diff --git a/Spectacle/Stat_desc.ipynb b/Spectacle/Stat_desc.ipynb
index 80a3be3..2fb2c0d 100644
--- a/Spectacle/Stat_desc.ipynb
+++ b/Spectacle/Stat_desc.ipynb
@@ -18,7 +18,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 2,
    "id": "aa915888-cede-4eb0-8a26-7df573d29a3e",
    "metadata": {},
    "outputs": [],
@@ -34,7 +34,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 3,
    "id": "17949e81-c30b-4fdf-9872-d7dc2b22ba9e",
    "metadata": {},
    "outputs": [],
@@ -46,7 +46,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 4,
    "id": "9c1737a2-bad8-4266-8dec-452085d8cfe7",
    "metadata": {},
    "outputs": [
@@ -59,7 +59,7 @@
        " 'projet-bdc2324-team1/0_Input/Company_10/target_information.csv']"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -75,7 +75,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "a35dc2f6-2017-4b21-abd2-2c4c112c96b2",
    "metadata": {},
    "outputs": [],
@@ -89,7 +89,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 6,
    "id": "40b705eb-fd18-436b-b150-61611a3c6a84",
    "metadata": {},
    "outputs": [],
@@ -109,7 +109,512 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 10,
+   "id": "c56decc3-de19-4786-82a4-1386c72a6bfb",
+   "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>id</th>\n",
+       "      <th>customer_id</th>\n",
+       "      <th>target_name</th>\n",
+       "      <th>target_type_is_import</th>\n",
+       "      <th>target_type_name</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1165098</td>\n",
+       "      <td>618562</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1165100</td>\n",
+       "      <td>618559</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1165101</td>\n",
+       "      <td>618561</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1165102</td>\n",
+       "      <td>618560</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1165103</td>\n",
+       "      <td>618558</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>69253</th>\n",
+       "      <td>1698158</td>\n",
+       "      <td>18580</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>69254</th>\n",
+       "      <td>1698159</td>\n",
+       "      <td>18569</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>69255</th>\n",
+       "      <td>1698160</td>\n",
+       "      <td>2962</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>69256</th>\n",
+       "      <td>1698161</td>\n",
+       "      <td>3825</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>69257</th>\n",
+       "      <td>1698162</td>\n",
+       "      <td>5731</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>69258 rows × 5 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "            id  customer_id           target_name  target_type_is_import  \\\n",
+       "0      1165098       618562  Newsletter mensuelle                  False   \n",
+       "1      1165100       618559  Newsletter mensuelle                  False   \n",
+       "2      1165101       618561  Newsletter mensuelle                  False   \n",
+       "3      1165102       618560  Newsletter mensuelle                  False   \n",
+       "4      1165103       618558  Newsletter mensuelle                  False   \n",
+       "...        ...          ...                   ...                    ...   \n",
+       "69253  1698158        18580  Newsletter mensuelle                  False   \n",
+       "69254  1698159        18569  Newsletter mensuelle                  False   \n",
+       "69255  1698160         2962  Newsletter mensuelle                  False   \n",
+       "69256  1698161         3825  Newsletter mensuelle                  False   \n",
+       "69257  1698162         5731  Newsletter mensuelle                  False   \n",
+       "\n",
+       "           target_type_name  \n",
+       "0      manual_static_filter  \n",
+       "1      manual_static_filter  \n",
+       "2      manual_static_filter  \n",
+       "3      manual_static_filter  \n",
+       "4      manual_static_filter  \n",
+       "...                     ...  \n",
+       "69253  manual_static_filter  \n",
+       "69254  manual_static_filter  \n",
+       "69255  manual_static_filter  \n",
+       "69256  manual_static_filter  \n",
+       "69257  manual_static_filter  \n",
+       "\n",
+       "[69258 rows x 5 columns]"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "target_information"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "c825d64b-356c-4b71-aa3c-90e0dd7ca092",
+   "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>ticket_id</th>\n",
+       "      <th>customer_id</th>\n",
+       "      <th>purchase_id</th>\n",
+       "      <th>event_type_id</th>\n",
+       "      <th>supplier_name</th>\n",
+       "      <th>purchase_date</th>\n",
+       "      <th>amount</th>\n",
+       "      <th>is_full_price</th>\n",
+       "      <th>name_event_types</th>\n",
+       "      <th>name_facilities</th>\n",
+       "      <th>name_categories</th>\n",
+       "      <th>name_events</th>\n",
+       "      <th>name_seasons</th>\n",
+       "      <th>start_date_time</th>\n",
+       "      <th>end_date_time</th>\n",
+       "      <th>open</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1799177</td>\n",
+       "      <td>36984</td>\n",
+       "      <td>409613</td>\n",
+       "      <td>2</td>\n",
+       "      <td>guichet</td>\n",
+       "      <td>2016-04-28 17:58:26+02:00</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>False</td>\n",
+       "      <td>danse</td>\n",
+       "      <td>le grand t</td>\n",
+       "      <td>abo t gourmand jeune</td>\n",
+       "      <td>aringa rossa</td>\n",
+       "      <td>test 2016/2017</td>\n",
+       "      <td>2016-09-27 00:00:00+02:00</td>\n",
+       "      <td>1901-01-01 00:09:21+00:09</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1799178</td>\n",
+       "      <td>36984</td>\n",
+       "      <td>409613</td>\n",
+       "      <td>3</td>\n",
+       "      <td>guichet</td>\n",
+       "      <td>2016-04-28 17:58:26+02:00</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>False</td>\n",
+       "      <td>cirque</td>\n",
+       "      <td>le grand t</td>\n",
+       "      <td>abo t gourmand jeune</td>\n",
+       "      <td>5èmes hurlants</td>\n",
+       "      <td>test 2016/2017</td>\n",
+       "      <td>2016-11-18 00:00:00+01:00</td>\n",
+       "      <td>1901-01-01 00:09:21+00:09</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1799179</td>\n",
+       "      <td>36984</td>\n",
+       "      <td>409613</td>\n",
+       "      <td>1</td>\n",
+       "      <td>guichet</td>\n",
+       "      <td>2016-04-28 17:58:26+02:00</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>False</td>\n",
+       "      <td>théâtre</td>\n",
+       "      <td>le grand t</td>\n",
+       "      <td>abo t gourmand jeune</td>\n",
+       "      <td>dom juan</td>\n",
+       "      <td>test 2016/2017</td>\n",
+       "      <td>2016-12-07 00:00:00+01:00</td>\n",
+       "      <td>1901-01-01 00:09:21+00:09</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1799180</td>\n",
+       "      <td>36984</td>\n",
+       "      <td>409613</td>\n",
+       "      <td>1</td>\n",
+       "      <td>guichet</td>\n",
+       "      <td>2016-04-28 17:58:26+02:00</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>False</td>\n",
+       "      <td>théâtre</td>\n",
+       "      <td>le grand t</td>\n",
