API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Jul 16th, 2019
71
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 28.47 KB | None | 0 0
raw download clone embed print report
  1. {
  2. "cells": [
  3. {
  4. "cell_type": "code",
  5. "execution_count": 1,
  6. "metadata": {},
  7. "outputs": [
  8. {
  9. "name": "stderr",
  10. "output_type": "stream",
  11. "text": [
  12. "/usr/local/lib/python3.5/dist-packages/psycopg2/__init__.py:144: UserWarning: The psycopg2 wheel package will be renamed from release 2.8; in order to keep installing from binary please use \"pip install psycopg2-binary\" instead. For details see: <http://initd.org/psycopg/docs/install.html#binary-install-from-pypi>.\n",
  13. " \"\"\")\n"
  14. ]
  15. }
  16. ],
  17. "source": [
  18. "import pandas as pd\n",
  19. "from platform_web.tools.data_utils import upload_initial_data"
  20. ]
  21. },
  22. {
  23. "cell_type": "code",
  24. "execution_count": 24,
  25. "metadata": {},
  26. "outputs": [
  27. {
  28. "data": {
  29. "text/html": [
  30. "<div>\n",
  31. "<style scoped>\n",
  32. " .dataframe tbody tr th:only-of-type {\n",
  33. " vertical-align: middle;\n",
  34. " }\n",
  35. "\n",
  36. " .dataframe tbody tr th {\n",
  37. " vertical-align: top;\n",
  38. " }\n",
  39. "\n",
  40. " .dataframe thead th {\n",
  41. " text-align: right;\n",
  42. " }\n",
  43. "</style>\n",
  44. "<table border=\"1\" class=\"dataframe\">\n",
  45. " <thead>\n",
  46. " <tr style=\"text-align: right;\">\n",
  47. " <th></th>\n",
  48. " <th>Unnamed: 0</th>\n",
  49. " <th>link_id</th>\n",
  50. " <th>description0</th>\n",
  51. " <th>description1</th>\n",
  52. " <th>description2</th>\n",
  53. " <th>description3</th>\n",
  54. " <th>moderation</th>\n",
  55. " <th>prediction</th>\n",
  56. " </tr>\n",
  57. " </thead>\n",
  58. " <tbody>\n",
  59. " <tr>\n",
  60. " <th>0</th>\n",
  61. " <td>0</td>\n",
  62. " <td>35618</td>\n",
  63. " <td>{\"url\": \"https://s3.eu-central-1.amazonaws.com...</td>\n",
  64. " <td>Мойка 5745 врезная овал малый 570*450 мм, прав...</td>\n",
  65. " <td>00069344</td>\n",
  66. " <td>{\"url\": \"https://www.33komoda.ru/catalog/moyki...</td>\n",
  67. " <td>-&gt;Мебель-&gt;Кухня-&gt;Мойки, сушки и смесители</td>\n",
  68. " <td>-&gt;Мебель-&gt;Кухня-&gt;Мойки, сушки и смесители</td>\n",
  69. " </tr>\n",
  70. " <tr>\n",
  71. " <th>1</th>\n",
  72. " <td>1</td>\n",
  73. " <td>30029</td>\n",
  74. " <td>{\"url\": \"https://s3.eu-central-1.amazonaws.com...</td>\n",
  75. " <td>Тумба туалетная Ника Н6, дуб сонома/белый</td>\n",
  76. " <td>00061601</td>\n",
  77. " <td>{\"url\": \"https://www.33komoda.ru/catalog/tumby...</td>\n",
  78. " <td>-&gt;Мебель-&gt;Разная мебель-&gt;Комоды</td>\n",
  79. " <td>-&gt;Мебель-&gt;Спальня-&gt;Прикроватные тумбы</td>\n",
  80. " </tr>\n",
  81. " <tr>\n",
  82. " <th>2</th>\n",
  83. " <td>2</td>\n",
  84. " <td>30010</td>\n",
  85. " <td>{\"url\": \"https://s3.eu-central-1.amazonaws.com...</td>\n",
  86. " <td>Полка Юниор Ю17, вейв светлый/ясень шимо темный</td>\n",
