├── README.md ├── generate_people.py ├── generate_dataset.ipynb └── Analyse Dataset.ipynb /README.md: -------------------------------------------------------------------------------- 1 | # pandas_workshop 2 | A tutorial on creating, editing and analysing CSV files with the Pandas Framework. 3 | 4 | Includes two notebooks and the data generating script. 5 | -------------------------------------------------------------------------------- /generate_people.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | import random 3 | 4 | names = ["Albert","John","Richard","Henry","William"] 5 | surnames = ["Goodman","Black","White","Green","Joneson"] 6 | salaries = [500*random.randint(10,30) for _ in range(10)] 7 | 8 | def generate_random_person(names, surnames, salaries): 9 | return {"name":random.sample(names,1)[0], 10 | "surname":random.sample(surnames,1)[0], 11 | "salary":random.sample(salaries,1)[0]} 12 | def generate_people(k): 13 | return [generate_random_person(names, surnames, salaries) for _ in range(k)] 14 | 15 | df = pd.DataFrame(generate_people(50),columns=["name","surname","salary"]) 16 | df.to_csv("random_people.csv") 17 | 18 | -------------------------------------------------------------------------------- /generate_dataset.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 3, 6 | "metadata": {}, 7 | "outputs": [], 8 | "source": [ 9 | "import pandas as pd\n", 10 | "import random" 11 | ] 12 | }, 13 | { 14 | "cell_type": "code", 15 | "execution_count": 4, 16 | "metadata": {}, 17 | "outputs": [], 18 | "source": [ 19 | "names = [\"Albert\",\"John\",\"Richard\",\"Henry\",\"William\"]\n", 20 | "surnames = [\"Goodman\",\"Black\",\"White\",\"Green\",\"Joneson\"]\n", 21 | "salaries = [500*random.randint(10,30) for _ in range(10)]" 22 | ] 23 | }, 24 | { 25 | "cell_type": "code", 26 | "execution_count": 25, 27 | "metadata": {}, 28 | "outputs": [], 29 | "source": [ 30 | "def generate_random_person(names, surnames, salaries):\n", 31 | " return {\"name\":random.sample(names,1)[0],\n", 32 | " \"surname\":random.sample(surnames,1)[0],\n", 33 | " \"salary\":random.sample(salaries,1)[0]}\n", 34 | "def generate_people(k):\n", 35 | " return [generate_random_person(names, surnames, salaries) for _ in range(k)]" 36 | ] 37 | }, 38 | { 39 | "cell_type": "code", 40 | "execution_count": 26, 41 | "metadata": {}, 42 | "outputs": [ 43 | { 44 | "data": { 45 | "text/plain": [ 46 | "{'name': 'Richard', 'salary': 7500, 'surname': 'Joneson'}" 47 | ] 48 | }, 49 | "execution_count": 26, 50 | "metadata": {}, 51 | "output_type": "execute_result" 52 | } 53 | ], 54 | "source": [ 55 | "generate_random_person(names, surnames, salaries)" 56 | ] 57 | }, 58 | { 59 | "cell_type": "code", 60 | "execution_count": 28, 61 | "metadata": {}, 62 | "outputs": [], 63 | "source": [ 64 | "df = pd.DataFrame(generate_people(50),columns=[\"name\",\"surname\",\"salary\"])" 65 | ] 66 | }, 67 | { 68 | "cell_type": "code", 69 | "execution_count": 29, 70 | "metadata": {}, 71 | "outputs": [ 72 | { 73 | "data": { 74 | "text/html": [ 75 | "
