Nettoyage

This commit is contained in:
Antoine JOUBREL 2024-02-10 13:25:12 +00:00
parent c682d436b8
commit a83055cc48

View File

@ -2345,8 +2345,8 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 76, "execution_count": 77,
"id": "c78f5ade-c721-49d9-a474-73c217686ed1", "id": "a7a452a6-cd5e-4c8b-b250-8a7d26e48fad",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -2395,323 +2395,460 @@
" <td>3053.0</td>\n", " <td>3053.0</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>1</th>\n", " <th>3615</th>\n",
" <td>6733</td>\n",
" <td>35527</td>\n",
" <td>1188.0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>2015-09-09 13:48:38+00:00</td>\n",
" <td>2023-11-03 09:42:40+00:00</td>\n",
" <td>2976 days 19:54:02</td>\n",
" <td>30896.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>41</td>\n",
" <td>16263</td>\n",
" <td>37642.0</td>\n",
" <td>6</td>\n",
" <td>1</td>\n",
" <td>2014-01-23 16:56:57+00:00</td>\n",
" <td>2023-10-25 09:13:16+00:00</td>\n",
" <td>3561 days 16:16:19</td>\n",
" <td>13993.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>12</td>\n",
" <td>5871</td>\n",
" <td>38767.0</td>\n",
" <td>2</td>\n", " <td>2</td>\n",
" <td>307</td>\n", " <td>1</td>\n",
" <td>2018-04-04 07:46:31+00:00</td>\n",
" <td>2023-11-04 13:46:59+00:00</td>\n",
" <td>2040 days 06:00:28</td>\n",
" <td>167.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32809</th>\n",
" <td>63488</td>\n",
" <td>5851</td>\n",
" <td>64350.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2020-08-18 08:32:57+00:00</td>\n",
" <td>2022-08-25 13:08:38+00:00</td>\n",
" <td>737 days 04:35:41</td>\n",
" <td>5851.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3708</th>\n",
" <td>6916</td>\n",
" <td>5482</td>\n",
" <td>51489.5</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2018-03-26 11:13:43+00:00</td>\n",
" <td>2021-08-26 12:49:17+00:00</td>\n",
" <td>1249 days 01:35:34</td>\n",
" <td>5481.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32616</th>\n",
" <td>63194</td>\n",
" <td>4507</td>\n",
" <td>13232.0</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>2017-11-28 13:52:15+00:00</td>\n",
" <td>2022-09-07 12:55:33+00:00</td>\n",
" <td>1743 days 23:03:18</td>\n",
" <td>826.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>78</th>\n",
" <td>81</td>\n",
" <td>3562</td>\n",
" <td>38746.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2017-01-05 13:04:58+00:00</td>\n",
" <td>2022-08-30 11:51:34+00:00</td>\n",
" <td>2062 days 22:46:36</td>\n",
" <td>3562.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>35295</th>\n",
" <td>84002</td>\n",
" <td>3403</td>\n",
" <td>19830.0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>2021-05-28 10:22:33+00:00</td>\n",
" <td>2023-11-06 15:59:22+00:00</td>\n",
" <td>892 days 05:36:49</td>\n",
" <td>869.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3377</th>\n",
" <td>5618</td>\n",
" <td>3294</td>\n",
" <td>31684.5</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2018-10-25 11:04:24+00:00</td>\n",
" <td>2022-02-24 07:47:20+00:00</td>\n",
" <td>1217 days 20:42:56</td>\n",
" <td>3294.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30011</th>\n",
" <td>59259</td>\n",
" <td>2591</td>\n",
