└── PANDAS_NOTEBOOK_3.ipynb


/PANDAS_NOTEBOOK_3.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "markdown",
   5 |    "id": "f15d6659",
   6 |    "metadata": {},
   7 |    "source": [
   8 |     "## Advanced Aggregation Functions: Aggregate() Function"
   9 |    ]
  10 |   },
  11 |   {
  12 |    "cell_type": "code",
  13 |    "execution_count": 1,
  14 |    "id": "6185cdeb",
  15 |    "metadata": {},
  16 |    "outputs": [],
  17 |    "source": [
  18 |     "import pandas as pd\n",
  19 |     "import numpy as np"
  20 |    ]
  21 |   },
  22 |   {
  23 |    "cell_type": "code",
  24 |    "execution_count": 2,
  25 |    "id": "2ba48364",
  26 |    "metadata": {},
  27 |    "outputs": [],
  28 |    "source": [
  29 |     "df = pd.DataFrame({'groups': ['X', 'Y', 'Z', 'X', 'Y', 'Z'],\n",
  30 |     "                   'val1': [2, 15, 25, 14, 3, 91],\n",
  31 |     "                   'val2': [92,245,325,254,103,961]})"
  32 |    ]
  33 |   },
  34 |   {
  35 |    "cell_type": "code",
  36 |    "execution_count": 3,
  37 |    "id": "f9bfd7a6",
  38 |    "metadata": {},
  39 |    "outputs": [
  40 |     {
  41 |      "data": {
  42 |       "text/html": [
  43 |        "<div>\n",
  44 |        "<style scoped>\n",
  45 |        "    .dataframe tbody tr th:only-of-type {\n",
  46 |        "        vertical-align: middle;\n",
  47 |        "    }\n",
  48 |        "\n",
  49 |        "    .dataframe tbody tr th {\n",
  50 |        "        vertical-align: top;\n",
  51 |        "    }\n",
  52 |        "\n",
  53 |        "    .dataframe thead th {\n",
  54 |        "        text-align: right;\n",
  55 |        "    }\n",
  56 |        "</style>\n",
  57 |        "<table border=\"1\" class=\"dataframe\">\n",
  58 |        "  <thead>\n",
  59 |        "    <tr style=\"text-align: right;\">\n",
  60 |        "      <th></th>\n",
  61 |        "      <th>groups</th>\n",
  62 |        "      <th>val1</th>\n",
  63 |        "      <th>val2</th>\n",
  64 |        "    </tr>\n",
  65 |        "  </thead>\n",
  66 |        "  <tbody>\n",
  67 |        "    <tr>\n",
  68 |        "      <th>0</th>\n",
  69 |        "      <td>X</td>\n",
  70 |        "      <td>2</td>\n",
  71 |        "      <td>92</td>\n",
  72 |        "    </tr>\n",
  73 |        "    <tr>\n",
  74 |        "      <th>1</th>\n",
  75 |        "      <td>Y</td>\n",
  76 |        "      <td>15</td>\n",
  77 |        "      <td>245</td>\n",
  78 |        "    </tr>\n",
  79 |        "    <tr>\n",
  80 |        "      <th>2</th>\n",
  81 |        "      <td>Z</td>\n",
  82 |        "      <td>25</td>\n",
  83 |        "      <td>325</td>\n",
  84 |        "    </tr>\n",
  85 |        "    <tr>\n",
  86 |        "      <th>3</th>\n",
  87 |        "      <td>X</td>\n",
  88 |        "      <td>14</td>\n",
  89 |        "      <td>254</td>\n",
  90 |        "    </tr>\n",
  91 |        "    <tr>\n",
  92 |        "      <th>4</th>\n",
  93 |        "      <td>Y</td>\n",
  94 |        "      <td>3</td>\n",
  95 |        "      <td>103</td>\n",
  96 |        "    </tr>\n",
  97 |        "    <tr>\n",
  98 |        "      <th>5</th>\n",
  99 |        "      <td>Z</td>\n",
 100 |        "      <td>91</td>\n",
 101 |        "      <td>961</td>\n",
 102 |        "    </tr>\n",
 103 |        "  </tbody>\n",
 104 |        "</table>\n",
 105 |        "</div>"
 106 |       ],
 107 |       "text/plain": [
 108 |        "  groups  val1  val2\n",
 109 |        "0      X     2    92\n",
 110 |        "1      Y    15   245\n",
 111 |        "2      Z    25   325\n",
 112 |        "3      X    14   254\n",
 113 |        "4      Y     3   103\n",
 114 |        "5      Z    91   961"
 115 |       ]
 116 |      },
 117 |      "execution_count": 3,
 118 |      "metadata": {},
 119 |      "output_type": "execute_result"
 120 |     }
 121 |    ],
 122 |    "source": [
 123 |     "df"
 124 |    ]
 125 |   },
 126 |   {
 127 |    "cell_type": "code",
 128 |    "execution_count": 4,
 129 |    "id": "03518204",
 130 |    "metadata": {
 131 |     "scrolled": false
 132 |    },
 133 |    "outputs": [
 134 |     {
 135 |      "data": {
 136 |       "text/html": [
 137 |        "<div>\n",
 138 |        "<style scoped>\n",
 139 |        "    .dataframe tbody tr th:only-of-type {\n",
 140 |        "        vertical-align: middle;\n",
 141 |        "    }\n",
 142 |        "\n",
 143 |        "    .dataframe tbody tr th {\n",
 144 |        "        vertical-align: top;\n",
 145 |        "    }\n",
 146 |        "\n",
 147 |        "    .dataframe thead th {\n",
 148 |        "        text-align: right;\n",
 149 |        "    }\n",
 150 |        "</style>\n",
 151 |        "<table border=\"1\" class=\"dataframe\">\n",
 152 |        "  <thead>\n",
 153 |        "    <tr style=\"text-align: right;\">\n",
 154 |        "      <th></th>\n",
 155 |        "      <th>val1</th>\n",
 156 |        "      <th>val2</th>\n",
 157 |        "    </tr>\n",
 158 |        "    <tr>\n",
 159 |        "      <th>groups</th>\n",
 160 |        "      <th></th>\n",
 161 |        "      <th></th>\n",
 162 |        "    </tr>\n",
 163 |        "  </thead>\n",
 164 |        "  <tbody>\n",
 165 |        "    <tr>\n",
 166 |        "      <th>X</th>\n",
 167 |        "      <td>8</td>\n",
 168 |        "      <td>173</td>\n",
 169 |        "    </tr>\n",
 170 |        "    <tr>\n",
 171 |        "      <th>Y</th>\n",