\n", 76 | "\n", 89 | "\n", 90 | " \n", 91 | " \n", 92 | " \n", 93 | " \n", 94 | " \n", 95 | " \n", 96 | " \n", 97 | " \n", 98 | " \n", 99 | " \n", 100 | " \n", 101 | " \n", 102 | " \n", 103 | " \n", 104 | " \n", 105 | " \n", 106 | " \n", 107 | " \n", 108 | " \n", 109 | " \n", 110 | " \n", 111 | " \n", 112 | " \n", 113 | " \n", 114 | " \n", 115 | " \n", 116 | " \n", 117 | " \n", 118 | " \n", 119 | " \n", 120 | " \n", 121 | " \n", 122 | " \n", 123 | " \n", 124 | " \n", 125 | " \n", 126 | " \n", 127 | " \n", 128 | " \n", 129 | " \n", 130 | " \n", 131 | " \n", 132 | " \n", 133 | " \n", 134 | " \n", 135 | " \n", 136 | " \n", 137 | " \n", 138 | " \n", 139 | " \n", 140 | " \n", 141 | " \n", 142 | " \n", 143 | " \n", 144 | " \n", 145 | " \n", 146 | " \n", 147 | " \n", 148 | " \n", 149 | " \n", 150 | " \n", 151 | " \n", 152 | " \n", 153 | " \n", 154 | " \n", 155 | " \n", 156 | " \n", 157 | " \n", 158 | " \n", 159 | " \n", 160 | " \n", 161 | " \n", 162 | " \n", 163 | " \n", 164 | " \n", 165 | " \n", 166 | " \n", 167 | " \n", 168 | " \n", 169 | " \n", 170 | " \n", 171 | " \n", 172 | " \n", 173 | " \n", 174 | " \n", 175 | " \n", 176 | " \n", 177 | " \n", 178 | " \n", 179 | " \n", 180 | " \n", 181 | " \n", 182 | " \n", 183 | " \n", 184 | " \n", 185 | " \n", 186 | " \n", 187 | " \n", 188 | " \n", 189 | " \n", 190 | " \n", 191 | " \n", 192 | " \n", 193 | " \n", 194 | " \n", 195 | " \n", 196 | " \n", 197 | " \n", 198 | " \n", 199 | " \n", 200 | " \n", 201 | " \n", 202 | " \n", 203 | " \n", 204 | " \n", 205 | " \n", 206 | " \n", 207 | " \n", 208 | " \n", 209 | " \n", 210 | " \n", 211 | " \n", 212 | " \n", 213 | " \n", 214 | " \n", 215 | " \n", 216 | " \n", 217 | " \n", 218 | " \n", 219 | " \n", 220 | " \n", 221 | " \n", 222 | " \n", 223 | " \n", 224 | " \n", 225 | " \n", 226 | " \n", 227 | " \n", 228 | " \n", 229 | " \n", 230 | " \n", 231 | " \n", 232 | " \n", 233 | " \n", 234 | " \n", 235 | " \n", 236 | " \n", 237 | " \n", 238 | " \n", 239 | " \n", 240 | " \n", 241 | " \n", 242 | " \n", 243 | " \n", 244 | " \n", 245 | " \n", 246 | " \n", 247 | " \n", 248 | " \n", 249 | " \n", 250 | " \n", 251 | " \n", 252 | " \n", 253 | " \n", 254 | " \n", 255 | " \n", 256 | " \n", 257 | " \n", 258 | " \n", 259 | " \n", 260 | " \n", 261 | " \n", 262 | " \n", 263 | " \n", 264 | " \n", 265 | " \n", 266 | " \n", 267 | " \n", 268 | " \n", 269 | " \n", 270 | " \n", 271 | " \n", 272 | " \n", 273 | " \n", 274 | " \n", 275 | " \n", 276 | " \n", 277 | " \n", 278 | " \n", 279 | " \n", 280 | " \n", 281 | " \n", 282 | " \n", 283 | " \n", 284 | " \n", 285 | " \n", 286 | " \n", 287 | " \n", 288 | " \n", 289 | " \n", 290 | " \n", 291 | " \n", 292 | " \n", 293 | " \n", 294 | " \n", 295 | " \n", 296 | " \n", 297 | " \n", 298 | " \n", 299 | " \n", 300 | " \n", 301 | " \n", 302 | " \n", 303 | " \n", 304 | " \n", 305 | " \n", 306 | " \n", 307 | " \n", 308 | " \n", 309 | " \n", 310 | " \n", 311 | " \n", 312 | " \n", 313 | " \n", 314 | " \n", 315 | " \n", 316 | " \n", 317 | " \n", 318 | " \n", 319 | " \n", 320 | " \n", 321 | " \n", 322 | " \n", 323 | " \n", 324 | " \n", 325 | " \n", 326 | " \n", 327 | " \n", 328 | " \n", 329 | " \n", 330 | " \n", 331 | " \n", 332 | " \n", 333 | " \n", 334 | " \n", 335 | " \n", 336 | " \n", 337 | " \n", 338 | " \n", 339 | " \n", 340 | " \n", 341 | " \n", 342 | " \n", 343 | " \n", 344 | " \n", 345 | " \n", 346 | " \n", 347 | " \n", 348 | " \n", 349 | " \n", 350 | " \n", 351 | " \n", 352 | " \n", 353 | " \n", 354 | " \n", 355 | " \n", 356 | " \n", 357 | " \n", 358 | " \n", 359 | " \n", 360 | " \n", 361 | " \n", 362 | " \n", 363 | " \n", 364 | " \n", 365 | " \n", 366 | " \n", 367 | " \n", 368 | " \n", 369 | " \n", 370 | " \n", 371 | " \n", 372 | " \n", 373 | " \n", 374 | " \n", 375 | " \n", 376 | " \n", 377 | " \n", 378 | " \n", 379 | " \n", 380 | " \n", 381 | " \n", 382 | " \n", 383 | " \n", 384 | " \n", 385 | " \n", 386 | " \n", 387 | " \n", 388 | " \n", 389 | " \n", 390 | " \n", 391 | " \n", 392 | " \n", 393 | " \n", 394 | " \n", 395 | " \n", 396 | " \n", 397 | " \n", 398 | " \n", 399 | " \n", 400 | "