  87. " <td>00065412</td>\n",
  88. " <td>{\"url\": \"https://www.33komoda.ru/catalog/polki...</td>\n",
  89. " <td>-&gt;Мебель-&gt;Домашний офис-&gt;Полки и стеллажи</td>\n",
  90. " <td>-&gt;Мебель-&gt;Домашний офис-&gt;Полки и стеллажи</td>\n",
  91. " </tr>\n",
  92. " <tr>\n",
  93. " <th>3</th>\n",
  94. " <td>3</td>\n",
  95. " <td>35293</td>\n",
  96. " <td>{\"url\": \"https://s3.eu-central-1.amazonaws.com...</td>\n",
  97. " <td>Кухня Гранд, серый/синий/белый</td>\n",
  98. " <td>00079567</td>\n",
  99. " <td>{\"url\": \"https://www.33komoda.ru/catalog/modul...</td>\n",
  100. " <td>-&gt;Мебель-&gt;Кухня-&gt;Модульные кухни</td>\n",
  101. " <td>-&gt;Мебель-&gt;Кухня-&gt;Модульные кухни</td>\n",
  102. " </tr>\n",
  103. " <tr>\n",
  104. " <th>4</th>\n",
  105. " <td>4</td>\n",
  106. " <td>32949</td>\n",
  107. " <td>{\"url\": \"https://s3.eu-central-1.amazonaws.com...</td>\n",
  108. " <td>Линолеум Force Sorbona 5 4 м</td>\n",
  109. " <td>П0009997</td>\n",
  110. " <td>{\"url\": \"https://www.33komoda.ru/catalog/linol...</td>\n",
  111. " <td>-&gt;Напольные покрытия-&gt;Линолеум</td>\n",
  112. " <td>-&gt;Напольные покрытия-&gt;Линолеум</td>\n",
  113. " </tr>\n",
  114. " </tbody>\n",
  115. "</table>\n",
  116. "</div>"
  117. ],
  118. "text/plain": [
  119. " Unnamed: 0 link_id description0 \\\n",
  120. "0 0 35618 {\"url\": \"https://s3.eu-central-1.amazonaws.com... \n",
  121. "1 1 30029 {\"url\": \"https://s3.eu-central-1.amazonaws.com... \n",
  122. "2 2 30010 {\"url\": \"https://s3.eu-central-1.amazonaws.com... \n",
  123. "3 3 35293 {\"url\": \"https://s3.eu-central-1.amazonaws.com... \n",
  124. "4 4 32949 {\"url\": \"https://s3.eu-central-1.amazonaws.com... \n",
  125. "\n",
  126. " description1 description2 \\\n",
  127. "0 Мойка 5745 врезная овал малый 570*450 мм, прав... 00069344 \n",
  128. "1 Тумба туалетная Ника Н6, дуб сонома/белый 00061601 \n",
  129. "2 Полка Юниор Ю17, вейв светлый/ясень шимо темный 00065412 \n",
  130. "3 Кухня Гранд, серый/синий/белый 00079567 \n",
  131. "4 Линолеум Force Sorbona 5 4 м П0009997 \n",
  132. "\n",
  133. " description3 \\\n",
  134. "0 {\"url\": \"https://www.33komoda.ru/catalog/moyki... \n",
  135. "1 {\"url\": \"https://www.33komoda.ru/catalog/tumby... \n",
  136. "2 {\"url\": \"https://www.33komoda.ru/catalog/polki... \n",
  137. "3 {\"url\": \"https://www.33komoda.ru/catalog/modul... \n",
  138. "4 {\"url\": \"https://www.33komoda.ru/catalog/linol... \n",
  139. "\n",
  140. " moderation \\\n",
  141. "0 ->Мебель->Кухня->Мойки, сушки и смесители \n",
  142. "1 ->Мебель->Разная мебель->Комоды \n",
  143. "2 ->Мебель->Домашний офис->Полки и стеллажи \n",
  144. "3 ->Мебель->Кухня->Модульные кухни \n",
  145. "4 ->Напольные покрытия->Линолеум \n",
  146. "\n",
  147. " prediction \n",
  148. "0 ->Мебель->Кухня->Мойки, сушки и смесители \n",
  149. "1 ->Мебель->Спальня->Прикроватные тумбы \n",
  150. "2 ->Мебель->Домашний офис->Полки и стеллажи \n",
  151. "3 ->Мебель->Кухня->Модульные кухни \n",
