API tools faq
paste
Guest User

Untitled

a guest
Mar 23rd, 2018
70
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 40.81 KB | None | 0 0
raw download clone embed print report
  1. {
  2. "cells": [
  3. {
  4. "cell_type": "markdown",
  5. "metadata": {},
  6. "source": [
  7. "### Imprort libraries"
  8. ]
  9. },
  10. {
  11. "cell_type": "code",
  12. "execution_count": 1,
  13. "metadata": {
  14. "collapsed": true
  15. },
  16. "outputs": [],
  17. "source": [
  18. "import pandas as pd\n",
  19. "import numpy as np"
  20. ]
  21. },
  22. {
  23. "cell_type": "markdown",
  24. "metadata": {},
  25. "source": [
  26. "### Load dataset"
  27. ]
  28. },
  29. {
  30. "cell_type": "code",
  31. "execution_count": 2,
  32. "metadata": {
  33. "collapsed": true
  34. },
  35. "outputs": [],
  36. "source": [
  37. "data = pd.read_csv('gapminder.csv', low_memory=False)"
  38. ]
  39. },
  40. {
  41. "cell_type": "markdown",
  42. "metadata": {},
  43. "source": [
  44. "### Explore data set"
  45. ]
  46. },
  47. {
  48. "cell_type": "code",
  49. "execution_count": 3,
  50. "metadata": {},
  51. "outputs": [
  52. {
  53. "data": {
  54. "text/html": [
  55. "<div>\n",
  56. "<table border=\"1\" class=\"dataframe\">\n",
  57. " <thead>\n",
  58. " <tr style=\"text-align: right;\">\n",
  59. " <th></th>\n",
  60. " <th>country</th>\n",
  61. " <th>incomeperperson</th>\n",
  62. " <th>alcconsumption</th>\n",
  63. " <th>armedforcesrate</th>\n",
  64. " <th>breastcancerper100th</th>\n",
  65. " <th>co2emissions</th>\n",
  66. " <th>femaleemployrate</th>\n",
  67. " <th>hivrate</th>\n",
  68. " <th>internetuserate</th>\n",
  69. " <th>lifeexpectancy</th>\n",
  70. " <th>oilperperson</th>\n",
  71. " <th>polityscore</th>\n",
  72. " <th>relectricperperson</th>\n",
  73. " <th>suicideper100th</th>\n",
  74. " <th>employrate</th>\n",
  75. " <th>urbanrate</th>\n",
  76. " </tr>\n",
  77. " </thead>\n",
  78. " <tbody>\n",
  79. " <tr>\n",
  80. " <th>0</th>\n",
  81. " <td>Afghanistan</td>\n",
  82. " <td></td>\n",
  83. " <td>.03</td>\n",
  84. " <td>.5696534</td>\n",
  85. " <td>26.8</td>\n",
  86. " <td>75944000</td>\n",
  87. " <td>25.6000003814697</td>\n",
  88. " <td></td>\n",
  89. " <td>3.65412162280064</td>\n",
  90. " <td>48.673</td>\n",
  91. " <td></td>\n",
  92. " <td>0</td>\n",
  93. " <td></td>\n",
  94. " <td>6.68438529968262</td>\n",
  95. " <td>55.7000007629394</td>\n",
  96. " <td>24.04</td>\n",
  97. " </tr>\n",
  98. " <tr>\n",
  99. " <th>1</th>\n",
  100. " <td>Albania</td>\n",
  101. " <td>1914.99655094922</td>\n",
  102. " <td>7.29</td>\n",
  103. " <td>1.0247361</td>\n",
  104. " <td>57.4</td>\n",
  105. " <td>223747333.333333</td>\n",
  106. " <td>42.0999984741211</td>\n",
  107. " <td></td>\n",
  108. " <td>44.9899469578783</td>\n",
  109. " <td>76.918</td>\n",
  110. " <td></td>\n",
  111. " <td>9</td>\n",
  112. " <td>636.341383366604</td>\n",
  113. " <td>7.69932985305786</td>\n",
  114. " <td>51.4000015258789</td>\n",
  115. " <td>46.72</td>\n",
  116. " </tr>\n",
  117. " <tr>\n",
  118. " <th>2</th>\n",
  119. " <td>Algeria</td>\n",
  120. " <td>2231.99333515006</td>\n",
  121. " <td>.69</td>\n",
  122. " <td>2.306817</td>\n",
  123. " <td>23.5</td>\n",
  124. " <td>2932108666.66667</td>\n",
  125. " <td>31.7000007629394</td>\n",
  126. " <td>.1</td>\n",
  127. " <td>12.5000733055148</td>\n",
  128. " <td>73.131</td>\n",
  129. " <td>.42009452521537</td>\n",
  130. " <td>2</td>\n",
  131. " <td>590.509814347428</td>\n",
  132. " <td>4.8487696647644</td>\n",
  133. " <td>50.5</td>\n",
  134. " <td>65.22</td>\n",
  135. " </tr>\n",
  136. " <tr>\n",
  137. " <th>3</th>\n",
  138. " <td>Andorra</td>\n",
  139. " <td>21943.3398976022</td>\n",
  140. " <td>10.17</td>\n",
  141. " <td></td>\n",
  142. " <td></td>\n",
  143. " <td></td>\n",
  144. " <td></td>\n",
  145. " <td></td>\n",
  146. " <td>81</td>\n",
  147. " <td></td>\n",
  148. " <td></td>\n",
  149. " <td></td>\n",
  150. " <td></td>\n",
  151. " <td>5.36217880249023</td>\n",
  152. " <td></td>\n",
  153. " <td>88.92</td>\n",
  154. " </tr>\n",
  155. " <tr>\n",
  156. " <th>4</th>\n",
  157. " <td>Angola</td>\n",
  158. " <td>1381.00426770244</td>\n",
  159. " <td>5.57</td>\n",
  160. " <td>1.4613288</td>\n",
  161. " <td>23.1</td>\n",
  162. " <td>248358000</td>\n",
  163. " <td>69.4000015258789</td>\n",
  164. " <td>2</td>\n",
  165. " <td>9.99995388324075</td>\n",
  166. " <td>51.093</td>\n",
  167. " <td></td>\n",
  168. " <td>-2</td>\n",
  169. " <td>172.999227388199</td>\n",
  170. " <td>14.5546770095825</td>\n",
  171. " <td>75.6999969482422</td>\n",
  172. " <td>56.7</td>\n",
  173. " </tr>\n",
  174. " </tbody>\n",
  175. "</table>\n",
  176. "</div>"