+       "      <td>abo t gourmand jeune</td>\n",
+       "      <td>vanishing point</td>\n",
+       "      <td>test 2016/2017</td>\n",
+       "      <td>2017-01-04 00:00:00+01:00</td>\n",
+       "      <td>1901-01-01 00:09:21+00:09</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1799181</td>\n",
+       "      <td>36984</td>\n",
+       "      <td>409613</td>\n",
+       "      <td>3</td>\n",
+       "      <td>guichet</td>\n",
+       "      <td>2016-04-28 17:58:26+02:00</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>False</td>\n",
+       "      <td>cirque</td>\n",
+       "      <td>la cite des congres</td>\n",
+       "      <td>abo t gourmand jeune</td>\n",
+       "      <td>a o lang pho</td>\n",
+       "      <td>test 2016/2017</td>\n",
+       "      <td>2017-01-03 00:00:00+01:00</td>\n",
+       "      <td>1901-01-01 00:09:21+00:09</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>492309</th>\n",
+       "      <td>3252232</td>\n",
+       "      <td>621716</td>\n",
+       "      <td>710062</td>\n",
+       "      <td>1</td>\n",
+       "      <td>guichet</td>\n",
+       "      <td>2023-03-09 12:08:45+01:00</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>False</td>\n",
+       "      <td>théâtre</td>\n",
+       "      <td>cap nort</td>\n",
+       "      <td>tarif sco co 1 seance scolaire</td>\n",
+       "      <td>sur moi, le temps</td>\n",
+       "      <td>2022/2023</td>\n",
+       "      <td>2023-03-13 14:00:00+01:00</td>\n",
+       "      <td>1901-01-01 00:09:21+00:09</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>492310</th>\n",
+       "      <td>3252233</td>\n",
+       "      <td>621716</td>\n",
+       "      <td>710062</td>\n",
+       "      <td>1</td>\n",
+       "      <td>guichet</td>\n",
+       "      <td>2023-03-09 12:08:45+01:00</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>False</td>\n",
+       "      <td>théâtre</td>\n",
+       "      <td>cap nort</td>\n",
+       "      <td>tarif sco co 1 seance scolaire</td>\n",
+       "      <td>sur moi, le temps</td>\n",
+       "      <td>2022/2023</td>\n",
+       "      <td>2023-03-13 14:00:00+01:00</td>\n",
+       "      <td>1901-01-01 00:09:21+00:09</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>492311</th>\n",
+       "      <td>3252234</td>\n",
+       "      <td>621716</td>\n",
+       "      <td>710062</td>\n",
+       "      <td>1</td>\n",
+       "      <td>guichet</td>\n",
+       "      <td>2023-03-09 12:08:45+01:00</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>False</td>\n",
+       "      <td>théâtre</td>\n",
+       "      <td>cap nort</td>\n",
+       "      <td>tarif sco co 1 seance scolaire</td>\n",
+       "      <td>sur moi, le temps</td>\n",
+       "      <td>2022/2023</td>\n",
+       "      <td>2023-03-13 14:00:00+01:00</td>\n",
+       "      <td>1901-01-01 00:09:21+00:09</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>492312</th>\n",
+       "      <td>3252235</td>\n",
+       "      <td>621716</td>\n",
+       "      <td>710062</td>\n",
+       "      <td>1</td>\n",
+       "      <td>guichet</td>\n",
+       "      <td>2023-03-09 12:08:45+01:00</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>False</td>\n",
+       "      <td>théâtre</td>\n",
+       "      <td>cap nort</td>\n",
+       "      <td>tarif sco co 1 seance scolaire</td>\n",
+       "      <td>sur moi, le temps</td>\n",
+       "      <td>2022/2023</td>\n",
+       "      <td>2023-03-13 14:00:00+01:00</td>\n",
+       "      <td>1901-01-01 00:09:21+00:09</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>492313</th>\n",
+       "      <td>3252236</td>\n",
+       "      <td>621716</td>\n",
+       "      <td>710062</td>\n",
+       "      <td>1</td>\n",
+       "      <td>guichet</td>\n",
+       "      <td>2023-03-09 12:08:45+01:00</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>False</td>\n",
+       "      <td>théâtre</td>\n",
+       "      <td>cap nort</td>\n",
+       "      <td>tarif sco co 1 seance scolaire</td>\n",
+       "      <td>sur moi, le temps</td>\n",
+       "      <td>2022/2023</td>\n",
+       "      <td>2023-03-13 14:00:00+01:00</td>\n",
+       "      <td>1901-01-01 00:09:21+00:09</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>492314 rows × 16 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        ticket_id  customer_id  purchase_id  event_type_id supplier_name  \\\n",
+       "0         1799177        36984       409613              2       guichet   \n",
+       "1         1799178        36984       409613              3       guichet   \n",
+       "2         1799179        36984       409613              1       guichet   \n",
+       "3         1799180        36984       409613              1       guichet   \n",
+       "4         1799181        36984       409613              3       guichet   \n",
+       "...           ...          ...          ...            ...           ...   \n",
+       "492309    3252232       621716       710062              1       guichet   \n",
+       "492310    3252233       621716       710062              1       guichet   \n",
+       "492311    3252234       621716       710062              1       guichet   \n",
+       "492312    3252235       621716       710062              1       guichet   \n",
+       "492313    3252236       621716       710062              1       guichet   \n",
+       "\n",
+       "                    purchase_date  amount  is_full_price name_event_types  \\\n",
+       "0       2016-04-28 17:58:26+02:00     9.0          False            danse   \n",
+       "1       2016-04-28 17:58:26+02:00     9.0          False           cirque   \n",
+       "2       2016-04-28 17:58:26+02:00     9.0          False          théâtre   \n",
+       "3       2016-04-28 17:58:26+02:00     9.0          False          théâtre   \n",
+       "4       2016-04-28 17:58:26+02:00    12.0          False           cirque   \n",
+       "...                           ...     ...            ...              ...   \n",
+       "492309  2023-03-09 12:08:45+01:00     7.0          False          théâtre   \n",
+       "492310  2023-03-09 12:08:45+01:00     7.0          False          théâtre   \n",
+       "492311  2023-03-09 12:08:45+01:00     7.0          False          théâtre   \n",
+       "492312  2023-03-09 12:08:45+01:00     7.0          False          théâtre   \n",
+       "492313  2023-03-09 12:08:45+01:00     7.0          False          théâtre   \n",
+       "\n",
+       "            name_facilities                 name_categories  \\\n",
+       "0                le grand t            abo t gourmand jeune   \n",
+       "1                le grand t            abo t gourmand jeune   \n",
+       "2                le grand t            abo t gourmand jeune   \n",
+       "3                le grand t            abo t gourmand jeune   \n",
+       "4       la cite des congres            abo t gourmand jeune   \n",
+       "...                     ...                             ...   \n",
+       "492309             cap nort  tarif sco co 1 seance scolaire   \n",
+       "492310             cap nort  tarif sco co 1 seance scolaire   \n",
+       "492311             cap nort  tarif sco co 1 seance scolaire   \n",
+       "492312             cap nort  tarif sco co 1 seance scolaire   \n",
+       "492313             cap nort  tarif sco co 1 seance scolaire   \n",
+       "\n",
