|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "markdown", |
| 5 | + "metadata": {}, |
| 6 | + "source": [ |
| 7 | + "# Optional Challenge - Verified Email List\n", |
| 8 | + "\n", |
| 9 | + "We want you to produce a new DataFrame that contains the only following columns:\n", |
| 10 | + "* first_name\n", |
| 11 | + "* last_name\n", |
| 12 | + "* email\n", |
| 13 | + "\n", |
| 14 | + "Ensure that all first names are title cased. Do not include any records that have a missing last name, and make sure that their email is verified (**`email_verified`** should be set True). Sort by last name and then by first.\n" |
| 15 | + ] |
| 16 | + }, |
| 17 | + { |
| 18 | + "cell_type": "code", |
| 19 | + "execution_count": 1, |
| 20 | + "metadata": {}, |
| 21 | + "outputs": [], |
| 22 | + "source": [ |
| 23 | + "# Setup\n", |
| 24 | + "import os\n", |
| 25 | + "\n", |
| 26 | + "import pandas as pd\n", |
| 27 | + "\n", |
| 28 | + "from utils import make_chaos\n", |
| 29 | + "\n", |
| 30 | + "from tests.helpers import check\n", |
| 31 | + "\n", |
| 32 | + "pd.options.display.max_rows = 10\n", |
| 33 | + "users = pd.read_csv(os.path.join('data', 'users.csv'), index_col=0)\n", |
| 34 | + "# Pay no attention to the person behind the curtain\n", |
| 35 | + "make_chaos(users, 19, ['first_name'], lambda val: val.lower())" |
| 36 | + ] |
| 37 | + }, |
| 38 | + { |
| 39 | + "cell_type": "code", |
| 40 | + "execution_count": 2, |
| 41 | + "metadata": {}, |
| 42 | + "outputs": [ |
| 43 | + { |
| 44 | + "data": { |
| 45 | + "text/html": [ |
| 46 | + "<div>\n", |
| 47 | + "<style scoped>\n", |
| 48 | + " .dataframe tbody tr th:only-of-type {\n", |
| 49 | + " vertical-align: middle;\n", |
| 50 | + " }\n", |
| 51 | + "\n", |
| 52 | + " .dataframe tbody tr th {\n", |
| 53 | + " vertical-align: top;\n", |
| 54 | + " }\n", |
| 55 | + "\n", |
| 56 | + " .dataframe thead th {\n", |
| 57 | + " text-align: right;\n", |
| 58 | + " }\n", |
| 59 | + "</style>\n", |
| 60 | + "<table border=\"1\" class=\"dataframe\">\n", |
| 61 | + " <thead>\n", |
| 62 | + " <tr style=\"text-align: right;\">\n", |
| 63 | + " <th></th>\n", |
| 64 | + " <th>first_name</th>\n", |
| 65 | + " <th>last_name</th>\n", |
| 66 | + " <th>email</th>\n", |
| 67 | + " <th>email_verified</th>\n", |
| 68 | + " <th>signup_date</th>\n", |
| 69 | + " <th>referral_count</th>\n", |
| 70 | + " <th>balance</th>\n", |
| 71 | + " </tr>\n", |
| 72 | + " </thead>\n", |
| 73 | + " <tbody>\n", |
| 74 | + " <tr>\n", |
| 75 | + " <th>aaron</th>\n", |
| 76 | + " <td>Aaron</td>\n", |
| 77 | + " <td>Davis</td>\n", |
| 78 | + " <td>aaron6348@gmail.com</td>\n", |
| 79 | + " <td>True</td>\n", |
| 80 | + " <td>2018-08-31</td>\n", |
| 81 | + " <td>6.0</td>\n", |
| 82 | + " <td>18.14</td>\n", |
| 83 | + " </tr>\n", |
| 84 | + " <tr>\n", |
| 85 | + " <th>acook</th>\n", |
| 86 | + " <td>Anthony</td>\n", |
| 87 | + " <td>Cook</td>\n", |
| 88 | + " <td>cook@gmail.com</td>\n", |
| 89 | + " <td>True</td>\n", |
| 90 | + " <td>2018-05-12</td>\n", |
| 91 | + " <td>2.0</td>\n", |
| 92 | + " <td>55.45</td>\n", |
| 93 | + " </tr>\n", |
| 94 | + " <tr>\n", |
| 95 | + " <th>adam.saunders</th>\n", |
| 96 | + " <td>Adam</td>\n", |
| 97 | + " <td>Saunders</td>\n", |
| 98 | + " <td>adam@gmail.com</td>\n", |