  177. ],
  178. "text/plain": [
  179. " country incomeperperson alcconsumption armedforcesrate \\\n",
  180. "0 Afghanistan .03 .5696534 \n",
  181. "1 Albania 1914.99655094922 7.29 1.0247361 \n",
  182. "2 Algeria 2231.99333515006 .69 2.306817 \n",
  183. "3 Andorra 21943.3398976022 10.17 \n",
  184. "4 Angola 1381.00426770244 5.57 1.4613288 \n",
  185. "\n",
  186. " breastcancerper100th co2emissions femaleemployrate hivrate \\\n",
  187. "0 26.8 75944000 25.6000003814697 \n",
  188. "1 57.4 223747333.333333 42.0999984741211 \n",
  189. "2 23.5 2932108666.66667 31.7000007629394 .1 \n",
  190. "3 \n",
  191. "4 23.1 248358000 69.4000015258789 2 \n",
  192. "\n",
  193. " internetuserate lifeexpectancy oilperperson polityscore \\\n",
  194. "0 3.65412162280064 48.673 0 \n",
  195. "1 44.9899469578783 76.918 9 \n",
  196. "2 12.5000733055148 73.131 .42009452521537 2 \n",
  197. "3 81 \n",
  198. "4 9.99995388324075 51.093 -2 \n",
  199. "\n",
  200. " relectricperperson suicideper100th employrate urbanrate \n",
  201. "0 6.68438529968262 55.7000007629394 24.04 \n",
  202. "1 636.341383366604 7.69932985305786 51.4000015258789 46.72 \n",
  203. "2 590.509814347428 4.8487696647644 50.5 65.22 \n",
  204. "3 5.36217880249023 88.92 \n",
  205. "4 172.999227388199 14.5546770095825 75.6999969482422 56.7 "
  206. ]
  207. },
  208. "execution_count": 3,
  209. "metadata": {},
  210. "output_type": "execute_result"
  211. }
  212. ],
  213. "source": [
  214. "data.head(5)"
  215. ]
  216. },
  217. {
  218. "cell_type": "code",
  219. "execution_count": 4,
  220. "metadata": {},
  221. "outputs": [
  222. {
  223. "name": "stdout",
  224. "output_type": "stream",
  225. "text": [
  226. "(213, 16)\n",
  227. "213\n",
  228. "16\n"
  229. ]
  230. }
  231. ],
  232. "source": [
  233. "print(data.shape) # dimension of dataframe\n",
  234. "print (len(data)) # number of observations (rows)\n",
  235. "print (len(data.columns)) # number of variables (columns)"
  236. ]
  237. },
  238. {
  239. "cell_type": "code",
  240. "execution_count": 5,
  241. "metadata": {},
  242. "outputs": [
  243. {
  244. "data": {
  245. "text/plain": [
  246. "Index(['country', 'incomeperperson', 'alcconsumption', 'armedforcesrate',\n",
  247. " 'breastcancerper100th', 'co2emissions', 'femaleemployrate', 'hivrate',\n",
  248. " 'internetuserate', 'lifeexpectancy', 'oilperperson', 'polityscore',\n",
  249. " 'relectricperperson', 'suicideper100th', 'employrate', 'urbanrate'],\n",
  250. " dtype='object')"
  251. ]
  252. },
  253. "execution_count": 5,
  254. "metadata": {},
  255. "output_type": "execute_result"
  256. }
  257. ],
  258. "source": [
  259. "# Columns name\n",
  260. "data.columns"
  261. ]
  262. },
  263. {
  264. "cell_type": "markdown",
  265. "metadata": {},
  266. "source": [
  267. "### Setting variables you will be working with to numeric"
  268. ]
  269. },
  270. {
  271. "cell_type": "code",
  272. "execution_count": 6,
  273. "metadata": {
  274. "collapsed": true
  275. },
  276. "outputs": [],
  277. "source": [
  278. "#setting variables you will be working with to numeric\n",
  279. "data['suicideper100th'] =pd.to_numeric(data['suicideper100th'], errors='coerce')\n",
  280. "data['incomeperperson'] =pd.to_numeric(data['incomeperperson'], errors='coerce')\n",
  281. "data['internetuserate'] =pd.to_numeric(data['internetuserate'], errors='coerce')\n",
  282. "data['urbanrate'] =pd.to_numeric(data['urbanrate'], errors='coerce')"
  283. ]
  284. },
  285. {
  286. "cell_type": "code",
  287. "execution_count": 7,
  288. "metadata": {},
  289. "outputs": [
  290. {
  291. "name": "stdout",
  292. "output_type": "stream",
  293. "text": [
  294. "<class 'pandas.core.frame.DataFrame'>\n",
  295. "RangeIndex: 213 entries, 0 to 212\n",
  296. "Data columns (total 16 columns):\n",
  297. "country 213 non-null object\n",
  298. "incomeperperson 190 non-null float64\n",
  299. "alcconsumption 213 non-null object\n",
  300. "armedforcesrate 213 non-null object\n",
  301. "breastcancerper100th 213 non-null object\n",
  302. "co2emissions 213 non-null object\n",
  303. "femaleemployrate 213 non-null object\n",
  304. "hivrate 213 non-null object\n",
  305. "internetuserate 192 non-null float64\n",
  306. "lifeexpectancy 213 non-null object\n",
  307. "oilperperson 213 non-null object\n",
  308. "polityscore 213 non-null object\n",
  309. "relectricperperson 213 non-null object\n",
  310. "suicideper100th 191 non-null float64\n",
  311. "employrate 213 non-null object\n",
  312. "urbanrate 203 non-null float64\n",
  313. "dtypes: float64(4), object(12)\n",
  314. "memory usage: 26.7+ KB\n"
  315. ]
  316. }
  317. ],
  318. "source": [
  319. "# Check type of data after converting\n",
