API tools faq
paste
Guest User

Untitled

a guest
Jun 25th, 2018
94
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 9.89 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": "stdout",
  10. "output_type": "stream",
  11. "text": [
  12. "(6, 2)\n",
  13. "RangeIndex(start=0, stop=6, step=1)\n"
  14. ]
  15. },
  16. {
  17. "data": {
  18. "text/html": [
  19. "<div>\n",
  20. "<style scoped>\n",
  21. " .dataframe tbody tr th:only-of-type {\n",
  22. " vertical-align: middle;\n",
  23. " }\n",
  24. "\n",
  25. " .dataframe tbody tr th {\n",
  26. " vertical-align: top;\n",
  27. " }\n",
  28. "\n",
  29. " .dataframe thead th {\n",
  30. " text-align: right;\n",
  31. " }\n",
  32. "</style>\n",
  33. "<table border=\"1\" class=\"dataframe\">\n",
  34. " <thead>\n",
  35. " <tr style=\"text-align: right;\">\n",
  36. " <th></th>\n",
  37. " <th>col1</th>\n",
  38. " <th>col2</th>\n",
  39. " </tr>\n",
  40. " </thead>\n",
  41. " <tbody>\n",
  42. " <tr>\n",
  43. " <th>0</th>\n",
  44. " <td>1</td>\n",
  45. " <td>2</td>\n",
  46. " </tr>\n",
  47. " <tr>\n",
  48. " <th>1</th>\n",
  49. " <td>3</td>\n",
  50. " <td>4</td>\n",
  51. " </tr>\n",
  52. " <tr>\n",
  53. " <th>2</th>\n",
  54. " <td>5</td>\n",
  55. " <td>6</td>\n",
  56. " </tr>\n",
  57. " <tr>\n",
  58. " <th>3</th>\n",
  59. " <td>7</td>\n",
  60. " <td>8</td>\n",
  61. " </tr>\n",
  62. " <tr>\n",
  63. " <th>4</th>\n",
  64. " <td>9</td>\n",
  65. " <td>10</td>\n",
  66. " </tr>\n",
  67. " <tr>\n",
  68. " <th>5</th>\n",
  69. " <td>11</td>\n",
  70. " <td>12</td>\n",
  71. " </tr>\n",
  72. " </tbody>\n",
  73. "</table>\n",
  74. "</div>"
  75. ],
  76. "text/plain": [
  77. " col1 col2\n",
  78. "0 1 2\n",
  79. "1 3 4\n",
  80. "2 5 6\n",
  81. "3 7 8\n",
  82. "4 9 10\n",
  83. "5 11 12"
  84. ]
  85. },
  86. "execution_count": 1,
  87. "metadata": {},
  88. "output_type": "execute_result"
  89. }
  90. ],
  91. "source": [
  92. "import pandas as pd\n",
  93. "\n",
  94. "df = pd.DataFrame([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]], columns=['col1', 'col2'])\n",
  95. "print(df.shape)\n",
  96. "print(df.index)\n",
  97. "df"
  98. ]
  99. },
  100. {
  101. "cell_type": "code",
  102. "execution_count": 2,
  103. "metadata": {},
  104. "outputs": [
  105. {
  106. "name": "stdout",
  107. "output_type": "stream",
  108. "text": [
  109. "Int64Index([2, 5], dtype='int64')\n"
  110. ]
  111. },
  112. {
  113. "data": {
  114. "text/html": [
  115. "<div>\n",
  116. "<style scoped>\n",
  117. " .dataframe tbody tr th:only-of-type {\n",
  118. " vertical-align: middle;\n",
  119. " }\n",
  120. "\n",
  121. " .dataframe tbody tr th {\n",
  122. " vertical-align: top;\n",
  123. " }\n",
  124. "\n",
  125. " .dataframe thead th {\n",
  126. " text-align: right;\n",
  127. " }\n",
  128. "</style>\n",
  129. "<table border=\"1\" class=\"dataframe\">\n",
  130. " <thead>\n",
  131. " <tr style=\"text-align: right;\">\n",
  132. " <th></th>\n",
  133. " <th>col1</th>\n",
  134. " <th>col2</th>\n",
  135. " </tr>\n",
  136. " </thead>\n",
  137. " <tbody>\n",
  138. " <tr>\n",
  139. " <th>2</th>\n",
  140. " <td>5</td>\n",
  141. " <td>6</td>\n",
  142. " </tr>\n",
  143. " <tr>\n",
  144. " <th>5</th>\n",