| 99 | + " <td>False</td>\n", |
| 100 | + " <td>2018-05-29</td>\n", |
| 101 | + " <td>3.0</td>\n", |
| 102 | + " <td>72.12</td>\n", |
| 103 | + " </tr>\n", |
| 104 | + " <tr>\n", |
| 105 | + " <th>adrian</th>\n", |
| 106 | + " <td>Adrian</td>\n", |
| 107 | + " <td>Yang</td>\n", |
| 108 | + " <td>adrian.yang@teamtreehouse.com</td>\n", |
| 109 | + " <td>True</td>\n", |
| 110 | + " <td>2018-04-28</td>\n", |
| 111 | + " <td>3.0</td>\n", |
| 112 | + " <td>30.01</td>\n", |
| 113 | + " </tr>\n", |
| 114 | + " <tr>\n", |
| 115 | + " <th>adrian.blair</th>\n", |
| 116 | + " <td>Adrian</td>\n", |
| 117 | + " <td>Blair</td>\n", |
| 118 | + " <td>adrian9335@gmail.com</td>\n", |
| 119 | + " <td>True</td>\n", |
| 120 | + " <td>2018-06-16</td>\n", |
| 121 | + " <td>7.0</td>\n", |
| 122 | + " <td>25.85</td>\n", |
| 123 | + " </tr>\n", |
| 124 | + " <tr>\n", |
| 125 | + " <th>...</th>\n", |
| 126 | + " <td>...</td>\n", |
| 127 | + " <td>...</td>\n", |
| 128 | + " <td>...</td>\n", |
| 129 | + " <td>...</td>\n", |
| 130 | + " <td>...</td>\n", |
| 131 | + " <td>...</td>\n", |
| 132 | + " <td>...</td>\n", |
| 133 | + " </tr>\n", |
| 134 | + " <tr>\n", |
| 135 | + " <th>wilson</th>\n", |
| 136 | + " <td>Robert</td>\n", |
| 137 | + " <td>Wilson</td>\n", |
| 138 | + " <td>robert@yahoo.com</td>\n", |
| 139 | + " <td>False</td>\n", |
| 140 | + " <td>2018-05-16</td>\n", |
| 141 | + " <td>5.0</td>\n", |
| 142 | + " <td>59.75</td>\n", |
| 143 | + " </tr>\n", |
| 144 | + " <tr>\n", |
| 145 | + " <th>wking</th>\n", |
| 146 | + " <td>Wanda</td>\n", |
| 147 | + " <td>King</td>\n", |
| 148 | + " <td>wanda.king@holt.com</td>\n", |
| 149 | + " <td>True</td>\n", |
| 150 | + " <td>2018-06-01</td>\n", |
| 151 | + " <td>2.0</td>\n", |
| 152 | + " <td>67.08</td>\n", |
| 153 | + " </tr>\n", |
| 154 | + " <tr>\n", |
| 155 | + " <th>wright3590</th>\n", |
| 156 | + " <td>Jacqueline</td>\n", |
| 157 | + " <td>Wright</td>\n", |
| 158 | + " <td>jacqueline.wright@gonzalez.com</td>\n", |
| 159 | + " <td>True</td>\n", |
| 160 | + " <td>2018-02-08</td>\n", |
| 161 | + " <td>6.0</td>\n", |
| 162 | + " <td>18.48</td>\n", |
| 163 | + " </tr>\n", |
| 164 | + " <tr>\n", |
| 165 | + " <th>young</th>\n", |
| 166 | + " <td>Jessica</td>\n", |
| 167 | + " <td>Young</td>\n", |
| 168 | + " <td>jessica4028@yahoo.com</td>\n", |
| 169 | + " <td>True</td>\n", |
| 170 | + " <td>2018-07-17</td>\n", |
| 171 | + " <td>4.0</td>\n", |
| 172 | + " <td>75.39</td>\n", |
| 173 | + " </tr>\n", |
| 174 | + " <tr>\n", |
| 175 | + " <th>zachary.neal</th>\n", |
| 176 | + " <td>Zachary</td>\n", |
| 177 | + " <td>Neal</td>\n", |
| 178 | + " <td>zneal@gmail.com</td>\n", |
| 179 | + " <td>True</td>\n", |
| 180 | + " <td>2018-07-26</td>\n", |
| 181 | + " <td>1.0</td>\n", |
| 182 | + " <td>39.90</td>\n", |
| 183 | + " </tr>\n", |
| 184 | + " </tbody>\n", |
| 185 | + "</table>\n", |
| 186 | + "<p>475 rows × 7 columns</p>\n", |
| 187 | + "</div>" |
| 188 | + ], |
| 189 | + "text/plain": [ |
| 190 | + " first_name last_name email \\\n", |
| 191 | + "aaron Aaron Davis aaron6348@gmail.com \n", |
| 192 | + "acook Anthony Cook cook@gmail.com \n", |
| 193 | + "adam.saunders Adam Saunders adam@gmail.com \n", |
| 194 | + "adrian Adrian Yang adrian.yang@teamtreehouse.com \n", |