namesurnamesalary
0HenryGoodman7500
1HenryBlack9500
2WilliamGoodman7000
3JohnBlack6000
4AlbertWhite9500
5WilliamGoodman7500
6RichardGreen12500
7AlbertGoodman7500
8AlbertJoneson12500
9RichardBlack6000
10WilliamGreen7500
11WilliamJoneson6000
12WilliamJoneson7500
13RichardGreen7000
14HenryGoodman9500
15RichardJoneson6000
16WilliamGreen8500
17JohnGreen7500
18HenryWhite9500
19JohnJoneson7000
20AlbertBlack7500
21RichardWhite7500
22RichardBlack8500
23HenryGoodman7500
24HenryBlack7000
25JohnGreen11500
26JohnBlack8500
27AlbertGreen11500
28JohnGoodman7500
29JohnWhite11500
30WilliamWhite7000
31JohnWhite9500
32AlbertGreen9500
33WilliamGreen6000
34WilliamBlack7000
35HenryWhite7000
36AlbertBlack7000
37JohnGoodman7500
38RichardWhite11500
39RichardGoodman7000
40HenryGreen7500
41RichardGoodman8500
42WilliamWhite11500
43JohnBlack12500
44JohnGreen7500
45RichardJoneson8500
46WilliamGoodman9500
47WilliamWhite6000
48AlbertBlack7000
49WilliamGreen12500
\n", 401 | "
" 402 | ], 403 | "text/plain": [ 404 | " name surname salary\n", 405 | "0 Henry Goodman 7500\n", 406 | "1 Henry Black 9500\n", 407 | "2 William Goodman 7000\n", 408 | "3 John Black 6000\n", 409 | "4 Albert White 9500\n", 410 | "5 William Goodman 7500\n", 411 | "6 Richard Green 12500\n", 412 | "7 Albert Goodman 7500\n", 413 | "8 Albert Joneson 12500\n", 414 | "9 Richard Black 6000\n", 415 | "10 William Green 7500\n", 416 | "11 William Joneson 6000\n", 417 | "12 William Joneson 7500\n", 418 | "13 Richard Green 7000\n", 419 | "14 Henry Goodman 9500\n", 420 | "15 Richard Joneson 6000\n", 421 | "16 William Green 8500\n", 422 | "17 John Green 7500\n", 423 | "18 Henry White 9500\n", 424 | "19 John Joneson 7000\n", 425 | "20 Albert Black 7500\n", 426 | "21 Richard White 7500\n", 427 | "22 Richard Black 8500\n", 428 | "23 Henry Goodman 7500\n", 429 | "24 Henry Black 7000\n", 430 | "25 John Green 11500\n", 431 | "26 John Black 8500\n", 432 | "27 Albert Green 11500\n", 433 | "28 John Goodman 7500\n", 434 | "29 John White 11500\n", 435 | "30 William White 7000\n", 436 | "31 John White 9500\n", 437 | "32 Albert Green 9500\n", 438 | "33 William Green 6000\n", 439 | "34 William Black 7000\n", 440 | "35 Henry White 7000\n", 441 | "36 Albert Black 7000\n", 442 | "37 John Goodman 7500\n", 443 | "38 Richard White 11500\n", 444 | "39 Richard Goodman 7000\n", 445 | "40 Henry Green 7500\n", 446 | "41 Richard Goodman 8500\n", 447 | "42 William White 11500\n", 448 | "43 John Black 12500\n", 449 | "44 John Green 7500\n", 450 | "45 Richard Joneson 8500\n", 451 | "46 William Goodman 9500\n", 452 | "47 William White 6000\n", 453 | "48 Albert Black 7000\n", 454 | "49 William Green 12500" 455 | ] 456 | }, 457 | "execution_count": 29, 458 | "metadata": {}, 459 | "output_type": "execute_result" 460 | } 461 | ], 462 | "source": [ 463 | "df" 464 | ] 465 | }, 466 | { 467 | "cell_type": "code", 468 | "execution_count": null, 469 | "metadata": {}, 470 | "outputs": [], 471 | "source": [] 472 | } 473 | ], 474 | "metadata": { 475 | "kernelspec": { 476 | "display_name": "Python 2", 477 | "language": "python", 478 | "name": "python2" 479 | }, 480 | "language_info": { 481 | "codemirror_mode": { 482 | "name": "ipython", 483 | "version": 2 484 | }, 485 | "file_extension": ".py", 486 | "mimetype": "text/x-python", 487 | "name": "python", 488 | "nbconvert_exporter": "python", 489 | "pygments_lexer": "ipython2", 490 | "version": "2.7.12" 491 | } 492 | }, 493 | "nbformat": 4, 494 | "nbformat_minor": 2 495 | } 496 | -------------------------------------------------------------------------------- /Analyse Dataset.