  320. "data.info()"
  321. ]
  322. },
  323. {
  324. "cell_type": "markdown",
  325. "metadata": {},
  326. "source": [
  327. "### Make subset of the data"
  328. ]
  329. },
  330. {
  331. "cell_type": "code",
  332. "execution_count": 8,
  333. "metadata": {
  334. "collapsed": true
  335. },
  336. "outputs": [],
  337. "source": [
  338. "sub_data = data[['country','suicideper100th', 'incomeperperson', 'internetuserate', 'urbanrate']].copy()"
  339. ]
  340. },
  341. {
  342. "cell_type": "code",
  343. "execution_count": 9,
  344. "metadata": {},
  345. "outputs": [
  346. {
  347. "data": {
  348. "text/html": [
  349. "<div>\n",
  350. "<table border=\"1\" class=\"dataframe\">\n",
  351. " <thead>\n",
  352. " <tr style=\"text-align: right;\">\n",
  353. " <th></th>\n",
  354. " <th>country</th>\n",
  355. " <th>suicideper100th</th>\n",
  356. " <th>incomeperperson</th>\n",
  357. " <th>internetuserate</th>\n",
  358. " <th>urbanrate</th>\n",
  359. " </tr>\n",
  360. " </thead>\n",
  361. " <tbody>\n",
  362. " <tr>\n",
  363. " <th>106</th>\n",
  364. " <td>Lesotho</td>\n",
  365. " <td>7.858619</td>\n",
  366. " <td>495.734247</td>\n",
  367. " <td>3.860565</td>\n",
  368. " <td>25.46</td>\n",
  369. " </tr>\n",
  370. " <tr>\n",
  371. " <th>92</th>\n",
  372. " <td>Italy</td>\n",
  373. " <td>4.930045</td>\n",
  374. " <td>18982.269285</td>\n",
  375. " <td>53.740217</td>\n",
  376. " <td>68.08</td>\n",
  377. " </tr>\n",
  378. " <tr>\n",
  379. " <th>131</th>\n",
  380. " <td>Mozambique</td>\n",
  381. " <td>10.550375</td>\n",
  382. " <td>389.763634</td>\n",
  383. " <td>4.170136</td>\n",
  384. " <td>36.84</td>\n",
  385. " </tr>\n",
  386. " <tr>\n",
  387. " <th>23</th>\n",
  388. " <td>Bosnia and Herzegovina</td>\n",
  389. " <td>11.836716</td>\n",
  390. " <td>2183.344867</td>\n",
  391. " <td>52.002061</td>\n",
  392. " <td>47.44</td>\n",
  393. " </tr>\n",
  394. " <tr>\n",
  395. " <th>199</th>\n",
  396. " <td>Uganda</td>\n",
  397. " <td>12.289122</td>\n",
  398. " <td>377.421113</td>\n",
  399. " <td>12.500255</td>\n",
  400. " <td>12.98</td>\n",
  401. " </tr>\n",
  402. " <tr>\n",
  403. " <th>122</th>\n",
  404. " <td>Mauritania</td>\n",
  405. " <td>6.882952</td>\n",
  406. " <td>609.131206</td>\n",
  407. " <td>2.999803</td>\n",
  408. " <td>41.00</td>\n",
  409. " </tr>\n",
  410. " <tr>\n",
  411. " <th>68</th>\n",
  412. " <td>Georgia</td>\n",
  413. " <td>1.574350</td>\n",
  414. " <td>1258.762596</td>\n",
  415. " <td>26.297251</td>\n",
  416. " <td>52.74</td>\n",
  417. " </tr>\n",
  418. " <tr>\n",
  419. " <th>21</th>\n",
  420. " <td>Bhutan</td>\n",
  421. " <td>15.542603</td>\n",
  422. " <td>1324.194906</td>\n",
  423. " <td>13.598876</td>\n",
  424. " <td>34.48</td>\n",
  425. " </tr>\n",
  426. " <tr>\n",
  427. " <th>133</th>\n",
  428. " <td>Namibia</td>\n",
  429. " <td>8.021970</td>\n",
  430. " <td>2667.246710</td>\n",
  431. " <td>6.500823</td>\n",
  432. " <td>36.84</td>\n",
  433. " </tr>\n",
  434. " <tr>\n",
  435. " <th>30</th>\n",
  436. " <td>Cambodia</td>\n",
  437. " <td>4.961071</td>\n",
  438. " <td>557.947513</td>\n",
  439. " <td>1.259934</td>\n",
  440. " <td>21.56</td>\n",
  441. " </tr>\n",
  442. " </tbody>\n",
  443. "</table>\n",
  444. "</div>"
  445. ],
  446. "text/plain": [
  447. " country suicideper100th incomeperperson \\\n",
  448. "106 Lesotho 7.858619 495.734247 \n",
  449. "92 Italy 4.930045 18982.269285 \n",
  450. "131 Mozambique 10.550375 389.763634 \n",
  451. "23 Bosnia and Herzegovina 11.836716 2183.344867 \n",
  452. "199 Uganda 12.289122 377.421113 \n",
  453. "122 Mauritania 6.882952 609.131206 \n",
  454. "68 Georgia 1.574350 1258.762596 \n",
  455. "21 Bhutan 15.542603 1324.194906 \n",
  456. "133 Namibia 8.021970 2667.246710 \n",
  457. "30 Cambodia 4.961071 557.947513 \n",
  458. "\n",
  459. " internetuserate urbanrate \n",
  460. "106 3.860565 25.46 \n",
  461. "92 53.740217 68.08 \n",
  462. "131 4.170136 36.84 \n",
  463. "23 52.002061 47.44 \n",
  464. "199 12.500255 12.98 \n",
  465. "122 2.999803 41.00 \n",
  466. "68 26.297251 52.74 \n",
  467. "21 13.598876 34.48 \n",
  468. "133 6.500823 36.84 \n",
  469. "30 1.259934 21.56 "
  470. ]
  471. },
  472. "execution_count": 9,
  473. "metadata": {},
  474. "output_type": "execute_result"
  475. }
  476. ],
  477. "source": [
  478. "sub_data.sample(10)"
  479. ]
  480. },
  481. {
  482. "cell_type": "markdown",
  483. "metadata": {},
  484. "source": [
  485. "### Check for missing values"
  486. ]
  487. },
  488. {
  489. "cell_type": "code",
  490. "execution_count": 10,
  491. "metadata": {},
  492. "outputs": [
  493. {
  494. "data": {
  495. "text/plain": [
  496. "country 0\n",
