Update

module3/exo3/exercice.ipynb

@@ -162,7 +162,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 4,
    "metadata": {
     "hideCode": true,
     "hidePrompt": true,
@@ -171,13 +171,44 @@
    "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>CO2</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Date</th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
       "text/plain": [
-       "<bound method DataFrame.info of Empty DataFrame\n",
+       "Empty DataFrame\n",
        "Columns: [CO2]\n",
-       "Index: []>"
+       "Index: []"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -195,10 +226,56 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "From: 1958-05-03 00:00:00 To: 1958-05-17 00:00:00 Missing: 14 days\n",
+      "From: 1958-05-24 00:00:00 To: 1958-07-05 00:00:00 Missing: 42 days\n",
+      "From: 1958-08-16 00:00:00 To: 1958-08-30 00:00:00 Missing: 14 days\n",
+      "From: 1958-09-06 00:00:00 To: 1958-11-08 00:00:00 Missing: 63 days\n",
+      "From: 1959-01-31 00:00:00 To: 1959-02-14 00:00:00 Missing: 14 days\n",
+      "From: 1959-03-07 00:00:00 To: 1959-03-21 00:00:00 Missing: 14 days\n",
+      "From: 1959-05-23 00:00:00 To: 1959-06-06 00:00:00 Missing: 14 days\n",
+      "From: 1959-08-08 00:00:00 To: 1959-08-22 00:00:00 Missing: 14 days\n",
+      "From: 1962-08-18 00:00:00 To: 1962-09-15 00:00:00 Missing: 28 days\n",
+      "From: 1962-12-22 00:00:00 To: 1963-01-05 00:00:00 Missing: 14 days\n",
+      "From: 1963-02-09 00:00:00 To: 1963-02-23 00:00:00 Missing: 14 days\n",
+      "From: 1963-04-27 00:00:00 To: 1963-05-11 00:00:00 Missing: 14 days\n",
+      "From: 1963-11-16 00:00:00 To: 1963-11-30 00:00:00 Missing: 14 days\n",
+      "From: 1964-01-18 00:00:00 To: 1964-05-30 00:00:00 Missing: 133 days\n",
+      "From: 1964-06-06 00:00:00 To: 1964-06-27 00:00:00 Missing: 21 days\n",
+      "From: 1964-08-01 00:00:00 To: 1964-08-15 00:00:00 Missing: 14 days\n",
+      "From: 1966-07-09 00:00:00 To: 1966-08-06 00:00:00 Missing: 28 days\n",
+      "From: 1966-10-29 00:00:00 To: 1966-11-12 00:00:00 Missing: 14 days\n",
+      "From: 1967-01-14 00:00:00 To: 1967-02-04 00:00:00 Missing: 21 days\n",
+      "From: 1976-06-19 00:00:00 To: 1976-07-03 00:00:00 Missing: 14 days\n",
+      "From: 1984-03-24 00:00:00 To: 1984-04-28 00:00:00 Missing: 35 days\n",
+      "From: 1985-07-27 00:00:00 To: 1985-08-10 00:00:00 Missing: 14 days\n",
+      "From: 2003-06-07 00:00:00 To: 2003-06-21 00:00:00 Missing: 14 days\n",
+      "From: 2003-10-04 00:00:00 To: 2003-10-25 00:00:00 Missing: 21 days\n",
+      "From: 2005-02-19 00:00:00 To: 2005-03-26 00:00:00 Missing: 35 days\n",
+      "From: 2006-02-04 00:00:00 To: 2006-02-25 00:00:00 Missing: 21 days\n",
+      "From: 2007-01-20 00:00:00 To: 2007-02-03 00:00:00 Missing: 14 days\n",
+      "From: 2012-09-29 00:00:00 To: 2012-10-20 00:00:00 Missing: 21 days\n",
+      "From: 2020-01-11 00:00:00 To: 2020-01-25 00:00:00 Missing: 14 days\n",
+      "Total week missing: 72.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "dates = new_data.index\n",
+    "missing_weeks = 0\n",
+    "for dt1, dt2 in zip(dates[:-1], dates[1:]):\n",
+    "    delta = dt2 - dt1\n",
+    "    if delta > pd.Timedelta(\"7d\"):\n",
+    "        print(\"From: {0:} To: {1:} Missing: {2:} days\".format(dt1, dt2, delta.days))\n",
+    "        missing_weeks += (delta.days-7)/7\n",
+    "print(\"Total week missing: {0:}\".format(missing_weeks))"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -207,12 +284,17 @@
     "hidePrompt": true
    },
    "source": [
-    "Aucune donnée n'est visiblement manquante dans le fichier."
+    "Aucune donnée n'est visiblement manquante dans le fichier, autrement dit toutes les lignes présentes bien une valeur.\n",
+    "En revanche nous voyons qu'il manque un certain nombre de semaines dans le fichier 72 au total dans le fichier.\n",
+    "Nous voyons également que l'année 1964 est celle présentant le moins de relevés hebdomadaires, en partie dû à un intervalle de 133 jours entre deux relevés.\n",
+    "Nous gardons donc cette information en mémoire pour la suite de l'analyse.\n",
+    "\n",
+    "A présent, nous pouvons représenter les données."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -221,7 +303,7 @@
        "Text(0,0.5,'$\\\\rm CO_2$ [ppm]')"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     },