  152. "4 ->Напольные покрытия->Линолеум "
  153. ]
  154. },
  155. "execution_count": 24,
  156. "metadata": {},
  157. "output_type": "execute_result"
  158. }
  159. ],
  160. "source": [
  161. "df_moderated=pd.read_csv('2019-02-21_33komoda_moderated_6K.csv')\n",
  162. "df_moderated.head()"
  163. ]
  164. },
  165. {
  166. "cell_type": "code",
  167. "execution_count": 25,
  168. "metadata": {},
  169. "outputs": [],
  170. "source": [
  171. "df_moderated=df_moderated[['description1', 'description2', 'moderation', 'prediction']]"
  172. ]
  173. },
  174. {
  175. "cell_type": "code",
  176. "execution_count": 26,
  177. "metadata": {},
  178. "outputs": [
  179. {
  180. "data": {
  181. "text/html": [
  182. "<div>\n",
  183. "<style scoped>\n",
  184. " .dataframe tbody tr th:only-of-type {\n",
  185. " vertical-align: middle;\n",
  186. " }\n",
  187. "\n",
  188. " .dataframe tbody tr th {\n",
  189. " vertical-align: top;\n",
  190. " }\n",
  191. "\n",
  192. " .dataframe thead th {\n",
  193. " text-align: right;\n",
  194. " }\n",
  195. "</style>\n",
  196. "<table border=\"1\" class=\"dataframe\">\n",
  197. " <thead>\n",
  198. " <tr style=\"text-align: right;\">\n",
  199. " <th></th>\n",
  200. " <th>description1</th>\n",
  201. " <th>description2</th>\n",
  202. " <th>moderation</th>\n",
  203. " <th>prediction</th>\n",
  204. " </tr>\n",
  205. " </thead>\n",
  206. " <tbody>\n",
  207. " <tr>\n",
  208. " <th>0</th>\n",
  209. " <td>Мойка 5745 врезная овал малый 570*450 мм, прав...</td>\n",
  210. " <td>00069344</td>\n",
  211. " <td>-&gt;Мебель-&gt;Кухня-&gt;Мойки, сушки и смесители</td>\n",
  212. " <td>-&gt;Мебель-&gt;Кухня-&gt;Мойки, сушки и смесители</td>\n",
  213. " </tr>\n",
  214. " <tr>\n",
  215. " <th>1</th>\n",
  216. " <td>Тумба туалетная Ника Н6, дуб сонома/белый</td>\n",
  217. " <td>00061601</td>\n",
  218. " <td>-&gt;Мебель-&gt;Разная мебель-&gt;Комоды</td>\n",
  219. " <td>-&gt;Мебель-&gt;Спальня-&gt;Прикроватные тумбы</td>\n",
  220. " </tr>\n",
  221. " <tr>\n",
  222. " <th>2</th>\n",
  223. " <td>Полка Юниор Ю17, вейв светлый/ясень шимо темный</td>\n",
  224. " <td>00065412</td>\n",
  225. " <td>-&gt;Мебель-&gt;Домашний офис-&gt;Полки и стеллажи</td>\n",
  226. " <td>-&gt;Мебель-&gt;Домашний офис-&gt;Полки и стеллажи</td>\n",
  227. " </tr>\n",
  228. " <tr>\n",
  229. " <th>3</th>\n",
  230. " <td>Кухня Гранд, серый/синий/белый</td>\n",
  231. " <td>00079567</td>\n",
  232. " <td>-&gt;Мебель-&gt;Кухня-&gt;Модульные кухни</td>\n",
  233. " <td>-&gt;Мебель-&gt;Кухня-&gt;Модульные кухни</td>\n",
  234. " </tr>\n",
  235. " <tr>\n",
  236. " <th>4</th>\n",
  237. " <td>Линолеум Force Sorbona 5 4 м</td>\n",
  238. " <td>П0009997</td>\n",
  239. " <td>-&gt;Напольные покрытия-&gt;Линолеум</td>\n",
  240. " <td>-&gt;Напольные покрытия-&gt;Линолеум</td>\n",
  241. " </tr>\n",
  242. " </tbody>\n",
  243. "</table>\n",
  244. "</div>"
  245. ],
  246. "text/plain": [
  247. " description1 description2 \\\n",
  248. "0 Мойка 5745 врезная овал малый 570*450 мм, прав... 00069344 \n",