" <td>4350.0</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>2019-11-25 08:52:48+00:00</td>\n",
" <td>2023-06-12 14:05:19+00:00</td>\n",
" <td>1295 days 05:12:31</td>\n",
" <td>52.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>34937</th>\n",
" <td>74876</td>\n",
" <td>2571</td>\n",
" <td>2600.0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2018-02-08 12:54:01+00:00</td>\n",
" <td>2023-10-02 08:13:05+00:00</td>\n",
" <td>2061 days 19:19:04</td>\n",
" <td>448.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>270</th>\n",
" <td>295</td>\n",
" <td>2570</td>\n",
" <td>17678.5</td>\n",
" <td>6</td>\n",
" <td>1</td>\n",
" <td>2014-01-24 15:16:17+00:00</td>\n",
" <td>2023-10-16 10:19:22+00:00</td>\n",
" <td>3551 days 19:03:05</td>\n",
" <td>1479.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>866</th>\n",
" <td>1221</td>\n",
" <td>2320</td>\n",
" <td>9652.0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2017-03-29 08:00:09+00:00</td>\n",
" <td>2022-09-19 12:55:15+00:00</td>\n",
" <td>2000 days 04:55:06</td>\n",
" <td>104.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1022</th>\n",
" <td>1429</td>\n",
" <td>2249</td>\n",
" <td>3500.0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>2014-12-03 14:56:38+00:00</td>\n",
" <td>2023-11-06 08:30:37+00:00</td>\n",
" <td>3259 days 17:33:59</td>\n",
" <td>690.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3922</th>\n",
" <td>7249</td>\n",
" <td>1827</td>\n",
" <td>13385.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2019-05-07 12:34:56+00:00</td>\n",
" <td>2021-10-26 12:28:40+00:00</td>\n",
" <td>902 days 23:53:44</td>\n",
" <td>1827.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>54425</th>\n",
" <td>1070539</td>\n",
" <td>1800</td>\n",
" <td>19800.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2022-05-02 16:09:03+00:00</td>\n",
" <td>2022-07-25 12:49:27+00:00</td>\n",
" <td>83 days 20:40:24</td>\n",
" <td>1800.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>69520</th>\n",
" <td>1216801</td>\n",
" <td>1623</td>\n",
" <td>12562.0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2023-06-16 14:16:04+00:00</td>\n",
" <td>2023-09-29 16:34:38+00:00</td>\n",
" <td>105 days 02:18:34</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30056</th>\n",
" <td>59330</td>\n",
" <td>1551</td>\n",
" <td>0.0</td>\n", " <td>0.0</td>\n",
" <td>1</td>\n", " <td>1</td>\n",
" <td>0</td>\n", " <td>0</td>\n",
" <td>2018-04-07 12:55:07+00:00</td>\n", " <td>2018-02-02 08:53:51+00:00</td>\n",
" <td>2020-03-08 12:06:43+00:00</td>\n", " <td>2023-11-06 10:22:14+00:00</td>\n",
" <td>700 days 23:11:36</td>\n", " <td>2103 days 01:28:23</td>\n",
" <td>0.0</td>\n", " <td>0.0</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>2</th>\n", " <th>3243</th>\n",
" <td>5441</td>\n",
" <td>1544</td>\n",
" <td>14133.0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2017-12-14 12:50:23+00:00</td>\n",
" <td>2022-09-22 08:21:47+00:00</td>\n",
" <td>1742 days 19:31:24</td>\n",
" <td>1384.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>55195</th>\n",
" <td>1084435</td>\n",
" <td>1500</td>\n",
" <td>16500.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2022-05-18 08:04:41+00:00</td>\n",