+       "              name_events    name_seasons            start_date_time  \\\n",
+       "0            aringa rossa  test 2016/2017  2016-09-27 00:00:00+02:00   \n",
+       "1          5èmes hurlants  test 2016/2017  2016-11-18 00:00:00+01:00   \n",
+       "2                dom juan  test 2016/2017  2016-12-07 00:00:00+01:00   \n",
+       "3         vanishing point  test 2016/2017  2017-01-04 00:00:00+01:00   \n",
+       "4            a o lang pho  test 2016/2017  2017-01-03 00:00:00+01:00   \n",
+       "...                   ...             ...                        ...   \n",
+       "492309  sur moi, le temps       2022/2023  2023-03-13 14:00:00+01:00   \n",
+       "492310  sur moi, le temps       2022/2023  2023-03-13 14:00:00+01:00   \n",
+       "492311  sur moi, le temps       2022/2023  2023-03-13 14:00:00+01:00   \n",
+       "492312  sur moi, le temps       2022/2023  2023-03-13 14:00:00+01:00   \n",
+       "492313  sur moi, le temps       2022/2023  2023-03-13 14:00:00+01:00   \n",
+       "\n",
+       "                    end_date_time  open  \n",
+       "0       1901-01-01 00:09:21+00:09  True  \n",
+       "1       1901-01-01 00:09:21+00:09  True  \n",
+       "2       1901-01-01 00:09:21+00:09  True  \n",
+       "3       1901-01-01 00:09:21+00:09  True  \n",
+       "4       1901-01-01 00:09:21+00:09  True  \n",
+       "...                           ...   ...  \n",
+       "492309  1901-01-01 00:09:21+00:09  True  \n",
+       "492310  1901-01-01 00:09:21+00:09  True  \n",
+       "492311  1901-01-01 00:09:21+00:09  True  \n",
+       "492312  1901-01-01 00:09:21+00:09  True  \n",
+       "492313  1901-01-01 00:09:21+00:09  True  \n",
+       "\n",
+       "[492314 rows x 16 columns]"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "products_purchased_reduced"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
    "id": "afd044b8-ac83-4a35-b959-700cae0b3b41",
    "metadata": {},
    "outputs": [
@@ -124,7 +629,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
      ]
     },
@@ -139,7 +644,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
      ]
     },
@@ -154,7 +659,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
      ]
     },
@@ -169,7 +674,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n",
       "<string>:27: SettingWithCopyWarning: \n",
       "A value is trying to be set on a copy of a slice from a DataFrame\n",
@@ -181,21 +686,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "File path :  projet-bdc2324-team1/0_Input/Company_11/customerplus_cleaned.csv\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
-      "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "File path :  projet-bdc2324-team1/0_Input/Company_11/customerplus_cleaned.csv\n",
       "File path :  projet-bdc2324-team1/0_Input/Company_11/campaigns_information.csv\n"
      ]
     },
@@ -203,7 +694,9 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
      ]
     },
@@ -218,7 +711,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
      ]
     },
@@ -233,7 +726,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n",
       "<string>:27: SettingWithCopyWarning: \n",
       "A value is trying to be set on a copy of a slice from a DataFrame\n",
@@ -252,7 +745,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
      ]
     },
@@ -267,7 +760,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
      ]
     },
@@ -282,9 +775,9 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n",
-      "/tmp/ipykernel_1173/2987234667.py:8: DtypeWarning: Columns (4,8,10) have mixed types. Specify dtype option on import or set low_memory=False.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: DtypeWarning: Columns (4,8,10) have mixed types. Specify dtype option on import or set low_memory=False.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
      ]
     },
@@ -299,7 +792,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n",
       "<string>:27: SettingWithCopyWarning: \n",
       "A value is trying to be set on a copy of a slice from a DataFrame\n",
@@ -318,7 +811,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
      ]
     },
@@ -333,7 +826,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
      ]
     },
@@ -348,7 +841,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
      ]
     },
@@ -363,7 +856,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n",
       "<string>:27: SettingWithCopyWarning: \n",
       "A value is trying to be set on a copy of a slice from a DataFrame\n",
@@ -382,7 +875,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
      ]
     },
@@ -397,7 +890,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
      ]
     },
@@ -412,9 +905,9 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n",
-      "/tmp/ipykernel_1173/2987234667.py:8: DtypeWarning: Columns (8,9) have mixed types. Specify dtype option on import or set low_memory=False.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: DtypeWarning: Columns (8,9) have mixed types. Specify dtype option on import or set low_memory=False.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n"
      ]
     },
@@ -429,7 +922,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_1173/2987234667.py:8: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
+      "/tmp/ipykernel_430/3170175140.py:10: FutureWarning: The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.\n",
       "  df = pd.read_csv(file_in, sep=\",\", parse_dates = datetime_col, date_parser=custom_date_parser)\n",
       "<string>:27: SettingWithCopyWarning: \n",
       "A value is trying to be set on a copy of a slice from a DataFrame\n",
@@ -642,164 +1135,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 1,
    "id": "b9b6ec1f-36fb-4ee9-a1ed-09ff41878005",
    "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>customer_id</th>\n",
-       "      <th>street_id</th>\n",
-       "      <th>structure_id</th>\n",
-       "      <th>mcp_contact_id</th>\n",
-       "      <th>fidelity</th>\n",
-       "      <th>tenant_id</th>\n",
-       "      <th>is_partner</th>\n",
-       "      <th>deleted_at</th>\n",
-       "      <th>gender</th>\n",
-       "      <th>is_email_true</th>\n",
-       "      <th>...</th>\n",
-       "      <th>purchase_count</th>\n",
-       "      <th>first_buying_date</th>\n",
-       "      <th>country</th>\n",
-       "      <th>gender_label</th>\n",
-       "      <th>gender_female</th>\n",
-       "      <th>gender_male</th>\n",
-       "      <th>gender_other</th>\n",
-       "      <th>country_fr</th>\n",
-       "      <th>has_tags</th>\n",
-       "      <th>number_compagny</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>74896</th>\n",
-       "      <td>1</td>\n",
-       "      <td>139</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0</td>\n",
-       "      <td>875</td>\n",
-       "      <td>False</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2</td>\n",
-       "      <td>False</td>\n",
-       "      <td>...</td>\n",
-       "      <td>19</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>other</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0</td>\n",
-       "      <td>10</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>53006</th>\n",
-       "      <td>1</td>\n",
-       "      <td>312707</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1556</td>\n",
-       "      <td>False</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0</td>\n",
-       "      <td>True</td>\n",
-       "      <td>...</td>\n",