| 195 | + "adrian.blair Adrian Blair adrian9335@gmail.com \n", |
| 196 | + "... ... ... ... \n", |
| 197 | + "wilson Robert Wilson robert@yahoo.com \n", |
| 198 | + "wking Wanda King wanda.king@holt.com \n", |
| 199 | + "wright3590 Jacqueline Wright jacqueline.wright@gonzalez.com \n", |
| 200 | + "young Jessica Young jessica4028@yahoo.com \n", |
| 201 | + "zachary.neal Zachary Neal zneal@gmail.com \n", |
| 202 | + "\n", |
| 203 | + " email_verified signup_date referral_count balance \n", |
| 204 | + "aaron True 2018-08-31 6.0 18.14 \n", |
| 205 | + "acook True 2018-05-12 2.0 55.45 \n", |
| 206 | + "adam.saunders False 2018-05-29 3.0 72.12 \n", |
| 207 | + "adrian True 2018-04-28 3.0 30.01 \n", |
| 208 | + "adrian.blair True 2018-06-16 7.0 25.85 \n", |
| 209 | + "... ... ... ... ... \n", |
| 210 | + "wilson False 2018-05-16 5.0 59.75 \n", |
| 211 | + "wking True 2018-06-01 2.0 67.08 \n", |
| 212 | + "wright3590 True 2018-02-08 6.0 18.48 \n", |
| 213 | + "young True 2018-07-17 4.0 75.39 \n", |
| 214 | + "zachary.neal True 2018-07-26 1.0 39.90 \n", |
| 215 | + "\n", |
| 216 | + "[475 rows x 7 columns]" |
| 217 | + ] |
| 218 | + }, |
| 219 | + "execution_count": 2, |
| 220 | + "metadata": {}, |
| 221 | + "output_type": "execute_result" |
| 222 | + } |
| 223 | + ], |
| 224 | + "source": [ |
| 225 | + "## CHALLENGE - Verified email list ##\n", |
| 226 | + "\n", |
| 227 | + "# TODO: Narrow list to those that have email verified.\n", |
| 228 | + "# The only columns should be first, last and email\n", |
| 229 | + "email_list = users[:]\n", |
| 230 | + "\n", |
| 231 | + "# TODO: Remove any rows missing last names\n", |
| 232 | + "\n", |
| 233 | + "\n", |
| 234 | + "# TODO: Ensure that the first names are the proper case\n", |
| 235 | + "\n", |
| 236 | + "\n", |
| 237 | + "# Return the new sorted DataFrame\n", |
| 238 | + "email_list" |
| 239 | + ] |
| 240 | + }, |
| 241 | + { |
| 242 | + "cell_type": "code", |
| 243 | + "execution_count": 3, |
| 244 | + "metadata": {}, |
| 245 | + "outputs": [ |
| 246 | + { |
| 247 | + "data": { |
| 248 | + "text/markdown": [ |
| 249 | + "```\n", |
| 250 | + "FFFFF\n", |
| 251 | + "======================================================================\n", |
| 252 | + "FAIL: test_columns (tests.helpers.TestVerifiedEmailList)\n", |
| 253 | + "----------------------------------------------------------------------\n", |
| 254 | + "Traceback (most recent call last):\n", |
| 255 | + " File \"/Users/craig/Code/scripting/intro-to-pandas/tests/test_cells.py\", line 92, in test_columns\n", |
| 256 | + " ', '.join(expected.columns))\n", |
| 257 | + "AssertionError: 7 != 3 : Please only return the following columns: first_name, last_name, email\n", |
| 258 | + "\n", |
| 259 | + "======================================================================\n", |
| 260 | + "FAIL: test_email_verified (tests.helpers.TestVerifiedEmailList)\n", |
| 261 | + "----------------------------------------------------------------------\n", |
| 262 | + "Traceback (most recent call last):\n", |
| 263 | + " File \"/Users/craig/Code/scripting/intro-to-pandas/tests/test_cells.py\", line 100, in test_email_verified\n", |
| 264 | + " \"Ensure that you are only including users with verified emails\"\n", |