" <td>2022-09-27 14:32:13+00:00</td>\n",
" <td>132 days 06:27:32</td>\n",
" <td>1500.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28983</th>\n",
" <td>57816</td>\n",
" <td>1485</td>\n",
" <td>0.0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2019-01-21 14:19:18+00:00</td>\n",
" <td>2023-05-22 07:30:55+00:00</td>\n",
" <td>1581 days 17:11:37</td>\n",
" <td>357.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2231</th>\n",
" <td>2942</td>\n",
" <td>1307</td>\n",
" <td>100.0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2017-10-25 15:06:58+00:00</td>\n",
" <td>2023-06-29 09:33:58+00:00</td>\n",
" <td>2072 days 18:27:00</td>\n",
" <td>676.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>24</td>\n",
" <td>1266</td>\n",
" <td>0.0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2015-09-30 16:07:52+00:00</td>\n",
" <td>2023-10-19 07:20:48+00:00</td>\n",
" <td>2940 days 15:12:56</td>\n",
" <td>556.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4513</th>\n",
" <td>9592</td>\n",
" <td>1211</td>\n",
" <td>62.0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>2018-02-25 07:17:19+00:00</td>\n",
" <td>2023-10-17 09:39:40+00:00</td>\n",
" <td>2060 days 02:22:21</td>\n",
" <td>353.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2936</th>\n",
" <td>5059</td>\n",
" <td>1186</td>\n",
" <td>6308.0</td>\n",
" <td>3</td>\n", " <td>3</td>\n",
" <td>6</td>\n",
" <td>110.0</td>\n",
" <td>1</td>\n", " <td>1</td>\n",
" <td>1</td>\n", " <td>2018-02-01 11:16:51+00:00</td>\n",
" <td>2019-09-19 15:15:01+00:00</td>\n", " <td>2023-05-22 13:41:22+00:00</td>\n",
" <td>2023-09-27 09:13:09+00:00</td>\n", " <td>1936 days 02:24:31</td>\n",
" <td>1468 days 17:58:08</td>\n", " <td>1182.0</td>\n",
" <td>6.0</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>3</th>\n", " <th>11484</th>\n",
" <td>4</td>\n", " <td>25100</td>\n",
" <td>4</td>\n", " <td>1123</td>\n",
" <td>41.0</td>\n", " <td>0.0</td>\n",
" <td>1</td>\n", " <td>1</td>\n",
" <td>1</td>\n", " <td>1</td>\n",
" <td>2019-09-19 15:43:49+00:00</td>\n", " <td>2015-12-21 15:38:05+00:00</td>\n",
" <td>2021-09-02 18:42:19+00:00</td>\n", " <td>2021-07-13 07:39:57+00:00</td>\n",
" <td>714 days 02:58:30</td>\n", " <td>2030 days 16:01:52</td>\n",
" <td>4.0</td>\n", " <td>1123.0</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>4</th>\n", " <th>934</th>\n",
" <td>5</td>\n", " <td>1326</td>\n",
" <td>2</td>\n", " <td>1098</td>\n",
" <td>19.0</td>\n", " <td>798.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2019-09-19 15:45:36+00:00</td>\n",
" <td>2019-09-19 15:45:36+00:00</td>\n",
" <td>0 days 00:00:00</td>\n",
" <td>2.0</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",
" </tr>\n",
" <tr>\n",
" <th>73513</th>\n",
" <td>1256133</td>\n",
" <td>3</td>\n", " <td>3</td>\n",
" <td>33.0</td>\n",
" <td>1</td>\n", " <td>1</td>\n",
" <td>1</td>\n", " <td>2018-02-13 13:13:48+00:00</td>\n",
" <td>2023-11-08 16:51:19+00:00</td>\n", " <td>2023-02-01 08:39:45+00:00</td>\n",
" <td>2023-11-08 16:51:19+00:00</td>\n", " <td>1813 days 19:25:57</td>\n",
" <td>0 days 00:00:00</td>\n", " <td>266.0</td>\n",
" <td>3.0</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>73514</th>\n", " <th>30156</th>\n",
