "Tri des données et affichage"
+    "Finalement, on obtient les émissions de CO2 en fonction du temps. On observe une superposition de deux effets : une évolution périodique et une évolution systématique."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -215,8 +173,7 @@
    ],
    "source": [
     "sorted_data = data.set_index('period').sort_index()\n",
-    "sorted_data['CO2'].plot()\n",
-    "print(sorted_data[:10])"
+    "sorted_data['CO2'].plot()"
    ]
   },
   {
@@ -224,12 +181,13 @@
    "metadata": {},
    "source": [
     "## Détermination des modèles d'évolution\n",
+    "### Etude de l'évolution périodique\n",
     "Calcul des émissions de CO2 pour l'année 1960 :"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -246,27 +204,27 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "L'oscillation périodique suit une évolution sinusoïdale."
+    "L'oscillation périodique suit une évolution sinusoïdale :"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[<matplotlib.lines.Line2D at 0x7fafc012df60>]"
+       "[<matplotlib.lines.Line2D at 0x7fd487a0b9e8>]"
       ]
      },
-     "execution_count": 30,
+     "execution_count": 32,
      "metadata": {},
      "output_type": "execute_result"
     },
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXkAAAD8CAYAAACSCdTiAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvIxREBQAAIABJREFUeJzt3Xl8VNX5x/HPIWyKuKOCgLihdQHRmAZB0RY1WgWLQrGotfwoLlSlahUrtbjVpdhWkSpUrWtBUKwsUghrI4IQLFhwpSiKosYVFQRCzu+PZ9IEmCyTuTN35s73/XrlNcm9d+59ziR55s5zzz3Hee8REZFoahR2ACIikjpK8iIiEaYkLyISYUryIiIRpiQvIhJhSvIiIhGmJC8iEmFK8iIiEaYkLyISYY3DOOjee+/tO3ToEMahRUSy1tKlSz/13rdK5DmhJPkOHTpQWloaxqFFRLKWc25Nos9RuUZEJMKU5EVEIkxJXkQkwpTkRUQiTEleRCTClORFRCJMSV5EJMKU5CUSnnsO3nkn7ChEMk8oN0OJVPryS5gyBT74AD78ENats8cPP4Tu3eGJJ+rex0cfwbnnwk9+AuPGpT5mkWyiJC+h+eorOOUUWLbMft5tN2jdGtq0gVat4Mkn4Y47oG3b2vfzj3+A9zB9OmzZAk2apD52kWyRdLnGOdfcObfYObfcObfSOXdzEIFJtH33HZxzDqxYAc8+C998Y2f1r78Os2dXncE/+2zd+3r2WcjLszeNkpLUxi2SbYKoyW8CfuC97wwcAxQ55woD2K9koWeegX33hdtvh/Ly+Nts3QoDBsC8efDoo9CnD7Rose02hx0GnTrBxIm1H+/zz2HuXLj8cmjWzEo/IlIl6STvzTexH5vEvnyy+5Xs89hjVhdv1AiGD4cePWD16m238R6GDIFJk+BPf7JkX5O+fWHBAli7tuZtJk+2N40LL4SePeH55+0YImIC6V3jnMtzzi0DPgGKvfcvB7FfyR6jR8PFF1uNfdUqeOopWLkSOneGRx6pSrwjRsCYMTBsGAwdWvs++/a1x9pKNpMmQfv2kJ8PZ59tPWxeey2IFolEhPc+sC9gd2AucFScdYOBUqC0ffv2XqLjzju9B+979fJ+48aq5WvWeH/KKbbunHO8v+MO+37gQO8rKuq3706dvO/WLf669eu9b9bM+6FD7ee1a23/d9yRXHtEMhVQ6hPMy4H2k/fefwnMA4rirBvrvc/33ue3apXQmPeSoby3ssywYXD++VaPb968an379jBrFowcCS+8ADfcAL162Zm8c/U7Rm0lm2nTYNMmq+kD7L+/ndFPnpx820SiIojeNa2cc7vHvt8J6Am8kex+JfNdc41dYP3FL6w3TLyui40a2XZLlsDNN8P48dA4gY67tZVsJk2yi7wnnFC17OyzYdEi+OSTxNoiElVBnMm3BuY6514FlmA1+akB7Fcy2Btv2IXTSy+1M/O8vNq379QJbroJdtopseNU9rKZMGHb5Rs32qeDH/9422P36mWfMKZNS+w4IlEVRO+aV733Xbz3nbz3R3nvbwkiMMlsM2fa4/XX17/00lD9+sFLL21bspkxA779tqpUU6lzZ2jXTiUbkUoau0YapLgYDjkE0jEfe7ySzaRJsMcecPLJ227rnJVsZs60s32RXKckLwnbvNluZDr11PQcr2PHbUs2mzfbmXrv3vGvA/TqBRs2wJw56YlPJJMpyUvCFi2yYQhOOy19x6xespkzx4Yw2L5UU+nkk2GXXXT3qwgoyUsDFBfbxc5TTknfMauXbCZNsiRe0yeJZs3g9NMtyVdUpC9GkUykJC8JKy6GggIbNTJdOna0i6rjxtmok2edtW2f/O316mXDFb/ySvpiFMlESvKSkC++sD7v6arHV9e3L7z8MpSV1VyqqXTmmdZHXyUbyXVK8pKQOXOsBJLOenylypJN8+Zwxhm1b7v33naTlLpSSq5TkpeEFBdDy5ZWrkm3jh0tcffpYzX5upx9tk1I8t57qY9NJFMpyUtCiovtgmtYsy/NnWtj0NdH7972+PDDKQtHJOMpyUu9/fe/Nj58GPX4Sk2b1v8N5rDDbHz7u+6y2EVykZJ8DnrgAfjZzxKfXKO42B7DTPKJuucee1O48kpNJiK5SUk+B40aBY8/bhNlJ6K42IYP7tgxNXGlwv77wy232GBm//hH2NGIpJ+SfI55/32bLLtJE7j2Wps8uz62brWeNaeemvoByYJ2xRVw9NFw1VU2qJlILlGSzzGVJZeHHoJPP7VJP+qjtNTeELKpVFOpcWP4y1/sDe6228KORiS9lORzzIwZ0KaNTXx9+eVWn1+6tO7nzZxpZ/A//GHqY0yF7t1tDtp77rGx8EVyhZJ8Dtm61abjO+00S9i33gqtWlmyr2uMl+JiOPZYu8koW911F7RoAUOG6CKs5A4l+Rzyyivw+edVd6vuvrvNv7p4sZVvavL117BwYXaWaqrbZx/4/e/t2sLTT4cdjUh6KMnnkMrZnHr2rFo2YAD06GGTcZeVxX/e/PlQXp79SR5g8GCb7Pvqq+3NSyTqlORzyIwZVnJp1apqmXMwerQlvGHD4j9v5kybm7Vbt/TEmUp5efCHP8C6dTB9etjRiKRe47ADkPRYv95KLr/+9Y7rjjwShg610k1hofVGWbfOhupdt87KGyedZOO0R8EJJ9ggZy+/bJORiERZ0kneOdcOeBzYD6gAxnrv7012vxKsefOs5FLT6JG/+x2MH2/ljEq77249cY47Lv6bQ7Zq2tTatHBh2JGIpF4QZ/LlwDXe+1eccy2Bpc65Yu/9awHsWwIyc6b1LOnaNf76XXax6fXeew9at7avnXZKb4zp1LWr3fm7aVN0PqGIxJN0Td57v857/0rs+6+B14H9k92vBGvmTJv7tLaE1q6d1d0POijaCR6sLLVpEyxfHnYkIqkV6IVX51wHoAvwcpD7leS88w68/XY4E31kqsJCe1TJRqIusCTvnNsFeBYY6r1fH2f9YOdcqXOutKymvnqSEpVdJ08/Pdw4Msn++0PbtrBoUdiRiKRWIEneOdcES/BPee8nxdvGez/We5/vvc9vVb0Pn6TczJnZN3pkOnTtqiQv0Zd0knfOOeBh4HXv/R+TD0mCVF4Os2dXDWUgVQoL4d134aOPwo5EJHWCOJPvBlwI/MA5tyz2dWYA+5UALF4MX32lenw8lXV5nc1LlCXdhdJ7/yKgc8QMNXMmNGqUvaNHptKxx9q4+osWwTnnhB2NSGpoWIOImzkTjj8e9twz7EgyT/Pm0KWLzuQl2pTkI+zLL+3WfZVqalZYCEuW2LWLmnz+ubpaSvZSko+wOXNsnHgl+ZoVFsKGDfCf/9S8zaBBNt7NhAnpi0skKEryETZ7tg1X8P3vhx1J5qoc5qGmks3q1TYB+M47w0UXwYIF6YtNJAhK8hFWUmJJrEmTsCPJXAccAPvuW3M55v77bXjihQvtXoPeve3uYZFsoSQfUV98AStWwIknhh1JZnPOSjbxzuS//hoefhjOOw86dbLx552DM86oeYIVkUyjJB9RCxbYPKZK8nXr2tXOzj/7bNvljz1m4/APHWo/H3wwTJkCH3xgZ/QbN6Y/VpFEKclHVEmJlWlUj69b5U1RL1cbVq+iAu67z16/6q9hYSE89ZSd+V94Yd0ToIuETUk+okpKbC7TqA8ZHIT8fLthrHpdfvp0O7uvPIuvrk8fuOceePZZGD48fXGKNISSfARt3AilpSrV1FeLFlZzr16Xv/deG6ny3HPjP2foULjgAvjjH60fvUimUpKPoJdfhi1blOQT0bWrvW5bt8LKlVBcDJdfXnPPJOfg2mtt4pEnnkhvrCKJUJKPoJISS0LduoUdSfYoLLTeNK+/brX45s23ne82ns6doaAAxoyxi9wimUhJPoJKSuCoo2CPPcKOJHtUXnydNg0ef9xKMXvvXffzLrnE3hh0k5RkKiX5iCkvtwuIKtUk5tBDbRC3W2+F776DK6+s3/N+8hPYdVc7mxfJREryEbNsGXzzjZJ8oipvivr2WxuW+eij6/e8Fi3srH/iRF2AlcykJB8xJSX2qCSfuMqSzVVXJfa8wYN1AVYyl5J8xJSUwIEHWvc/Scwll8CoUfCjHyX2vM6d7YYpXYCVTKQkHyHew4sv6iy+ofbZB375S7sxKlGDB+sCrGQmJfksUlZmZ5urV8df/+abto2SfPrpAqxkKiX5LHLllTB2rI1rvnXrjutVjw+PLsBKpgokyTvnHnHOfeKcWxHE/mRHU6bA+PFw0klWErjvvh23KSmxkkPHjumPT6ouwD7+eNiRiFQJ6kz+UaAooH3Jdr76Ci67zG5wKi6Gs86C3/wG3npr2+1KSqB7d+sOKOlXeQF27FhdgJXMEUiS997/C9CH1BQZNgzWrbMJLJo2tbpv8+bw859XlW3WroV331WpJmyVd8C++GLYkYgY1eQz3Pz58OCDNuphQYEta9PGyjUvvVRVtlE9PjP062cXYB96KOxIREzakrxzbrBzrtQ5V1qmudPqZeNG+MUvrN/7Lbdsu+6CC+Dss6vKNiUlNml3587hxCqmRQvo2xcmTdLMUZIZ0pbkvfdjvff53vv8Vq1apeuwWe2WW2ziirFjLXlU59y2ZZv58+GEE6Bx43BilSr9+9vQEi+8EHYkIirXZKx//xv+8AdL4D17xt+mdeuqss1rr6lUkylOOQX23dd6Q4mELagulOOAhcBhzrm1zrn/C2K/uaqiAgYNglatbJq52lSWbUBJPlPk5VnJZupUmwhcJExB9a4533vf2nvfxHvf1nv/cBD7zVUrVsArr8DNN9c9Jrxz8Mgj8Oc/W/dJyQz9+9uQxZMnhx2J5DqVazLQvHn2ePrp9dt+771t5MS8vJSFJAnq2hXat1fJRsKnJJ+B5s2zHjUHHBB2JNJQjRrZeDYzZsBnn4UdjeQyJfkMU1FhPWVOPjnsSCRZ/fvbTF2TJoUdieQyJfkMs2KFDXClJJ/9unSxcYTGjQs7EsllSvIZprIe36NHqGFIAJyzs/l582xYCpEwKMlnGNXjo6V/fxusbOLEsCORXKUkn0FUj4+e733PhppQyUbCoiSfQVSPj6b+/WHRInjnnbAjkVykJB+w55+3m5gaQvX4aPrJT+xxwoRw45DcpCQfoC1bbCLoESNg6dLEn696fDQdeCAUFqpkI+FQkg/Q00/b5B15eXDHHYk9V/X4aOvfH5YvtwlFRNJJST4g3sPIkXDEEXD99XYDTCL/0KrHR1u/ftalUr1sJN2U5AMya5adqV1zDfzqV7DTTnDXXfV//ty59qgkH02tW9vMXhpjXtJNST4gI0fCfvvBgAE2YNjgwfDkkzbvan3MmwcHHWSDWkk0FRXB4sUay0bSS0k+AMuXw8yZcOWV0KyZLbvmGhukauTIup+venxuKCqysl5xcdiRSC5Rkg/APffY9HyXXlq1rG1b+NnPbELnjz6q/fn/+Q988YWSfNQdfzzsuSf8859hRyK5REk+Se+/b13jBg3acYKP666zbpV//nPt+1D/+NyQlwennWZJvqIi7GgkVyjJJ+m+++wj+NChO6479FDrVfGXv9iZek1Uj88dRUXw8cfw6qthRyK5Qkk+CV99BWPG2HyeHTrE3+aGG+Drr2H06PjrVY/PLaedZo/Tp4cbh+QOJfkk/PWvlsCvuabmbTp1grPOspLNt9/uuF71+NzSujUcc4zq8pI+SvINtHmzJe6TT4b8/Nq3/c1vrNvcjTfaDVJbt1atUz0+9xQVwUsv2SdBkVQLJMk754qcc28651Y554YFsc9MN24cfPAB/PrXdW/btSv06gX33mt3xO62G5x4ot009dRTqsfnmjPOsGkB58wJOxLJBUkneedcHjAaOAM4AjjfOXdEsvvNZJs2we9+Zx+7i4rq95xJk6w08+ij8POf29n8mDGwZAmcfnpKw5UM07UrtGypko2kR+MA9lEArPLerwZwzo0HegOvBbDvbQwdOpRly5YFvduErV0La9bYGfkPftCwfTRtav2mN260cWtUk88tzZrBY4/Bm2+GHYmk2zHHHMOf6+pXHaAgyjX7A+9X+3ltbNk2nHODnXOlzrnSsrKyAA4bjvJyS/C7775jv/hEOQc772x3xkpu2XNP+0S4YUPYkUjUBXEm7+Is8zss8H4sMBYgPz9/h/X1kc53v5rceCMsWACzZ8Oxx4YdjWSr996zeQP694errw47GomyIM4h1wLtqv3cFvgwgP1mnA8+gD/9Cc4/XwlektO+vV2EV11eUi2IJL8EONQ5d6BzrinQH5gcwH4zzs03W7nmttvCjkSioKjIboSLd/+ESFCSTvLe+3Lgl8AM4HVggvd+ZbL7DcIzz0BJSTD7ev11ePhhuOwy6/IokqyiIrvfYv78sCORKAvkkp/3/gXvfUfv/cHe+9uD2Geyli61cWNOPhnuvtvGl6lLeXnN637zGxtpcvjwwEKUHHfiiTa5zPYlm02bYPx4G7paF2ajpfqNkOkSyX4dFRVw+eWwzz7Qp49Nx3f++TV/LF63zib5aNYMunSxN4X33qtav2AB/OMfNqpkq1bpaYNEX/PmcMopVePYvPWW3VzXtq39vY4aFdwnUQnf6tV2HWbBgvQeN5JJ/qGHbAaekSNhwgSbhm/iRDjhBHuhK33zDYwYYaNFPvooXHSRJfrrr7eeDyeeCA88YP94++1nd6iKBKmoCFatgm7d4LDDbKiMHj3s7xHqP7OYZLbNm60n1ccfQ5s2aT649z7tX8cdd5xPlU8+8X6PPbzv0cP7ioqq5TNm2PI99vB+2jTvH3zQ+3339R6879vX+1WrqrZdtcr7227z/ogjbD3Y9iJBW73a+yZNvD/wQO9//3vv162z5eXl3jdu7P2wYeHGJ8G4+mrLI888k9x+gFKfYL6NXJIfOND+OVau3HHdqlXeH310VeLu3t37RYtq3ldFhffLl3v/6KP2TyeSCmVl3m/duuPygw7yvn//9McjwZo82fLNkCHJ76shST6Im6EyxksvwSOPWHnliDij5xx8MCxcCL//vQ0p0Lu33XVaE+dsqOBOnVIXs8jee8df3qGDyjXZ7v334eKLbZyr+sz3nAqRSfLl5XaxtW1buOmmmrdr0QJuz4j+PyK169ABXngh7CikocrL4ac/td5STz9tF9rDEJkkP3o0LF9ufeN32SXsaESS16GDTQK/caN1tZTsMmIEvPgiPPkkdOwYXhyR6F2zbh389rc2ZG+fPmFHIxKMyiklq3fnlexQXGxl4YEDYcCAcGOJRJIfPtw+Eo0aVXuNXSSbVCZ51eWzyxtvwAUXwOGHw333hR1NBJL8li1WohkwwPq7i0SFknz2WbYMTjrJTjaffdauAYYt65P8ggWwfr1Nli0SJW3aQOPGSvLZYtEiu4O5eXP417/ge98LOyKT9Ul+2jRo0gROPTXsSESClZdnQxIryWe+OXOgZ0/Yay8biiLMC63by/okP3Wq3QbesmXYkYgE78ADleQz3bRpcOaZVl4rKbEhUTJJVif51avtIodKNRJVuiEqsz39NJxzDhx1FMybB61bhx3RjrI6yU+bZo8/+lG4cYikSvW+8pI5Nmywmy/794fCQpsOtKY7l8OW9Um+Y0c45JCwIxFJDfWVzzxLltiQ5A88YPPzFhfDbruFHVXNsjbJf/MNzJ2rUo1Em7pRZo7ycrj1VhuyfMMGO3u/557whiuor6wd1mD2bBujWaUaiTIl+cywerXd4LRwoU3oMno07LFH2FHVT9Ym+WnTrEdN9+5hRyKSOq1bWxdhJfnwrFljk7p89x38/e+W5LNJViZ57y3Jn346NG0adjQiqaO+8uH68kvrHrlxow1lHm8I80yXVE3eOdfXObfSOVfhnMsPKqi6LFsGH36oUo3kBnWjDMfmzTbg4dtvw3PPZWeCh+QvvK4A+gD/CiCWeps2zcaGOOOMdB5VJBxK8unnPQwaZJ07HnnEhivIVkmVa7z3rwO4NA/9OHWqzey0775pPaxIKDSufPqNGAFPPGG9aS64IOxokpN1XSjLymDxYpVqJHeor3x6/e1vcMstNhb8jTeGHU3y6kzyzrlZzrkVcb56J3Ig59xg51ypc660rKyswQFPn24fpdQ/XnKFulGmz5w5MHiwDXj44IPRmJ+iznKN975nEAfy3o8FxgLk5+f7hu5n6lTrVtalSxBRiWS+yiT/zjuhhhF5FRXwy1/CQQfBxInWdTUKsqoL5ZYtMGMG9O0bjXdYkfpQX/n0mDoVXn8dnnoqs4cpSFSyXSh/7JxbC3QFpjnnZgQTVnyaIERykfrKp8ddd9mnpn79wo4kWMn2rnkOeC6gWOo0dard/NQzkAKSSPZQN8rUevFFu9lp1CibjStKsqo5RUWw336wyy5hRyKSXh062EmOpMadd9pQwQMHhh1J8LIqyffsqbN4yU0dOsDHH6uvfCqsWGE3WN58M+y8c9jRBC/r+smL5KLKHjZr1oQaRiTdfbcl9yFDwo4kNZTkRbKA+sqnxnvvwbhx1jd+r73CjiY1lORFsoCSfGr88Y/2ePXV4caRSkryIllAfeWD99ln8Ne/wk9/Cu3ahR1N6ijJi2QB9ZUP3ujRNo3fddeFHUlqKcmLZAn1lQ/Ohg3WJ/6ss+DII8OOJrWU5EWyhJJ8cB54AD79FIYNCzuS1FOSF8kS1fvKS8O9+y7cdJMNV96tW9jRpJ6SvEiWUF/55Hlv3SXz8uxsPhcoyYtkiQMPtEeVbBru8cehuNiGMYhyj5rqlORFsoT6yifn44/hV7+C7t3h0kvDjiZ9lORFsoT6yifniivg22+tb3yjHMp8WTVAmUgua9QIDjhASb4hnn/eZnu6/XY4/PCwo0mvHHo/E8l+6kaZuC+/hMsvh86d4de/Djua9FOSF8kiSvKJu+46+OgjeOih6MzbmgiVa0SySGVf+c8+i+6oiQ2xbh2ceqpND7q999+Ha6+F/Pz0x5UJlORFskivXvC738ENN8DYsWFHkznGjYOVK+HCC3ecvm+//WD48HDiygRK8iJZ5OijrRvgyJFw0UXWHVBgwgTo0sX6wcu2kqrJO+f+4Jx7wzn3qnPuOefc7kEFJiLxjRhhI1Jecgls3hx2NOF77z14+WXo2zfsSDJTshdei4GjvPedgLeAG5IPSURq06KFDZP72mt2Rp/rnnnGHpXk40sqyXvvZ3rvy2M/LgLaJh+SiNTlrLPgvPPg1lth1aqwowlXZanmkEPCjiQzBdmFciAwPcD9iUgt7r0XmjaFyy6zgbdy0Zo1KtXUpc4k75yb5ZxbEeerd7VtbgTKgadq2c9g51ypc660rKwsmOhFclibNnDHHTBrFvz972FHEw6VaurmfJKnAM65nwGXAj/03m+oz3Py8/N9aWlpUscVEdi61cZEX70a3ngD9twz7IjSq7DQLj6/8krYkaSHc26p9z6hHv/J9q4pAq4HetU3wYtIcPLyYMwY+PxzGDTILsbmSummslTTr1/YkWS2ZGvy9wMtgWLn3DLn3IMBxCQiCejc2W6Qeu45m6/0kEPgqqusjBPlLpYq1dRP0uWahlC5RiR4H3wAU6fClCkwezZ89x3suitccIFNktGyZdgRBquwELZsgaVLw44kfdJerhGRzLH//naD1NSpNrbN5MnQpw88+CAccwwsXBh2hMFRr5r6U5IXiaCdd4azz4a//Q3mz4eKChsC4be/tbPfbKdSTf0pyYtEXPfusHy5jXVz221wwgnw5pthR5WcCRPg2GPh4IPDjiTzKcmL5IBdd7Wz+meese6WXbpUnQ1nmzVrYPFincXXl5K8SA4591xYscJ65Pz855Yws41KNYlRkhfJMa1bw/jx9v2gQdnXr16lmsQoyYvkoAMOsBEsZ83KrslH7r/fSjXnnx92JNlDSV4kRw0eDD172tR42TBv7N/+BldcAb17281eUj9K8iI5yjmb3Boyv2zz9NMW42mn2fe5OCF3QynJi+SwyrLN7NmZW7aZMsXu2u3WzYZuaNYs7Iiyi5K8SI7L5LLNrFnWi+aYY+xO3p13Djui7KMkL5LjKss2zmVW2ebFF63+3rEjzJhhff0lcUryIrJN2SbMCUi2bLGSTFERnHQStG0LxcW5N05+kJTkRQSAX/zC+tD/85/pP/a778KNN0L79jao2ooVcNNNdja/777pjydKGocdgIhkBufg+9+3fujpdNVVMGqUHf/MM+0awRlnQGNlp0DoTF5E/qegAN56C774Ij3HmzAB7rsPBg60s/kpU2z0TCX44CjJi8j/FBTYYzrm9PnwQ7jsMjvmgw9Cu3apP2YuUpIXkf/Jj805lOqSjffWk2fjRnjiCZ25p5JeWhH5n912g8MPT32SHzMGpk+3sWg6dkztsXKdzuRFZBsFBTa1Xqr6y69aBddcA6eeauUaSa2kkrxz7lbn3KvOuWXOuZnOuTZBBSYi4SgogI8/hrVrg993ebnNUNW0qQ041kinmSmX7Ev8B+99J+/9McBU4KYAYhKREB1/vD2momRz9902ofhf/mITj0vqJZXkvffrq/3YAsiQG6JFpKE6d7ZRHoNO8suWwYgR0K8f9O8f7L6lZklfeHXO3Q5cBHwFnJJ0RCISqmbNbECwJUuC3e+IEbD77nYW71yw+5aa1Xkm75yb5ZxbEeerN4D3/kbvfTvgKeCXtexnsHOu1DlXWlZWFlwLRCRwBQXWV37r1mD2t369DZcwYADstVcw+5T6qTPJe+97eu+PivP1/Hab/h04t5b9jPXe53vv81u1apVs3CKSQgUF8PXX8OabwexvyhTYtEmTb4ch2d41h1b7sRfwRnLhiEgmqLzzNai6/MSJdqG1sDCY/Un9Jdu75s5Y6eZV4DRAMy+KREDHjjZ+exBJvrJU07evukyGIakLr977GsszIpK9GjWyrpRBJHmVasKl91URiaugAJYvh+++S24/EybY5B8q1YRDSV5E4ioosDtUly2Lv/6tt+DCC+GTT2rex/r1NnXfeeepVBMWvewiEldtF1+9t5mknnwSrr++5n1Ulmr69UtNjFI3JXkRiatNG+sREy/JP/kk/Otfdnfso4/xlJG/AAAF10lEQVTagGbxVJZqvv/9lIYqtVCSF5EaFRTsmOS//BKuvdZq7PPn27ywV1wBFRXbblfZq0almnDppReRGhUUwNtvw+efVy0bPhw+/dSGJ9htNxt0bMkSG1WyusmTYfNmlWrCpiQvIjXafjrApUvhgQdgyBDo0sWWDRgA3brBDTfYWX6liRNVqskESvIiUqPjjrPBxBYvtnLM5ZdDq1Zw661V2zgHo0bZ2f2IEbZMN0BlDr38IlKjyukAlyyBhx6yZD9ypC2vrksXuOQSm85vxYqqUo1ugAqf86ma46sW+fn5vjQd08GLSNIuvhimTrVuk0cfDXPnxh8q+LPP4NBDbZjili3h3/+Gd9/VmXyQnHNLvff5iTxHL7+I1KqgwBL4+vUwenTNY8HvtRfcdpu9CUyerF41mUK/AhGpVeVwBL/6FRx5ZO3bXnKJ9Z0HlWoyRdIzQ4lItB17LBQXw0kn1b1tXh48/jiMH69eNZlCSV5E6tSzZ/237dTJviQzqFwjIhJhSvIiIhGmJC8iEmFK8iIiEaYkLyISYUryIiIRpiQvIhJhSvIiIhEWygBlzrkyYE0Dnro38GnA4YRFbclMaktmUlvMAd77Vok8IZQk31DOudJER2DLVGpLZlJbMpPa0nAq14iIRJiSvIhIhGVbkh8bdgABUlsyk9qSmdSWBsqqmryIiCQm287kRUQkEd77lH4BjwCfACuqLesMLAT+A0wBdq22rlNs3crY+uax5cfFfl4F3EfsU0ic48XdDjgJeAUoB87L4nZcGlu+DHgROCKL23IxUBZryzJgUBa35U/V2vEW8GWW/78cAMwGXgXmAW2zoC23A+8D32y3PKn//YDbEjfGBH4vCbcl4cY24MU5CTh2uxdnCdAj9v1A4NbY941jf1SdYz/vBeTFvl8MdAUcMB04o4bjxd0O6BB74R9vyC86g9pR/Q+pF/DPLG7LxcD9Ufj72m6bK4BHsrk9wETgZ7HvfwA8kQVtKQRas2OS70AS//sBtyVujAn8XhJuS4P/uRJ8gTps9+Ksp+qdqR3wWuz7M4En4zy/NfBGtZ/PB8Y0ZDvg0SR+0RnTjmrLp2drWwggyWdKW7bb7iXg1GxuD3YG2jb2vQPWZ3JbtntO3ARKEv/7QbSlPjHWt82JtCWsmvwK7CwUoC/2AgF0BLxzboZz7hXn3HWx5fsDa6s9f21s2fbqu11QQmmHc26Ic+6/wN3AlUm3woT1OznXOfeqc+4Z51w7ghHa35dz7gDgQGBOUi3YVhjtWQ6cG/v+x0BL59xeSbXCpKotYUi0LfUVaJvDSvIDgSHOuaVAS2BzbHljoDswIPb4Y+fcD7Ezie35OMvqu11QQmmH93609/5g4HpgeMPD30YYbZkCdPDedwJmAY81PPxthPn31R94xnu/tSGB1yCM9lwL9HDO/RvoAXyA1YGTlaq2hCHRttRXoG0OZSJv7/0bwGkAzrmOwI9iq9YC8733n8bWvYDVwZ4E2lbbRVvgQ+dcHrA0tmwy8EC87VLUjExox/jYtlnZFu/9Z9WW/xW4K1vbUk1/YEgQ7agU0u/mQ6BPbL+7AOd677/K1LZ4729KNrZENaAts+PtJ+V5rKH1qSRrWfvEHhthFxAGxn7eA7tyvDP2BjQL+FFs3RLsokXlhYgzazhWrdsRbE0+7e0ADq22zdlAaRa3pXW1bX4MLMrWtsTWHQa8Sw29P7KpPdggWo1i398O3JLpbal2jHTV5BNuS10x1ufvLNG2NPgPMYEXZhywDtiCvcP9H3AV1s3sLeDO6v8UwAXYRZ8VwN3VlufHlv0XuL+mf6SatgOOjx3/W+AzYGWWtuPe2H6XAXOBI7P4d3JHbL/LY205PFvbEls3ArgzIv8v5wFvx475ENAsC9pyd+w4FbHHEUH87wfclrgxJvB7SbgtuuNVRCTCdMeriEiEKcmLiESYkryISIQpyYuIRJiSvIhIhCnJi4hEmJK8iEiEKcmLiETY/wNQ/EKYJLBPzQAAAABJRU5ErkJggg==\n",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -278,23 +236,151 @@
     }
    ],
    "source": [
-    "plt.plot(absc, ordo)\n",
-    "plt.plot(absc, [mean]*len(absc))"
+    "plt.plot(absc, ordo[:]-mean, color = 'b')\n",
+    "plt.plot(absc, [0]*len(absc), color = 'k')"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "L'évolution systématique peut être affichée en calculant une moyenne annuelle des émissions de CO2 :"
+    "### Etude de l'évolution systématique\n",
+    "L'évolution systématique peut être affichée en calculant une moyenne annuelle des émissions de CO2. Dans un premier temps, on calcule les émissions totales de CO2 par an :"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "yearly_incidence = [sorted_data['CO2'][0]]\n",