  497. "suicideper100th 22\n",
  498. "incomeperperson 23\n",
  499. "internetuserate 21\n",
  500. "urbanrate 10\n",
  501. "dtype: int64"
  502. ]
  503. },
  504. "execution_count": 10,
  505. "metadata": {},
  506. "output_type": "execute_result"
  507. }
  508. ],
  509. "source": [
  510. "sub_data.isnull().sum()"
  511. ]
  512. },
  513. {
  514. "cell_type": "code",
  515. "execution_count": 11,
  516. "metadata": {},
  517. "outputs": [
  518. {
  519. "data": {
  520. "text/plain": [
  521. "(213, 5)"
  522. ]
  523. },
  524. "execution_count": 11,
  525. "metadata": {},
  526. "output_type": "execute_result"
  527. }
  528. ],
  529. "source": [
  530. "sub_data.shape"
  531. ]
  532. },
  533. {
  534. "cell_type": "markdown",
  535. "metadata": {},
  536. "source": [
  537. "### To group the quantities into appropriate bins"
  538. ]
  539. },
  540. {
  541. "cell_type": "code",
  542. "execution_count": 12,
  543. "metadata": {},
  544. "outputs": [
  545. {
  546. "data": {
  547. "text/html": [
  548. "<div>\n",
  549. "<table border=\"1\" class=\"dataframe\">\n",
  550. " <thead>\n",
  551. " <tr style=\"text-align: right;\">\n",
  552. " <th></th>\n",
  553. " <th>suicideper100th</th>\n",
  554. " <th>incomeperperson</th>\n",
  555. " <th>internetuserate</th>\n",
  556. " <th>urbanrate</th>\n",
  557. " </tr>\n",
  558. " </thead>\n",
  559. " <tbody>\n",
  560. " <tr>\n",
  561. " <th>count</th>\n",
  562. " <td>191.000000</td>\n",
  563. " <td>190.000000</td>\n",
  564. " <td>192.000000</td>\n",
  565. " <td>203.000000</td>\n",
  566. " </tr>\n",
  567. " <tr>\n",
  568. " <th>mean</th>\n",
  569. " <td>9.640839</td>\n",
  570. " <td>8740.966076</td>\n",
  571. " <td>35.632716</td>\n",
  572. " <td>56.769360</td>\n",
  573. " </tr>\n",
  574. " <tr>\n",
  575. " <th>std</th>\n",
  576. " <td>6.300178</td>\n",
  577. " <td>14262.809083</td>\n",
  578. " <td>27.780285</td>\n",
  579. " <td>23.844933</td>\n",
  580. " </tr>\n",
  581. " <tr>\n",
  582. " <th>min</th>\n",
  583. " <td>0.201449</td>\n",
  584. " <td>103.775857</td>\n",
  585. " <td>0.210066</td>\n",
  586. " <td>10.400000</td>\n",
  587. " </tr>\n",
  588. " <tr>\n",
  589. " <th>25%</th>\n",
  590. " <td>4.988449</td>\n",
  591. " <td>748.245151</td>\n",
  592. " <td>9.999604</td>\n",
  593. " <td>36.830000</td>\n",
  594. " </tr>\n",
  595. " <tr>\n",
  596. " <th>50%</th>\n",
  597. " <td>8.262893</td>\n",
  598. " <td>2553.496056</td>\n",
  599. " <td>31.810121</td>\n",
  600. " <td>57.940000</td>\n",
  601. " </tr>\n",
  602. " <tr>\n",
  603. " <th>75%</th>\n",
  604. " <td>12.328551</td>\n",
  605. " <td>9379.891165</td>\n",
  606. " <td>56.416046</td>\n",
  607. " <td>74.210000</td>\n",
  608. " </tr>\n",
  609. " <tr>\n",
  610. " <th>max</th>\n",
  611. " <td>35.752872</td>\n",
  612. " <td>105147.437697</td>\n",
  613. " <td>95.638113</td>\n",
  614. " <td>100.000000</td>\n",
  615. " </tr>\n",
  616. " </tbody>\n",
  617. "</table>\n",
  618. "</div>"
  619. ],
  620. "text/plain": [
  621. " suicideper100th incomeperperson internetuserate urbanrate\n",
  622. "count 191.000000 190.000000 192.000000 203.000000\n",
  623. "mean 9.640839 8740.966076 35.632716 56.769360\n",
  624. "std 6.300178 14262.809083 27.780285 23.844933\n",
  625. "min 0.201449 103.775857 0.210066 10.400000\n",
  626. "25% 4.988449 748.245151 9.999604 36.830000\n",
  627. "50% 8.262893 2553.496056 31.810121 57.940000\n",
  628. "75% 12.328551 9379.891165 56.416046 74.210000\n",
  629. "max 35.752872 105147.437697 95.638113 100.000000"
  630. ]
  631. },
  632. "execution_count": 12,
  633. "metadata": {},
  634. "output_type": "execute_result"
  635. }
  636. ],
  637. "source": [
  638. "sub_data.describe()"
  639. ]
  640. },
  641. {
  642. "cell_type": "code",
  643. "execution_count": 13,
  644. "metadata": {
  645. "collapsed": true
  646. },
  647. "outputs": [],
  648. "source": [
  649. "for col in ('suicideper100th', 'incomeperperson', 'internetuserate', 'urbanrate'): \n",
  650. " if col == 'suicideper100th':\n",
  651. " sub_data.loc[sub_data[col] <= 5, col] = 1\n",
  652. " sub_data.loc[( sub_data[col] > 5) & ( sub_data[col] <= 10), col] = 2\n",
  653. " sub_data.loc[( sub_data[col] > 10) & ( sub_data[col] <= 15), col] = 3\n",
  654. " sub_data.loc[( sub_data[col] > 15) & ( sub_data[col] <= 20), col] = 4\n",
  655. " sub_data.loc[( sub_data[col] > 20) & ( sub_data[col] <= 25), col] = 5\n",
  656. " sub_data.loc[( sub_data[col] > 25) & ( sub_data[col] <= 30), col] = 6\n",
  657. " sub_data.loc[( sub_data[col] > 30) & ( sub_data[col] <= 35), col] = 7\n",
  658. " sub_data.loc[( sub_data[col] > 35) & ( sub_data[col] <= 40), col] = 8\n",
  659. " \n",
  660. " \n",