" <td>1256134</td>\n", " <td>59490</td>\n",
" <td>4</td>\n", " <td>1088</td>\n",
" <td>44.0</td>\n", " <td>0.0</td>\n",
" <td>1</td>\n", " <td>1</td>\n",
" <td>1</td>\n", " <td>0</td>\n",
" <td>2023-11-08 17:17:51+00:00</td>\n", " <td>2019-12-06 12:59:20+00:00</td>\n",
" <td>2023-11-08 17:17:51+00:00</td>\n", " <td>2023-10-05 08:23:50+00:00</td>\n",
" <td>0 days 00:00:00</td>\n", " <td>1398 days 19:24:30</td>\n",
" <td>4.0</td>\n", " <td>0.0</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>73515</th>\n", " <th>36478</th>\n",
" <td>1256135</td>\n", " <td>251268</td>\n",
" <td>1</td>\n", " <td>1086</td>\n",
" <td>11.0</td>\n", " <td>0.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2023-11-08 17:23:54+00:00</td>\n",
" <td>2023-11-08 17:23:54+00:00</td>\n",
" <td>0 days 00:00:00</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73516</th>\n",
" <td>1256136</td>\n",
" <td>2</td>\n", " <td>2</td>\n",
" <td>22.0</td>\n",
" <td>1</td>\n", " <td>1</td>\n",
" <td>1</td>\n", " <td>2018-02-02 09:06:22+00:00</td>\n",
" <td>2023-11-08 18:32:18+00:00</td>\n", " <td>2023-06-30 07:22:46+00:00</td>\n",
" <td>2023-11-08 18:32:18+00:00</td>\n", " <td>1973 days 22:16:24</td>\n",
" <td>0 days 00:00:00</td>\n", " <td>279.0</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73517</th>\n",
" <td>1256137</td>\n",
" <td>2</td>\n",
" <td>22.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2023-11-08 19:30:28+00:00</td>\n",
" <td>2023-11-08 19:30:28+00:00</td>\n",
" <td>0 days 00:00:00</td>\n",
" <td>2.0</td>\n",
" </tr>\n", " </tr>\n",
" </tbody>\n", " </tbody>\n",
"</table>\n", "</table>\n",
"<p>73518 rows × 9 columns</p>\n",
"</div>" "</div>"
], ],
"text/plain": [ "text/plain": [
" customer_id nb_tickets total_amount nb_suppliers \\\n", " customer_id nb_tickets total_amount nb_suppliers \\\n",
"0 1 1256574 8830567.5 7 \n", "0 1 1256574 8830567.5 7 \n",
"1 2 307 0.0 1 \n", "3615 6733 35527 1188.0 4 \n",
"2 3 6 110.0 1 \n", "39 41 16263 37642.0 6 \n",
"3 4 4 41.0 1 \n", "11 12 5871 38767.0 2 \n",
"4 5 2 19.0 1 \n", "32809 63488 5851 64350.0 1 \n",
"... ... ... ... ... \n", "3708 6916 5482 51489.5 2 \n",
"73513 1256133 3 33.0 1 \n", "32616 63194 4507 13232.0 3 \n",
"73514 1256134 4 44.0 1 \n", "78 81 3562 38746.0 1 \n",
"73515 1256135 1 11.0 1 \n", "35295 84002 3403 19830.0 4 \n",
"73516 1256136 2 22.0 1 \n", "3377 5618 3294 31684.5 1 \n",
"73517 1256137 2 22.0 1 \n", "30011 59259 2591 4350.0 3 \n",
"34937 74876 2571 2600.0 2 \n",
"270 295 2570 17678.5 6 \n",
"866 1221 2320 9652.0 2 \n",
"1022 1429 2249 3500.0 4 \n",
"3922 7249 1827 13385.0 1 \n",
"54425 1070539 1800 19800.0 1 \n",
"69520 1216801 1623 12562.0 2 \n",
"30056 59330 1551 0.0 1 \n",
"3243 5441 1544 14133.0 2 \n",
"55195 1084435 1500 16500.0 1 \n",
"28983 57816 1485 0.0 2 \n",
"2231 2942 1307 100.0 2 \n",
"23 24 1266 0.0 2 \n",
"4513 9592 1211 62.0 4 \n",
"2936 5059 1186 6308.0 3 \n",
"11484 25100 1123 0.0 1 \n",
"934 1326 1098 798.0 3 \n",
"30156 59490 1088 0.0 1 \n",
"36478 251268 1086 0.0 2 \n",
"\n", "\n",
" vente_internet_max purchase_date_min purchase_date_max \\\n", " vente_internet_max purchase_date_min purchase_date_max \\\n",
"0 1 2013-06-10 10:37:58+00:00 2023-11-08 15:59:45+00:00 \n", "0 1 2013-06-10 10:37:58+00:00 2023-11-08 15:59:45+00:00 \n",
