import local des données

module3/exo1/analyse-syndrome-grippal.ipynb

@@ -9,14 +9,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
     "%matplotlib inline\n",
     "import matplotlib.pyplot as plt\n",
     "import pandas as pd\n",
-    "import isoweek"
+    "import isoweek\n",
+    "import os\n",
+    "import urllib.request"
    ]
   },
   {
@@ -28,10 +30,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 5,
+   "metadata": {},
    "outputs": [],
    "source": [
     "data_url = \"http://www.sentiweb.fr/datasets/incidence-PAY-3.csv\""
@@ -59,14 +59,150 @@
     "La première ligne du fichier CSV est un commentaire, que nous ignorons en précisant `skiprows=1`."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Il se peut que l'URl change et devienne caduque au fil du temps. Ce fichier va d'abord tenter d'importer une copie locale si elle est disponible, sinon charger l'URL et créer le fichier. "
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
-   "outputs": [],
+   "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>week</th>\n",
+       "      <th>indicator</th>\n",
+       "      <th>inc</th>\n",
+       "      <th>inc_low</th>\n",
+       "      <th>inc_up</th>\n",
+       "      <th>inc100</th>\n",
+       "      <th>inc100_low</th>\n",
+       "      <th>inc100_up</th>\n",
+       "      <th>geo_insee</th>\n",
+       "      <th>geo_name</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>202011</td>\n",
+       "      <td>3</td>\n",
+       "      <td>101704</td>\n",
+       "      <td>93652.0</td>\n",
+       "      <td>109756.0</td>\n",
+       "      <td>154</td>\n",
+       "      <td>142.0</td>\n",
+       "      <td>166.0</td>\n",
+       "      <td>FR</td>\n",
+       "      <td>France</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>202010</td>\n",
+       "      <td>3</td>\n",
+       "      <td>104977</td>\n",
+       "      <td>96650.0</td>\n",
+       "      <td>113304.0</td>\n",
+       "      <td>159</td>\n",
+       "      <td>146.0</td>\n",
+       "      <td>172.0</td>\n",
+       "      <td>FR</td>\n",
+       "      <td>France</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>202009</td>\n",
+       "      <td>3</td>\n",
+       "      <td>110696</td>\n",
+       "      <td>102066.0</td>\n",
+       "      <td>119326.0</td>\n",
+       "      <td>168</td>\n",
+       "      <td>155.0</td>\n",
+       "      <td>181.0</td>\n",
+       "      <td>FR</td>\n",
+       "      <td>France</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>202008</td>\n",
+       "      <td>3</td>\n",
+       "      <td>143753</td>\n",
+       "      <td>133984.0</td>\n",
+       "      <td>153522.0</td>\n",
+       "      <td>218</td>\n",
+       "      <td>203.0</td>\n",
+       "      <td>233.0</td>\n",
+       "      <td>FR</td>\n",
+       "      <td>France</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>202007</td>\n",
+       "      <td>3</td>\n",
+       "      <td>183610</td>\n",
+       "      <td>172812.0</td>\n",
+       "      <td>194408.0</td>\n",
+       "      <td>279</td>\n",
+       "      <td>263.0</td>\n",
+       "      <td>295.0</td>\n",
+       "      <td>FR</td>\n",
+       "      <td>France</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     week  indicator     inc   inc_low    inc_up  inc100  inc100_low  \\\n",
+       "0  202011          3  101704   93652.0  109756.0     154       142.0   \n",
+       "1  202010          3  104977   96650.0  113304.0     159       146.0   \n",
+       "2  202009          3  110696  102066.0  119326.0     168       155.0   \n",
+       "3  202008          3  143753  133984.0  153522.0     218       203.0   \n",
+       "4  202007          3  183610  172812.0  194408.0     279       263.0   \n",
+       "\n",
+       "   inc100_up geo_insee geo_name  \n",
+       "0      166.0        FR   France  \n",
+       "1      172.0        FR   France  \n",
+       "2      181.0        FR   France  \n",
+       "3      233.0        FR   France  \n",
+       "4      295.0        FR   France  "
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "raw_data = pd.read_csv(data_url, skiprows=1)\n",
-    "raw_data"
+    "filename = \"./syndrome-grippal.csv\"\n",
+    "\n",
+    "if not os.path.exists(filename):\n",
+    "    urllib.request.urlretrieve(data_url, filename)\n",
+    "\n",
+    "raw_data = pd.read_csv(filename, skiprows=1)\n",
+    "raw_data.head()"
    ]
   },
   {
@@ -364,7 +500,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.1"
+   "version": "3.6.4"
   }
  },
  "nbformat": 4,