  661. " if col == 'incomeperperson':\n",
  662. " sub_data.loc[sub_data[col] <= 1000, col] = 1\n",
  663. " sub_data.loc[( sub_data[col] > 1000) & ( sub_data[col] <= 2000), col] = 2\n",
  664. " sub_data.loc[( sub_data[col] > 2000) & ( sub_data[col] <= 3000), col] = 3\n",
  665. " sub_data.loc[( sub_data[col] > 3000) & ( sub_data[col] <= 4000), col] = 4\n",
  666. " sub_data.loc[( sub_data[col] > 4000) & ( sub_data[col] <= 5000), col] = 5\n",
  667. " sub_data.loc[( sub_data[col] > 5000) & ( sub_data[col] <= 6000), col] = 6\n",
  668. " sub_data.loc[( sub_data[col] > 6000) & ( sub_data[col] <= 7000), col] = 7\n",
  669. " sub_data.loc[( sub_data[col] > 7000) & ( sub_data[col] <= 8000), col] = 8\n",
  670. " sub_data.loc[( sub_data[col] > 8000) & ( sub_data[col] <= 9000), col] = 9\n",
  671. " sub_data.loc[( sub_data[col] > 9000) & ( sub_data[col] <= 10000), col] = 10\n",
  672. " sub_data.loc[( sub_data[col] > 10000) & ( sub_data[col] <= 11000), col] =11\n",
  673. " sub_data.loc[( sub_data[col] > 11000) & ( sub_data[col] <= 12000), col] = 12\n",
  674. " sub_data.loc[( sub_data[col] > 12000) & ( sub_data[col] <= 13000), col] = 13\n",
  675. " sub_data.loc[( sub_data[col] > 13000) & ( sub_data[col] <= 14000), col] = 14\n",
  676. " sub_data.loc[( sub_data[col] > 14000) & ( sub_data[col] <= 15000), col] = 15\n",
  677. " sub_data.loc[( sub_data[col] > 15000), col] = 16\n",
  678. " \n",
  679. " \n",
  680. " \n",
  681. " if col == 'internetuserate':\n",
  682. " sub_data.loc[sub_data[col] <= 10, col] = 1\n",
  683. " sub_data.loc[( sub_data[col] > 10) & ( sub_data[col] <= 20), col] = 2\n",
  684. " sub_data.loc[( sub_data[col] > 20) & ( sub_data[col] <= 30), col] = 3\n",
  685. " sub_data.loc[( sub_data[col] > 30) & ( sub_data[col] <= 40), col] = 4\n",
  686. " sub_data.loc[( sub_data[col] > 40) & ( sub_data[col] <= 50), col] = 5\n",
  687. " sub_data.loc[( sub_data[col] > 50) & ( sub_data[col] <= 60), col] = 6\n",
  688. " sub_data.loc[( sub_data[col] > 60) & ( sub_data[col] <= 70), col] = 7\n",
  689. " sub_data.loc[( sub_data[col] > 70) & ( sub_data[col] <= 80), col] = 8\n",
  690. " sub_data.loc[( sub_data[col] > 80) & ( sub_data[col] <= 90), col] = 9\n",
  691. " sub_data.loc[( sub_data[col] > 90) & ( sub_data[col] <= 100), col] = 10\n",
  692. " sub_data.loc[( sub_data[col] > 100) & ( sub_data[col] <= 110), col] =11\n",
  693. " sub_data.loc[( sub_data[col] > 110), col] = 12\n",
  694. " \n",
  695. " \n",
  696. " if col == 'urbanrate':\n",
  697. " sub_data.loc[sub_data[col] <= 10, col] = 1\n",
  698. " sub_data.loc[( sub_data[col] > 10) & ( sub_data[col] <= 20), col] = 2\n",
  699. " sub_data.loc[( sub_data[col] > 20) & ( sub_data[col] <= 30), col] = 3\n",
  700. " sub_data.loc[( sub_data[col] > 30) & ( sub_data[col] <= 40), col] = 4\n",
  701. " sub_data.loc[( sub_data[col] > 40) & ( sub_data[col] <= 50), col] = 5\n",
  702. " sub_data.loc[( sub_data[col] > 50) & ( sub_data[col] <= 60), col] = 6\n",
  703. " sub_data.loc[( sub_data[col] > 60) & ( sub_data[col] <= 70), col] = 7\n",
  704. " sub_data.loc[( sub_data[col] > 70) & ( sub_data[col] <= 80), col] = 8\n",
  705. " sub_data.loc[( sub_data[col] > 80) & ( sub_data[col] <= 90), col] = 9\n",
  706. " sub_data.loc[( sub_data[col] > 90) & ( sub_data[col] <= 100), col] = 10\n",
  707. " sub_data.loc[( sub_data[col] > 100) & ( sub_data[col] <= 110), col] =11\n",
  708. " sub_data.loc[( sub_data[col] > 110), col] = 12\n",
  709. " \n",
  710. " \n",
  711. " \n",
  712. " "
  713. ]
  714. },
  715. {
  716. "cell_type": "markdown",
  717. "metadata": {},
  718. "source": [
  719. "### Counts and percentages (i.e. frequency distributions) for each variable"
  720. ]
  721. },
  722. {
  723. "cell_type": "code",
  724. "execution_count": 14,
  725. "metadata": {},
  726. "outputs": [
  727. {
  728. "data": {
  729. "text/html": [
  730. "<div>\n",
  731. "<table border=\"1\" class=\"dataframe\">\n",
  732. " <thead>\n",
  733. " <tr style=\"text-align: right;\">\n",
  734. " <th></th>\n",
  735. " <th>country</th>\n",
  736. " <th>suicideper100th</th>\n",
  737. " <th>incomeperperson</th>\n",
  738. " <th>internetuserate</th>\n",
  739. " <th>urbanrate</th>\n",
  740. " </tr>\n",
  741. " </thead>\n",
  742. " <tbody>\n",
  743. " <tr>\n",
  744. " <th>47</th>\n",
  745. " <td>Cuba</td>\n",
  746. " <td>3.0</td>\n",
  747. " <td>5.0</td>\n",
  748. " <td>2.0</td>\n",
  749. " <td>8.0</td>\n",
  750. " </tr>\n",
  751. " <tr>\n",
  752. " <th>119</th>\n",
  753. " <td>Malta</td>\n",
  754. " <td>1.0</td>\n",
  755. " <td>12.0</td>\n",
  756. " <td>7.0</td>\n",
  757. " <td>10.0</td>\n",
  758. " </tr>\n",
  759. " <tr>\n",
  760. " <th>171</th>\n",
  761. " <td>Seychelles</td>\n",
  762. " <td>2.0</td>\n",