"1 0 2018-04-07 12:55:07+00:00 2020-03-08 12:06:43+00:00 \n", "3615 1 2015-09-09 13:48:38+00:00 2023-11-03 09:42:40+00:00 \n",
"2 1 2019-09-19 15:15:01+00:00 2023-09-27 09:13:09+00:00 \n", "39 1 2014-01-23 16:56:57+00:00 2023-10-25 09:13:16+00:00 \n",
"3 1 2019-09-19 15:43:49+00:00 2021-09-02 18:42:19+00:00 \n", "11 1 2018-04-04 07:46:31+00:00 2023-11-04 13:46:59+00:00 \n",
"4 1 2019-09-19 15:45:36+00:00 2019-09-19 15:45:36+00:00 \n", "32809 1 2020-08-18 08:32:57+00:00 2022-08-25 13:08:38+00:00 \n",
"... ... ... ... \n", "3708 1 2018-03-26 11:13:43+00:00 2021-08-26 12:49:17+00:00 \n",
"73513 1 2023-11-08 16:51:19+00:00 2023-11-08 16:51:19+00:00 \n", "32616 1 2017-11-28 13:52:15+00:00 2022-09-07 12:55:33+00:00 \n",
"73514 1 2023-11-08 17:17:51+00:00 2023-11-08 17:17:51+00:00 \n", "78 1 2017-01-05 13:04:58+00:00 2022-08-30 11:51:34+00:00 \n",
"73515 1 2023-11-08 17:23:54+00:00 2023-11-08 17:23:54+00:00 \n", "35295 1 2021-05-28 10:22:33+00:00 2023-11-06 15:59:22+00:00 \n",
"73516 1 2023-11-08 18:32:18+00:00 2023-11-08 18:32:18+00:00 \n", "3377 1 2018-10-25 11:04:24+00:00 2022-02-24 07:47:20+00:00 \n",
"73517 1 2023-11-08 19:30:28+00:00 2023-11-08 19:30:28+00:00 \n", "30011 1 2019-11-25 08:52:48+00:00 2023-06-12 14:05:19+00:00 \n",
"34937 1 2018-02-08 12:54:01+00:00 2023-10-02 08:13:05+00:00 \n",
"270 1 2014-01-24 15:16:17+00:00 2023-10-16 10:19:22+00:00 \n",
"866 1 2017-03-29 08:00:09+00:00 2022-09-19 12:55:15+00:00 \n",
"1022 1 2014-12-03 14:56:38+00:00 2023-11-06 08:30:37+00:00 \n",
"3922 1 2019-05-07 12:34:56+00:00 2021-10-26 12:28:40+00:00 \n",
"54425 1 2022-05-02 16:09:03+00:00 2022-07-25 12:49:27+00:00 \n",
"69520 0 2023-06-16 14:16:04+00:00 2023-09-29 16:34:38+00:00 \n",
"30056 0 2018-02-02 08:53:51+00:00 2023-11-06 10:22:14+00:00 \n",
"3243 1 2017-12-14 12:50:23+00:00 2022-09-22 08:21:47+00:00 \n",
"55195 1 2022-05-18 08:04:41+00:00 2022-09-27 14:32:13+00:00 \n",
"28983 1 2019-01-21 14:19:18+00:00 2023-05-22 07:30:55+00:00 \n",
"2231 1 2017-10-25 15:06:58+00:00 2023-06-29 09:33:58+00:00 \n",
"23 1 2015-09-30 16:07:52+00:00 2023-10-19 07:20:48+00:00 \n",
"4513 1 2018-02-25 07:17:19+00:00 2023-10-17 09:39:40+00:00 \n",
"2936 1 2018-02-01 11:16:51+00:00 2023-05-22 13:41:22+00:00 \n",
"11484 1 2015-12-21 15:38:05+00:00 2021-07-13 07:39:57+00:00 \n",
"934 1 2018-02-13 13:13:48+00:00 2023-02-01 08:39:45+00:00 \n",
"30156 0 2019-12-06 12:59:20+00:00 2023-10-05 08:23:50+00:00 \n",
"36478 1 2018-02-02 09:06:22+00:00 2023-06-30 07:22:46+00:00 \n",
"\n", "\n",
" time_between_purchase nb_tickets_internet \n", " time_between_purchase nb_tickets_internet \n",
"0 3803 days 05:21:47 3053.0 \n", "0 3803 days 05:21:47 3053.0 \n",
"1 700 days 23:11:36 0.0 \n", "3615 2976 days 19:54:02 30896.0 \n",
"2 1468 days 17:58:08 6.0 \n", "39 3561 days 16:16:19 13993.0 \n",
"3 714 days 02:58:30 4.0 \n", "11 2040 days 06:00:28 167.0 \n",
"4 0 days 00:00:00 2.0 \n", "32809 737 days 04:35:41 5851.0 \n",
"... ... ... \n", "3708 1249 days 01:35:34 5481.0 \n",
"73513 0 days 00:00:00 3.0 \n", "32616 1743 days 23:03:18 826.0 \n",
"73514 0 days 00:00:00 4.0 \n", "78 2062 days 22:46:36 3562.0 \n",
"73515 0 days 00:00:00 1.0 \n", "35295 892 days 05:36:49 869.0 \n",
