API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Jul 24th, 2016
57
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 12.80 KB | None | 0 0
raw download clone embed print report
  1. {
  2. "cells": [
  3. {
  4. "cell_type": "code",
  5. "execution_count": 7,
  6. "metadata": {
  7. "collapsed": false
  8. },
  9. "outputs": [
  10. {
  11. "name": "stdout",
  12. "output_type": "stream",
  13. "text": [
  14. "3.5.1 (default, Dec 26 2015, 18:11:22) \n",
  15. "[GCC 4.2.1 Compatible Apple LLVM 7.0.2 (clang-700.1.81)]\n",
  16. "Pandas: 0.18.1\n"
  17. ]
  18. }
  19. ],
  20. "source": [
  21. "# Version info\n",
  22. "import sys\n",
  23. "print(sys.version)\n",
  24. "print('Pandas: ', pd.__version__)"
  25. ]
  26. },
  27. {
  28. "cell_type": "code",
  29. "execution_count": 1,
  30. "metadata": {
  31. "collapsed": true
  32. },
  33. "outputs": [],
  34. "source": [
  35. "# Sample data\n",
  36. "data=\"\"\"01, home #sweet home\n",
  37. "01, #happy #life \n",
  38. "02, #world peace\n",
  39. "03, #all are one\n",
  40. "\"\"\""
  41. ]
  42. },
  43. {
  44. "cell_type": "code",
  45. "execution_count": 2,
  46. "metadata": {
  47. "collapsed": true
  48. },
  49. "outputs": [],
  50. "source": [
  51. "import pandas as pd\n",
  52. "from io import StringIO"
  53. ]
  54. },
  55. {
  56. "cell_type": "code",
  57. "execution_count": 3,
  58. "metadata": {
  59. "collapsed": false
  60. },
  61. "outputs": [],
  62. "source": [
  63. "df = pd.read_csv(StringIO(data), \n",
  64. " header=None, \n",
  65. " names=['col1', 'col2'],\n",
  66. " index_col=0)"
  67. ]
  68. },
  69. {
  70. "cell_type": "code",
  71. "execution_count": 4,
  72. "metadata": {
  73. "collapsed": false
  74. },
  75. "outputs": [
  76. {
  77. "data": {
  78. "text/html": [
  79. "<div>\n",
  80. "<table border=\"1\" class=\"dataframe\">\n",
  81. " <thead>\n",
  82. " <tr style=\"text-align: right;\">\n",
  83. " <th></th>\n",
  84. " <th>col2</th>\n",
  85. " </tr>\n",
  86. " <tr>\n",
  87. " <th>col1</th>\n",
  88. " <th></th>\n",
  89. " </tr>\n",
  90. " </thead>\n",
  91. " <tbody>\n",
  92. " <tr>\n",
  93. " <th>1</th>\n",
  94. " <td>home #sweet home</td>\n",
  95. " </tr>\n",
  96. " <tr>\n",
  97. " <th>1</th>\n",
  98. " <td>#happy #life</td>\n",
  99. " </tr>\n",
  100. " <tr>\n",
  101. " <th>2</th>\n",
  102. " <td>#world peace</td>\n",
  103. " </tr>\n",
  104. " <tr>\n",
  105. " <th>3</th>\n",
  106. " <td>#all are one</td>\n",
  107. " </tr>\n",
  108. " </tbody>\n",
  109. "</table>\n",
  110. "</div>"
  111. ],
  112. "text/plain": [
  113. " col2\n",
  114. "col1 \n",
  115. "1 home #sweet home\n",
  116. "1 #happy #life \n",
  117. "2 #world peace\n",
  118. "3 #all are one"
  119. ]
  120. },
  121. "execution_count": 4,
  122. "metadata": {},
  123. "output_type": "execute_result"
  124. }
  125. ],
  126. "source": [
  127. "df"
  128. ]
  129. },
  130. {
  131. "cell_type": "code",
  132. "execution_count": 5,
  133. "metadata": {
  134. "collapsed": false
  135. },
  136. "outputs": [
  137. {
  138. "data": {
  139. "text/html": [
  140. "<div>\n",
  141. "<table border=\"1\" class=\"dataframe\">\n",
  142. " <thead>\n",
  143. " <tr style=\"text-align: right;\">\n",
  144. " <th></th>\n",
  145. " <th></th>\n",
  146. " <th>0</th>\n",
  147. " </tr>\n",
  148. " <tr>\n",
  149. " <th>col1</th>\n",
  150. " <th>match</th>\n",
  151. " <th></th>\n",
  152. " </tr>\n",
  153. " </thead>\n",
  154. " <tbody>\n",
  155. " <tr>\n",
  156. " <th rowspan=\"3\" valign=\"top\">1</th>\n",
  157. " <th>0</th>\n",
  158. " <td>s</td>\n",
  159. " </tr>\n",
  160. " <tr>\n",
  161. " <th>0</th>\n",
  162. " <td>h</td>\n",
  163. " </tr>\n",
  164. " <tr>\n",
  165. " <th>1</th>\n",
  166. " <td>l</td>\n",
  167. " </tr>\n",
  168. " <tr>\n",
  169. " <th>2</th>\n",
  170. " <th>0</th>\n",
  171. " <td>w</td>\n",
  172. " </tr>\n",
  173. " <tr>\n",
  174. " <th>3</th>\n",
  175. " <th>0</th>\n",
  176. " <td>a</td>\n",
  177. " </tr>\n",
  178. " </tbody>\n",
  179. "</table>\n",
  180. "</div>"
  181. ],
  182. "text/plain": [
  183. " 0\n",
  184. "col1 match \n",
  185. "1 0 s\n",
  186. " 0 h\n",
  187. " 1 l\n",
  188. "2 0 w\n",
  189. "3 0 a"
  190. ]
  191. },
  192. "execution_count": 5,
  193. "metadata": {},
  194. "output_type": "execute_result"
  195. }
  196. ],
  197. "source": [
  198. "# This should work (will only output the first character of each match)\n",
  199. "df['col2'].str.extractall('#(\\S)')"
  200. ]
  201. },
  202. {
  203. "cell_type": "code",
  204. "execution_count": 8,
  205. "metadata": {
  206. "collapsed": false
  207. },
  208. "outputs": [
  209. {
  210. "ename": "AssertionError",
  211. "evalue": "1 columns passed, passed data had 6 columns",
  212. "output_type": "error",
  213. "traceback": [
  214. "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
  215. "\u001b[0;31mAssertionError\u001b[0m Traceback (most recent call last)",
  216. "\u001b[0;32m<ipython-input-8-4792d3b6c94f>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m# This won't work due to a bug\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'col2'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextractall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'(#\\S+)'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