  249. "1 Тумба туалетная Ника Н6, дуб сонома/белый 00061601 \n",
  250. "2 Полка Юниор Ю17, вейв светлый/ясень шимо темный 00065412 \n",
  251. "3 Кухня Гранд, серый/синий/белый 00079567 \n",
  252. "4 Линолеум Force Sorbona 5 4 м П0009997 \n",
  253. "\n",
  254. " moderation \\\n",
  255. "0 ->Мебель->Кухня->Мойки, сушки и смесители \n",
  256. "1 ->Мебель->Разная мебель->Комоды \n",
  257. "2 ->Мебель->Домашний офис->Полки и стеллажи \n",
  258. "3 ->Мебель->Кухня->Модульные кухни \n",
  259. "4 ->Напольные покрытия->Линолеум \n",
  260. "\n",
  261. " prediction \n",
  262. "0 ->Мебель->Кухня->Мойки, сушки и смесители \n",
  263. "1 ->Мебель->Спальня->Прикроватные тумбы \n",
  264. "2 ->Мебель->Домашний офис->Полки и стеллажи \n",
  265. "3 ->Мебель->Кухня->Модульные кухни \n",
  266. "4 ->Напольные покрытия->Линолеум "
  267. ]
  268. },
  269. "execution_count": 26,
  270. "metadata": {},
  271. "output_type": "execute_result"
  272. }
  273. ],
  274. "source": [
  275. "df_moderated.head()"
  276. ]
  277. },
  278. {
  279. "cell_type": "code",
  280. "execution_count": 30,
  281. "metadata": {},
  282. "outputs": [
  283. {
  284. "data": {
  285. "text/html": [
  286. "<div>\n",
  287. "<style scoped>\n",
  288. " .dataframe tbody tr th:only-of-type {\n",
  289. " vertical-align: middle;\n",
  290. " }\n",
  291. "\n",
  292. " .dataframe tbody tr th {\n",
  293. " vertical-align: top;\n",
  294. " }\n",
  295. "\n",
  296. " .dataframe thead th {\n",
  297. " text-align: right;\n",
  298. " }\n",
  299. "</style>\n",
  300. "<table border=\"1\" class=\"dataframe\">\n",
  301. " <thead>\n",
  302. " <tr style=\"text-align: right;\">\n",
  303. " <th></th>\n",
  304. " <th>Unnamed: 0</th>\n",
  305. " <th>description</th>\n",
  306. " </tr>\n",
  307. " </thead>\n",
  308. " <tbody>\n",
  309. " <tr>\n",
  310. " <th>0</th>\n",
  311. " <td>19</td>\n",
  312. " <td>Мягкий элемент стула Бордо, Нитро блек</td>\n",
  313. " </tr>\n",
  314. " <tr>\n",
  315. " <th>1</th>\n",
  316. " <td>20</td>\n",
  317. " <td>Мягкий элемент стула Бордо, Оттава милк</td>\n",
  318. " </tr>\n",
  319. " <tr>\n",
  320. " <th>2</th>\n",
  321. " <td>21</td>\n",
  322. " <td>Стол раздв. Соренто 1, (1100/1420*700мм), стек...</td>\n",
  323. " </tr>\n",
  324. " <tr>\n",
  325. " <th>3</th>\n",
  326. " <td>22</td>\n",
  327. " <td>Стол раздв. Соренто 1, (1100/1420*700мм), стек...</td>\n",
  328. " </tr>\n",
  329. " <tr>\n",
  330. " <th>4</th>\n",
  331. " <td>23</td>\n",
  332. " <td>Стол раздв. Соренто 1, (1100/1420*700мм), стек...</td>\n",
  333. " </tr>\n",
  334. " </tbody>\n",
  335. "</table>\n",
  336. "</div>"
  337. ],
  338. "text/plain": [
  339. " Unnamed: 0 description\n",
  340. "0 19 Мягкий элемент стула Бордо, Нитро блек\n",
  341. "1 20 Мягкий элемент стула Бордо, Оттава милк\n",
  342. "2 21 Стол раздв. Соренто 1, (1100/1420*700мм), стек...\n",
  343. "3 22 Стол раздв. Соренто 1, (1100/1420*700мм), стек...\n",
  344. "4 23 Стол раздв. Соренто 1, (1100/1420*700мм), стек..."
