wip

module3/exo3/exercice.ipynb

@@ -7,6 +7,205 @@
     "# Sujet 1 : Concentration de CO2 dans l'atmosphère depuis 1958"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
+    "import isoweek\n",
+    "\n",
+    "# set diagram sizes\n",
+    "# print(plt.rcParams['figure.dpi'])  # default = 72\n",
+    "# print(plt.rcParams['figure.figsize'])  # default = 6.0, 4.0\n",
+    "# plt.rcParams['figure.dpi'] = 100\n",
+    "plt.rcParams['figure.figsize'] = [12.0, 4.0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Les données sont disponibles sur le site Web de l'[institut Scripps. ](https://scrippsco2.ucsd.edu/data/atmospheric_co2/primary_mlo_co2_record.html)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "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>date</th>\n",
+       "      <th>value</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1958-03-29</td>\n",
+       "      <td>316.19</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1958-04-05</td>\n",
+       "      <td>317.31</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1958-04-12</td>\n",
+       "      <td>317.69</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1958-04-19</td>\n",
+       "      <td>317.58</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1958-04-26</td>\n",
+       "      <td>316.48</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         date   value\n",
+       "0  1958-03-29  316.19\n",
+       "1  1958-04-05  317.31\n",
+       "2  1958-04-12  317.69\n",
+       "3  1958-04-19  317.58\n",
+       "4  1958-04-26  316.48"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# récolte le 12/02\n",
+    "data_url = \"https://scrippsco2.ucsd.edu/assets/data/atmospheric/stations/in_situ_co2/weekly/weekly_in_situ_co2_mlo.csv\"\n",
+    "data = pd.read_csv(data_url, encoding = 'utf-8', comment='\"', names=[\"date\", \"value\"])\n",
+    "data.head(5)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Contrôle Qualité\n",
+    "### Recherche des lignes sans donnée"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "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>date</th>\n",
+       "      <th>value</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "Empty DataFrame\n",
+       "Columns: [date, value]\n",
+       "Index: []"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data[data.isnull().any(axis=1)]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Il ne manque aucune donnée.\n",
+    "\n",
+    "### Vérification des écarts entre les données\n",
+    "On attend un écart de 7 jours entre chaque mesure."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data['timestamp'] = [ pd.to_datetime(d) for d in data['date'] ]\n",
+    "sorted_data = data.set_index('timestamp').sort_index()\n",
+    "sorted_data.head(5)\n",
+    "# for row1, row2 in zip(sorted_data[:-1], sorted_data[1:]):\n",
+    "#    delta = (row2['timestamp'] - row1['timestamp']).days\n",
+    "#    if delta != 7:\n",
+    "#        print(row1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "l_index = sorted_data.index\n",
+    "l_index.head(5)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,