-       "      <td>10</td>\n",
-       "      <td>2018-12-26 13:06:49+00:00</td>\n",
-       "      <td>fr</td>\n",
-       "      <td>female</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>11</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>142042</th>\n",
-       "      <td>1</td>\n",
-       "      <td>2772</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>3954.0</td>\n",
-       "      <td>2</td>\n",
-       "      <td>862</td>\n",
-       "      <td>False</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>2</td>\n",
-       "      <td>True</td>\n",
-       "      <td>...</td>\n",
-       "      <td>2</td>\n",
-       "      <td>2016-09-09 17:02:00+00:00</td>\n",
-       "      <td>fr</td>\n",
-       "      <td>other</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>14</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>3 rows × 29 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "        customer_id  street_id  structure_id  mcp_contact_id  fidelity  \\\n",
-       "74896             1        139           NaN             NaN         0   \n",
-       "53006             1     312707           NaN             NaN         0   \n",
-       "142042            1       2772           NaN          3954.0         2   \n",
-       "\n",
-       "        tenant_id  is_partner  deleted_at  gender  is_email_true  ...  \\\n",
-       "74896         875       False         NaN       2          False  ...   \n",
-       "53006        1556       False         NaN       0           True  ...   \n",
-       "142042        862       False         NaN       2           True  ...   \n",
-       "\n",
-       "        purchase_count          first_buying_date  country  gender_label  \\\n",
-       "74896               19                        NaN      NaN         other   \n",
-       "53006               10  2018-12-26 13:06:49+00:00       fr        female   \n",
-       "142042               2  2016-09-09 17:02:00+00:00       fr         other   \n",
-       "\n",
-       "        gender_female  gender_male  gender_other  country_fr  has_tags  \\\n",
-       "74896               0            0             1         NaN         0   \n",
-       "53006               1            0             0         1.0         0   \n",
-       "142042              0            0             1         1.0         0   \n",
-       "\n",
-       "        number_compagny  \n",
-       "74896                10  \n",
-       "53006                11  \n",
-       "142042               14  \n",
-       "\n",
-       "[3 rows x 29 columns]"
-      ]
-     },
-     "execution_count": 38,
-     "metadata": {},
-     "output_type": "execute_result"
+     "ename": "NameError",
+     "evalue": "name 'customerplus_clean_spectacle' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[1], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mcustomerplus_clean_spectacle\u001b[49m[customerplus_clean_spectacle[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcustomer_id\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m==\u001b[39m\u001b[38;5;241m1\u001b[39m]\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'customerplus_clean_spectacle' is not defined"
+     ]
     }
    ],
    "source": [
@@ -3465,7 +3814,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 223,
+   "execution_count": 8,
    "id": "74534ded-8121-43fb-8cf8-af353bed2c77",
    "metadata": {},
    "outputs": [
@@ -3493,7 +3842,7 @@
        "dtype: int64"
       ]
      },
-     "execution_count": 223,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3651,6 +4000,20 @@
     "products_purchased_reduced_spectacle.head()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e1a95b8f-6539-48bd-b09d-6f8f63d25fb2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#nombre de ticket par compagnie\n",
+    "\n",
+    "company_campaigns_stats = campaigns_information_spectacle.groupby(\"number_compagny\")[[\"nb_campaigns\", \"nb_campaigns_opened\"]].sum().reset_index()\n",
+    "company_campaigns_stats[\"ratio_campaigns_opened\"] = company_campaigns_stats[\"nb_campaigns_opened\"]  / company_campaigns_stats[\"nb_campaigns\"]\n",
+    "company_campaigns_stats"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "b9e84af4-a02b-4f83-81ae-b7a73475d060",
@@ -3694,6 +4057,193 @@
     "print(\"Nombre de lignes de la table : \",target_information_spectacle.shape[0])\n",
     "target_information_spectacle.isna().sum()"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "985b6403-3c75-420e-a4a4-d3045213e9ef",
+   "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>id</th>\n",
+       "      <th>customer_id</th>\n",
+       "      <th>target_name</th>\n",
+       "      <th>target_type_is_import</th>\n",
+       "      <th>target_type_name</th>\n",
+       "      <th>number_compagny</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1165098</td>\n",
+       "      <td>618562</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "      <td>10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1165100</td>\n",
+       "      <td>618559</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "      <td>10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1165101</td>\n",
+       "      <td>618561</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "      <td>10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1165102</td>\n",
+       "      <td>618560</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "      <td>10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1165103</td>\n",
+       "      <td>618558</td>\n",
+       "      <td>Newsletter mensuelle</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "      <td>10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>779653</th>\n",
+       "      <td>4207082</td>\n",
+       "      <td>6764876</td>\n",
+       "      <td>INSCRIPTION NL VOYAGES HUMA</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "      <td>14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>779654</th>\n",
+       "      <td>4207083</td>\n",
+       "      <td>6764877</td>\n",
+       "      <td>Inscriptions newsletters (depuis 2019)</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "      <td>14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>779655</th>\n",
+       "      <td>4207084</td>\n",
+       "      <td>6801322</td>\n",
+       "      <td>Inscriptions newsletters (depuis 2019)</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "      <td>14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>779656</th>\n",
+       "      <td>4207085</td>\n",
+       "      <td>6837768</td>\n",
+       "      <td>Inscriptions newsletters (depuis 2019)</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "      <td>14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>779657</th>\n",
+       "      <td>4207086</td>\n",
+       "      <td>6837769</td>\n",
+       "      <td>Inscriptions newsletters (depuis 2019)</td>\n",
+       "      <td>False</td>\n",
+       "      <td>manual_static_filter</td>\n",
+       "      <td>14</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>6240166 rows × 6 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             id  customer_id                             target_name  \\\n",
+       "0       1165098       618562                    Newsletter mensuelle   \n",
+       "1       1165100       618559                    Newsletter mensuelle   \n",
+       "2       1165101       618561                    Newsletter mensuelle   \n",