  345. ]
  346. },
  347. "execution_count": 30,
  348. "metadata": {},
  349. "output_type": "execute_result"
  350. }
  351. ],
  352. "source": [
  353. "df_add=pd.read_csv('33_komoda_cut.csv')\n",
  354. "df_add.head()"
  355. ]
  356. },
  357. {
  358. "cell_type": "code",
  359. "execution_count": 11,
  360. "metadata": {},
  361. "outputs": [
  362. {
  363. "data": {
  364. "text/html": [
  365. "<div>\n",
  366. "<style scoped>\n",
  367. " .dataframe tbody tr th:only-of-type {\n",
  368. " vertical-align: middle;\n",
  369. " }\n",
  370. "\n",
  371. " .dataframe tbody tr th {\n",
  372. " vertical-align: top;\n",
  373. " }\n",
  374. "\n",
  375. " .dataframe thead th {\n",
  376. " text-align: right;\n",
  377. " }\n",
  378. "</style>\n",
  379. "<table border=\"1\" class=\"dataframe\">\n",
  380. " <thead>\n",
  381. " <tr style=\"text-align: right;\">\n",
  382. " <th></th>\n",
  383. " <th>L1</th>\n",
  384. " <th>L2</th>\n",
  385. " <th>L3</th>\n",
  386. " </tr>\n",
  387. " </thead>\n",
  388. " <tbody>\n",
  389. " <tr>\n",
  390. " <th>0</th>\n",
  391. " <td>Сантехника</td>\n",
  392. " <td>Душевые кабины</td>\n",
  393. " <td>Асимметричные</td>\n",
  394. " </tr>\n",
  395. " <tr>\n",
  396. " <th>1</th>\n",
  397. " <td>Сантехника</td>\n",
  398. " <td>Душевые кабины</td>\n",
  399. " <td>Угловые</td>\n",
  400. " </tr>\n",
  401. " <tr>\n",
  402. " <th>2</th>\n",
  403. " <td>Сантехника</td>\n",
  404. " <td>Душевые кабины</td>\n",
  405. " <td>Прямоугольные</td>\n",
  406. " </tr>\n",
  407. " <tr>\n",
  408. " <th>3</th>\n",
  409. " <td>Сантехника</td>\n",
  410. " <td>Душевые кабины</td>\n",
  411. " <td>Душевые ограждения,уголки</td>\n",
  412. " </tr>\n",
  413. " <tr>\n",
  414. " <th>4</th>\n",
  415. " <td>Сантехника</td>\n",
  416. " <td>Смесители</td>\n",
  417. " <td>Для раковины</td>\n",
  418. " </tr>\n",
  419. " </tbody>\n",
  420. "</table>\n",
  421. "</div>"
  422. ],
  423. "text/plain": [
  424. " L1 L2 L3\n",
  425. "0 Сантехника Душевые кабины Асимметричные\n",
  426. "1 Сантехника Душевые кабины Угловые\n",
  427. "2 Сантехника Душевые кабины Прямоугольные\n",
  428. "3 Сантехника Душевые кабины Душевые ограждения,уголки\n",
  429. "4 Сантехника Смесители Для раковины"
  430. ]
  431. },
  432. "execution_count": 11,
  433. "metadata": {},
  434. "output_type": "execute_result"
  435. }
  436. ],
  437. "source": [
  438. "cat = pd.read_csv('input_ontology.csv')\n",
  439. "cat.head()"
  440. ]
  441. },
  442. {
  443. "cell_type": "code",
  444. "execution_count": 35,