 172 |        "      <td>9</td>\n",
 173 |        "      <td>174</td>\n",
 174 |        "    </tr>\n",
 175 |        "    <tr>\n",
 176 |        "      <th>Z</th>\n",
 177 |        "      <td>58</td>\n",
 178 |        "      <td>643</td>\n",
 179 |        "    </tr>\n",
 180 |        "  </tbody>\n",
 181 |        "</table>\n",
 182 |        "</div>"
 183 |       ],
 184 |       "text/plain": [
 185 |        "        val1  val2\n",
 186 |        "groups            \n",
 187 |        "X          8   173\n",
 188 |        "Y          9   174\n",
 189 |        "Z         58   643"
 190 |       ]
 191 |      },
 192 |      "execution_count": 4,
 193 |      "metadata": {},
 194 |      "output_type": "execute_result"
 195 |     }
 196 |    ],
 197 |    "source": [
 198 |     "df.groupby(\"groups\").mean()"
 199 |    ]
 200 |   },
 201 |   {
 202 |    "cell_type": "code",
 203 |    "execution_count": 5,
 204 |    "id": "ccd5b657",
 205 |    "metadata": {},
 206 |    "outputs": [
 207 |     {
 208 |      "data": {
 209 |       "text/html": [
 210 |        "<div>\n",
 211 |        "<style scoped>\n",
 212 |        "    .dataframe tbody tr th:only-of-type {\n",
 213 |        "        vertical-align: middle;\n",
 214 |        "    }\n",
 215 |        "\n",
 216 |        "    .dataframe tbody tr th {\n",
 217 |        "        vertical-align: top;\n",
 218 |        "    }\n",
 219 |        "\n",
 220 |        "    .dataframe thead tr th {\n",
 221 |        "        text-align: left;\n",
 222 |        "    }\n",
 223 |        "\n",
 224 |        "    .dataframe thead tr:last-of-type th {\n",
 225 |        "        text-align: right;\n",
 226 |        "    }\n",
 227 |        "</style>\n",
 228 |        "<table border=\"1\" class=\"dataframe\">\n",
 229 |        "  <thead>\n",
 230 |        "    <tr>\n",
 231 |        "      <th></th>\n",
 232 |        "      <th colspan=\"4\" halign=\"left\">val1</th>\n",
 233 |        "      <th colspan=\"4\" halign=\"left\">val2</th>\n",
 234 |        "    </tr>\n",
 235 |        "    <tr>\n",
 236 |        "      <th></th>\n",
 237 |        "      <th>mean</th>\n",
 238 |        "      <th>median</th>\n",
 239 |        "      <th>min</th>\n",
 240 |        "      <th>sum</th>\n",
 241 |        "      <th>mean</th>\n",
 242 |        "      <th>median</th>\n",
 243 |        "      <th>min</th>\n",
 244 |        "      <th>sum</th>\n",
 245 |        "    </tr>\n",
 246 |        "    <tr>\n",
 247 |        "      <th>groups</th>\n",
 248 |        "      <th></th>\n",
 249 |        "      <th></th>\n",
 250 |        "      <th></th>\n",
 251 |        "      <th></th>\n",
 252 |        "      <th></th>\n",
 253 |        "      <th></th>\n",
 254 |        "      <th></th>\n",
 255 |        "      <th></th>\n",
 256 |        "    </tr>\n",
 257 |        "  </thead>\n",
 258 |        "  <tbody>\n",
 259 |        "    <tr>\n",
 260 |        "      <th>X</th>\n",
 261 |        "      <td>8</td>\n",
 262 |        "      <td>8</td>\n",
 263 |        "      <td>2</td>\n",
 264 |        "      <td>16</td>\n",
 265 |        "      <td>173</td>\n",
 266 |        "      <td>173</td>\n",
 267 |        "      <td>92</td>\n",
 268 |        "      <td>346</td>\n",
 269 |        "    </tr>\n",
 270 |        "    <tr>\n",
 271 |        "      <th>Y</th>\n",
 272 |        "      <td>9</td>\n",
 273 |        "      <td>9</td>\n",
 274 |        "      <td>3</td>\n",
 275 |        "      <td>18</td>\n",
 276 |        "      <td>174</td>\n",
 277 |        "      <td>174</td>\n",
 278 |        "      <td>103</td>\n",
 279 |        "      <td>348</td>\n",
 280 |        "    </tr>\n",
 281 |        "    <tr>\n",
 282 |        "      <th>Z</th>\n",
 283 |        "      <td>58</td>\n",
 284 |        "      <td>58</td>\n",
 285 |        "      <td>25</td>\n",
 286 |        "      <td>116</td>\n",
 287 |        "      <td>643</td>\n",
 288 |        "      <td>643</td>\n",
 289 |        "      <td>325</td>\n",
 290 |        "      <td>1286</td>\n",
 291 |        "    </tr>\n",
 292 |        "  </tbody>\n",
 293 |        "</table>\n",
 294 |        "</div>"
 295 |       ],
 296 |       "text/plain": [
 297 |        "       val1                 val2                  \n",
 298 |        "       mean median min  sum mean median  min   sum\n",
 299 |        "groups                                            \n",
 300 |        "X         8      8   2   16  173    173   92   346\n",
 301 |        "Y         9      9   3   18  174    174  103   348\n",
 302 |        "Z        58     58  25  116  643    643  325  1286"
 303 |       ]
 304 |      },
 305 |      "execution_count": 5,
 306 |      "metadata": {},
 307 |      "output_type": "execute_result"
 308 |     }
 309 |    ],
 310 |    "source": [
 311 |     "df.groupby(\"groups\").aggregate([\"mean\", np.median, min, \"sum\"])"
 312 |    ]
 313 |   },
 314 |   {
 315 |    "cell_type": "code",
 316 |    "execution_count": 6,
 317 |    "id": "5c3fcf02",
 318 |    "metadata": {},
 319 |    "outputs": [
 320 |     {
 321 |      "data": {
 322 |       "text/html": [
 323 |        "<div>\n",
 324 |        "<style scoped>\n",
 325 |        "    .dataframe tbody tr th:only-of-type {\n",
 326 |        "        vertical-align: middle;\n",
 327 |        "    }\n",
 328 |        "\n",
 329 |        "    .dataframe tbody tr th {\n",
 330 |        "        vertical-align: top;\n",