+       "3       1165102       618560                    Newsletter mensuelle   \n",
+       "4       1165103       618558                    Newsletter mensuelle   \n",
+       "...         ...          ...                                     ...   \n",
+       "779653  4207082      6764876             INSCRIPTION NL VOYAGES HUMA   \n",
+       "779654  4207083      6764877  Inscriptions newsletters (depuis 2019)   \n",
+       "779655  4207084      6801322  Inscriptions newsletters (depuis 2019)   \n",
+       "779656  4207085      6837768  Inscriptions newsletters (depuis 2019)   \n",
+       "779657  4207086      6837769  Inscriptions newsletters (depuis 2019)   \n",
+       "\n",
+       "        target_type_is_import      target_type_name  number_compagny  \n",
+       "0                       False  manual_static_filter               10  \n",
+       "1                       False  manual_static_filter               10  \n",
+       "2                       False  manual_static_filter               10  \n",
+       "3                       False  manual_static_filter               10  \n",
+       "4                       False  manual_static_filter               10  \n",
+       "...                       ...                   ...              ...  \n",
+       "779653                  False  manual_static_filter               14  \n",
+       "779654                  False  manual_static_filter               14  \n",
+       "779655                  False  manual_static_filter               14  \n",
+       "779656                  False  manual_static_filter               14  \n",
+       "779657                  False  manual_static_filter               14  \n",
+       "\n",
+       "[6240166 rows x 6 columns]"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "target_information_spectacle"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0a180f0a-c6de-4e66-9ae8-fdbfdf8837c9",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
diff --git a/code_base_train_test.ipynb b/code_base_train_test.ipynb
new file mode 100644
index 0000000..b7e6578
--- /dev/null
+++ b/code_base_train_test.ipynb
@@ -0,0 +1,814 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "bf34b03c-536f-4f93-93a5-e452552653aa",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Choisissez le type de compagnie : sport ? musique ? musee ? musique\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "File path :  projet-bdc2324-team1/0_Input/Company_10/products_purchased_reduced.csv\n",
+      "Couverture Company 10 : 2016-03-07 - 2023-09-25\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_11/products_purchased_reduced.csv\n",
+      "Couverture Company 11 : 2015-06-26 - 2023-11-08\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_12/products_purchased_reduced.csv\n",
+      "Couverture Company 12 : 2016-06-14 - 2023-11-08\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_13/products_purchased_reduced.csv\n",
+      "Couverture Company 13 : 2010-07-31 - 2023-11-08\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_14/products_purchased_reduced.csv\n",
+      "Couverture Company 14 : 1901-01-01 - 2023-11-08\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_10/customerplus_cleaned.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_10/campaigns_information.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_10/products_purchased_reduced.csv\n",
+      "Data filtering : SUCCESS\n",
+      "KPIs construction : SUCCESS\n",
+      "Explanatory variable construction : SUCCESS\n",
+      "Explained variable construction : SUCCESS\n",
+      "Exportation dataset test : SUCCESS\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_10/customerplus_cleaned.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_10/campaigns_information.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_10/products_purchased_reduced.csv\n",
+      "Data filtering : SUCCESS\n",
+      "KPIs construction : SUCCESS\n",
+      "Explanatory variable construction : SUCCESS\n",
+      "Explained variable construction : SUCCESS\n",
+      "Exportation dataset train : SUCCESS\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_11/customerplus_cleaned.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_11/campaigns_information.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_11/products_purchased_reduced.csv\n",
+      "Data filtering : SUCCESS\n",
+      "KPIs construction : SUCCESS\n",
+      "Explanatory variable construction : SUCCESS\n",
+      "Explained variable construction : SUCCESS\n",
+      "Exportation dataset test : SUCCESS\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_11/customerplus_cleaned.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_11/campaigns_information.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_11/products_purchased_reduced.csv\n",
+      "Data filtering : SUCCESS\n",
+      "KPIs construction : SUCCESS\n",
+      "Explanatory variable construction : SUCCESS\n",
+      "Explained variable construction : SUCCESS\n",
+      "Exportation dataset train : SUCCESS\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_12/customerplus_cleaned.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_12/campaigns_information.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_12/products_purchased_reduced.csv\n",
+      "Data filtering : SUCCESS\n",
+      "KPIs construction : SUCCESS\n",
+      "Explanatory variable construction : SUCCESS\n",
+      "Explained variable construction : SUCCESS\n",
+      "Exportation dataset test : SUCCESS\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_12/customerplus_cleaned.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_12/campaigns_information.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_12/products_purchased_reduced.csv\n",
+      "Data filtering : SUCCESS\n",
+      "KPIs construction : SUCCESS\n",
+      "Explanatory variable construction : SUCCESS\n",
+      "Explained variable construction : SUCCESS\n",
+      "Exportation dataset train : SUCCESS\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_13/customerplus_cleaned.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_13/campaigns_information.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_13/products_purchased_reduced.csv\n",
+      "Data filtering : SUCCESS\n",
+      "KPIs construction : SUCCESS\n",
+      "Explanatory variable construction : SUCCESS\n",
+      "Explained variable construction : SUCCESS\n",
+      "Exportation dataset test : SUCCESS\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_13/customerplus_cleaned.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_13/campaigns_information.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_13/products_purchased_reduced.csv\n",
+      "Data filtering : SUCCESS\n",
+      "KPIs construction : SUCCESS\n",
+      "Explanatory variable construction : SUCCESS\n",
+      "Explained variable construction : SUCCESS\n",
+      "Exportation dataset train : SUCCESS\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_14/customerplus_cleaned.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_14/campaigns_information.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_14/products_purchased_reduced.csv\n",
+      "Data filtering : SUCCESS\n",
+      "KPIs construction : SUCCESS\n",
+      "Explanatory variable construction : SUCCESS\n",
+      "Explained variable construction : SUCCESS\n",