+    "year = ['1958']\n",
+    "ct = 0\n",
+    "week = [1]\n",
+    "for i in range(len(sorted_data)):\n",
+    "    yr = sorted_data['date'][i][:4]\n",
+    "    if yr != year[ct]:\n",
+    "        year.append(yr)\n",
+    "        yearly_incidence.append(sorted_data['CO2'][i])\n",
+    "        ct += 1\n",
+    "        week.append(1)\n",
+    "    else:\n",
+    "        yearly_incidence[ct] += sorted_data['CO2'][i]\n",
+    "        week[ct] += 1"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Chaque année ne comptant pas le même nombre de semaines, on calcule la moyenne annuelle des émissions en divisant par le nombre de semaines :"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "yearly_incidence = [yearly_incidence[i]/week[i] for i in range(len(week))]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "On peut ensuite tracer l'évolution des émissions de CO2 annuelles :"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x7fd493644550>"
+      ]
+     },
+     "execution_count": 11,
+     "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": [
+    "yearly_inc = pd.Series(data=yearly_incidence, index=year)\n",
+    "yearly_inc.plot(style='o')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "On peut modéliser cette courbe par une interpolation polynomiale d'ordre 2 :"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.preprocessing import PolynomialFeatures\n",
+    "from sklearn.pipeline import make_pipeline\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "deg = 2\n",
+    "polyreg = make_pipeline(PolynomialFeatures(deg), LinearRegression())\n",
+    "polyreg.fit(np.array([int(i) for i in year]).reshape(-1, 1), yearly_incidence)\n",
+    "yearly_interp = pd.Series(polyreg.predict(np.array([int(i) for i in year]).reshape(-1, 1)), index = year)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x7fd4877b61d0>"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAADuCAYAAAA3IMxxAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvIxREBQAAIABJREFUeJzt3XuYjeX+x/H3d8ZhjFPSEI1ZanfY6aSSaqtEKR1JJ0UpRSFJiaR09LNVlEJMFJuVQwclIZFDOondTlG77JghahwizBhzuH9/rDXLrJnRDGZmHebzui6Xte7nXqt7uurj6/vcz/OYcw4REYleMaFegIiIlC0FvYhIlFPQi4hEOQW9iEiUU9CLiEQ5Bb2ISJQrcdCbWayZfWNms/3vnzezH81slZnNNLMj8s0daGZrzey/ZnZ5WSxcRERK5mAq+j7AD/nefwyc6pw7HfgJGAhgZk2AjsApQFtgjJnFls5yRUTkYJUo6M0sEbgKGJ835pyb75zL9r/9Ekj0v24HTHPOZTrn1gFrgealt2QRETkYlUo47yWgP1DzAMe7AtP9r4/BF/x5NvrHDuioo45yjRs3LuFSREQEYOXKlVudcwnFzSs26M3saiDNObfSzC4u4vggIBvw5g0V8TWF7rNgZt2B7gBJSUmsWLGiuKWIiEg+ZpZSknklad20AK41s/XANKC1mU3x/0O6AFcDndz+m+ZsBBrl+3wisKnglzrnkp1zzZxzzRISiv0DSUREDlGxQe+cG+icS3TONcZ3kvUT51xnM2sLDACudc6l5/vILKCjmVU1s2OBE4DlZbB2EREpgZL26IsyCqgKfGxmAF865+51zq02sxnAGnwtnV7OuZzDX6qIiByKgwp659xiYLH/9fF/MW8IMORwFiYiIqVDV8aKiEQ5Bb2ISAh4vdA8cRM1bTeNG/velxUFvYhIOfN64em7U3nz14v4gKvZkrKH7t3LLuwV9CIiZczrhcaNISbG9/sL961n3t6WHM//uJglvM0NpKc7Bg0qm3/+4ey6ERGRYni90L07pPs3ocem/I/3aI2HVAAyqcIYegJGamrZrEFBLyJShgYN2h/yx/Mzi2hFIr8CsJeqdOBd5nIlAElJZbMGBb2ISBnKq9JP4kc+oTUN2QxABnG0430+5jIA4uNhSBltSlePXkSkDCUlQRNWs5iLAyGfTjVurTWbnzyXYQYeDyQnQ6dOZbMGBb2ISCkqeOK1W/NvWczFHM3vAOymOh2qzuGGMZewfj3k5sL69WUX8qDWjYhIqSl44vWolBX0SLmMI/kDgF3UoGv9Odw2/MIyDfaCFPQiIqUk/4nX8/iCebSlNn/6BmrXpua8ebx13nnlvi61bkRESkneidcLWcp8LguE/DaOhIULIQQhDwp6EZFSk5QEl7CAebSlJrsBSCOBTg0Wwdlnh2xdCnoRkVIy8YbZzOZq4skAYDNHc0XcYm57/vSQrktBLyJyiPLvsOmZ8BYXvXQdcWQCsIFEbm24hAfHNynXE69F0clYEZFDkH+HTWcm88rWO4gh13fwuONotHAhixo3Duka86iiFxE5BHk7bLqRzCS6EOsP+f9VOgmWLvWV+mFCQS8icghSU6EvI0jmHmJwAKziNFpkL4Fjjgnx6oIp6EVESijQkzfHEzzFCB4KHPuaZlzMYuI89UO3wANQj15EpAT29+Qdz/Mw/dzwwLGlXMjVzCYnvlaZ3ZjscKiiFxEpgUGDICM9l1fpQT/2h/x8LuMK5nGkp1aZ3pjscKiiFxEpgU0pWfyLO+nM/uf9vct13MpU9rqqIVxZ8VTRi4gUIf8e+ZM8e3m/8g1BIT+ZztzEDI72hHfIgyp6EZFC8u+Rr8EuXk1tR2sWBY6P5R56MoZq8TFh2ZMvSBW9iEgBeXvk67CdBVwaFPKv1hpAT14lyRMTtj35glTRi4gUkJoKR7OZ+VzGaXwfGB/IUIbufIQeIVzboVBFLyJSQIsGv7CMCwIhn4vRgzFM9TwS4pUdGlX0IiL5ffcdH6VfTrz/+a7ZxNKFSbwX34nkCOjHF0UVvYhIni+/hJYtid/hC/m9FkcHZvKZp1PE9OOLoopeRCo8rxfmPvgx49LaUx3/swBr1SLugw+YddFFoV1cKVBFLyIVmtcLc7u+xetpVwVCfgsJzHl4EURByMNBBL2ZxZrZN2Y22//+SDP72Mx+9v9eJ9/cgWa21sz+a2aXl8XCRURKw5r7x/KvfTdThSwAUmnEBXxKz/FnhXhlpedgKvo+wA/53j8CLHTOnQAs9L/HzJoAHYFTgLbAGDOLLZ3lioiUEufgmWcYsr1H4DbDP/B3WvAZP3FS4EHf0aBEQW9micBVwPh8w+2ASf7Xk4D2+canOecynXPrgLVA89JZrohIKcjNhT59YPDgwNBXNOdCPmUjjQDfg76jRUkr+peA/pD3nCwA6jvnNgP4f6/nHz8G2JBv3kb/WBAz625mK8xsxZYtWw564SIih2LqpH28V/M2eOWVwNjCmDZcwkK2cRQA8fFExK0NSqrYoDezq4E059zKEn6nFTHmCg04l+yca+aca5aQkFDCrxYROXTTJ+wmoes1tE9/MzD2duxNvH/3BxzlqYEZeDxE9FbKopRke2UL4FozuxKIA2qZ2RTgdzNr4JzbbGYNgDT//I3g/7uPTyKwqTQXLSJy0LZs4aSeV9E09+vA0Bh60DvnFRp9FMv69aFbWlkrtqJ3zg10ziU65xrjO8n6iXOuMzAL6OKf1gV43/96FtDRzKqa2bHACcDyUl+5iEhJrV8PLVrQdN/+kB/MU/RiNLnERtWJ16Iczj76fwJtzOxnoI3/Pc651cAMYA0wD+jlnMs53IWKiBwsrxfaNlzFpmP/AT//DEAOMdzDWJ5hMHmd5mg68VqUg7oy1jm3GFjsf70NuOQA84YAUXQqQ0QijdcLk+9azLTM9hzBTgAyqcJtlabyVnaHwLxoO/FaFF0ZKyJR6bMH3uL9zMsDIb+TWlzGfD6p3QGPh6g98VoU3etGRKLPyy8zausDgQuhNtGAK5jLKs7AtsPWrSFeXzlTRS8i0SM3FwYMgD59AiH/IyfxDz5nFWcA0d+PL4oqehGJClMn7aNKr7u5fs/kwNhXMedxZe5stlMXqBj9+KKooheRiDf9tT+p3/WqoJD/MPYa3uy6kJqeuhWqH18UVfQiEtk2beL0Xldwcu6qwFAy3eiZM4bEjytF9YVQJaWKXkQi15o1cN55nJy1P+Qf4xnuYRw5VIr6C6FKSkEvIhHp48eXsvO0FrDBdw/FLCpxB28whMeoKBdClZRaNyIScZbdN42LRnehKvsA2EUNbuBt5rP/OUcV9cRrUVTRi0jkcA6GDeOC0bcEQv436tOSJczncmJjK9aFUCWlil5EIkN2NvTuDWPHBobWcDJXMocUGgO+bfS5uQf4fAWmil5Ewt70CbtZWKt9UMgvpiUt+CwQ8qCe/IEo6EUkrL0zajMndmvJJRkfBsam2q1cU/kjdlAnMKae/IEp6EUkfH33Hec9cC5nun8HhobwKJ3cZKrWqlrhbk52qNSjF5HwNH8+3Hgjx+T8CUA2sfRkDK/RHYDtFfDmZIdKQS8i4Wf8eLj3XsjxPbPoT2pyI28FbZ9UP77k1LoRkfCRm8vqawdCt26BkP+jeiJt4pZpj/xhUNCLSHhITyf1vJs45YN/Bob+zZk0y/mKs+88Xf34w6DWjYiE3m+/Qbt2JH29PDA0m6voyDT27K3BnDno5mSHQRW9iITWd9/BuefC8v0h/xJ9aMf77KEGgG5OdpgU9CISMov6z2XXGS0CSZ5DDL0YRV9eIpfYwDydeD08at2ISPlzjhVdXuGiyX2JxXfPgj+pSafY6cyPvQL/bWwAnXgtDaroRaR8ZWVBz540m9wnEPIpJNGCz5idcwU1a6ITr6VMFb2IlAuvF4YN3MHwDTfShgWB8S84j/a8Rxr1AV0IVRYU9CJS5rxeGHb3z0zfey0n82Ng/E1uoSuvk0lcYEz9+NKn1o2IlLnZD37C4r3nBoX8YJ6iM96gkFc/vmwo6EWkbI0dy+S0yziSPwDIII6OTOUZBuMw9ePLgVo3IlLqvF4Y/Gg2fVP7ch+jAkGziQa05z2+pjngC3ddCFX2FPQiUqq8XhjQbTtvZNwcdNJ1pZ3Nte59NnEMoDZNeVLrRkRK1ev9f2BRxrlBIT+DG2lfZymVPceoTRMCxVb0ZhYHLAWq+ue/7Zx7wsyaAmOBOCAb6OmcW+7/zEDgLiAHuN8591EZrV9EwsmHHzJz0y3UYldg6Ame5GkGY38YudtCuLYKrCStm0ygtXNut5lVBpaZ2VzgaeAp59xcM7sSeA642MyaAB2BU4CGwAIzO9E5l1NGP4OIhJh3imND7+fov2MgtXAA7CGe2/kX73I9oG2ToVRs0DvnHLDb/7ay/5fz/6rlH68NbPK/bgdMc85lAuvMbC3QHPiiFNctImFi2hsZxHbrxiM53sBYCklcyyxWcQagfnyolehkrJnFAiuB44HRzrmvzOwB4CMzewFfr/8f/unHAF/m+/hG/1jB7+wOvmeCJemPepHItGEDp9zbntNy9j/T9VMu4HreYXtsPSzXV8kPGaJ+fCiV6GSscy7HOdcUSASam9mpQA+gr3OuEdAXmOCfbkV9RRHfmeyca+aca5aQkHBoqxeR0Fm2DJo147R9+0M+mW5cwkK2UI/cXMjN9W2fVMiH1kHtunHO7QAWA22BLsC7/kNvgX9jrK+Cb5TvY4nsb+uISITzeuHRuuPYd2FrSEsDIItK9GAM9zCOLKoA6smHk2KD3swSzOwI/+tqwKXAj/jCu6V/WmvgZ//rWUBHM6tqZscCJwDLEZGIN3ViJhl33Mv/bb+XKmQBkEYCbSstZCw9yPsLvXry4aUkPfoGwCR/nz4GmOGcm21mO4CRZlYJ2Iu/3+6cW21mM4A1+LZd9tKOG5EosHkzJ957PWdn799X8W/OpD3vkV47CU8N3/ND1JMPP+bbVBNazZo1cytWrAj1MkTkQL74Aq6/HjZvDgxNpSN3MYEM4jHz9eOlfJnZSudcs+Lm6cpYETkgrxcG1k1m3z9aBkI+hxgeZDi38iYZxAPqx4c73etGRIo0dWIm++6+j6E54wNjW6lL50rT+Sj7ksCY+vHhT0EvIoVt2MDJ99xA05z9+yi+oSnXMZPdtRurHx9hFPQiEmzRIrj5Zpru2xIYmkInupPs68frUX8RRz16EfFxDkaMgDZtYIsv5LOoRG9e5jYmqx8fwVTRiwjs2kXKpXfhWf5WYGhntfrckPsWCzIvDIypHx+ZVNGLVHQ//MDOvzcPCvnPOZ+z3L85oeuFetRfFFBFL1KRzZgBXbtSe8+ewNAoevEgI8jaW4U5c/Sov2igil6kIsrKggcfhJtvBn/Ip1ONTkyhN6MC96tJTQ3lIqW0qKIXqWh+/ZUtrW4i4efPA0O/xBxPu9x3+Z7TgqbqxGt0UEUvUpEsWMDeJmcGhfx7tKN5zAp+qhIc8jrxGj0U9CIVQW4uPPssXHYZcX/6tk5mE0t/hnEdM9mWXZuaNdGJ1yil1o1IlHt77Fbq9r2dVnvnBsY2czQdmcbSwJ3GYbsuhIpaCnqRKPbRE59z3jM3k+g2BsYWcTG3MJXfOTporvrx0UutG5Eo4