 331 |        "    }\n",
 332 |        "\n",
 333 |        "    .dataframe thead th {\n",
 334 |        "        text-align: right;\n",
 335 |        "    }\n",
 336 |        "</style>\n",
 337 |        "<table border=\"1\" class=\"dataframe\">\n",
 338 |        "  <thead>\n",
 339 |        "    <tr style=\"text-align: right;\">\n",
 340 |        "      <th></th>\n",
 341 |        "      <th>val1</th>\n",
 342 |        "      <th>val2</th>\n",
 343 |        "    </tr>\n",
 344 |        "    <tr>\n",
 345 |        "      <th>groups</th>\n",
 346 |        "      <th></th>\n",
 347 |        "      <th></th>\n",
 348 |        "    </tr>\n",
 349 |        "  </thead>\n",
 350 |        "  <tbody>\n",
 351 |        "    <tr>\n",
 352 |        "      <th>X</th>\n",
 353 |        "      <td>8</td>\n",
 354 |        "      <td>173</td>\n",
 355 |        "    </tr>\n",
 356 |        "    <tr>\n",
 357 |        "      <th>Y</th>\n",
 358 |        "      <td>9</td>\n",
 359 |        "      <td>174</td>\n",
 360 |        "    </tr>\n",
 361 |        "    <tr>\n",
 362 |        "      <th>Z</th>\n",
 363 |        "      <td>58</td>\n",
 364 |        "      <td>643</td>\n",
 365 |        "    </tr>\n",
 366 |        "  </tbody>\n",
 367 |        "</table>\n",
 368 |        "</div>"
 369 |       ],
 370 |       "text/plain": [
 371 |        "        val1  val2\n",
 372 |        "groups            \n",
 373 |        "X          8   173\n",
 374 |        "Y          9   174\n",
 375 |        "Z         58   643"
 376 |       ]
 377 |      },
 378 |      "execution_count": 6,
 379 |      "metadata": {},
 380 |      "output_type": "execute_result"
 381 |     }
 382 |    ],
 383 |    "source": [
 384 |     "df.groupby(\"groups\").aggregate({\"val1\" : \"mean\", \"val2\" : \"median\"})"
 385 |    ]
 386 |   },
 387 |   {
 388 |    "cell_type": "markdown",
 389 |    "id": "0f2b9d90",
 390 |    "metadata": {},
 391 |    "source": [
 392 |     "## Advanced Aggregation Functions: Filter() Function"
 393 |    ]
 394 |   },
 395 |   {
 396 |    "cell_type": "code",
 397 |    "execution_count": 7,
 398 |    "id": "e103a217",
 399 |    "metadata": {},
 400 |    "outputs": [],
 401 |    "source": [
 402 |     "import pandas as pd\n",
 403 |     "import numpy as np"
 404 |    ]
 405 |   },
 406 |   {
 407 |    "cell_type": "code",
 408 |    "execution_count": 8,
 409 |    "id": "77ce20db",
 410 |    "metadata": {},
 411 |    "outputs": [],
 412 |    "source": [
 413 |     "df = pd.DataFrame({'groups': ['X', 'Y', 'Z', 'X', 'Y', 'Z'],\n",
 414 |     "                   'val1': [2, 15, 25, 14, 3, 91],\n",
 415 |     "                   'val2': [92,245,325,254,103,961]})"
 416 |    ]
 417 |   },
 418 |   {
 419 |    "cell_type": "code",
 420 |    "execution_count": 9,
 421 |    "id": "78184ade",
 422 |    "metadata": {},
 423 |    "outputs": [
 424 |     {
 425 |      "data": {
 426 |       "text/html": [
 427 |        "<div>\n",
 428 |        "<style scoped>\n",
 429 |        "    .dataframe tbody tr th:only-of-type {\n",
 430 |        "        vertical-align: middle;\n",
 431 |        "    }\n",
 432 |        "\n",
 433 |        "    .dataframe tbody tr th {\n",
 434 |        "        vertical-align: top;\n",
 435 |        "    }\n",
 436 |        "\n",
 437 |        "    .dataframe thead th {\n",
 438 |        "        text-align: right;\n",
 439 |        "    }\n",
 440 |        "</style>\n",
 441 |        "<table border=\"1\" class=\"dataframe\">\n",
 442 |        "  <thead>\n",
 443 |        "    <tr style=\"text-align: right;\">\n",
 444 |        "      <th></th>\n",
 445 |        "      <th>groups</th>\n",
 446 |        "      <th>val1</th>\n",
 447 |        "      <th>val2</th>\n",
 448 |        "    </tr>\n",
 449 |        "  </thead>\n",
 450 |        "  <tbody>\n",
 451 |        "    <tr>\n",
 452 |        "      <th>0</th>\n",
 453 |        "      <td>X</td>\n",
 454 |        "      <td>2</td>\n",
 455 |        "      <td>92</td>\n",
 456 |        "    </tr>\n",
 457 |        "    <tr>\n",
 458 |        "      <th>1</th>\n",
 459 |        "      <td>Y</td>\n",
 460 |        "      <td>15</td>\n",
 461 |        "      <td>245</td>\n",
 462 |        "    </tr>\n",
 463 |        "    <tr>\n",
 464 |        "      <th>2</th>\n",
 465 |        "      <td>Z</td>\n",
 466 |        "      <td>25</td>\n",
 467 |        "      <td>325</td>\n",
 468 |        "    </tr>\n",
 469 |        "    <tr>\n",
 470 |        "      <th>3</th>\n",
 471 |        "      <td>X</td>\n",
 472 |        "      <td>14</td>\n",
 473 |        "      <td>254</td>\n",
 474 |        "    </tr>\n",
 475 |        "    <tr>\n",
 476 |        "      <th>4</th>\n",
 477 |        "      <td>Y</td>\n",
 478 |        "      <td>3</td>\n",
 479 |        "      <td>103</td>\n",
 480 |        "    </tr>\n",
 481 |        "    <tr>\n",
 482 |        "      <th>5</th>\n",
 483 |        "      <td>Z</td>\n",
 484 |        "      <td>91</td>\n",
 485 |        "      <td>961</td>\n",
 486 |        "    </tr>\n",
 487 |        "  </tbody>\n",
 488 |        "</table>\n",
 489 |        "</div>"
 490 |       ],
 491 |       "text/plain": [
 492 |        "  groups  val1  val2\n",
 493 |        "0      X     2    92\n",
 494 |        "1      Y    15   245\n",
 495 |        "2      Z    25   325\n",
 496 |        "3      X    14   254\n",
 497 |        "4      Y     3   103\n",