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 2, 6 | "metadata": {}, 7 | "outputs": [], 8 | "source": [ 9 | "import pandas as pd \n", 10 | "\n", 11 | "df = pd.read_csv(\"random_people.csv\")" 12 | ] 13 | }, 14 | { 15 | "cell_type": "code", 16 | "execution_count": 3, 17 | "metadata": {}, 18 | "outputs": [ 19 | { 20 | "data": { 21 | "text/html": [ 22 | "
\n", 23 | "\n", 36 | "\n", 37 | " \n", 38 | " \n", 39 | " \n", 40 | " \n", 41 | " \n", 42 | " \n", 43 | " \n", 44 | " \n", 45 | " \n", 46 | " \n", 47 | " \n", 48 | " \n", 49 | " \n", 50 | " \n", 51 | " \n", 52 | " \n", 53 | " \n", 54 | " \n", 55 | " \n", 56 | " \n", 57 | " \n", 58 | " \n", 59 | " \n", 60 | " \n", 61 | " \n", 62 | " \n", 63 | " \n", 64 | " \n", 65 | " \n", 66 | " \n", 67 | " \n", 68 | " \n", 69 | " \n", 70 | " \n", 71 | " \n", 72 | " \n", 73 | " \n", 74 | " \n", 75 | " \n", 76 | " \n", 77 | " \n", 78 | " \n", 79 | " \n", 80 | " \n", 81 | " \n", 82 | " \n", 83 | " \n", 84 | " \n", 85 | " \n", 86 | " \n", 87 | " \n", 88 | " \n", 89 | " \n", 90 | " \n", 91 | " \n", 92 | " \n", 93 | " \n", 94 | " \n", 95 | " \n", 96 | " \n", 97 | " \n", 98 | " \n", 99 | " \n", 100 | " \n", 101 | " \n", 102 | " \n", 103 | " \n", 104 | " \n", 105 | " \n", 106 | " \n", 107 | " \n", 108 | " \n", 109 | " \n", 110 | " \n", 111 | " \n", 112 | " \n", 113 | " \n", 114 | " \n", 115 | " \n", 116 | " \n", 117 | " \n", 118 | "
Unnamed: 0namesurnamesalary
00HenryJoneson5000
11AlbertGoodman10000
22WilliamGoodman10000
33JohnJoneson10000
44AlbertBlack10000
55HenryJoneson12000
66RichardGreen5500
77HenryJoneson11000
88HenryGoodman12000
99AlbertJoneson11000
\n", 119 | "
" 120 | ], 121 | "text/plain": [ 122 | " Unnamed: 0 name surname salary\n", 123 | "0 0 Henry Joneson 5000\n", 124 | "1 1 Albert Goodman 10000\n", 125 | "2 2 William Goodman 10000\n", 126 | "3 3 John Joneson 10000\n", 127 | "4 4 Albert Black 10000\n", 128 | "5 5 Henry Joneson 12000\n", 129 | "6 6 Richard Green 5500\n", 130 | "7 7 Henry Joneson 11000\n", 131 | "8 8 Henry Goodman 12000\n", 132 | "9 9 Albert Joneson 11000" 133 | ] 134 | }, 135 | "execution_count": 3, 136 | "metadata": {}, 137 | "output_type": "execute_result" 138 | } 139 | ], 140 | "source": [ 141 | "#start getting a feel of the data\n", 142 | "df.head(10)" 143 | ] 144 | }, 145 | { 146 | "cell_type": "code", 147 | "execution_count": 6, 148 | "metadata": {}, 149 | "outputs": [ 150 | { 151 | "data": { 152 | "text/plain": [ 153 | "10000 16\n", 154 | "12000 8\n", 155 | "11000 7\n", 156 | "9500 6\n", 157 | "5500 5\n", 158 | "13500 5\n", 159 | "5000 3\n", 160 | "Name: salary, dtype: int64" 161 | ] 162 | }, 163 | "execution_count": 6, 164 | "metadata": {}, 165 | "output_type": "execute_result" 166 | } 167 | ], 168 | "source": [ 169 | "df['salary'].value_counts()" 170 | ] 171 | }, 172 | { 173 | "cell_type": "code", 174 | "execution_count": 12, 175 | "metadata": {}, 176 | "outputs": [ 177 | { 178 | "data": { 179 | "text/plain": [ 180 | "10000.0" 181 | ] 182 | }, 183 | "execution_count": 12, 184 | "metadata": {}, 185 | "output_type": "execute_result" 186 | } 187 | ], 188 | "source": [ 189 | "df['salary'].median()" 190 | ] 191 | }, 192 | { 193 | "cell_type": "code", 194 | "execution_count": 13, 195 | "metadata": {}, 196 | "outputs": [], 197 | "source": [ 198 | "df[\"salary_after_tax\"] = df[\"salary\"]*.8" 199 | ] 200 | }, 201 | { 202 | "cell_type": "code", 203 | "execution_count": 15, 204 | "metadata": {}, 205 | "outputs": [], 206 | "source": [ 207 | "def tax(s):\n", 208 | " if s>=6000:\n", 209 | " return s*.7\n", 210 | " else:\n", 211 | " return s*.85" 212 | ] 213 | }, 214 | { 215 | "cell_type": "code", 216 | "execution_count": 16, 217 | "metadata": {}, 218 | "outputs": [], 219 | "source": [ 220 | "df[\"salary_after_tax\"] = df[\"salary\"].apply(tax)" 221 | ] 222 | }, 223 | { 224 | "cell_type": "code", 225 | "execution_count": 17, 226 | "metadata": {}, 227 | "outputs": [ 228 | { 229 | "data": { 230 | "text/html": [ 231 | "
\n", 232 | "\n", 245 | "\n", 246 | " \n", 247 | " \n", 248 | " \n", 249 | " \n", 250 | " \n", 251 | " \n", 252 | " \n", 253 | " \n", 254 | " \n", 255 | " \n", 256 | " \n", 257 | " \n", 258 | " \n", 259 | " \n", 260 | " \n", 261 | " \n", 262 | " \n", 263 | " \n", 264 | " \n", 265 | " \n", 266 | " \n", 267 | " \n", 268 | " \n", 269 | " \n", 270 | " \n", 271 | " \n", 272 | " \n", 273 | " \n", 274 | " \n", 275 | " \n", 276 | " \n", 277 | " \n", 278 | " \n", 279 | " \n", 280 | " \n", 281 | " \n", 282 | " \n", 283 | " \n", 284 | " \n", 285 | " \n", 286 | " \n", 287 | " \n", 288 | " \n", 289 | " \n", 290 | " \n", 291 | " \n", 292 | " \n", 293 | " \n", 294 | " \n", 295 | " \n", 296 | " \n", 297 | " \n", 298 | "
Unnamed: 0namesurnamesalarysalary_after_tax
00HenryJoneson50004250.0
11AlbertGoodman100007000.0
22WilliamGoodman100007000.0
33JohnJoneson100007000.0
44AlbertBlack100007000.0
\n", 299 | "
" 300 | ], 301 | "text/plain": [ 302 | " Unnamed: 0 name surname salary salary_after_tax\n", 303 | "0 0 Henry Joneson 5000 4250.0\n", 304 | "1 1 Albert Goodman 10000 7000.0\n", 305 | "2 2 William Goodman 10000 7000.0\n", 306 | "3 3 John Joneson 10000 7000.0\n", 307 | "4 4 Albert Black 10000 7000.0" 308 | ] 309 | }, 310 | "execution_count": 17, 311 | "metadata": {}, 312 | "output_type": "execute_result" 313 | } 314 | ], 315 | "source": [] 316 | }, 317 | { 318 | "cell_type": "code", 319 | "execution_count": 18, 320 | "metadata": {}, 321 | "outputs": [], 322 | "source": [ 323 | "df_low = df[df[\"salary\"]<6000]\n", 324 | "df_high = df[df[\"salary\"]>=6000]" 325 | ] 326 | }, 327 | { 328 | "cell_type": "code", 329 | "execution_count": 20, 330 | "metadata": {}, 331 | "outputs": [ 332 | { 333 | "data": { 334 | "text/plain": [ 335 | "10892.857142857143" 336 | ] 337 | }, 338 | "execution_count": 20, 339 | "metadata": {}, 340 | "output_type": "execute_result" 341 | } 342 | ], 343 | "source": [ 344 | "df_high[\"salary\"].mean()" 345 | ] 346 | }, 347 | { 348 | "cell_type": "code", 349 | "execution_count": 53, 350 | "metadata": {}, 351 | "outputs": [], 352 | "source": [ 353 | "df_low= df.loc[df[\"salary\"]<6000,\"salary\"]\n", 354 | "df.loc[df[\"salary\"]<6000,\"salary_after_tax\"] = df_low*.85\n", 355 | "\n", 356 | "df_low= df.loc[df[\"salary\"]>=6000,\"salary\"]\n", 357 | "df.loc[df[\"salary\"]>=6000,\"salary_after_tax\"] = df_low*.7" 358 | ] 359 | }, 360 | { 361 | "cell_type": "code", 362 | "execution_count": 38, 363 | "metadata": {}, 364 | "outputs": [ 365 | { 366 | "data": { 367 | "text/plain": [ 368 | "0 4250.0\n", 369 | "6 4675.0\n", 370 | "14 4675.0\n", 371 | "17 4675.0\n", 372 | "21 4250.0\n", 373 | "32 4675.0\n", 374 | "33 4250.0\n", 375 | "37 4675.0\n", 376 | "Name: salary, dtype: float64" 377 | ] 378 | }, 379 | "execution_count": 38, 380 | "metadata": {}, 381 | "output_type": "execute_result" 382 | } 383 | ], 384 | "source": [ 385 | "df_low" 386 | ] 387 | }, 388 | { 389 | "cell_type": "code", 390 | "execution_count": 55, 391 | "metadata": {}, 392 | "outputs": [ 393 | { 394 | "data": { 395 | "text/html": [ 396 | "
