data is not defined

module3/exo2/exercice.ipynb

@@ -2074,53 +2074,58 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def convert_week(year_and_week_int):\n",
+    "    year_and_week_str = str(year_and_week_int)\n",
+    "    year = int(year_and_week_str[:4])\n",
+    "    week = int(year_and_week_str[4:])\n",
+    "    w = isoweek.Week(year, week)\n",
+    "    return pd.Period(w.day(0), 'W')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'data' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-40-4170f9fe0be0>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'period'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mconvert_week\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0myw\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0myw\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'week'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m: name 'data' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "data['period'] = [convert_week(yw) for yw in data['week']]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "1991 12615.384615384615\n",
-      "1992 15915.094339622641\n",
-      "1993 11412.211538461539\n",
-      "1994 12700.346153846154\n",
-      "1995 12588.423076923076\n",
-      "1996 12157.923076923076\n",
-      "1997 12005.807692307691\n",
-      "1998 14812.358490566037\n",
-      "1999 12423.5\n",
-      "2000 12434.942307692309\n",
-      "2001 10834.903846153846\n",
-      "2002 11337.442307692309\n",
-      "2003 13056.307692307691\n",
-      "2004 16052.169811320755\n",
-      "2005 12585.5\n",
-      "2006 10728.942307692309\n",
-      "2007 14963.826923076924\n",
-      "2008 14211.403846153846\n",
-      "2009 16527.11320754717\n",
-      "2010 14739.961538461539\n",
-      "2011 12346.807692307691\n",
-      "2012 13018.673076923076\n",
-      "2013 12659.961538461539\n",
-      "2014 12473.211538461539\n",
-      "2015 12259.283018867925\n",
-      "2016 14038.51923076923\n",
-      "2017 10703.461538461539\n",
-      "2018 10796.153846153846\n",
-      "2019 10401.423076923076\n",
-      "2020 4339.377358490566\n"
+     "ename": "NameError",
+     "evalue": "name 'data' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-41-eb886c840e17>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0msorted_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'period'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msort_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m: name 'data' is not defined"
      ]
     }
    ],
    "source": [
-    "raw_data[\"year\"] = raw_data[\"week\"].astype(str).apply(lambda x: x[:4])\n",
-    "raw_data[\"year\"] = raw_data[\"year\"].astype(int)\n",
-    "\n",
-    "for year in range(1991, 2021):\n",
-    "    print(year, raw_data[raw_data[\"year\"] == year][\"inc\"].mean())\n",
-    "\n"
+    "sorted_data = data.set_index('period').sort_index()"
    ]
   },
   {