  445. "metadata": {},
  446. "outputs": [
  447. {
  448. "data": {
  449. "text/plain": [
  450. "description1 0\n",
  451. "description2 0\n",
  452. "moderation 0\n",
  453. "prediction 4788\n",
  454. "dtype: int64"
  455. ]
  456. },
  457. "execution_count": 35,
  458. "metadata": {},
  459. "output_type": "execute_result"
  460. }
  461. ],
  462. "source": [
  463. "df_moderated.isnull().sum()"
  464. ]
  465. },
  466. {
  467. "cell_type": "markdown",
  468. "metadata": {},
  469. "source": [
  470. "# Заливка"
  471. ]
  472. },
  473. {
  474. "cell_type": "code",
  475. "execution_count": 39,
  476. "metadata": {},
  477. "outputs": [
  478. {
  479. "data": {
  480. "text/html": [
  481. "<div>\n",
  482. "<style scoped>\n",
  483. " .dataframe tbody tr th:only-of-type {\n",
  484. " vertical-align: middle;\n",
  485. " }\n",
  486. "\n",
  487. " .dataframe tbody tr th {\n",
  488. " vertical-align: top;\n",
  489. " }\n",
  490. "\n",
  491. " .dataframe thead th {\n",
  492. " text-align: right;\n",
  493. " }\n",
  494. "</style>\n",
  495. "<table border=\"1\" class=\"dataframe\">\n",
  496. " <thead>\n",
  497. " <tr style=\"text-align: right;\">\n",
  498. " <th></th>\n",
  499. " <th>Unnamed: 0</th>\n",
  500. " <th>description</th>\n",
  501. " </tr>\n",
  502. " </thead>\n",
  503. " <tbody>\n",
  504. " <tr>\n",
  505. " <th>0</th>\n",
  506. " <td>19</td>\n",
  507. " <td>Мягкий элемент стула Бордо, Нитро блек</td>\n",
  508. " </tr>\n",
  509. " <tr>\n",
  510. " <th>1</th>\n",
  511. " <td>20</td>\n",
  512. " <td>Мягкий элемент стула Бордо, Оттава милк</td>\n",
  513. " </tr>\n",
  514. " <tr>\n",
  515. " <th>2</th>\n",
  516. " <td>21</td>\n",
  517. " <td>Стол раздв. Соренто 1, (1100/1420*700мм), стек...</td>\n",
  518. " </tr>\n",
  519. " <tr>\n",
  520. " <th>3</th>\n",
  521. " <td>22</td>\n",
  522. " <td>Стол раздв. Соренто 1, (1100/1420*700мм), стек...</td>\n",
  523. " </tr>\n",
  524. " <tr>\n",
  525. " <th>4</th>\n",
  526. " <td>23</td>\n",
  527. " <td>Стол раздв. Соренто 1, (1100/1420*700мм), стек...</td>\n",
  528. " </tr>\n",
  529. " </tbody>\n",
  530. "</table>\n",
  531. "</div>"
  532. ],
  533. "text/plain": [
  534. " Unnamed: 0 description\n",
  535. "0 19 Мягкий элемент стула Бордо, Нитро блек\n",
  536. "1 20 Мягкий элемент стула Бордо, Оттава милк\n",
  537. "2 21 Стол раздв. Соренто 1, (1100/1420*700мм), стек...\n",
  538. "3 22 Стол раздв. Соренто 1, (1100/1420*700мм), стек...\n",
  539. "4 23 Стол раздв. Соренто 1, (1100/1420*700мм), стек..."