  145. " <td>11</td>\n",
  146. " <td>12</td>\n",
  147. " </tr>\n",
  148. " </tbody>\n",
  149. "</table>\n",
  150. "</div>"
  151. ],
  152. "text/plain": [
  153. " col1 col2\n",
  154. "2 5 6\n",
  155. "5 11 12"
  156. ]
  157. },
  158. "execution_count": 2,
  159. "metadata": {},
  160. "output_type": "execute_result"
  161. }
  162. ],
  163. "source": [
  164. "test_df = df.sample(frac=0.3)\n",
  165. "print(test_df.index)\n",
  166. "test_df"
  167. ]
  168. },
  169. {
  170. "cell_type": "code",
  171. "execution_count": 3,
  172. "metadata": {},
  173. "outputs": [
  174. {
  175. "name": "stdout",
  176. "output_type": "stream",
  177. "text": [
  178. "RangeIndex(start=0, stop=2, step=1)\n"
  179. ]
  180. },
  181. {
  182. "data": {
  183. "text/html": [
  184. "<div>\n",
  185. "<style scoped>\n",
  186. " .dataframe tbody tr th:only-of-type {\n",
  187. " vertical-align: middle;\n",
  188. " }\n",
  189. "\n",
  190. " .dataframe tbody tr th {\n",
  191. " vertical-align: top;\n",
  192. " }\n",
  193. "\n",
  194. " .dataframe thead th {\n",
  195. " text-align: right;\n",
  196. " }\n",
  197. "</style>\n",
  198. "<table border=\"1\" class=\"dataframe\">\n",
  199. " <thead>\n",
  200. " <tr style=\"text-align: right;\">\n",
  201. " <th></th>\n",
  202. " <th>index</th>\n",
  203. " <th>col1</th>\n",
  204. " <th>col2</th>\n",
  205. " </tr>\n",
  206. " </thead>\n",
  207. " <tbody>\n",
  208. " <tr>\n",
  209. " <th>0</th>\n",
  210. " <td>2</td>\n",
  211. " <td>5</td>\n",
  212. " <td>6</td>\n",
  213. " </tr>\n",
  214. " <tr>\n",
  215. " <th>1</th>\n",
  216. " <td>5</td>\n",
  217. " <td>11</td>\n",
  218. " <td>12</td>\n",
  219. " </tr>\n",
  220. " </tbody>\n",
  221. "</table>\n",
  222. "</div>"
  223. ],
  224. "text/plain": [
  225. " index col1 col2\n",
  226. "0 2 5 6\n",
  227. "1 5 11 12"
  228. ]
  229. },
  230. "execution_count": 3,
  231. "metadata": {},
  232. "output_type": "execute_result"
  233. }
  234. ],
  235. "source": [
  236. "test_df = test_df.reset_index()\n",
  237. "print(test_df.index)\n",
  238. "test_df"
  239. ]
  240. },
  241. {
  242. "cell_type": "code",
  243. "execution_count": 4,
  244. "metadata": {},
  245. "outputs": [
  246. {
  247. "name": "stdout",
  248. "output_type": "stream",
  249. "text": [
  250. "Int64Index([2, 3, 4, 5], dtype='int64')\n"
  251. ]
  252. },
  253. {
  254. "data": {
  255. "text/html": [
  256. "<div>\n",
  257. "<style scoped>\n",
  258. " .dataframe tbody tr th:only-of-type {\n",
  259. " vertical-align: middle;\n",
  260. " }\n",
  261. "\n",
  262. " .dataframe tbody tr th {\n",
  263. " vertical-align: top;\n",
  264. " }\n",
  265. "\n",
  266. " .dataframe thead th {\n",
  267. " text-align: right;\n",
  268. " }\n",
  269. "</style>\n",
  270. "<table border=\"1\" class=\"dataframe\">\n",
  271. " <thead>\n",
  272. " <tr style=\"text-align: right;\">\n",
  273. " <th></th>\n",
  274. " <th>col1</th>\n",
  275. " <th>col2</th>\n",
  276. " </tr>\n",
  277. " </thead>\n",
  278. " <tbody>\n",
  279. " <tr>\n",
  280. " <th>2</th>\n",
  281. " <td>5</td>\n",
  282. " <td>6</td>\n",
  283. " </tr>\n",
  284. " <tr>\n",
  285. " <th>3</th>\n",
  286. " <td>7</td>\n",
  287. " <td>8</td>\n",
  288. " </tr>\n",