/VCY4+jnw2n9dMtg0J+KI/Qho9Js+CQVz8+uqmiF4kiXi/07/YHozPupD3vB8a3U4fbmMwcrvINOF8fXjcmqxgU9CJR5K1+X/FZxs00JiUw9iXncjPTScUTGPN4dCFURaLWjUg0cA6GD+et3y4ICvkXeYCLWBoU8mrTVDwKepEI5vVC00bb+CDmWujXj8pkA7CD2nTgHR7kRbKoQmystk1WZGrdiEQorxdev+szZmXeQhIbAuNf2znc5KaznmMBXwWvcK/YVNGLRKKcHDbdN4SPMlsGhfwI+nJtnWU4z7Gq4CVAFb1IpNm8GW67jYd3LAwMbacOdzCRD7gW+wNyt4VwfRJ2FPQikWTePLj99sAToACW0YJbeZMN+K540oVPUpBaNyKRYN8+1lzVD664IhDyuRj/rPQYF7M4EPLaUSNFUdCLhLuffmLbSefTZM7wwNBmjubqqgtI7fYMiZ5K6sfLX1LrRiQMeb0w6FFHq9RJjLL7qOv2PwFqDldwBxPZklkPj54AJSWgoBcJM14v9Ou2k+EZPbiVqeB845lUoT/P8TL3AwboCVBSMgp6kTAz86FlfJHROegK1x85iVuYyn84M2iuTrxKSahHLxIusrNh8GCm/94yKOQn0JWzWVko5HXiVUpKQS8SYl4vXHjML3xR+UJ45hliyQXgD47gRmZwNxNIpzp16+oJUHJoig16M4szs+Vm9q2ZrTazp/Id621m//WPP5dvfKCZrfUfu7ysFi8S6bxTHEu6TuLDTU05ny8D40usJaezire5EfBV7yNH+k685ub6flfIS0mVpEefCbR2zu02s8rAMjObC1QD2gGnO+cyzawegJk1AToCpwANgQVmdqJzLqdsfgSRCLVtG3XuuYfkfe8EhrKoxOM8w+t1Hia+Ziym+8VLKSg26J1zDtjtf1vZ/8sBPYB/Oucy/fPS/HPaAdP84+vMbC3QHPiilNcuErnmz4c77uDK9M2BoZ84gU54WcE5uo2BlKoS9ejNLNbM/gOkAR87574CTgQuNLOvzGyJmZ3jn34M5LvLEmz0j4lUeNPeyOD1Wg/A5Zf77lnj9yr3cibfsALf/0baTSOlqUTbK/1tl6ZmdgQw08xO9X+2DnAecA4ww8yOI2+Db4GvKDhgZt2B7gBJ+q9aKoC5z67kjMG3cbL7ITCWRgL3VprAzOxrAmPaTSOl7aB23TjndgCLgbb4KvV3nc9yIBc4yj/eKN/HEoFNRXxXsnOumXOuWUJCwiEuXyQCZGfDs89y6ePnBYX8bK7iNL5jae1rtJtGylSxFb2ZJQBZzrkdZlYNuBQYhq9v3xpYbGYnAlWArcAs4E0zG4HvZOwJwPIyWr9IWJs1/GcSH72ds/Z9SWX/2G6q8yAjeI1ugGHbYevWUK5Sol1JWjcNgElmFovvbwAznHOzzawK8LqZfQ/sA7r4T9yuNrMZwBogG+ilHTdS4eTm8vWdY7j0X/2JJyMw/DnncxuT+YW/BcbUuZSyVpJdN6ugwCV5vvF9QOcDfGYIoC6jVCheLwwaBKSk4I3rSou9nwSOZVGJJ3iK5+hPTr7/7dSPl/KgK2NFDoHXC40bQ0yM7/eePaF7N0erlDdYxWlBIf8dp9Kc5Qzl0UDIqx8v5Uk3NRM5SF4vdO8O6em+9ykp8P6rm5hOd67mw8C8HGJ4nod5gqfYR9XAuMejWwtL+VLQixykQYP2hzw4OjOFl7mfOuwIzPmZ4+nCJL7gH0GfVatGQkGtG5FiFGzTpPhvLFmf33iP9kzm9qCQH0UvmvIfvuAfuhGZhAVV9CJ/oag2jeG4hTd5mfupy/bA3HU0piuvs5hWwP4bkSnYJdRU0YvkU7B679Mnf5sGGrCJ92iHl85BIf9apXt5+a5VrPO0UvUuYUcVvYhfUdX7fo4uTOJF+ga1aVJI4tF6E7hyxKW82AleLNcVi5SMgl7EL/gk636JbGAc93Alc4MP9OiBZ9gwvDVrls8CRQ6RWjdSYR3oJGseI5d7eZU1NAkK+V/sOBY8+gmMGQMKeYkAquilQiryJKuB899n9QR+Yjx3cxGfBj6TizGpZm+qvfh/dLyreghWLXJoFPRSIRXVpnEOKpNFX0bwJE9Sjb37D550EjETJnBnixblu1CRUqCglwopNbXw2FmsZDx3cyb/CYzlxsQS88gAePxxiIsrxxWKlB716KVCyn/HyHj28AIPsZzmQSHPmWcSs3KF71JWhbxEMAW9VBj5T77u3g1VqkAb5vM9p/IQI4gl1zcxLg6GDYOvvoKmTUO6ZpHSoNaNVAgFT77GbEtjovXlFt4Mnti6NYwbB8cfX/6LFCkjquilQth/8tXRlQn8yN+5xeUL+Tp14I03YMEChbxEHVX0UiGkpsJJ/Mg47qElS4MP3norjBgB9euHZnEiZUwVvUSl/P34k5IyeD7uMVZxelDI/8Kx3F5vnm+yQl6imCp6iTr5+/GXM4/RG3rxN34JHM8mlhfoxwvVBjNyRHwIVypSPhT0EvHyntWamurbNrl7NxyR/itv0JebeCto7sqq59M1cyw7PaczcojuLikVg4JeIlrB3TS/pmRxPy/zJE9Sk92BedupwyMMIzn9Lr6NUcdSKhYFvUS0/LcyuIBPGUNPTuP7oDmTuJ2HeZ54Tz2dlZIKSf/ZS0RLTYV6/M5EuvApFwWF/GqacDGLuINJ7Imvp2e1SoWloJeIkn83zd882TxSbSQ/cSJd+Fdgzh7ieSp+GO2TvmGpXaynPUmFp9aNRIz8/fgLWcro1F6F2jRvcz2Pxr3IE8mN+FnBLgKoopcwVtTzW49I/5UpdGIpLYNC/pdKJ3AFc+nneZsnxjdS9S6Sjyp6CUsFd9NsTsnkQUYwiCHUYE9g3h7ieZbHGbq7L3OrVg3RakXCmyp6CUv5701zNR+wmlMYyqNBIT+dm/g7PzLV8wgo5EUOSBW9hKXUVPg7P/AifWnLR0HHvuNU7udlFtOK+HhI1m4akb+kil7CQv5+/BmNtjO26v18x2lBIb+dOvSvPor2Sd+wxFppN41ICamil5DL68dnpmfTk7E8tfEJ6rI9cDyHGF6jG/9X7VmGjjuK5xTsIgel2IrezOLMbLmZfWtmq83sqQLH+5mZM7Oj8o0NNLO1ZvZfM7u8LBYukS1/Bd+lC1yYPo9vOYNR9A4K+c+rtuIsvuGfnrEMfe0oVe8ih6AkFX0m0No5t9vMKgPLzGyuc+5LM2sEtAECj1o2syZAR+AUoCGwwMxOdM7llMH6JQLl31FzCt/zQk6/Qn34XziWh3mBdzKu41uzEK1UJDoUW9E7n7y7Q1X2/3L+9y8C/fO9B2gHTHPOZTrn1gFrgealt2SJNEXth6+ensYYevAtZwSF/C5qMJD/owlrWOnpAAp5kcNWoh69mcUCK4HjgdHOua/M7FrgV+fctxb8P+MxwJf53m/0jxX8zu5Ad4CkpKRDW72EvYL74dNS0unLiwxgGLXYFZiXQwzjuZvBPE0a9YmPR/emESklJdp145zLcc41BRKB5mZ2OjAIGFzE9KJKMFdowLlk51wz51yzhISEg1mzRJC8/fAx5NCFifzEiQzhsaCQn08bmvIfesWOY4vV124akVJ2ULtunHM7zGwxvvbMsUBeNZ8I/NvMmuOr4Bvl+1gisKlUVisRJzUV2jCf5+hPU74NOraaJjzM88zlCuLjjUkKd5EyUZJdNwlmdoT/dTXgUuAb51w951xj51xjfOF+lnPuN2AW0NHMqprZscAJwPIy+wkkrOTvx1