  540. ]
  541. },
  542. "execution_count": 39,
  543. "metadata": {},
  544. "output_type": "execute_result"
  545. }
  546. ],
  547. "source": [
  548. "df_add.head()"
  549. ]
  550. },
  551. {
  552. "cell_type": "code",
  553. "execution_count": 40,
  554. "metadata": {},
  555. "outputs": [
  556. {
  557. "data": {
  558. "text/html": [
  559. "<div>\n",
  560. "<style scoped>\n",
  561. " .dataframe tbody tr th:only-of-type {\n",
  562. " vertical-align: middle;\n",
  563. " }\n",
  564. "\n",
  565. " .dataframe tbody tr th {\n",
  566. " vertical-align: top;\n",
  567. " }\n",
  568. "\n",
  569. " .dataframe thead th {\n",
  570. " text-align: right;\n",
  571. " }\n",
  572. "</style>\n",
  573. "<table border=\"1\" class=\"dataframe\">\n",
  574. " <thead>\n",
  575. " <tr style=\"text-align: right;\">\n",
  576. " <th></th>\n",
  577. " <th>description1</th>\n",
  578. " <th>description2</th>\n",
  579. " <th>moderation</th>\n",
  580. " <th>prediction</th>\n",
  581. " </tr>\n",
  582. " </thead>\n",
  583. " <tbody>\n",
  584. " <tr>\n",
  585. " <th>0</th>\n",
  586. " <td>Мойка 5745 врезная овал малый 570*450 мм, прав...</td>\n",
  587. " <td>00069344</td>\n",
  588. " <td>-&gt;Мебель-&gt;Кухня-&gt;Мойки, сушки и смесители</td>\n",
  589. " <td>-&gt;Мебель-&gt;Кухня-&gt;Мойки, сушки и смесители</td>\n",
  590. " </tr>\n",
  591. " <tr>\n",
  592. " <th>1</th>\n",
  593. " <td>Тумба туалетная Ника Н6, дуб сонома/белый</td>\n",
  594. " <td>00061601</td>\n",
  595. " <td>-&gt;Мебель-&gt;Разная мебель-&gt;Комоды</td>\n",
  596. " <td>-&gt;Мебель-&gt;Спальня-&gt;Прикроватные тумбы</td>\n",
  597. " </tr>\n",
  598. " <tr>\n",
  599. " <th>2</th>\n",
  600. " <td>Полка Юниор Ю17, вейв светлый/ясень шимо темный</td>\n",
  601. " <td>00065412</td>\n",
  602. " <td>-&gt;Мебель-&gt;Домашний офис-&gt;Полки и стеллажи</td>\n",
  603. " <td>-&gt;Мебель-&gt;Домашний офис-&gt;Полки и стеллажи</td>\n",
  604. " </tr>\n",
  605. " <tr>\n",
  606. " <th>3</th>\n",
  607. " <td>Кухня Гранд, серый/синий/белый</td>\n",
  608. " <td>00079567</td>\n",
  609. " <td>-&gt;Мебель-&gt;Кухня-&gt;Модульные кухни</td>\n",
  610. " <td>-&gt;Мебель-&gt;Кухня-&gt;Модульные кухни</td>\n",
  611. " </tr>\n",
  612. " <tr>\n",
  613. " <th>4</th>\n",
  614. " <td>Линолеум Force Sorbona 5 4 м</td>\n",
  615. " <td>П0009997</td>\n",
  616. " <td>-&gt;Напольные покрытия-&gt;Линолеум</td>\n",
  617. " <td>-&gt;Напольные покрытия-&gt;Линолеум</td>\n",
  618. " </tr>\n",
  619. " </tbody>\n",
  620. "</table>\n",
  621. "</div>"
  622. ],
  623. "text/plain": [
  624. " description1 description2 \\\n",
  625. "0 Мойка 5745 врезная овал малый 570*450 мм, прав... 00069344 \n",
  626. "1 Тумба туалетная Ника Н6, дуб сонома/белый 00061601 \n",
  627. "2 Полка Юниор Ю17, вейв светлый/ясень шимо темный 00065412 \n",
  628. "3 Кухня Гранд, серый/синий/белый 00079567 \n",
  629. "4 Линолеум Force Sorbona 5 4 м П0009997 \n",
  630. "\n",
  631. " moderation \\\n",