\n", 397 | "\n", 410 | "\n", 411 | " \n", 412 | " \n", 413 | " \n", 414 | " \n", 415 | " \n", 416 | " \n", 417 | " \n", 418 | " \n", 419 | " \n", 420 | " \n", 421 | " \n", 422 | " \n", 423 | " \n", 424 | " \n", 425 | " \n", 426 | " \n", 427 | " \n", 428 | " \n", 429 | " \n", 430 | " \n", 431 | " \n", 432 | " \n", 433 | " \n", 434 | " \n", 435 | " \n", 436 | " \n", 437 | " \n", 438 | " \n", 439 | " \n", 440 | " \n", 441 | " \n", 442 | " \n", 443 | " \n", 444 | " \n", 445 | " \n", 446 | " \n", 447 | " \n", 448 | " \n", 449 | " \n", 450 | " \n", 451 | " \n", 452 | " \n", 453 | " \n", 454 | " \n", 455 | " \n", 456 | " \n", 457 | " \n", 458 | " \n", 459 | " \n", 460 | " \n", 461 | " \n", 462 | " \n", 463 | " \n", 464 | " \n", 465 | " \n", 466 | " \n", 467 | " \n", 468 | " \n", 469 | " \n", 470 | " \n", 471 | " \n", 472 | " \n", 473 | " \n", 474 | " \n", 475 | " \n", 476 | " \n", 477 | " \n", 478 | " \n", 479 | " \n", 480 | " \n", 481 | " \n", 482 | " \n", 483 | " \n", 484 | " \n", 485 | " \n", 486 | " \n", 487 | " \n", 488 | " \n", 489 | " \n", 490 | " \n", 491 | " \n", 492 | " \n", 493 | " \n", 494 | " \n", 495 | " \n", 496 | " \n", 497 | " \n", 498 | " \n", 499 | " \n", 500 | " \n", 501 | " \n", 502 | " \n", 503 | " \n", 504 | " \n", 505 | " \n", 506 | " \n", 507 | " \n", 508 | " \n", 509 | " \n", 510 | " \n", 511 | " \n", 512 | " \n", 513 | " \n", 514 | " \n", 515 | " \n", 516 | " \n", 517 | " \n", 518 | " \n", 519 | " \n", 520 | " \n", 521 | " \n", 522 | " \n", 523 | " \n", 524 | " \n", 525 | " \n", 526 | " \n", 527 | " \n", 528 | " \n", 529 | " \n", 530 | " \n", 531 | " \n", 532 | " \n", 533 | " \n", 534 | " \n", 535 | " \n", 536 | " \n", 537 | " \n", 538 | " \n", 539 | " \n", 540 | " \n", 541 | " \n", 542 | " \n", 543 | " \n", 544 | " \n", 545 | " \n", 546 | " \n", 547 | " \n", 548 | " \n", 549 | " \n", 550 | " \n", 551 | " \n", 552 | " \n", 553 | " \n", 554 | " \n", 555 | " \n", 556 | " \n", 557 | " \n", 558 | " \n", 559 | " \n", 560 | " \n", 561 | " \n", 562 | " \n", 563 | " \n", 564 | " \n", 565 | " \n", 566 | " \n", 567 | " \n", 568 | " \n", 569 | " \n", 570 | " \n", 571 | " \n", 572 | " \n", 573 | " \n", 574 | " \n", 575 | " \n", 576 | " \n", 577 | " \n", 578 | " \n", 579 | " \n", 580 | " \n", 581 | " \n", 582 | " \n", 583 | " \n", 584 | " \n", 585 | " \n", 586 | " \n", 587 | " \n", 588 | " \n", 589 | " \n", 590 | " \n", 591 | " \n", 592 | " \n", 593 | " \n", 594 | " \n", 595 | " \n", 596 | " \n", 597 | " \n", 598 | " \n", 599 | " \n", 600 | " \n", 601 | " \n", 602 | " \n", 603 | " \n", 604 | " \n", 605 | " \n", 606 | " \n", 607 | " \n", 608 | " \n", 609 | " \n", 610 | " \n", 611 | " \n", 612 | " \n", 613 | " \n", 614 | " \n", 615 | " \n", 616 | " \n", 617 | " \n", 618 | " \n", 619 | " \n", 620 | " \n", 621 | " \n", 622 | " \n", 623 | " \n", 624 | " \n", 625 | " \n", 626 | " \n", 627 | " \n", 628 | " \n", 629 | " \n", 630 | " \n", 631 | " \n", 632 | " \n", 633 | " \n", 634 | " \n", 635 | " \n", 636 | " \n", 637 | " \n", 638 | " \n", 639 | " \n", 640 | " \n", 641 | " \n", 642 | " \n", 643 | " \n", 644 | " \n", 645 | " \n", 646 | " \n", 647 | " \n", 648 | " \n", 649 | " \n", 650 | " \n", 651 | " \n", 652 | " \n", 653 | " \n", 654 | " \n", 655 | " \n", 656 | " \n", 657 | " \n", 658 | " \n", 659 | " \n", 660 | " \n", 661 | " \n", 662 | " \n", 663 | " \n", 664 | " \n", 665 | " \n", 666 | " \n", 667 | " \n", 668 | " \n", 669 | " \n", 670 | " \n", 671 | " \n", 672 | " \n", 673 | " \n", 674 | " \n", 675 | " \n", 676 | " \n", 677 | " \n", 678 | " \n", 679 | " \n", 680 | " \n", 681 | " \n", 682 | " \n", 683 | " \n", 684 | " \n", 685 | " \n", 686 | " \n", 687 | " \n", 688 | " \n", 689 | " \n", 690 | " \n", 691 | " \n", 692 | " \n", 693 | " \n", 694 | " \n", 695 | " \n", 696 | " \n", 697 | " \n", 698 | " \n", 699 | " \n", 700 | " \n", 701 | " \n", 702 | " \n", 703 | " \n", 704 | " \n", 705 | " \n", 706 | " \n", 707 | " \n", 708 | " \n", 709 | " \n", 710 | " \n", 711 | " \n", 712 | " \n", 713 | " \n", 714 | " \n", 715 | " \n", 716 | " \n", 717 | " \n", 718 | " \n", 719 | " \n", 720 | " \n", 721 | " \n", 722 | " \n", 723 | " \n", 724 | " \n", 725 | " \n", 726 | " \n", 727 | " \n", 728 | " \n", 729 | " \n", 730 | " \n", 731 | " \n", 732 | " \n", 733 | " \n", 734 | " \n", 735 | " \n", 736 | " \n", 737 | " \n", 738 | " \n", 739 | " \n", 740 | " \n", 741 | " \n", 742 | " \n", 743 | " \n", 744 | " \n", 745 | " \n", 746 | " \n", 747 | " \n", 748 | " \n", 749 | " \n", 750 | " \n", 751 | " \n", 752 | " \n", 753 | " \n", 754 | " \n", 755 | " \n", 756 | " \n", 757 | " \n", 758 | " \n", 759 | " \n", 760 | " \n", 761 | " \n", 762 | " \n", 763 | " \n", 764 | " \n", 765 | " \n", 766 | " \n", 767 | " \n", 768 | " \n", 769 | " \n", 770 | " \n", 771 | " \n", 772 | " \n", 773 | " \n", 774 | " \n", 775 | " \n", 776 | " \n", 777 | " \n", 778 | " \n", 779 | " \n", 780 | " \n", 781 | " \n", 782 | " \n", 783 | " \n", 784 | " \n", 785 | " \n", 786 | " \n", 787 | " \n", 788 | " \n", 789 | " \n", 790 | " \n", 791 | " \n", 792 | " \n", 793 | " \n", 794 | " \n", 795 | " \n", 796 | " \n", 797 | " \n", 798 | " \n", 799 | " \n", 800 | " \n", 801 | " \n", 802 | " \n", 803 | " \n", 804 | " \n", 805 | " \n", 806 | " \n", 807 | " \n", 808 | " \n", 809 | " \n", 810 | " \n", 811 | " \n", 812 | " \n", 813 | " \n", 814 | " \n", 815 | " \n", 816 | " \n", 817 | " \n", 818 | " \n", 819 | " \n", 820 | " \n", 821 | " \n", 822 | " \n", 823 | "
Unnamed: 0namesurnamesalarysalary_after_tax
00HenryJoneson50004250.0
11AlbertGoodman100007000.0
22WilliamGoodman100007000.0
33JohnJoneson100007000.0
44AlbertBlack100007000.0
55HenryJoneson120008400.0
66RichardGreen55004675.0
77HenryJoneson110007700.0
88HenryGoodman120008400.0
99AlbertJoneson110007700.0
1010WilliamJoneson100007000.0
1111JohnWhite100007000.0
1212HenryBlack110007700.0
1313AlbertGoodman100007000.0
1414RichardGreen55004675.0
1515HenryBlack135009450.0
1616RichardWhite110007700.0
1717AlbertBlack55004675.0
1818HenryGreen100007000.0
1919AlbertJoneson110007700.0
2020WilliamGoodman120008400.0
2121WilliamGoodman50004250.0
2222JohnGreen95006650.0
2323JohnBlack135009450.0
2424RichardGreen135009450.0
2525HenryJoneson120008400.0
2626HenryGoodman100007000.0
2727JohnJoneson95006650.0
2828HenryGoodman110007700.0
2929WilliamGreen120008400.0
3030HenryGoodman100007000.0
3131RichardBlack100007000.0
3232RichardJoneson55004675.0
3333RichardJoneson50004250.0
3434HenryBlack95006650.0