 498 |        "5      Z    91   961"
 499 |       ]
 500 |      },
 501 |      "execution_count": 9,
 502 |      "metadata": {},
 503 |      "output_type": "execute_result"
 504 |     }
 505 |    ],
 506 |    "source": [
 507 |     "df"
 508 |    ]
 509 |   },
 510 |   {
 511 |    "cell_type": "code",
 512 |    "execution_count": 10,
 513 |    "id": "c8b04fe2",
 514 |    "metadata": {},
 515 |    "outputs": [
 516 |     {
 517 |      "data": {
 518 |       "text/html": [
 519 |        "<div>\n",
 520 |        "<style scoped>\n",
 521 |        "    .dataframe tbody tr th:only-of-type {\n",
 522 |        "        vertical-align: middle;\n",
 523 |        "    }\n",
 524 |        "\n",
 525 |        "    .dataframe tbody tr th {\n",
 526 |        "        vertical-align: top;\n",
 527 |        "    }\n",
 528 |        "\n",
 529 |        "    .dataframe thead th {\n",
 530 |        "        text-align: right;\n",
 531 |        "    }\n",
 532 |        "</style>\n",
 533 |        "<table border=\"1\" class=\"dataframe\">\n",
 534 |        "  <thead>\n",
 535 |        "    <tr style=\"text-align: right;\">\n",
 536 |        "      <th></th>\n",
 537 |        "      <th>val1</th>\n",
 538 |        "      <th>val2</th>\n",
 539 |        "    </tr>\n",
 540 |        "    <tr>\n",
 541 |        "      <th>groups</th>\n",
 542 |        "      <th></th>\n",
 543 |        "      <th></th>\n",
 544 |        "    </tr>\n",
 545 |        "  </thead>\n",
 546 |        "  <tbody>\n",
 547 |        "    <tr>\n",
 548 |        "      <th>X</th>\n",
 549 |        "      <td>8</td>\n",
 550 |        "      <td>173</td>\n",
 551 |        "    </tr>\n",
 552 |        "    <tr>\n",
 553 |        "      <th>Y</th>\n",
 554 |        "      <td>9</td>\n",
 555 |        "      <td>174</td>\n",
 556 |        "    </tr>\n",
 557 |        "    <tr>\n",
 558 |        "      <th>Z</th>\n",
 559 |        "      <td>58</td>\n",
 560 |        "      <td>643</td>\n",
 561 |        "    </tr>\n",
 562 |        "  </tbody>\n",
 563 |        "</table>\n",
 564 |        "</div>"
 565 |       ],
 566 |       "text/plain": [
 567 |        "        val1  val2\n",
 568 |        "groups            \n",
 569 |        "X          8   173\n",
 570 |        "Y          9   174\n",
 571 |        "Z         58   643"
 572 |       ]
 573 |      },
 574 |      "execution_count": 10,
 575 |      "metadata": {},
 576 |      "output_type": "execute_result"
 577 |     }
 578 |    ],
 579 |    "source": [
 580 |     "df.groupby(\"groups\").mean()"
 581 |    ]
 582 |   },
 583 |   {
 584 |    "cell_type": "code",
 585 |    "execution_count": 11,
 586 |    "id": "0bef7174",
 587 |    "metadata": {},
 588 |    "outputs": [],
 589 |    "source": [
 590 |     "def example_function(x):\n",
 591 |     "    return x[\"val2\"].mean() < 200"
 592 |    ]
 593 |   },
 594 |   {
 595 |    "cell_type": "code",
 596 |    "execution_count": 12,
 597 |    "id": "3c5ac82d",
 598 |    "metadata": {},
 599 |    "outputs": [
 600 |     {
 601 |      "data": {
 602 |       "text/html": [
 603 |        "<div>\n",
 604 |        "<style scoped>\n",
 605 |        "    .dataframe tbody tr th:only-of-type {\n",
 606 |        "        vertical-align: middle;\n",
 607 |        "    }\n",
 608 |        "\n",
 609 |        "    .dataframe tbody tr th {\n",
 610 |        "        vertical-align: top;\n",
 611 |        "    }\n",
 612 |        "\n",
 613 |        "    .dataframe thead th {\n",
 614 |        "        text-align: right;\n",
 615 |        "    }\n",
 616 |        "</style>\n",
 617 |        "<table border=\"1\" class=\"dataframe\">\n",
 618 |        "  <thead>\n",
 619 |        "    <tr style=\"text-align: right;\">\n",
 620 |        "      <th></th>\n",
 621 |        "      <th>groups</th>\n",
 622 |        "      <th>val1</th>\n",
 623 |        "      <th>val2</th>\n",
 624 |        "    </tr>\n",
 625 |        "  </thead>\n",
 626 |        "  <tbody>\n",
 627 |        "    <tr>\n",
 628 |        "      <th>0</th>\n",
 629 |        "      <td>X</td>\n",
 630 |        "      <td>2</td>\n",
 631 |        "      <td>92</td>\n",
 632 |        "    </tr>\n",
 633 |        "    <tr>\n",
 634 |        "      <th>1</th>\n",
 635 |        "      <td>Y</td>\n",
 636 |        "      <td>15</td>\n",
 637 |        "      <td>245</td>\n",
 638 |        "    </tr>\n",
 639 |        "    <tr>\n",
 640 |        "      <th>3</th>\n",
 641 |        "      <td>X</td>\n",
 642 |        "      <td>14</td>\n",
 643 |        "      <td>254</td>\n",
 644 |        "    </tr>\n",
 645 |        "    <tr>\n",
 646 |        "      <th>4</th>\n",
 647 |        "      <td>Y</td>\n",
 648 |        "      <td>3</td>\n",
 649 |        "      <td>103</td>\n",
 650 |        "    </tr>\n",
 651 |        "  </tbody>\n",
 652 |        "</table>\n",
 653 |        "</div>"
 654 |       ],
 655 |       "text/plain": [
 656 |        "  groups  val1  val2\n",
 657 |        "0      X     2    92\n",
 658 |        "1      Y    15   245\n",
 659 |        "3      X    14   254\n",
 660 |        "4      Y     3   103"
 661 |       ]
 662 |      },
 663 |      "execution_count": 12,
 664 |      "metadata": {},
 665 |      "output_type": "execute_result"
 666 |     }
 667 |    ],
 668 |    "source": [
 669 |     "df.groupby(\"groups\").filter(example_function)"
 670 |    ]
 671 |   },
 672 |   {
 673 |    "cell_type": "code",