+      "Exportation dataset test : SUCCESS\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_14/customerplus_cleaned.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_14/campaigns_information.csv\n",
+      "File path :  projet-bdc2324-team1/0_Input/Company_14/products_purchased_reduced.csv\n",
+      "Data filtering : SUCCESS\n",
+      "KPIs construction : SUCCESS\n",
+      "Explanatory variable construction : SUCCESS\n",
+      "Explained variable construction : SUCCESS\n",
+      "Exportation dataset train : SUCCESS\n",
+      "FIN DE LA GENERATION DES DATASETS : SUCCESS\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Business Data Challenge - Team 1\n",
+    "\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import os\n",
+    "import s3fs\n",
+    "import re\n",
+    "import warnings\n",
+    "from datetime import date, timedelta, datetime\n",
+    "\n",
+    "# Create filesystem object\n",
+    "S3_ENDPOINT_URL = \"https://\" + os.environ[\"AWS_S3_ENDPOINT\"]\n",
+    "fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': S3_ENDPOINT_URL})\n",
+    "\n",
+    "\n",
+    "# Import KPI construction functions\n",
+    "exec(open('0_KPI_functions.py').read())\n",
+    "\n",
+    "# Ignore warning\n",
+    "warnings.filterwarnings('ignore')\n",
+    "\n",
+    "\n",
+    "def display_covering_time(df, company, datecover):\n",
+    "    \"\"\"\n",
+    "    This function draws the time coverage of each company\n",
+    "    \"\"\"\n",
+    "    min_date = df['purchase_date'].min().strftime(\"%Y-%m-%d\")\n",
+    "    max_date = df['purchase_date'].max().strftime(\"%Y-%m-%d\")\n",
+    "    datecover[company] = [datetime.strptime(min_date, \"%Y-%m-%d\") + timedelta(days=x) for x in range((datetime.strptime(max_date, \"%Y-%m-%d\") - datetime.strptime(min_date, \"%Y-%m-%d\")).days)]\n",
+    "    print(f'Couverture Company {company} : {min_date} - {max_date}')\n",
+    "    return datecover\n",
+    "\n",
+    "\n",
+    "def compute_time_intersection(datecover):\n",
+    "    \"\"\"\n",
+    "    This function returns the time coverage for all companies\n",
+    "    \"\"\"\n",
+    "    timestamps_sets = [set(timestamps) for timestamps in datecover.values()]\n",
+    "    intersection = set.intersection(*timestamps_sets)\n",
+    "    intersection_list = list(intersection)\n",
+    "    formated_dates = [dt.strftime(\"%Y-%m-%d\") for dt in intersection_list]\n",
+    "    return sorted(formated_dates)\n",
+    "\n",
+    "\n",
+    "def df_coverage_modelization(sport, coverage_train = 0.7):\n",
+    "    \"\"\"\n",
+    "    This function returns start_date, end_of_features and final dates\n",
+    "    that help to construct train and test datasets\n",
+    "    \"\"\"\n",
+    "    datecover = {}\n",
+    "    for company in sport:\n",
+    "        df_products_purchased_reduced = display_databases(company, file_name = \"products_purchased_reduced\",\n",
+    "                                                          datetime_col = ['purchase_date'])\n",
+    "        datecover = display_covering_time(df_products_purchased_reduced, company, datecover)\n",
+    "    #print(datecover.keys())\n",
+    "    dt_coverage = compute_time_intersection(datecover)\n",
+    "    start_date = dt_coverage[0]\n",
+    "    end_of_features = dt_coverage[int(0.7 * len(dt_coverage))]\n",
+    "    final_date = dt_coverage[-1]\n",
+    "    return start_date, end_of_features, final_date\n",
+    "    \n",
+    "\n",
+    "def dataset_construction(min_date, end_features_date, max_date, directory_path):\n",
+    "    \n",
+    "    # Import customerplus\n",
+    "    df_customerplus_clean_0 = display_databases(directory_path, file_name = \"customerplus_cleaned\")\n",
+    "    df_campaigns_information = display_databases(directory_path, file_name = \"campaigns_information\", datetime_col = ['opened_at', 'sent_at', 'campaign_sent_at'])\n",
+    "    df_products_purchased_reduced = display_databases(directory_path, file_name = \"products_purchased_reduced\", datetime_col = ['purchase_date'])\n",
+    "    \n",
+    "    # Filtre de cohérence pour la mise en pratique de notre méthode\n",
+    "    max_date =  pd.to_datetime(max_date, utc = True, format = 'ISO8601') \n",
+    "    end_features_date = pd.to_datetime(end_features_date, utc = True, format = 'ISO8601')\n",
+    "    min_date = pd.to_datetime(min_date, utc = True, format = 'ISO8601')\n",
+    "\n",
+    "    #Filtre de la base df_campaigns_information\n",
+    "    df_campaigns_information = df_campaigns_information[(df_campaigns_information['sent_at'] <= end_features_date) & (df_campaigns_information['sent_at'] >= min_date)]\n",
+    "    df_campaigns_information['opened_at'][df_campaigns_information['opened_at'] >= end_features_date] = np.datetime64('NaT')\n",
+    "    \n",
+    "    #Filtre de la base df_products_purchased_reduced\n",
+    "    df_products_purchased_reduced = df_products_purchased_reduced[(df_products_purchased_reduced['purchase_date'] <= end_features_date) & (df_products_purchased_reduced['purchase_date'] >= min_date)]\n",
+    "\n",
+    "    print(\"Data filtering : SUCCESS\")\n",
+    "    \n",
+    "    # Fusion de l'ensemble et creation des KPI\n",
+    "\n",
+    "    # KPI sur les campagnes publicitaires\n",
+    "    df_campaigns_kpi = campaigns_kpi_function(campaigns_information = df_campaigns_information) \n",
+    "\n",
+    "    # KPI sur le comportement d'achat\n",
+    "    df_tickets_kpi = tickets_kpi_function(tickets_information = df_products_purchased_reduced)\n",
+    "\n",
+    "    # KPI sur les données socio-démographiques\n",
+    "    df_customerplus_clean = customerplus_kpi_function(customerplus_clean = df_customerplus_clean_0)\n",
+    "    \n",
+    "    print(\"KPIs construction : SUCCESS\")\n",
+    "    \n",
+    "    # Fusion avec KPI liés au customer\n",
+    "    df_customer = pd.merge(df_customerplus_clean, df_campaigns_kpi, on = 'customer_id', how = 'left')\n",
+    "    \n",
+    "    # Fill NaN values\n",
+    "    df_customer[['nb_campaigns', 'nb_campaigns_opened']] = df_customer[['nb_campaigns', 'nb_campaigns_opened']].fillna(0)\n",
+    "    \n",
+    "    # Fusion avec KPI liés au comportement d'achat\n",
+    "    df_customer_product = pd.merge(df_tickets_kpi, df_customer, on = 'customer_id', how = 'outer')\n",
+    "    \n",
+    "    # Fill NaN values\n",
+    "    df_customer_product[['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'vente_internet_max', 'nb_tickets_internet']] = df_customer_product[['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'vente_internet_max', 'nb_tickets_internet']].fillna(0)\n",
+    "\n",
+    "    print(\"Explanatory variable construction : SUCCESS\")\n",
+    "\n",
+    "    # 2. Construction of the explained variable \n",
+    "    df_products_purchased_to_predict = df_products_purchased_reduced[(df_products_purchased_reduced['purchase_date'] <= max_date) & (df_products_purchased_reduced['purchase_date'] > end_features_date)]\n",
+    "\n",
+    "    # Indicatrice d'achat\n",
+    "    df_products_purchased_to_predict['y_has_purchased'] = 1\n",
+    "\n",
+    "    y = df_products_purchased_to_predict[['customer_id', 'y_has_purchased']].drop_duplicates()\n",
+    "\n",
+    "    print(\"Explained variable construction : SUCCESS\")\n",
+    "    \n",
+    "    # 3. Merge between explained and explanatory variables\n",
+    "    dataset = pd.merge(df_customer_product, y, on = ['customer_id'], how = 'left')\n",