  763. " <td>9.0</td>\n",
  764. " <td>5.0</td>\n",
  765. " <td>6.0</td>\n",
  766. " </tr>\n",
  767. " <tr>\n",
  768. " <th>142</th>\n",
  769. " <td>Nigeria</td>\n",
  770. " <td>2.0</td>\n",
  771. " <td>1.0</td>\n",
  772. " <td>3.0</td>\n",
  773. " <td>5.0</td>\n",
  774. " </tr>\n",
  775. " <tr>\n",
  776. " <th>16</th>\n",
  777. " <td>Belarus</td>\n",
  778. " <td>6.0</td>\n",
  779. " <td>3.0</td>\n",
  780. " <td>4.0</td>\n",
  781. " <td>8.0</td>\n",
  782. " </tr>\n",
  783. " <tr>\n",
  784. " <th>61</th>\n",
  785. " <td>Faeroe Islands</td>\n",
  786. " <td>NaN</td>\n",
  787. " <td>NaN</td>\n",
  788. " <td>8.0</td>\n",
  789. " <td>5.0</td>\n",
  790. " </tr>\n",
  791. " <tr>\n",
  792. " <th>68</th>\n",
  793. " <td>Georgia</td>\n",
  794. " <td>1.0</td>\n",
  795. " <td>2.0</td>\n",
  796. " <td>3.0</td>\n",
  797. " <td>6.0</td>\n",
  798. " </tr>\n",
  799. " <tr>\n",
  800. " <th>5</th>\n",
  801. " <td>Antigua and Barbuda</td>\n",
  802. " <td>1.0</td>\n",
  803. " <td>12.0</td>\n",
  804. " <td>9.0</td>\n",
  805. " <td>4.0</td>\n",
  806. " </tr>\n",
  807. " <tr>\n",
  808. " <th>117</th>\n",
  809. " <td>Maldives</td>\n",
  810. " <td>5.0</td>\n",
  811. " <td>5.0</td>\n",
  812. " <td>3.0</td>\n",
  813. " <td>4.0</td>\n",
  814. " </tr>\n",
  815. " <tr>\n",
  816. " <th>110</th>\n",
  817. " <td>Lithuania</td>\n",
  818. " <td>7.0</td>\n",
  819. " <td>6.0</td>\n",
  820. " <td>7.0</td>\n",
  821. " <td>7.0</td>\n",
  822. " </tr>\n",
  823. " <tr>\n",
  824. " <th>85</th>\n",
  825. " <td>Iceland</td>\n",
  826. " <td>3.0</td>\n",
  827. " <td>16.0</td>\n",
  828. " <td>10.0</td>\n",
  829. " <td>10.0</td>\n",
  830. " </tr>\n",
  831. " <tr>\n",
  832. " <th>72</th>\n",
  833. " <td>Greece</td>\n",
  834. " <td>1.0</td>\n",
  835. " <td>14.0</td>\n",
  836. " <td>5.0</td>\n",
  837. " <td>7.0</td>\n",
  838. " </tr>\n",
  839. " <tr>\n",
  840. " <th>94</th>\n",
  841. " <td>Japan</td>\n",
  842. " <td>4.0</td>\n",
  843. " <td>16.0</td>\n",
  844. " <td>8.0</td>\n",
  845. " <td>7.0</td>\n",
  846. " </tr>\n",
  847. " <tr>\n",
  848. " <th>21</th>\n",
  849. " <td>Bhutan</td>\n",
  850. " <td>4.0</td>\n",
  851. " <td>2.0</td>\n",
  852. " <td>2.0</td>\n",
  853. " <td>4.0</td>\n",
  854. " </tr>\n",
  855. " <tr>\n",
  856. " <th>137</th>\n",
  857. " <td>Netherlands Antilles</td>\n",
  858. " <td>NaN</td>\n",
  859. " <td>NaN</td>\n",
  860. " <td>NaN</td>\n",
  861. " <td>10.0</td>\n",
  862. " </tr>\n",
  863. " <tr>\n",
  864. " <th>139</th>\n",
  865. " <td>New Zealand</td>\n",
  866. " <td>3.0</td>\n",
  867. " <td>15.0</td>\n",
  868. " <td>9.0</td>\n",
  869. " <td>9.0</td>\n",
  870. " </tr>\n",
  871. " <tr>\n",
  872. " <th>88</th>\n",
  873. " <td>Iran</td>\n",
  874. " <td>2.0</td>\n",
  875. " <td>3.0</td>\n",
  876. " <td>2.0</td>\n",
  877. " <td>7.0</td>\n",
  878. " </tr>\n",
  879. " <tr>\n",
  880. " <th>60</th>\n",
  881. " <td>Ethiopia</td>\n",
  882. " <td>3.0</td>\n",
  883. " <td>1.0</td>\n",
  884. " <td>1.0</td>\n",
  885. " <td>2.0</td>\n",
  886. " </tr>\n",
  887. " <tr>\n",
  888. " <th>13</th>\n",
  889. " <td>Bahrain</td>\n",
  890. " <td>1.0</td>\n",
  891. " <td>13.0</td>\n",
  892. " <td>6.0</td>\n",
  893. " <td>9.0</td>\n",
  894. " </tr>\n",
  895. " <tr>\n",
  896. " <th>116</th>\n",
  897. " <td>Malaysia</td>\n",
  898. " <td>2.0</td>\n",
  899. " <td>6.0</td>\n",
  900. " <td>6.0</td>\n",
  901. " <td>8.0</td>\n",
  902. " </tr>\n",
  903. " </tbody>\n",
  904. "</table>\n",
  905. "</div>"
  906. ],
  907. "text/plain": [
  908. " country suicideper100th incomeperperson internetuserate \\\n",
  909. "47 Cuba 3.0 5.0 2.0 \n",
  910. "119 Malta 1.0 12.0 7.0 \n",
  911. "171 Seychelles 2.0 9.0 5.0 \n",
  912. "142 Nigeria 2.0 1.0 3.0 \n",
  913. "16 Belarus 6.0 3.0 4.0 \n",
  914. "61 Faeroe Islands NaN NaN 8.0 \n",
  915. "68 Georgia 1.0 2.0 3.0 \n",
  916. "5 Antigua and Barbuda 1.0 12.0 9.0 \n",
  917. "117 Maldives 5.0 5.0 3.0 \n",
  918. "110 Lithuania 7.0 6.0 7.0 \n",
  919. "85 Iceland 3.0 16.0 10.0 \n",
  920. "72 Greece 1.0 14.0 5.0 \n",
  921. "94 Japan 4.0 16.0 8.0 \n",
  922. "21 Bhutan 4.0 2.0 2.0 \n",
  923. "137 Netherlands Antilles NaN NaN NaN \n",
  924. "139 New Zealand 3.0 15.0 9.0 \n",
  925. "88 Iran 2.0 3.0 2.0 \n",
  926. "60 Ethiopia 3.0 1.0 1.0 \n",
  927. "13 Bahrain 1.0 13.0 6.0 \n",
  928. "116 Malaysia 2.0 6.0 6.0 \n",
  929. "\n",
  930. " urbanrate \n",
  931. "47 8.0 \n",
  932. "119 10.0 \n",
  933. "171 6.0 \n",
  934. "142 5.0 \n",
  935. "16 8.0 \n",
  936. "61 5.0 \n",
  937. "68 6.0 \n",
  938. "5 4.0 \n",
  939. "117 4.0 \n",
  940. "110 7.0 \n",
  941. "85 10.0 \n",
  942. "72 7.0 \n",
  943. "94 7.0 \n",
  944. "21 4.0 \n",
  945. "137 10.0 \n",
  946. "139 9.0 \n",
  947. "88 7.0 \n",
  948. "60 2.0 \n",
  949. "13 9.0 \n",
  950. "116 8.0 "
  951. ]
  952. },
  953. "execution_count": 14,
  954. "metadata": {},
  955. "output_type": "execute_result"
  956. }
  957. ],
  958. "source": [
  959. "sub_data.sample(20)"
  960. ]
  961. },
  962. {
  963. "cell_type": "code",
  964. "execution_count": 15,
  965. "metadata": {},
  966. "outputs": [
  967. {
  968. "name": "stdout",
  969. "output_type": "stream",
  970. "text": [
  971. "counts for suicideper100th\n",
  972. " 2.0 65\n",
  973. " 3.0 51\n",
  974. " 1.0 49\n",
  975. "NaN 22\n",
  976. " 4.0 12\n",
  977. " 5.0 6\n",
  978. " 6.0 6\n",
  979. " 7.0 1\n",
  980. " 8.0 1\n",
  981. "Name: suicideper100th, dtype: int64\n",
  982. "percentages for suicideper100th\n",
  983. " 2.0 0.305164\n",
  984. " 3.0 0.239437\n",
  985. " 1.0 0.230047\n",
  986. "NaN 0.103286\n",
  987. " 4.0 0.056338\n",
  988. " 5.0 0.028169\n",
  989. " 6.0 0.028169\n",
  990. " 7.0 0.004695\n",
  991. " 8.0 0.004695\n",
  992. "Name: suicideper100th, dtype: float64\n"
  993. ]
  994. }
  995. ],
  996. "source": [
  997. "print ('counts for suicideper100th')\n",
  998. "c1 = sub_data['suicideper100th'].value_counts(sort=True, dropna=False)\n",
  999. "print (c1)\n",
  1000. "\n",
  1001. "\n",
  1002. "print ('percentages for suicideper100th')\n",
  1003. "p1 = sub_data['suicideper100th'].value_counts(sort=True, dropna=False, normalize=True)\n",
  1004. "print (p1)"
  1005. ]
  1006. },
  1007. {
  1008. "cell_type": "code",
  1009. "execution_count": 16,
  1010. "metadata": {},
  1011. "outputs": [
  1012. {
  1013. "name": "stdout",
  1014. "output_type": "stream",
  1015. "text": [
  1016. "counts for incomeperperson\n",
  1017. " 1.0 54\n",
  1018. " 16.0 37\n",
  1019. " 2.0 26\n",
  1020. "NaN 23\n",
  1021. " 3.0 22\n",
  1022. " 6.0 11\n",
  1023. " 7.0 8\n",
  1024. " 5.0 7\n",
  1025. " 4.0 6\n",
  1026. " 12.0 4\n",
  1027. " 10.0 4\n",
  1028. " 9.0 3\n",
  1029. " 11.0 2\n",
  1030. " 13.0 2\n",
  1031. " 8.0 2\n",
  1032. " 14.0 1\n",
  1033. " 15.0 1\n",
  1034. "Name: incomeperperson, dtype: int64\n",
  1035. "percentages for incomeperperson\n",
  1036. " 1.0 0.253521\n",
  1037. " 16.0 0.173709\n",
  1038. " 2.0 0.122066\n",
  1039. "NaN 0.107981\n",
  1040. " 3.0 0.103286\n",
  1041. " 6.0 0.051643\n",
  1042. " 7.0 0.037559\n",
  1043. " 5.0 0.032864\n",
  1044. " 4.0 0.028169\n",
  1045. " 12.0 0.018779\n",
  1046. " 10.0 0.018779\n",
  1047. " 9.0 0.014085\n",
  1048. " 11.0 0.009390\n",
  1049. " 13.0 0.009390\n",
  1050. " 8.0 0.009390\n",
  1051. " 14.0 0.004695\n",
  1052. " 15.0 0.004695\n",
  1053. "Name: incomeperperson, dtype: float64\n"
  1054. ]
  1055. }
  1056. ],
  1057. "source": [
  1058. "print ('counts for incomeperperson')\n",
  1059. "c2 = sub_data['incomeperperson'].value_counts(sort=True, dropna=False)\n",
  1060. "print (c2)\n",
  1061. "\n",
  1062. "\n",
  1063. "print ('percentages for incomeperperson')\n",
  1064. "p2= sub_data['incomeperperson'].value_counts(sort=True, dropna=False, normalize=True)\n",
  1065. "print (p2)"
  1066. ]
  1067. },
  1068. {
  1069. "cell_type": "code",
  1070. "execution_count": 17,
  1071. "metadata": {},
  1072. "outputs": [
  1073. {
  1074. "name": "stdout",
  1075. "output_type": "stream",
  1076. "text": [
  1077. "counts for internetuserate\n",
  1078. " 1.0 49\n",
  1079. " 2.0 27\n",
  1080. " 5.0 25\n",
  1081. "NaN 21\n",
  1082. " 4.0 18\n",
  1083. " 3.0 17\n",
  1084. " 8.0 16\n",
  1085. " 7.0 14\n",
  1086. " 9.0 12\n",
  1087. " 6.0 9\n",
  1088. " 10.0 5\n",
  1089. "Name: internetuserate, dtype: int64\n",
  1090. "percentages for internetuserate\n",
  1091. " 1.0 0.230047\n",
  1092. " 2.0 0.126761\n",
  1093. " 5.0 0.117371\n",
  1094. "NaN 0.098592\n",
  1095. " 4.0 0.084507\n",
  1096. " 3.0 0.079812\n",
  1097. " 8.0 0.075117\n",
  1098. " 7.0 0.065728\n",
  1099. " 9.0 0.056338\n",
  1100. " 6.0 0.042254\n",
  1101. " 10.0 0.023474\n",
  1102. "Name: internetuserate, dtype: float64\n"
  1103. ]
  1104. }
  1105. ],
  1106. "source": [
  1107. "print ('counts for internetuserate')\n",
  1108. "c3 = sub_data['internetuserate'].value_counts(sort=True, dropna=False)\n",
  1109. "print (c3)\n",
  1110. "\n",
  1111. "\n",
  1112. "print ('percentages for internetuserate')\n",
  1113. "p3 = sub_data['internetuserate'].value_counts(sort=True, dropna=False, normalize=True)\n",
  1114. "print (p3)"
  1115. ]
  1116. },
  1117. {
  1118. "cell_type": "code",
  1119. "execution_count": 18,
  1120. "metadata": {},
  1121. "outputs": [
  1122. {
  1123. "name": "stdout",
  1124. "output_type": "stream",
  1125. "text": [
  1126. "counts for urbanrate\n",