 674 |    "execution_count": 13,
 675 |    "id": "adadfb0f",
 676 |    "metadata": {},
 677 |    "outputs": [
 678 |     {
 679 |      "data": {
 680 |       "text/html": [
 681 |        "<div>\n",
 682 |        "<style scoped>\n",
 683 |        "    .dataframe tbody tr th:only-of-type {\n",
 684 |        "        vertical-align: middle;\n",
 685 |        "    }\n",
 686 |        "\n",
 687 |        "    .dataframe tbody tr th {\n",
 688 |        "        vertical-align: top;\n",
 689 |        "    }\n",
 690 |        "\n",
 691 |        "    .dataframe thead th {\n",
 692 |        "        text-align: right;\n",
 693 |        "    }\n",
 694 |        "</style>\n",
 695 |        "<table border=\"1\" class=\"dataframe\">\n",
 696 |        "  <thead>\n",
 697 |        "    <tr style=\"text-align: right;\">\n",
 698 |        "      <th></th>\n",
 699 |        "      <th>val1</th>\n",
 700 |        "      <th>val2</th>\n",
 701 |        "    </tr>\n",
 702 |        "    <tr>\n",
 703 |        "      <th>groups</th>\n",
 704 |        "      <th></th>\n",
 705 |        "      <th></th>\n",
 706 |        "    </tr>\n",
 707 |        "  </thead>\n",
 708 |        "  <tbody>\n",
 709 |        "    <tr>\n",
 710 |        "      <th>X</th>\n",
 711 |        "      <td>8.485281</td>\n",
 712 |        "      <td>114.551299</td>\n",
 713 |        "    </tr>\n",
 714 |        "    <tr>\n",
 715 |        "      <th>Y</th>\n",
 716 |        "      <td>8.485281</td>\n",
 717 |        "      <td>100.409163</td>\n",
 718 |        "    </tr>\n",
 719 |        "    <tr>\n",
 720 |        "      <th>Z</th>\n",
 721 |        "      <td>46.669048</td>\n",
 722 |        "      <td>449.719913</td>\n",
 723 |        "    </tr>\n",
 724 |        "  </tbody>\n",
 725 |        "</table>\n",
 726 |        "</div>"
 727 |       ],
 728 |       "text/plain": [
 729 |        "             val1        val2\n",
 730 |        "groups                       \n",
 731 |        "X        8.485281  114.551299\n",
 732 |        "Y        8.485281  100.409163\n",
 733 |        "Z       46.669048  449.719913"
 734 |       ]
 735 |      },
 736 |      "execution_count": 13,
 737 |      "metadata": {},
 738 |      "output_type": "execute_result"
 739 |     }
 740 |    ],
 741 |    "source": [
 742 |     "df.groupby(\"groups\").std()"
 743 |    ]
 744 |   },
 745 |   {
 746 |    "cell_type": "code",
 747 |    "execution_count": 14,
 748 |    "id": "ecb47ae5",
 749 |    "metadata": {},
 750 |    "outputs": [
 751 |     {
 752 |      "data": {
 753 |       "text/html": [
 754 |        "<div>\n",
 755 |        "<style scoped>\n",
 756 |        "    .dataframe tbody tr th:only-of-type {\n",
 757 |        "        vertical-align: middle;\n",
 758 |        "    }\n",
 759 |        "\n",
 760 |        "    .dataframe tbody tr th {\n",
 761 |        "        vertical-align: top;\n",
 762 |        "    }\n",
 763 |        "\n",
 764 |        "    .dataframe thead th {\n",
 765 |        "        text-align: right;\n",
 766 |        "    }\n",
 767 |        "</style>\n",
 768 |        "<table border=\"1\" class=\"dataframe\">\n",
 769 |        "  <thead>\n",
 770 |        "    <tr style=\"text-align: right;\">\n",
 771 |        "      <th></th>\n",
 772 |        "      <th>groups</th>\n",
 773 |        "      <th>val1</th>\n",
 774 |        "      <th>val2</th>\n",
 775 |        "    </tr>\n",
 776 |        "  </thead>\n",
 777 |        "  <tbody>\n",
 778 |        "    <tr>\n",
 779 |        "      <th>0</th>\n",
 780 |        "      <td>X</td>\n",
 781 |        "      <td>2</td>\n",
 782 |        "      <td>92</td>\n",
 783 |        "    </tr>\n",
 784 |        "    <tr>\n",
 785 |        "      <th>2</th>\n",
 786 |        "      <td>Z</td>\n",
 787 |        "      <td>25</td>\n",
 788 |        "      <td>325</td>\n",
 789 |        "    </tr>\n",
 790 |        "    <tr>\n",
 791 |        "      <th>3</th>\n",
 792 |        "      <td>X</td>\n",
 793 |        "      <td>14</td>\n",
 794 |        "      <td>254</td>\n",
 795 |        "    </tr>\n",
 796 |        "    <tr>\n",
 797 |        "      <th>5</th>\n",
 798 |        "      <td>Z</td>\n",
 799 |        "      <td>91</td>\n",
 800 |        "      <td>961</td>\n",
 801 |        "    </tr>\n",
 802 |        "  </tbody>\n",
 803 |        "</table>\n",
 804 |        "</div>"
 805 |       ],
 806 |       "text/plain": [
 807 |        "  groups  val1  val2\n",
 808 |        "0      X     2    92\n",
 809 |        "2      Z    25   325\n",
 810 |        "3      X    14   254\n",
 811 |        "5      Z    91   961"
 812 |       ]
 813 |      },
 814 |      "execution_count": 14,
 815 |      "metadata": {},
 816 |      "output_type": "execute_result"
 817 |     }
 818 |    ],
 819 |    "source": [
 820 |     "df.groupby(\"groups\").filter(lambda x : x[\"val2\"].std() > 105)"
 821 |    ]
 822 |   },
 823 |   {
 824 |    "cell_type": "markdown",
 825 |    "id": "e7eac850",
 826 |    "metadata": {},
 827 |    "source": [
 828 |     "## Advanced Aggregation Functions: Transform() Function"
 829 |    ]
 830 |   },
 831 |   {
 832 |    "cell_type": "code",
 833 |    "execution_count": 15,
 834 |    "id": "73f28b47",
 835 |    "metadata": {},
 836 |    "outputs": [],
 837 |    "source": [
 838 |     "import pandas as pd\n",
 839 |     "import numpy as np"
 840 |    ]
 841 |   },
 842 |   {