3535JohnWhite135009450.0
3636HenryGreen110007700.0
3737JohnBlack55004675.0
3838WilliamGreen120008400.0
3939AlbertGreen100007000.0
4040RichardJoneson95006650.0
4141WilliamJoneson120008400.0
4242JohnJoneson100007000.0
4343WilliamBlack100007000.0
4444AlbertBlack120008400.0
4545JohnGoodman135009450.0
4646JohnJoneson100007000.0
4747JohnJoneson95006650.0
4848RichardBlack95006650.0
4949AlbertWhite100007000.0
\n", 824 | "
" 825 | ], 826 | "text/plain": [ 827 | " Unnamed: 0 name surname salary salary_after_tax\n", 828 | "0 0 Henry Joneson 5000 4250.0\n", 829 | "1 1 Albert Goodman 10000 7000.0\n", 830 | "2 2 William Goodman 10000 7000.0\n", 831 | "3 3 John Joneson 10000 7000.0\n", 832 | "4 4 Albert Black 10000 7000.0\n", 833 | "5 5 Henry Joneson 12000 8400.0\n", 834 | "6 6 Richard Green 5500 4675.0\n", 835 | "7 7 Henry Joneson 11000 7700.0\n", 836 | "8 8 Henry Goodman 12000 8400.0\n", 837 | "9 9 Albert Joneson 11000 7700.0\n", 838 | "10 10 William Joneson 10000 7000.0\n", 839 | "11 11 John White 10000 7000.0\n", 840 | "12 12 Henry Black 11000 7700.0\n", 841 | "13 13 Albert Goodman 10000 7000.0\n", 842 | "14 14 Richard Green 5500 4675.0\n", 843 | "15 15 Henry Black 13500 9450.0\n", 844 | "16 16 Richard White 11000 7700.0\n", 845 | "17 17 Albert Black 5500 4675.0\n", 846 | "18 18 Henry Green 10000 7000.0\n", 847 | "19 19 Albert Joneson 11000 7700.0\n", 848 | "20 20 William Goodman 12000 8400.0\n", 849 | "21 21 William Goodman 5000 4250.0\n", 850 | "22 22 John Green 9500 6650.0\n", 851 | "23 23 John Black 13500 9450.0\n", 852 | "24 24 Richard Green 13500 9450.0\n", 853 | "25 25 Henry Joneson 12000 8400.0\n", 854 | "26 26 Henry Goodman 10000 7000.0\n", 855 | "27 27 John Joneson 9500 6650.0\n", 856 | "28 28 Henry Goodman 11000 7700.0\n", 857 | "29 29 William Green 12000 8400.0\n", 858 | "30 30 Henry Goodman 10000 7000.0\n", 859 | "31 31 Richard Black 10000 7000.0\n", 860 | "32 32 Richard Joneson 5500 4675.0\n", 861 | "33 33 Richard Joneson 5000 4250.0\n", 862 | "34 34 Henry Black 9500 6650.0\n", 863 | "35 35 John White 13500 9450.0\n", 864 | "36 36 Henry Green 11000 7700.0\n", 865 | "37 37 John Black 5500 4675.0\n", 866 | "38 38 William Green 12000 8400.0\n", 867 | "39 39 Albert Green 10000 7000.0\n", 868 | "40 40 Richard Joneson 9500 6650.0\n", 869 | "41 41 William Joneson 12000 8400.0\n", 870 | "42 42 John Joneson 10000 7000.0\n", 871 | "43 43 William Black 10000 7000.0\n", 872 | "44 44 Albert Black 12000 8400.0\n", 873 | "45 45 John Goodman 13500 9450.0\n", 874 | "46 46 John Joneson 10000 7000.0\n", 875 | "47 47 John Joneson 9500 6650.0\n", 876 | "48 48 Richard Black 9500 6650.0\n", 877 | "49 49 Albert White 10000 7000.0" 878 | ] 879 | }, 880 | "execution_count": 55, 881 | "metadata": {}, 882 | "output_type": "execute_result" 883 | } 884 | ], 885 | "source": [ 886 | "df.head(50)" 887 | ] 888 | } 889 | ], 890 | "metadata": { 891 | "kernelspec": { 892 | "display_name": "Python 2", 893 | "language": "python", 894 | "name": "python2" 895 | }, 896 | "language_info": { 897 | "codemirror_mode": { 898 | "name": "ipython", 899 | "version": 2 900 | }, 901 | "file_extension": ".py", 902 | "mimetype": "text/x-python", 903 | "name": "python", 904 | "nbconvert_exporter": "python", 905 | "pygments_lexer": "ipython2", 906 | "version": "2.7.12" 907 | } 908 | }, 909 | "nbformat": 4, 910 | "nbformat_minor": 2 911 | } 912 | --------------------------------------------------------------------------------