/V4N98UqkN87k8KOR/oz59qydzbdK3zLMr8XhMFbxIGSpJRd8AmOTv08cAM5xzsw802Tm32sxmAGuAbKCXdtxUDHn9+Hrp65jCIG79bWrQ8T3E8wL9GF3tYV4cV4MXFewi5cKcK9Q+L3fNmjVzK1asCPUy5DCd3SiN2zcOoQevUoWswHg2scyocRcP736Cyp6GDNGzWkVKhZmtdM41K26eroyVQ5b3UO4/Uv7k6drDWbJzeNBNxwBm0p5HGcoPu/7OrSFap0hFp6CXQ+L1Qu9ue+mS8SqDGMJRO7cFHV9GCwYwjM9pgccTokWKCKCgl0ORlcX397/BqoynSeTXoEOrOI2BDGUOVwKm/fAiYUB3r5QS8XrhOE8Onc3L+viTGbr9nqCQX0djOjOZM/mG1Z6rMDPthxcJE6ropVjeybnMuftdZu17klNZ7dtL5beZoxnCIJLpThZV8Hhg/fqQLVVEiqCglwNzDmbN4sy7nqBTVvDFTtupwzAe4RXuI4N4ALVpRMKUWjdSmHMs6vchq+LOgfbtaZIv5HdRg6d5nGNZx3P0p54nHjPUphEJY6roZT/nYO5ctvZ+kla/fB10aA/xvEJvnudhtlMXQG0akQihoBe8UxwLHpxDjy1P0ZyvOSrfsQziGENPhjGALdQLjKtNIxI5FPQVWW4uSx6axckvP0un3JVBh/ZSlbHcy3P0ZzMNA+NmkJSErm4ViSAK+grG64XHHs3lnNR3eKrys7TMWhV0PIM4xnFPoYAHtWpEIpWCPorl3aIgNdVXhV/dNpu9b0zlw31DacIP5LsdTSDghzGA32hQ6LvUqhGJXAr6KJX/yU5V2UvblIk8OO45jmNd0LzdVGcMPRnOQ6RRPzBety7UqLH/Dwm1akQil4I+Sg0aBDHpu3iQZB5iOA3ZHHT8T2ryCr15kb5sCzr96qveR45UsItECwV9NEpL4+6UV+jFKOqwI+jQVuryEg8wml7soA6g6l0k2inoo8m6dTB8OEyYwGPsDTr0Kw15gX6Mpxu7qREYV/UuEv10ZWw0WLmS9ed3JOe442H0aNi7P+TX8je6M47j+IXk+L7c1qMGHg+6mlWkAlFFH6mcg3nz4PnnYdEiGhc4/I2dxYo2jzD0xw6s3xCrloxIBaagjzR79/LF/W9y5MQRnJS1utDhBVzCMAawwF2K57/G+pQQrFFEwoqCPgJ4vTD8kS1cs/FVetlozndpQceziWUGN/EC/fiGswLjqanlvVIRCUcK+jA3+5/fs++xkXyWM4Vq7IV8z3LfTXVeoxsv8QCpFH5eX1JSOS5URMKWgj7M5N2i4LTUD+kfN5Kr9y4sNGcDiYykD+O5m50cUeT36EpWEcmjoA8jM17byX96TWR+1ihOYC0FdkiygrMZzkO8zQ1kUznomPbCi8iBKOjDwZo1MGoUV439Fze5PUGHcojhXTowkj58RgvACn1ce+FF5K8o6EMlO5ul/WYRM24MF/jbM9XzHf6DI3iNboymV6H+e+XKUKsWbN+u6l1EiqegL2+bN8Nrr5H+UjIX/fFrocPfcwqv0Bsvndjjv4JVbRkRORwK+vKQm8uCxxazd+RYLk+fSWWy/Y/T9skhhvdozyv0ZiktcfnaM2rLiMjhUtCXpa1bYeJE/hyezKW//Vzo8O/U4zW6kUx3NrB/L6QgF/nhAAAFM0lEQVTHo+pdREqPgr60+av3PSPH0zb9Haqyj1oFpizlQsbQk3fpQBZVgo7pKU4iUtoU9KVl82aYOJFdL03g0rT/FTq8g9pM5jaS6c73nFbkV2jvu4iUhWKD3szigKVAVf/8t51zT5jZ88A1wD7gf8Cdzrkd/s8MBO4CcoD7nXMfldH6QysriyUD5pA59g1aZ8ymEjnULDDlK5ozjnuYzs2kB+2r0UlWESkfJanoM4HWzrndZlYZWGZmc4GPgYHOuWwzGwYMBAaYWROgI3AK0BBYYGYnOudyyuhnKH9r1sDrr5Px2mRa/plW6PAOajOFzoznbr6laZFfoZOsIlJeir0fvfPZ7X9b2f/LOefmO+ey/eNfAon+1+2Aac65TOfcOmAt0LyU110uvF5o3BhiYuCMRttZfscYOPdcOOUUGD6cagVCfgkX0ZnJNGAzvRkVFPJ166L7wItISJSoR29mscBK4HhgtHPuqwJTugLT/a+PwRf8eTb6xwp+Z3egO0BSGNx9y+v1PWc1r41y5ZXgnZjFRRnzeIFJXLPxA6pO2lfoc7/SkEl0YSJ38DMnFvndqt5FJJRKFPT+tktTMzsCmGlmpzrnvgcws0FANuD1Ty98jX7QPRcD35kMJAM0a9as0PHy5PVC9+6Qng7gqJ+ynCavTmEt00hga6H5+6jMLK5lAnfxMW3IKfCvUb13EQknB7Xrxjm3w8wWA22B782sC3A1cIlzLi+sNwKN8n0sEdhUCmstNQWr99274Zj0n7iFqXRmiu+GYkVYzjlMogvT6Mh26hY5R9W7iISbkuy6SQCy/CFfDbgUGGZmbYEBQEvnXHq+j8wC3jSzEfhOxp4ALC/9pZdMUS2ZSZN81XtDfqVDynRuYSrnsKLIz28gES+dmEQXfuTkA/5zzFS9i0h4KklF3wCY5O/TxwAznHOzzWwtvi2XH5sZwJfOuXudc6vNbAawBl9Lp1eodtwEt2QgJQXefnULt/EONzOdliwhpnBXiZ3U4m1uwEtnFtMS5z9nbeZ7VGtBushJRMJZsUHvnFsFnFnE+PF/8ZkhQLlf+lNUSyY9HeqwnQ68y81MpxWLqEThP3cyqcJcruBNbuUDriEmvhpdusAvc4r+20AeXeQkIuEuoq+MzR/sRx4Ju3bBPv/GmPSUNDrwHtfzDq35hMpkF/p8LsYntGYqt7C4TgdyatUp9gRqixbBf5ioVSMi4S5ig75gW2bbNl/Pvb0/3FuyhFhyi/zsp1zADG7ibW7gNxoQHw/Jr5QssDt1UrCLSGSJ2KAfNMgX8ifwE9cxkw68y7l/cc73C85jBjcxO+5G2tyZyJw58HsqeFSVi0iUi9igj0/5ge+4kVNZXeTxXIxlXMDc+BtYVKcDyzclqtUiIhVSxAa9a5TE3zYE3yUym1gW0YqZXMd7tGdnfEOSk2Gogl1EKrCIDfrHhlZnYZfLuCRnPvNoy0yu46NKV5NT+8jAs1STVb2LiERu0HfqBDO3vsJZw+vy343VSUqCEQp2EZFCIjboAa7rk8R1fUK9ChGR8FbsbYpFRCSyKehFRKKcgl5EJMop6EVEopyCXkQkyinoRUSinLmibrBe3osw2wKkHMZXHAVFPPMvcmj9oRXp64fI/xm0/kPjcc4lFDcpLIL+cJnZCudcs1Cv41Bp/aEV6euHyP8ZtP6ypdaNiEiUU9CLiES5aAn65FAv4DBp/aEV6euHyP8ZtP4yFBU9ehERObBoqehFROQAFPQiIlFOQS8iEuUU9CIiUU5BLyIS5f4fA2V+68fxlOYAAAAASUVORK5CYII=\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.figure()\n",
+    "yearly_inc.plot(style='bo')\n",
+    "yearly_interp.plot(linewidth=3, style='r')"
+   ]
   }
  ],
  "metadata": {
@@ -303,6 +389,18 @@
    "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,
-- 
2.18.1