  289. " <tr>\n",
  290. " <th>4</th>\n",
  291. " <td>9</td>\n",
  292. " <td>10</td>\n",
  293. " </tr>\n",
  294. " <tr>\n",
  295. " <th>5</th>\n",
  296. " <td>11</td>\n",
  297. " <td>12</td>\n",
  298. " </tr>\n",
  299. " </tbody>\n",
  300. "</table>\n",
  301. "</div>"
  302. ],
  303. "text/plain": [
  304. " col1 col2\n",
  305. "2 5 6\n",
  306. "3 7 8\n",
  307. "4 9 10\n",
  308. "5 11 12"
  309. ]
  310. },
  311. "execution_count": 4,
  312. "metadata": {},
  313. "output_type": "execute_result"
  314. }
  315. ],
  316. "source": [
  317. "train_df = df.drop(test_df.index)\n",
  318. "print(train_df.index)\n",
  319. "train_df"
  320. ]
  321. },
  322. {
  323. "cell_type": "code",
  324. "execution_count": 5,
  325. "metadata": {},
  326. "outputs": [
  327. {
  328. "name": "stdout",
  329. "output_type": "stream",
  330. "text": [
  331. "RangeIndex(start=0, stop=4, step=1)\n"
  332. ]
  333. },
  334. {
  335. "data": {
  336. "text/html": [
  337. "<div>\n",
  338. "<style scoped>\n",
  339. " .dataframe tbody tr th:only-of-type {\n",
  340. " vertical-align: middle;\n",
  341. " }\n",
  342. "\n",
  343. " .dataframe tbody tr th {\n",
  344. " vertical-align: top;\n",
  345. " }\n",
  346. "\n",
  347. " .dataframe thead th {\n",
  348. " text-align: right;\n",
  349. " }\n",
  350. "</style>\n",
  351. "<table border=\"1\" class=\"dataframe\">\n",
  352. " <thead>\n",
  353. " <tr style=\"text-align: right;\">\n",
  354. " <th></th>\n",
  355. " <th>index</th>\n",
  356. " <th>col1</th>\n",
  357. " <th>col2</th>\n",
  358. " </tr>\n",
  359. " </thead>\n",
  360. " <tbody>\n",
  361. " <tr>\n",
  362. " <th>0</th>\n",
  363. " <td>2</td>\n",
  364. " <td>5</td>\n",
  365. " <td>6</td>\n",
  366. " </tr>\n",
  367. " <tr>\n",
  368. " <th>1</th>\n",
  369. " <td>3</td>\n",
  370. " <td>7</td>\n",
  371. " <td>8</td>\n",
  372. " </tr>\n",
  373. " <tr>\n",
  374. " <th>2</th>\n",
  375. " <td>4</td>\n",
  376. " <td>9</td>\n",
  377. " <td>10</td>\n",
  378. " </tr>\n",
  379. " <tr>\n",
  380. " <th>3</th>\n",
  381. " <td>5</td>\n",
  382. " <td>11</td>\n",
  383. " <td>12</td>\n",
  384. " </tr>\n",
  385. " </tbody>\n",
  386. "</table>\n",
  387. "</div>"
  388. ],
  389. "text/plain": [
  390. " index col1 col2\n",
  391. "0 2 5 6\n",
  392. "1 3 7 8\n",
  393. "2 4 9 10\n",
  394. "3 5 11 12"
  395. ]
  396. },
  397. "execution_count": 5,
  398. "metadata": {},
  399. "output_type": "execute_result"
  400. }
  401. ],
  402. "source": [
  403. "train_df = train_df.reset_index()\n",
  404. "print(train_df.index)\n",
  405. "train_df"
  406. ]
  407. }
  408. ],
  409. "metadata": {
  410. "kernelspec": {
  411. "display_name": "Python 3",
  412. "language": "python",
  413. "name": "python3"
  414. },
  415. "language_info": {
  416. "codemirror_mode": {
  417. "name": "ipython",
  418. "version": 3
  419. },
  420. "file_extension": ".py",
  421. "mimetype": "text/x-python",
  422. "name": "python",
  423. "nbconvert_exporter": "python",
  424. "pygments_lexer": "ipython3",
  425. "version": "3.6.4"
  426. }
  427. },
  428. "nbformat": 4,
  429. "nbformat_minor": 2
  430. }
Add Comment
Please, Sign In to add comment
Public Pastes
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!