| 265 | + "AssertionError: 475 != 358 : Ensure that you are only including users with verified emails\n", |
| 266 | + "\n", |
| 267 | + "======================================================================\n", |
| 268 | + "FAIL: test_has_na (tests.helpers.TestVerifiedEmailList)\n", |
| 269 | + "----------------------------------------------------------------------\n", |
| 270 | + "Traceback (most recent call last):\n", |
| 271 | + " File \"/Users/craig/Code/scripting/intro-to-pandas/tests/test_cells.py\", line 83, in test_has_na\n", |
| 272 | + " \"Looks like there are still rows with last names missing. Drop them!\"\n", |
| 273 | + "AssertionError: 45 != 0 : Looks like there are still rows with last names missing. Drop them!\n", |
| 274 | + "\n", |
| 275 | + "======================================================================\n", |
| 276 | + "FAIL: test_sort (tests.helpers.TestVerifiedEmailList)\n", |
| 277 | + "----------------------------------------------------------------------\n", |
| 278 | + "Traceback (most recent call last):\n", |
| 279 | + " File \"/Users/craig/Code/scripting/intro-to-pandas/tests/test_cells.py\", line 116, in test_sort\n", |
| 280 | + " msg\n", |
| 281 | + "AssertionError: 'Aaron' != 'Darlene'\n", |
| 282 | + "- Aaron\n", |
| 283 | + "+ Darlene\n", |
| 284 | + " : Check your sort, it should be last name and then first name\n", |
| 285 | + "\n", |
| 286 | + "======================================================================\n", |
| 287 | + "FAIL: test_title_cased (tests.helpers.TestVerifiedEmailList)\n", |
| 288 | + "----------------------------------------------------------------------\n", |
| 289 | + "Traceback (most recent call last):\n", |
| 290 | + " File \"/Users/craig/Code/scripting/intro-to-pandas/tests/test_cells.py\", line 107, in test_title_cased\n", |
| 291 | + " \"Make sure you title case the first names, there are still some lower case versions\"\n", |
| 292 | + "AssertionError: 19 != 0 : Make sure you title case the first names, there are still some lower case versions\n", |
| 293 | + "\n", |
| 294 | + "----------------------------------------------------------------------\n", |
| 295 | + "Ran 5 tests in 0.030s\n", |
| 296 | + "\n", |
| 297 | + "FAILED (failures=5)\n", |
| 298 | + "\n", |
| 299 | + "```" |
| 300 | + ], |
| 301 | + "text/plain": [ |
| 302 | + "<IPython.core.display.Markdown object>" |
| 303 | + ] |
| 304 | + }, |
| 305 | + "metadata": {}, |
| 306 | + "output_type": "display_data" |
| 307 | + } |
| 308 | + ], |
| 309 | + "source": [ |
| 310 | + "check(__name__, 'Verified email list')" |
| 311 | + ] |
| 312 | + } |
| 313 | + ], |
| 314 | + "metadata": { |
| 315 | + "kernelspec": { |
| 316 | + "display_name": "Python 3", |
| 317 | + "language": "python", |
| 318 | + "name": "python3" |
| 319 | + }, |
| 320 | + "language_info": { |
| 321 | + "codemirror_mode": { |
| 322 | + "name": "ipython", |
| 323 | + "version": 3 |
| 324 | + }, |
| 325 | + "file_extension": ".py", |
| 326 | + "mimetype": "text/x-python", |
| 327 | + "name": "python", |
| 328 | + "nbconvert_exporter": "python", |
| 329 | + "pygments_lexer": "ipython3", |
| 330 | + "version": "3.7.0" |
| 331 | + } |
| 332 | + }, |
| 333 | + "nbformat": 4, |
| 334 | + "nbformat_minor": 2 |
| 335 | +} |
0 commit comments