API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Oct 16th, 2019
106
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 9.73 KB | None | 0 0
raw download clone embed print report
  1. {
  2. "cells": [
  3. {
  4. "cell_type": "markdown",
  5. "metadata": {},
  6. "source": [
  7. "### Finding categorical variables"
  8. ]
  9. },
  10. {
  11. "cell_type": "code",
  12. "execution_count": 2,
  13. "metadata": {},
  14. "outputs": [
  15. {
  16. "data": {
  17. "text/html": [
  18. "<div>\n",
  19. "<style scoped>\n",
  20. " .dataframe tbody tr th:only-of-type {\n",
  21. " vertical-align: middle;\n",
  22. " }\n",
  23. "\n",
  24. " .dataframe tbody tr th {\n",
  25. " vertical-align: top;\n",
  26. " }\n",
  27. "\n",
  28. " .dataframe thead th {\n",
  29. " text-align: right;\n",
  30. " }\n",
  31. "</style>\n",
  32. "<table border=\"1\" class=\"dataframe\">\n",
  33. " <thead>\n",
  34. " <tr style=\"text-align: right;\">\n",
  35. " <th></th>\n",
  36. " <th>satisfaction</th>\n",
  37. " <th>evaluation</th>\n",
  38. " <th>number_of_projects</th>\n",
  39. " <th>average_montly_hours</th>\n",
  40. " <th>time_spend_company</th>\n",
  41. " <th>work_accident</th>\n",
  42. " <th>churn</th>\n",
  43. " <th>promotion</th>\n",
  44. " <th>department</th>\n",
  45. " <th>salary</th>\n",
  46. " </tr>\n",
  47. " </thead>\n",
  48. " <tbody>\n",
  49. " <tr>\n",
  50. " <th>0</th>\n",
  51. " <td>0.38</td>\n",
  52. " <td>0.53</td>\n",
  53. " <td>2</td>\n",
  54. " <td>157</td>\n",
  55. " <td>3</td>\n",
  56. " <td>0</td>\n",
  57. " <td>1</td>\n",
  58. " <td>0</td>\n",
  59. " <td>sales</td>\n",
  60. " <td>low</td>\n",
  61. " </tr>\n",
  62. " <tr>\n",
  63. " <th>1</th>\n",
  64. " <td>0.80</td>\n",
  65. " <td>0.86</td>\n",
  66. " <td>5</td>\n",
  67. " <td>262</td>\n",
  68. " <td>6</td>\n",
  69. " <td>0</td>\n",
  70. " <td>1</td>\n",
  71. " <td>0</td>\n",
  72. " <td>sales</td>\n",
  73. " <td>medium</td>\n",
  74. " </tr>\n",
  75. " <tr>\n",
  76. " <th>2</th>\n",
  77. " <td>0.11</td>\n",
  78. " <td>0.88</td>\n",
  79. " <td>7</td>\n",
  80. " <td>272</td>\n",
  81. " <td>4</td>\n",
  82. " <td>0</td>\n",
  83. " <td>1</td>\n",
  84. " <td>0</td>\n",
  85. " <td>sales</td>\n",
  86. " <td>medium</td>\n",
  87. " </tr>\n",
  88. " <tr>\n",
  89. " <th>3</th>\n",
  90. " <td>0.72</td>\n",
  91. " <td>0.87</td>\n",
  92. " <td>5</td>\n",
  93. " <td>223</td>\n",
  94. " <td>5</td>\n",
  95. " <td>0</td>\n",
  96. " <td>1</td>\n",
  97. " <td>0</td>\n",
  98. " <td>sales</td>\n",
  99. " <td>low</td>\n",
  100. " </tr>\n",
  101. " <tr>\n",
  102. " <th>4</th>\n",
  103. " <td>0.37</td>\n",
  104. " <td>0.52</td>\n",
  105. " <td>2</td>\n",
  106. " <td>159</td>\n",
  107. " <td>3</td>\n",
  108. " <td>0</td>\n",
  109. " <td>1</td>\n",
  110. " <td>0</td>\n",
  111. " <td>sales</td>\n",
  112. " <td>low</td>\n",
  113. " </tr>\n",
  114. " </tbody>\n",