  217. "\u001b[0;32m/Users/kristof/Development/virtualenv/jupyter/lib/python3.5/site-packages/pandas/core/strings.py\u001b[0m in \u001b[0;36mextractall\u001b[0;34m(self, pat, flags)\u001b[0m\n\u001b[1;32m 1619\u001b[0m \u001b[0;34m@\u001b[0m\u001b[0mcopy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstr_extractall\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1620\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mextractall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpat\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mflags\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1621\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mstr_extractall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_orig\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpat\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mflags\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mflags\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1622\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1623\u001b[0m _shared_docs['find'] = (\"\"\"\n",
  218. "\u001b[0;32m/Users/kristof/Development/virtualenv/jupyter/lib/python3.5/site-packages/pandas/core/strings.py\u001b[0m in \u001b[0;36mstr_extractall\u001b[0;34m(arr, pat, flags)\u001b[0m\n\u001b[1;32m 714\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 715\u001b[0m \u001b[0mindex\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 716\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmatch_list\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcolumns\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 717\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 718\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
  219. "\u001b[0;32m/Users/kristof/Development/virtualenv/jupyter/lib/python3.5/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, data, index, columns, dtype, copy)\u001b[0m\n\u001b[1;32m 261\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mcom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mis_named_tuple\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mcolumns\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 262\u001b[0m \u001b[0mcolumns\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_fields\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 263\u001b[0;31m \u001b[0marrays\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcolumns\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_to_arrays\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcolumns\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 264\u001b[0m \u001b[0mcolumns\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_ensure_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 265\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
  220. "\u001b[0;32m/Users/kristof/Development/virtualenv/jupyter/lib/python3.5/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m_to_arrays\u001b[0;34m(data, columns, coerce_float, dtype)\u001b[0m\n\u001b[1;32m 5350\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mlist\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtuple\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5351\u001b[0m return _list_to_arrays(data, columns, coerce_float=coerce_float,\n\u001b[0;32m-> 5352\u001b[0;31m dtype=dtype)\n\u001b[0m\u001b[1;32m 5353\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcollections\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mMapping\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5354\u001b[0m return _list_of_dict_to_arrays(data, columns,\n",
  221. "\u001b[0;32m/Users/kristof/Development/virtualenv/jupyter/lib/python3.5/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m_list_to_arrays\u001b[0;34m(data, columns, coerce_float, dtype)\u001b[0m\n\u001b[1;32m 5429\u001b[0m \u001b[0mcontent\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_object_array\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mT\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5430\u001b[0m return _convert_object_array(content, columns, dtype=dtype,\n\u001b[0;32m-> 5431\u001b[0;31m coerce_float=coerce_float)\n\u001b[0m\u001b[1;32m 5432\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5433\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
  222. "\u001b[0;32m/Users/kristof/Development/virtualenv/jupyter/lib/python3.5/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m_convert_object_array\u001b[0;34m(content, columns, coerce_float, dtype)\u001b[0m\n\u001b[1;32m 5487\u001b[0m \u001b[0;31m# caller's responsibility to check for this...\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5488\u001b[0m raise AssertionError('%d columns passed, passed data had %s '\n\u001b[0;32m-> 5489\u001b[0;31m 'columns' % (len(columns), len(content)))\n\u001b[0m\u001b[1;32m 5490\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5491\u001b[0m \u001b[0;31m# provide soft conversion of object dtypes\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
  223. "\u001b[0;31mAssertionError\u001b[0m: 1 columns passed, passed data had 6 columns"
  224. ]
  225. }
  226. ],
  227. "source": [
  228. "# This won't work due to a bug\n",
  229. "df['col2'].str.extractall('(#\\S+)')"
  230. ]
  231. },
  232. {
  233. "cell_type": "code",
  234. "execution_count": null,
  235. "metadata": {
  236. "collapsed": true
  237. },
  238. "outputs": [],
  239. "source": []
  240. }
  241. ],
  242. "metadata": {
  243. "kernelspec": {
  244. "display_name": "Python 3",
  245. "language": "python",
  246. "name": "python3"
  247. },
  248. "language_info": {
  249. "codemirror_mode": {
  250. "name": "ipython",
  251. "version": 3
  252. },
  253. "file_extension": ".py",
  254. "mimetype": "text/x-python",
  255. "name": "python",
  256. "nbconvert_exporter": "python",
  257. "pygments_lexer": "ipython3",
  258. "version": "3.5.1"
  259. }
  260. },
  261. "nbformat": 4,
  262. "nbformat_minor": 0
  263. }
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!