 843 |    "cell_type": "code",
 844 |    "execution_count": 16,
 845 |    "id": "cd8edd85",
 846 |    "metadata": {},
 847 |    "outputs": [],
 848 |    "source": [
 849 |     "df = pd.DataFrame({'groups': ['X', 'Y', 'Z', 'X', 'Y', 'Z'],\n",
 850 |     "                   'val1': [2, 15, 25, 14, 3, 91],\n",
 851 |     "                   'val2': [92,245,325,254,103,961]})"
 852 |    ]
 853 |   },
 854 |   {
 855 |    "cell_type": "code",
 856 |    "execution_count": 17,
 857 |    "id": "f39a11b3",
 858 |    "metadata": {},
 859 |    "outputs": [
 860 |     {
 861 |      "data": {
 862 |       "text/html": [
 863 |        "<div>\n",
 864 |        "<style scoped>\n",
 865 |        "    .dataframe tbody tr th:only-of-type {\n",
 866 |        "        vertical-align: middle;\n",
 867 |        "    }\n",
 868 |        "\n",
 869 |        "    .dataframe tbody tr th {\n",
 870 |        "        vertical-align: top;\n",
 871 |        "    }\n",
 872 |        "\n",
 873 |        "    .dataframe thead th {\n",
 874 |        "        text-align: right;\n",
 875 |        "    }\n",
 876 |        "</style>\n",
 877 |        "<table border=\"1\" class=\"dataframe\">\n",
 878 |        "  <thead>\n",
 879 |        "    <tr style=\"text-align: right;\">\n",
 880 |        "      <th></th>\n",
 881 |        "      <th>groups</th>\n",
 882 |        "      <th>val1</th>\n",
 883 |        "      <th>val2</th>\n",
 884 |        "    </tr>\n",
 885 |        "  </thead>\n",
 886 |        "  <tbody>\n",
 887 |        "    <tr>\n",
 888 |        "      <th>0</th>\n",
 889 |        "      <td>X</td>\n",
 890 |        "      <td>2</td>\n",
 891 |        "      <td>92</td>\n",
 892 |        "    </tr>\n",
 893 |        "    <tr>\n",
 894 |        "      <th>1</th>\n",
 895 |        "      <td>Y</td>\n",
 896 |        "      <td>15</td>\n",
 897 |        "      <td>245</td>\n",
 898 |        "    </tr>\n",
 899 |        "    <tr>\n",
 900 |        "      <th>2</th>\n",
 901 |        "      <td>Z</td>\n",
 902 |        "      <td>25</td>\n",
 903 |        "      <td>325</td>\n",
 904 |        "    </tr>\n",
 905 |        "    <tr>\n",
 906 |        "      <th>3</th>\n",
 907 |        "      <td>X</td>\n",
 908 |        "      <td>14</td>\n",
 909 |        "      <td>254</td>\n",
 910 |        "    </tr>\n",
 911 |        "    <tr>\n",
 912 |        "      <th>4</th>\n",
 913 |        "      <td>Y</td>\n",
 914 |        "      <td>3</td>\n",
 915 |        "      <td>103</td>\n",
 916 |        "    </tr>\n",
 917 |        "    <tr>\n",
 918 |        "      <th>5</th>\n",
 919 |        "      <td>Z</td>\n",
 920 |        "      <td>91</td>\n",
 921 |        "      <td>961</td>\n",
 922 |        "    </tr>\n",
 923 |        "  </tbody>\n",
 924 |        "</table>\n",
 925 |        "</div>"
 926 |       ],
 927 |       "text/plain": [
 928 |        "  groups  val1  val2\n",
 929 |        "0      X     2    92\n",
 930 |        "1      Y    15   245\n",
 931 |        "2      Z    25   325\n",
 932 |        "3      X    14   254\n",
 933 |        "4      Y     3   103\n",
 934 |        "5      Z    91   961"
 935 |       ]
 936 |      },
 937 |      "execution_count": 17,
 938 |      "metadata": {},
 939 |      "output_type": "execute_result"
 940 |     }
 941 |    ],
 942 |    "source": [
 943 |     "df"
 944 |    ]
 945 |   },
 946 |   {
 947 |    "cell_type": "code",
 948 |    "execution_count": 18,
 949 |    "id": "2f15e109",
 950 |    "metadata": {},
 951 |    "outputs": [],
 952 |    "source": [
 953 |     "df_new = df.loc[:, \"val1\":\"val2\"]"
 954 |    ]
 955 |   },
 956 |   {
 957 |    "cell_type": "code",
 958 |    "execution_count": 19,
 959 |    "id": "869b3bd1",
 960 |    "metadata": {
 961 |     "scrolled": true
 962 |    },
 963 |    "outputs": [
 964 |     {
 965 |      "data": {
 966 |       "text/html": [
 967 |        "<div>\n",
 968 |        "<style scoped>\n",
 969 |        "    .dataframe tbody tr th:only-of-type {\n",
 970 |        "        vertical-align: middle;\n",
 971 |        "    }\n",
 972 |        "\n",
 973 |        "    .dataframe tbody tr th {\n",
 974 |        "        vertical-align: top;\n",
 975 |        "    }\n",
 976 |        "\n",
 977 |        "    .dataframe thead th {\n",
 978 |        "        text-align: right;\n",
 979 |        "    }\n",
 980 |        "</style>\n",
 981 |        "<table border=\"1\" class=\"dataframe\">\n",
 982 |        "  <thead>\n",
 983 |        "    <tr style=\"text-align: right;\">\n",
 984 |        "      <th></th>\n",
 985 |        "      <th>val1</th>\n",
 986 |        "      <th>val2</th>\n",
 987 |        "    </tr>\n",
 988 |        "  </thead>\n",
 989 |        "  <tbody>\n",
 990 |        "    <tr>\n",
 991 |        "      <th>0</th>\n",
 992 |        "      <td>2</td>\n",
 993 |        "      <td>92</td>\n",
 994 |        "    </tr>\n",
 995 |        "    <tr>\n",
 996 |        "      <th>1</th>\n",
 997 |        "      <td>15</td>\n",
 998 |        "      <td>245</td>\n",
 999 |        "    </tr>\n",
1000 |        "    <tr>\n",
1001 |        "      <th>2</th>\n",
1002 |        "      <td>25</td>\n",
1003 |        "      <td>325</td>\n",
1004 |        "    </tr>\n",
1005 |        "    <tr>\n",
1006 |        "      <th>3</th>\n",
1007 |        "      <td>14</td>\n",
1008 |        "      <td>254</td>\n",
1009 |        "    </tr>\n",
1010 |        "    <tr>\n",