+    "\n",
+    "    # 0 if there is no purchase\n",
+    "    dataset[['y_has_purchased']].fillna(0)\n",
+    "\n",
+    "    # add id_company prefix to customer_id\n",
+    "    dataset['customer_id'] = directory_path + '_' + dataset['customer_id'].astype('str')\n",
+    "    \n",
+    "    return dataset\n",
+    "\n",
+    "## Exportation\n",
+    "\n",
+    "companies = {'musee' : ['1', '2', '3', '4', '101'],\n",
+    "            'sport': ['5', '6', '7', '8', '9'],\n",
+    "            'musique' : ['10', '11', '12', '13', '14']}\n",
+    "\n",
+    "type_of_comp = input('Choisissez le type de compagnie : sport ? musique ? musee ?')\n",
+    "list_of_comp = companies[type_of_comp] \n",
+    "# Dossier d'exportation\n",
+    "BUCKET_OUT = f'projet-bdc2324-team1/Generalization/{type_of_comp}'\n",
+    "\n",
+    "# Create test dataset and train dataset for sport companies\n",
+    "\n",
+    "start_date, end_of_features, final_date = df_coverage_modelization(list_of_comp, coverage_train = 0.7)\n",
+    "\n",
+    "for company in list_of_comp:\n",
+    "    dataset_test = dataset_construction(min_date = start_date, end_features_date = end_of_features,\n",
+    "                                        max_date = final_date, directory_path = company)    \n",
+    "\n",
+    "    # Exportation\n",
+    "    FILE_KEY_OUT_S3 = \"dataset_test\" + company +  \".csv\"\n",
+    "    FILE_PATH_OUT_S3 = BUCKET_OUT + \"/Test_set/\" + FILE_KEY_OUT_S3\n",
+    "    \n",
+    "    with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:\n",
+    "        dataset_test.to_csv(file_out, index = False)\n",
+    "    \n",
+    "    print(\"Exportation dataset test : SUCCESS\")\n",
+    "\n",
+    "# Dataset train\n",
+    "    dataset_train = dataset_construction(min_date = start_date, end_features_date = end_of_features,\n",
+    "                                        max_date = final_date, directory_path = company)\n",
+    "    # Export\n",
+    "    FILE_KEY_OUT_S3 = \"dataset_train\" + company + \".csv\" \n",
+    "    FILE_PATH_OUT_S3 = BUCKET_OUT + \"/Train_test/\" + FILE_KEY_OUT_S3\n",
+    "    \n",
+    "    with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:\n",
+    "        dataset_train.to_csv(file_out, index = False)\n",
+    "        \n",
+    "    print(\"Exportation dataset train : SUCCESS\")\n",
+    "\n",
+    "\n",
+    "print(\"FIN DE LA GENERATION DES DATASETS : SUCCESS\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "3721427e-5957-4556-b278-2e7ffca892f4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'projet-bdc2324-team1/Generalization/musique/Train_test/dataset_train14.csv'"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "FILE_PATH_OUT_S3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "a3bfeeb6-2db0-4f1d-866c-8721343e97c5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer_id               0.000000\n",
+       "nb_tickets                0.000000\n",
+       "nb_purchases              0.000000\n",
+       "total_amount              0.000000\n",
+       "nb_suppliers              0.000000\n",
+       "vente_internet_max        0.000000\n",
+       "purchase_date_min         0.858950\n",
+       "purchase_date_max         0.858950\n",
+       "time_between_purchase     0.858950\n",
+       "nb_tickets_internet       0.000000\n",
+       "street_id                 0.000000\n",
+       "structure_id              0.869838\n",
+       "mcp_contact_id            0.276677\n",
+       "fidelity                  0.000000\n",
+       "tenant_id                 0.000000\n",
+       "is_partner                0.000000\n",
+       "deleted_at                1.000000\n",
+       "gender                    0.000000\n",
+       "is_email_true             0.000000\n",
+       "opt_in                    0.000000\n",
+       "last_buying_date          0.709626\n",
+       "max_price                 0.709626\n",
+       "ticket_sum                0.000000\n",
+       "average_price             0.709626\n",
+       "average_purchase_delay    0.709731\n",
+       "average_price_basket      0.709731\n",
+       "average_ticket_basket     0.709731\n",
+       "total_price               0.000000\n",
+       "purchase_count            0.000000\n",
+       "first_buying_date         0.709626\n",
+       "country                   0.152090\n",
+       "gender_label              0.000000\n",
+       "gender_female             0.000000\n",
+       "gender_male               0.000000\n",
+       "gender_other              0.000000\n",
+       "country_fr                0.152090\n",
+       "has_tags                  0.000000\n",
+       "nb_campaigns              0.000000\n",
+       "nb_campaigns_opened       0.000000\n",
+       "time_to_open              0.848079\n",
+       "y_has_purchased           1.000000\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    " dataset_train.isna().sum()/dataset_train.shape[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "a4c4e994-231b-4467-aa1b-0a5283c59dd5",
+   "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>customer_id</th>\n",
+       "      <th>nb_tickets</th>\n",
+       "      <th>nb_purchases</th>\n",
+       "      <th>total_amount</th>\n",
+       "      <th>nb_suppliers</th>\n",
+       "      <th>vente_internet_max</th>\n",
+       "      <th>purchase_date_min</th>\n",
+       "      <th>purchase_date_max</th>\n",
+       "      <th>time_between_purchase</th>\n",
+       "      <th>nb_tickets_internet</th>\n",
+       "      <th>...</th>\n",
+       "      <th>gender_label</th>\n",
+       "      <th>gender_female</th>\n",
+       "      <th>gender_male</th>\n",
+       "      <th>gender_other</th>\n",
+       "      <th>country_fr</th>\n",
+       "      <th>has_tags</th>\n",
+       "      <th>nb_campaigns</th>\n",
+       "      <th>nb_campaigns_opened</th>\n",
+       "      <th>time_to_open</th>\n",
+       "      <th>y_has_purchased</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>14_1</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>70.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1464.938449</td>\n",
+       "      <td>1464.938021</td>\n",
+       "      <td>0.000428</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>other</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0 days 00:36:13</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>14_2</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>145.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1466.030116</td>\n",
+       "      <td>365.335000</td>\n",
+       "      <td>1100.695116</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>male</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>0 days 02:30:09.250000</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>14_3</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>70.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1476.907894</td>\n",
+       "      <td>1476.907662</td>\n",
+       "      <td>0.000231</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>female</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0 days 20:58:45</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>14_4</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>32.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1465.907894</td>\n",
+       "      <td>1465.907465</td>\n",