  115. "</table>\n",
  116. "</div>"
  117. ],
  118. "text/plain": [
  119. " satisfaction evaluation number_of_projects average_montly_hours \\\n",
  120. "0 0.38 0.53 2 157 \n",
  121. "1 0.80 0.86 5 262 \n",
  122. "2 0.11 0.88 7 272 \n",
  123. "3 0.72 0.87 5 223 \n",
  124. "4 0.37 0.52 2 159 \n",
  125. "\n",
  126. " time_spend_company work_accident churn promotion department salary \n",
  127. "0 3 0 1 0 sales low \n",
  128. "1 6 0 1 0 sales medium \n",
  129. "2 4 0 1 0 sales medium \n",
  130. "3 5 0 1 0 sales low \n",
  131. "4 3 0 1 0 sales low "
  132. ]
  133. },
  134. "execution_count": 2,
  135. "metadata": {},
  136. "output_type": "execute_result"
  137. }
  138. ],
  139. "source": [
  140. "# Import pandas (as pd) to read the data\n",
  141. "import pandas as pd\n",
  142. "\n",
  143. "# Read \"turnover.csv\" and save it in a DataFrame called data\n",
  144. "data = pd.read_csv(\"turnover.csv\")\n",
  145. "\n",
  146. "# Take a quick look to the first 5 rows of data\n",
  147. "data.head()"
  148. ]
  149. },
  150. {
  151. "cell_type": "markdown",
  152. "metadata": {},
  153. "source": [
  154. "### Encoding categories"
  155. ]
  156. },
  157. {
  158. "cell_type": "code",
  159. "execution_count": 8,
  160. "metadata": {},
  161. "outputs": [],
  162. "source": [
  163. "# Change the type of the \"salary\" column to categorical\n",
  164. "data.salary = data.salary.astype('category')\n",
  165. "\n",
  166. "# Provide the correct order of categories\n",
  167. "data.salary = data.salary.cat.reorder_categories(['low', 'medium', 'high'])\n",
  168. "\n",
  169. "# Encode categories\n",
  170. "data.salary = data.salary.cat.codes"
  171. ]
  172. },
  173. {
  174. "cell_type": "markdown",
  175. "metadata": {},
  176. "source": [
  177. "### Getting dummies"
  178. ]
  179. },
  180. {
  181. "cell_type": "code",
  182. "execution_count": 9,
  183. "metadata": {},
  184. "outputs": [
  185. {
  186. "data": {
  187. "text/html": [
  188. "<div>\n",
  189. "<style scoped>\n",
  190. " .dataframe tbody tr th:only-of-type {\n",
  191. " vertical-align: middle;\n",
  192. " }\n",
  193. "\n",
  194. " .dataframe tbody tr th {\n",
  195. " vertical-align: top;\n",
  196. " }\n",
  197. "\n",
  198. " .dataframe thead th {\n",
  199. " text-align: right;\n",
  200. " }\n",
  201. "</style>\n",
  202. "<table border=\"1\" class=\"dataframe\">\n",
  203. " <thead>\n",
  204. " <tr style=\"text-align: right;\">\n",
  205. " <th></th>\n",
  206. " <th>IT</th>\n",
  207. " <th>RandD</th>\n",
  208. " <th>accounting</th>\n",
  209. " <th>hr</th>\n",
  210. " <th>management</th>\n",
  211. " <th>marketing</th>\n",
  212. " <th>product_mng</th>\n",
  213. " <th>sales</th>\n",
  214. " <th>support</th>\n",
  215. " <th>technical</th>\n",
  216. " </tr>\n",
  217. " </thead>\n",
  218. " <tbody>\n",
  219. " <tr>\n",
  220. " <th>0</th>\n",