1011 |        "      <th>4</th>\n",
1012 |        "      <td>3</td>\n",
1013 |        "      <td>103</td>\n",
1014 |        "    </tr>\n",
1015 |        "    <tr>\n",
1016 |        "      <th>5</th>\n",
1017 |        "      <td>91</td>\n",
1018 |        "      <td>961</td>\n",
1019 |        "    </tr>\n",
1020 |        "  </tbody>\n",
1021 |        "</table>\n",
1022 |        "</div>"
1023 |       ],
1024 |       "text/plain": [
1025 |        "   val1  val2\n",
1026 |        "0     2    92\n",
1027 |        "1    15   245\n",
1028 |        "2    25   325\n",
1029 |        "3    14   254\n",
1030 |        "4     3   103\n",
1031 |        "5    91   961"
1032 |       ]
1033 |      },
1034 |      "execution_count": 19,
1035 |      "metadata": {},
1036 |      "output_type": "execute_result"
1037 |     }
1038 |    ],
1039 |    "source": [
1040 |     "df_new"
1041 |    ]
1042 |   },
1043 |   {
1044 |    "cell_type": "code",
1045 |    "execution_count": 20,
1046 |    "id": "0e717299",
1047 |    "metadata": {},
1048 |    "outputs": [],
1049 |    "source": [
1050 |     "def normalize(x):\n",
1051 |     "    return (x - x.min()) / (x.max() - x.min())"
1052 |    ]
1053 |   },
1054 |   {
1055 |    "cell_type": "code",
1056 |    "execution_count": 21,
1057 |    "id": "9f20ee93",
1058 |    "metadata": {},
1059 |    "outputs": [
1060 |     {
1061 |      "data": {
1062 |       "text/html": [
1063 |        "<div>\n",
1064 |        "<style scoped>\n",
1065 |        "    .dataframe tbody tr th:only-of-type {\n",
1066 |        "        vertical-align: middle;\n",
1067 |        "    }\n",
1068 |        "\n",
1069 |        "    .dataframe tbody tr th {\n",
1070 |        "        vertical-align: top;\n",
1071 |        "    }\n",
1072 |        "\n",
1073 |        "    .dataframe thead th {\n",
1074 |        "        text-align: right;\n",
1075 |        "    }\n",
1076 |        "</style>\n",
1077 |        "<table border=\"1\" class=\"dataframe\">\n",
1078 |        "  <thead>\n",
1079 |        "    <tr style=\"text-align: right;\">\n",
1080 |        "      <th></th>\n",
1081 |        "      <th>val1</th>\n",
1082 |        "      <th>val2</th>\n",
1083 |        "    </tr>\n",
1084 |        "  </thead>\n",
1085 |        "  <tbody>\n",
1086 |        "    <tr>\n",
1087 |        "      <th>0</th>\n",
1088 |        "      <td>0.000000</td>\n",
1089 |        "      <td>0.000000</td>\n",
1090 |        "    </tr>\n",
1091 |        "    <tr>\n",
1092 |        "      <th>1</th>\n",
1093 |        "      <td>0.146067</td>\n",
1094 |        "      <td>0.176064</td>\n",
1095 |        "    </tr>\n",
1096 |        "    <tr>\n",
1097 |        "      <th>2</th>\n",
1098 |        "      <td>0.258427</td>\n",
1099 |        "      <td>0.268124</td>\n",
1100 |        "    </tr>\n",
1101 |        "    <tr>\n",
1102 |        "      <th>3</th>\n",
1103 |        "      <td>0.134831</td>\n",
1104 |        "      <td>0.186421</td>\n",
1105 |        "    </tr>\n",
1106 |        "    <tr>\n",
1107 |        "      <th>4</th>\n",
1108 |        "      <td>0.011236</td>\n",
1109 |        "      <td>0.012658</td>\n",
1110 |        "    </tr>\n",
1111 |        "    <tr>\n",
1112 |        "      <th>5</th>\n",
1113 |        "      <td>1.000000</td>\n",
1114 |        "      <td>1.000000</td>\n",
1115 |        "    </tr>\n",
1116 |        "  </tbody>\n",
1117 |        "</table>\n",
1118 |        "</div>"
1119 |       ],
1120 |       "text/plain": [
1121 |        "       val1      val2\n",
1122 |        "0  0.000000  0.000000\n",
1123 |        "1  0.146067  0.176064\n",
1124 |        "2  0.258427  0.268124\n",
1125 |        "3  0.134831  0.186421\n",
1126 |        "4  0.011236  0.012658\n",
1127 |        "5  1.000000  1.000000"
1128 |       ]
1129 |      },
1130 |      "execution_count": 21,
1131 |      "metadata": {},
1132 |      "output_type": "execute_result"
1133 |     }
1134 |    ],
1135 |    "source": [
1136 |     "df_new.transform(normalize)"
1137 |    ]
1138 |   },
1139 |   {
1140 |    "cell_type": "code",
1141 |    "execution_count": 22,
1142 |    "id": "0f194072",
1143 |    "metadata": {},
1144 |    "outputs": [
1145 |     {
1146 |      "data": {
1147 |       "text/plain": [
1148 |        "15"
1149 |       ]
1150 |      },
1151 |      "execution_count": 22,
1152 |      "metadata": {},
1153 |      "output_type": "execute_result"
1154 |     }
1155 |    ],
1156 |    "source": [
1157 |     "df_new.loc[1, \"val1\"]"
1158 |    ]
1159 |   },
1160 |   {
1161 |    "cell_type": "code",
1162 |    "execution_count": 23,
1163 |    "id": "96f69f3b",
1164 |    "metadata": {},
1165 |    "outputs": [
1166 |     {
1167 |      "data": {
1168 |       "text/plain": [
1169 |        "0.14606741573033707"
1170 |       ]
1171 |      },
1172 |      "execution_count": 23,
1173 |      "metadata": {},
1174 |      "output_type": "execute_result"
1175 |     }
1176 |    ],
1177 |    "source": [
1178 |     "(df_new.loc[1, \"val1\"] - df[\"val1\"].min()) / (df[\"val1\"].max() - df[\"val1\"].min())"
1179 |    ]
1180 |   },
1181 |   {
1182 |    "cell_type": "code",
1183 |    "execution_count": 24,
1184 |    "id": "7cee8da6",
1185 |    "metadata": {},
1186 |    "outputs": [
1187 |     {
1188 |      "data": {
1189 |       "text/html": [
1190 |        "<div>\n",
1191 |        "<style scoped>\n",
1192 |        "    .dataframe tbody tr th:only-of-type {\n",
1193 |        "        vertical-align: middle;\n",