  632. "0 ->Мебель->Кухня->Мойки, сушки и смесители \n",
  633. "1 ->Мебель->Разная мебель->Комоды \n",
  634. "2 ->Мебель->Домашний офис->Полки и стеллажи \n",
  635. "3 ->Мебель->Кухня->Модульные кухни \n",
  636. "4 ->Напольные покрытия->Линолеум \n",
  637. "\n",
  638. " prediction \n",
  639. "0 ->Мебель->Кухня->Мойки, сушки и смесители \n",
  640. "1 ->Мебель->Спальня->Прикроватные тумбы \n",
  641. "2 ->Мебель->Домашний офис->Полки и стеллажи \n",
  642. "3 ->Мебель->Кухня->Модульные кухни \n",
  643. "4 ->Напольные покрытия->Линолеум "
  644. ]
  645. },
  646. "execution_count": 40,
  647. "metadata": {},
  648. "output_type": "execute_result"
  649. }
  650. ],
  651. "source": [
  652. "df_moderated.head()"
  653. ]
  654. },
  655. {
  656. "cell_type": "code",
  657. "execution_count": 41,
  658. "metadata": {},
  659. "outputs": [
  660. {
  661. "name": "stdout",
  662. "output_type": "stream",
  663. "text": [
  664. "Created prediction list \"2019-03-27_33komoda\" id:133\n",
  665. "Created model \"2019-03-27_33komoda\" id:574\n",
  666. "Performing predictions validation...\n",
  667. "Performing moderation validation...\n",
  668. "OK\n",
  669. "Uploading 6820/6820 products. Chunk size 50000. Offset 0\n",
  670. "Uploaded 6820/6820 products. Time: 4s\n",
  671. "Total time 4s\n"
  672. ]
  673. }
  674. ],
  675. "source": [
  676. "upload_initial_data(df_moderated, '2019-03-27_33komoda', '2019-03-27_33komoda', '33komoda', cat_df=cat, \n",
  677. " text_columns=['description1'], moderation_column='moderation', prediction_column='prediction', production_db=True)"
  678. ]
  679. },
  680. {
  681. "cell_type": "code",
  682. "execution_count": 42,
  683. "metadata": {},
  684. "outputs": [
  685. {
  686. "name": "stdout",
  687. "output_type": "stream",
  688. "text": [
  689. "Uploading 13889/13889 products. Chunk size 50000. Offset 0\n",
  690. "Uploaded 13889/13889 products. Time: 3s\n",
  691. "Total time 3s\n"
  692. ]
  693. }
  694. ],
  695. "source": [
  696. "upload_initial_data(df_add, '2019-03-27_33komoda', '2019-03-27_33komoda', '33komoda', \n",
  697. " text_columns=['description'], create_model=False, create_prediction_list=False, production_db=True)"
  698. ]
  699. },
  700. {
  701. "cell_type": "code",
  702. "execution_count": null,
  703. "metadata": {},
  704. "outputs": [],
  705. "source": []
  706. }
  707. ],
  708. "metadata": {
  709. "kernelspec": {
  710. "display_name": "Python 3",
  711. "language": "python",
  712. "name": "python3"
  713. },
  714. "language_info": {
  715. "codemirror_mode": {
  716. "name": "ipython",
  717. "version": 3
  718. },
  719. "file_extension": ".py",
  720. "mimetype": "text/x-python",
  721. "name": "python",
  722. "nbconvert_exporter": "python",
  723. "pygments_lexer": "ipython3",
  724. "version": "3.5.2"
  725. }
  726. },
  727. "nbformat": 4,
  728. "nbformat_minor": 2
  729. }
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!