  1127. " 7.0 34\n",
  1128. " 8.0 24\n",
  1129. " 4.0 24\n",
  1130. " 6.0 24\n",
  1131. " 5.0 22\n",
  1132. " 3.0 22\n",
  1133. " 9.0 21\n",
  1134. " 10.0 19\n",
  1135. " 2.0 13\n",
  1136. "NaN 10\n",
  1137. "Name: urbanrate, dtype: int64\n",
  1138. "percentages for urbanrate\n",
  1139. " 7.0 0.159624\n",
  1140. " 8.0 0.112676\n",
  1141. " 4.0 0.112676\n",
  1142. " 6.0 0.112676\n",
  1143. " 5.0 0.103286\n",
  1144. " 3.0 0.103286\n",
  1145. " 9.0 0.098592\n",
  1146. " 10.0 0.089202\n",
  1147. " 2.0 0.061033\n",
  1148. "NaN 0.046948\n",
  1149. "Name: urbanrate, dtype: float64\n"
  1150. ]
  1151. }
  1152. ],
  1153. "source": [
  1154. "print ('counts for urbanrate')\n",
  1155. "c4 = sub_data['urbanrate'].value_counts(sort=True, dropna=False)\n",
  1156. "print (c4)\n",
  1157. "\n",
  1158. "\n",
  1159. "print ('percentages for urbanrate')\n",
  1160. "p4 = sub_data['urbanrate'].value_counts(sort=True, dropna=False, normalize=True)\n",
  1161. "print (p4)"
  1162. ]
  1163. },
  1164. {
  1165. "cell_type": "code",
  1166. "execution_count": 19,
  1167. "metadata": {},
  1168. "outputs": [
  1169. {
  1170. "data": {
  1171. "text/html": [
  1172. "<div>\n",
  1173. "<table border=\"1\" class=\"dataframe\">\n",
  1174. " <thead>\n",
  1175. " <tr style=\"text-align: right;\">\n",
  1176. " <th></th>\n",
  1177. " <th>suicideper100th</th>\n",
  1178. " <th>incomeperperson</th>\n",
  1179. " <th>internetuserate</th>\n",
  1180. " <th>urbanrate</th>\n",
  1181. " </tr>\n",
  1182. " </thead>\n",
  1183. " <tbody>\n",
  1184. " <tr>\n",
  1185. " <th>count</th>\n",
  1186. " <td>191.000000</td>\n",
  1187. " <td>190.000000</td>\n",
  1188. " <td>192.000000</td>\n",
  1189. " <td>203.000000</td>\n",
  1190. " </tr>\n",
  1191. " <tr>\n",
  1192. " <th>mean</th>\n",
  1193. " <td>2.413613</td>\n",
  1194. " <td>6.068421</td>\n",
  1195. " <td>4.109375</td>\n",
  1196. " <td>6.162562</td>\n",
  1197. " </tr>\n",
  1198. " <tr>\n",
  1199. " <th>std</th>\n",
  1200. " <td>1.310533</td>\n",
  1201. " <td>5.745074</td>\n",
  1202. " <td>2.789944</td>\n",
  1203. " <td>2.377322</td>\n",
  1204. " </tr>\n",
  1205. " <tr>\n",
  1206. " <th>min</th>\n",
  1207. " <td>1.000000</td>\n",
  1208. " <td>1.000000</td>\n",
  1209. " <td>1.000000</td>\n",
  1210. " <td>2.000000</td>\n",
  1211. " </tr>\n",
  1212. " <tr>\n",
  1213. " <th>25%</th>\n",
  1214. " <td>1.000000</td>\n",
  1215. " <td>1.000000</td>\n",
  1216. " <td>1.000000</td>\n",
  1217. " <td>4.000000</td>\n",
  1218. " </tr>\n",
  1219. " <tr>\n",
  1220. " <th>50%</th>\n",
  1221. " <td>2.000000</td>\n",
  1222. " <td>3.000000</td>\n",
  1223. " <td>4.000000</td>\n",
  1224. " <td>6.000000</td>\n",
  1225. " </tr>\n",
  1226. " <tr>\n",
  1227. " <th>75%</th>\n",
  1228. " <td>3.000000</td>\n",
  1229. " <td>10.000000</td>\n",
  1230. " <td>6.000000</td>\n",
  1231. " <td>8.000000</td>\n",
  1232. " </tr>\n",
  1233. " <tr>\n",
  1234. " <th>max</th>\n",
  1235. " <td>8.000000</td>\n",
  1236. " <td>16.000000</td>\n",
  1237. " <td>10.000000</td>\n",
  1238. " <td>10.000000</td>\n",
  1239. " </tr>\n",
  1240. " </tbody>\n",
  1241. "</table>\n",
  1242. "</div>"
  1243. ],
  1244. "text/plain": [
  1245. " suicideper100th incomeperperson internetuserate urbanrate\n",
  1246. "count 191.000000 190.000000 192.000000 203.000000\n",
  1247. "mean 2.413613 6.068421 4.109375 6.162562\n",
  1248. "std 1.310533 5.745074 2.789944 2.377322\n",
  1249. "min 1.000000 1.000000 1.000000 2.000000\n",
  1250. "25% 1.000000 1.000000 1.000000 4.000000\n",
  1251. "50% 2.000000 3.000000 4.000000 6.000000\n",
  1252. "75% 3.000000 10.000000 6.000000 8.000000\n",
  1253. "max 8.000000 16.000000 10.000000 10.000000"
  1254. ]
  1255. },
  1256. "execution_count": 19,
  1257. "metadata": {},
  1258. "output_type": "execute_result"
  1259. }
  1260. ],
  1261. "source": [
  1262. "sub_data.describe()"
  1263. ]
  1264. },
  1265. {
  1266. "cell_type": "code",
  1267. "execution_count": null,
  1268. "metadata": {
  1269. "collapsed": true
  1270. },
  1271. "outputs": [],
  1272. "source": []
  1273. }
  1274. ],
  1275. "metadata": {
  1276. "kernelspec": {
  1277. "display_name": "Python3",
  1278. "language": "python",
  1279. "name": "python3"
  1280. },
  1281. "language_info": {
  1282. "codemirror_mode": {
  1283. "name": "ipython",
  1284. "version": 3
  1285. },
  1286. "file_extension": ".py",
  1287. "mimetype": "text/x-python",
  1288. "name": "python",
  1289. "nbconvert_exporter": "python",
  1290. "pygments_lexer": "ipython3",
  1291. "version": "3.6.3"
  1292. }
  1293. },
  1294. "nbformat": 4,
  1295. "nbformat_minor": 2
  1296. }
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!