+       "      <td>0.000428</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>male</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaT</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>14_5</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>70.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1465.373866</td>\n",
+       "      <td>1465.373819</td>\n",
+       "      <td>0.000046</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>female</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaT</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>343121</th>\n",
+       "      <td>14_6884748</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>male</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaT</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>343122</th>\n",
+       "      <td>14_6884749</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>male</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaT</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>343123</th>\n",
+       "      <td>14_6884750</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>male</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaT</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>343124</th>\n",
+       "      <td>14_6884751</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>female</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaT</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>343125</th>\n",
+       "      <td>14_6884753</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>male</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaT</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>343126 rows × 41 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       customer_id  nb_tickets  nb_purchases  total_amount  nb_suppliers  \\\n",
+       "0             14_1         2.0           2.0          70.0           1.0   \n",
+       "1             14_2         7.0           3.0         145.0           2.0   \n",
+       "2             14_3         2.0           2.0          70.0           1.0   \n",
+       "3             14_4         2.0           2.0          32.0           1.0   \n",
+       "4             14_5         2.0           2.0          70.0           1.0   \n",
+       "...            ...         ...           ...           ...           ...   \n",
+       "343121  14_6884748         0.0           0.0           0.0           0.0   \n",
+       "343122  14_6884749         0.0           0.0           0.0           0.0   \n",
+       "343123  14_6884750         0.0           0.0           0.0           0.0   \n",
+       "343124  14_6884751         0.0           0.0           0.0           0.0   \n",
+       "343125  14_6884753         0.0           0.0           0.0           0.0   \n",
+       "\n",
+       "        vente_internet_max  purchase_date_min  purchase_date_max  \\\n",
+       "0                      1.0        1464.938449        1464.938021   \n",
+       "1                      1.0        1466.030116         365.335000   \n",
+       "2                      1.0        1476.907894        1476.907662   \n",
+       "3                      1.0        1465.907894        1465.907465   \n",
+       "4                      1.0        1465.373866        1465.373819   \n",
+       "...                    ...                ...                ...   \n",
+       "343121                 0.0                NaN                NaN   \n",
+       "343122                 0.0                NaN                NaN   \n",
+       "343123                 0.0                NaN                NaN   \n",
+       "343124                 0.0                NaN                NaN   \n",
+       "343125                 0.0                NaN                NaN   \n",
+       "\n",
+       "        time_between_purchase  nb_tickets_internet  ...  gender_label  \\\n",
+       "0                    0.000428                  2.0  ...         other   \n",
+       "1                 1100.695116                  7.0  ...          male   \n",
+       "2                    0.000231                  2.0  ...        female   \n",
+       "3                    0.000428                  2.0  ...          male   \n",
+       "4                    0.000046                  2.0  ...        female   \n",
+       "...                       ...                  ...  ...           ...   \n",
+       "343121                    NaN                  0.0  ...          male   \n",
+       "343122                    NaN                  0.0  ...          male   \n",
+       "343123                    NaN                  0.0  ...          male   \n",
+       "343124                    NaN                  0.0  ...        female   \n",
+       "343125                    NaN                  0.0  ...          male   \n",
+       "\n",
+       "        gender_female  gender_male  gender_other  country_fr  has_tags  \\\n",
+       "0                   0            0             1         1.0         0   \n",
+       "1                   0            1             0         1.0         1   \n",
+       "2                   1            0             0         1.0         0   \n",
+       "3                   0            1             0         1.0         0   \n",
+       "4                   1            0             0         1.0         0   \n",
+       "...               ...          ...           ...         ...       ...   \n",
+       "343121              0            1             0         1.0         0   \n",
+       "343122              0            1             0         1.0         0   \n",
+       "343123              0            1             0         1.0         0   \n",
+       "343124              1            0             0         1.0         0   \n",
+       "343125              0            1             0         1.0         0   \n",
+       "\n",
+       "        nb_campaigns  nb_campaigns_opened           time_to_open  \\\n",
+       "0                9.0                  1.0        0 days 00:36:13   \n",
+       "1                9.0                  4.0 0 days 02:30:09.250000   \n",
+       "2                6.0                  1.0        0 days 20:58:45   \n",
+       "3                6.0                  0.0                    NaT   \n",
+       "4                7.0                  0.0                    NaT   \n",
+       "...              ...                  ...                    ...   \n",
+       "343121           0.0                  0.0                    NaT   \n",
+       "343122           0.0                  0.0                    NaT   \n",
+       "343123           0.0                  0.0                    NaT   \n",
+       "343124           0.0                  0.0                    NaT   \n",
+       "343125           0.0                  0.0                    NaT   \n",
+       "\n",
+       "        y_has_purchased  \n",
+       "0                   NaN  \n",
+       "1                   NaN  \n",
+       "2                   NaN  \n",
+       "3                   NaN  \n",
+       "4                   NaN  \n",
+       "...                 ...  \n",
+       "343121              NaN  \n",
+       "343122              NaN  \n",
+       "343123              NaN  \n",
+       "343124              NaN  \n",
+       "343125              NaN  \n",
+       "\n",
+       "[343126 rows x 41 columns]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dataset_test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "75f9a672-641f-49a2-a8d6-7673845506f5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}