  221. " <td>0</td>\n",
  222. " <td>0</td>\n",
  223. " <td>0</td>\n",
  224. " <td>0</td>\n",
  225. " <td>0</td>\n",
  226. " <td>0</td>\n",
  227. " <td>0</td>\n",
  228. " <td>1</td>\n",
  229. " <td>0</td>\n",
  230. " <td>0</td>\n",
  231. " </tr>\n",
  232. " <tr>\n",
  233. " <th>1</th>\n",
  234. " <td>0</td>\n",
  235. " <td>0</td>\n",
  236. " <td>0</td>\n",
  237. " <td>0</td>\n",
  238. " <td>0</td>\n",
  239. " <td>0</td>\n",
  240. " <td>0</td>\n",
  241. " <td>1</td>\n",
  242. " <td>0</td>\n",
  243. " <td>0</td>\n",
  244. " </tr>\n",
  245. " <tr>\n",
  246. " <th>2</th>\n",
  247. " <td>0</td>\n",
  248. " <td>0</td>\n",
  249. " <td>0</td>\n",
  250. " <td>0</td>\n",
  251. " <td>0</td>\n",
  252. " <td>0</td>\n",
  253. " <td>0</td>\n",
  254. " <td>1</td>\n",
  255. " <td>0</td>\n",
  256. " <td>0</td>\n",
  257. " </tr>\n",
  258. " <tr>\n",
  259. " <th>3</th>\n",
  260. " <td>0</td>\n",
  261. " <td>0</td>\n",
  262. " <td>0</td>\n",
  263. " <td>0</td>\n",
  264. " <td>0</td>\n",
  265. " <td>0</td>\n",
  266. " <td>0</td>\n",
  267. " <td>1</td>\n",
  268. " <td>0</td>\n",
  269. " <td>0</td>\n",
  270. " </tr>\n",
  271. " <tr>\n",
  272. " <th>4</th>\n",
  273. " <td>0</td>\n",
  274. " <td>0</td>\n",
  275. " <td>0</td>\n",
  276. " <td>0</td>\n",
  277. " <td>0</td>\n",
  278. " <td>0</td>\n",
  279. " <td>0</td>\n",
  280. " <td>1</td>\n",
  281. " <td>0</td>\n",
  282. " <td>0</td>\n",
  283. " </tr>\n",
  284. " </tbody>\n",
  285. "</table>\n",
  286. "</div>"
  287. ],
  288. "text/plain": [
  289. " IT RandD accounting hr management marketing product_mng sales \\\n",
  290. "0 0 0 0 0 0 0 0 1 \n",
  291. "1 0 0 0 0 0 0 0 1 \n",
  292. "2 0 0 0 0 0 0 0 1 \n",
  293. "3 0 0 0 0 0 0 0 1 \n",
  294. "4 0 0 0 0 0 0 0 1 \n",
  295. "\n",
  296. " support technical \n",
  297. "0 0 0 \n",
  298. "1 0 0 \n",
  299. "2 0 0 \n",
  300. "3 0 0 \n",
  301. "4 0 0 "
  302. ]
  303. },
  304. "execution_count": 9,
  305. "metadata": {},
  306. "output_type": "execute_result"
  307. }
  308. ],
  309. "source": [
  310. "# Get dummies and save them inside a new DataFrame\n",
  311. "departments = pd.get_dummies(data.department)\n",
  312. "\n",
  313. "# Take a quick look to the first 5 rows of the new DataFrame called departments\n",
  314. "departments.head()"
  315. ]
  316. }
  317. ],
  318. "metadata": {
  319. "kernelspec": {
  320. "display_name": "Python 3",
  321. "language": "python",
  322. "name": "python3"
  323. },
  324. "language_info": {
  325. "codemirror_mode": {
  326. "name": "ipython",
  327. "version": 3
  328. },
  329. "file_extension": ".py",
  330. "mimetype": "text/x-python",
  331. "name": "python",
  332. "nbconvert_exporter": "python",
  333. "pygments_lexer": "ipython3",
  334. "version": "3.7.3"
  335. }
  336. },
  337. "nbformat": 4,
  338. "nbformat_minor": 2
  339. }
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!