"73516 0 days 00:00:00 2.0 \n", "3377 1217 days 20:42:56 3294.0 \n",
"73517 0 days 00:00:00 2.0 \n", "30011 1295 days 05:12:31 52.0 \n",
"\n", "34937 2061 days 19:19:04 448.0 \n",
"[73518 rows x 9 columns]" "270 3551 days 19:03:05 1479.0 \n",
"866 2000 days 04:55:06 104.0 \n",
"1022 3259 days 17:33:59 690.0 \n",
"3922 902 days 23:53:44 1827.0 \n",
"54425 83 days 20:40:24 1800.0 \n",
"69520 105 days 02:18:34 0.0 \n",
"30056 2103 days 01:28:23 0.0 \n",
"3243 1742 days 19:31:24 1384.0 \n",
"55195 132 days 06:27:32 1500.0 \n",
"28983 1581 days 17:11:37 357.0 \n",
"2231 2072 days 18:27:00 676.0 \n",
"23 2940 days 15:12:56 556.0 \n",
"4513 2060 days 02:22:21 353.0 \n",
"2936 1936 days 02:24:31 1182.0 \n",
"11484 2030 days 16:01:52 1123.0 \n",
"934 1813 days 19:25:57 266.0 \n",
"30156 1398 days 19:24:30 0.0 \n",
"36478 1973 days 22:16:24 279.0 "
] ]
}, },
"execution_count": 76, "execution_count": 77,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
], ],
"source": [
"df1_tickets_kpi"
]
},
{
"cell_type": "code",
"execution_count": 63,
"id": "de1ecf15-1aa1-4aa2-9467-8ad8e9be5856",
"metadata": {},
"outputs": [],
"source": [
" df_tickets_information_copy = df1_products_purchased_reduced.copy()\n",
"\n",
" # Dummy : Canal de vente en ligne\n",
" liste_mots = ['en ligne', 'internet', 'web', 'net', 'vad', 'online'] # vad = vente à distance\n",
" df_tickets_information_copy['vente_internet'] = df_tickets_information_copy['supplier_name'].str.contains('|'.join(liste_mots), case=False).astype(int)\n",
"\n",
" # Proportion de vente en ligne\n",
" prop_vente_internet = df_tickets_information_copy[df_tickets_information_copy['vente_internet'] == 1].groupby('customer_id')['ticket_id'].count().reset_index()\n"
]
},
{
"cell_type": "code",
"execution_count": 64,
"id": "9cd36178-11dc-409c-b148-fb1d208c2faf",
"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>ticket_id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>3053</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>3</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>6</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56744</th>\n",
" <td>1256133</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56745</th>\n",
" <td>1256134</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56746</th>\n",
" <td>1256135</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56747</th>\n",
" <td>1256136</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56748</th>\n",
" <td>1256137</td>\n",
" <td>2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>56749 rows × 2 columns</p>\n",
"</div>"
],
"text/plain": [
" customer_id ticket_id\n",
"0 1 3053\n",
"1 3 6\n",
"2 4 4\n",
"3 5 2\n",
"4 6 2\n",
"... ... ...\n",
"56744 1256133 3\n",
"56745 1256134 4\n",
"56746 1256135 1\n",
"56747 1256136 2\n",
"56748 1256137 2\n",
"\n",
"[56749 rows x 2 columns]"
]
},
"execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"prop_vente_internet"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a7a452a6-cd5e-4c8b-b250-8a7d26e48fad",
"metadata": {},
"outputs": [],
"source": [ "source": [
"df1_tickets_kpi.sort_values(by='nb_tickets', ascending=False).head(30)" "df1_tickets_kpi.sort_values(by='nb_tickets', ascending=False).head(30)"
] ]