1194 |        "    }\n",
1195 |        "\n",
1196 |        "    .dataframe tbody tr th {\n",
1197 |        "        vertical-align: top;\n",
1198 |        "    }\n",
1199 |        "\n",
1200 |        "    .dataframe thead th {\n",
1201 |        "        text-align: right;\n",
1202 |        "    }\n",
1203 |        "</style>\n",
1204 |        "<table border=\"1\" class=\"dataframe\">\n",
1205 |        "  <thead>\n",
1206 |        "    <tr style=\"text-align: right;\">\n",
1207 |        "      <th></th>\n",
1208 |        "      <th>val1</th>\n",
1209 |        "      <th>val2</th>\n",
1210 |        "    </tr>\n",
1211 |        "  </thead>\n",
1212 |        "  <tbody>\n",
1213 |        "    <tr>\n",
1214 |        "      <th>0</th>\n",
1215 |        "      <td>2</td>\n",
1216 |        "      <td>92</td>\n",
1217 |        "    </tr>\n",
1218 |        "    <tr>\n",
1219 |        "      <th>1</th>\n",
1220 |        "      <td>15</td>\n",
1221 |        "      <td>245</td>\n",
1222 |        "    </tr>\n",
1223 |        "    <tr>\n",
1224 |        "      <th>2</th>\n",
1225 |        "      <td>25</td>\n",
1226 |        "      <td>325</td>\n",
1227 |        "    </tr>\n",
1228 |        "    <tr>\n",
1229 |        "      <th>3</th>\n",
1230 |        "      <td>14</td>\n",
1231 |        "      <td>254</td>\n",
1232 |        "    </tr>\n",
1233 |        "    <tr>\n",
1234 |        "      <th>4</th>\n",
1235 |        "      <td>3</td>\n",
1236 |        "      <td>103</td>\n",
1237 |        "    </tr>\n",
1238 |        "    <tr>\n",
1239 |        "      <th>5</th>\n",
1240 |        "      <td>91</td>\n",
1241 |        "      <td>961</td>\n",
1242 |        "    </tr>\n",
1243 |        "  </tbody>\n",
1244 |        "</table>\n",
1245 |        "</div>"
1246 |       ],
1247 |       "text/plain": [
1248 |        "   val1  val2\n",
1249 |        "0     2    92\n",
1250 |        "1    15   245\n",
1251 |        "2    25   325\n",
1252 |        "3    14   254\n",
1253 |        "4     3   103\n",
1254 |        "5    91   961"
1255 |       ]
1256 |      },
1257 |      "execution_count": 24,
1258 |      "metadata": {},
1259 |      "output_type": "execute_result"
1260 |     }
1261 |    ],
1262 |    "source": [
1263 |     "df_new"
1264 |    ]
1265 |   },
1266 |   {
1267 |    "cell_type": "code",
1268 |    "execution_count": 25,
1269 |    "id": "5a10fc63",
1270 |    "metadata": {},
1271 |    "outputs": [
1272 |     {
1273 |      "data": {
1274 |       "text/html": [
1275 |        "<div>\n",
1276 |        "<style scoped>\n",
1277 |        "    .dataframe tbody tr th:only-of-type {\n",
1278 |        "        vertical-align: middle;\n",
1279 |        "    }\n",
1280 |        "\n",
1281 |        "    .dataframe tbody tr th {\n",
1282 |        "        vertical-align: top;\n",
1283 |        "    }\n",
1284 |        "\n",
1285 |        "    .dataframe thead th {\n",
1286 |        "        text-align: right;\n",
1287 |        "    }\n",
1288 |        "</style>\n",
1289 |        "<table border=\"1\" class=\"dataframe\">\n",
1290 |        "  <thead>\n",
1291 |        "    <tr style=\"text-align: right;\">\n",
1292 |        "      <th></th>\n",
1293 |        "      <th>val1</th>\n",
1294 |        "      <th>val2</th>\n",
1295 |        "    </tr>\n",
1296 |        "  </thead>\n",
1297 |        "  <tbody>\n",
1298 |        "    <tr>\n",
1299 |        "      <th>0</th>\n",
1300 |        "      <td>0.909297</td>\n",
1301 |        "      <td>-0.779466</td>\n",
1302 |        "    </tr>\n",
1303 |        "    <tr>\n",
1304 |        "      <th>1</th>\n",
1305 |        "      <td>0.650288</td>\n",
1306 |        "      <td>-0.044213</td>\n",
1307 |        "    </tr>\n",
1308 |        "    <tr>\n",
1309 |        "      <th>2</th>\n",
1310 |        "      <td>-0.132352</td>\n",
1311 |        "      <td>-0.988036</td>\n",
1312 |        "    </tr>\n",
1313 |        "    <tr>\n",
1314 |        "      <th>3</th>\n",
1315 |        "      <td>0.990607</td>\n",
1316 |        "      <td>0.451999</td>\n",
1317 |        "    </tr>\n",
1318 |        "    <tr>\n",
1319 |        "      <th>4</th>\n",
1320 |        "      <td>0.141120</td>\n",
1321 |        "      <td>0.622989</td>\n",
1322 |        "    </tr>\n",
1323 |        "    <tr>\n",
1324 |        "      <th>5</th>\n",
1325 |        "      <td>0.105988</td>\n",
1326 |        "      <td>-0.321537</td>\n",
1327 |        "    </tr>\n",
1328 |        "  </tbody>\n",
1329 |        "</table>\n",
1330 |        "</div>"
1331 |       ],
1332 |       "text/plain": [
1333 |        "       val1      val2\n",
1334 |        "0  0.909297 -0.779466\n",
1335 |        "1  0.650288 -0.044213\n",
1336 |        "2 -0.132352 -0.988036\n",
1337 |        "3  0.990607  0.451999\n",
1338 |        "4  0.141120  0.622989\n",
1339 |        "5  0.105988 -0.321537"
1340 |       ]
1341 |      },
1342 |      "execution_count": 25,
1343 |      "metadata": {},
1344 |      "output_type": "execute_result"
1345 |     }
1346 |    ],
1347 |    "source": [
1348 |     "df_new.transform(lambda a : np.sin(a))"
1349 |    ]
1350 |   },
1351 |   {
1352 |    "cell_type": "code",
1353 |    "execution_count": 26,
1354 |    "id": "6d7b6b4f",
1355 |    "metadata": {},
1356 |    "outputs": [
1357 |     {
1358 |      "data": {
1359 |       "text/plain": [
1360 |        "0   -0.779466\n",
1361 |        "1   -0.044213\n",
1362 |        "2   -0.988036\n",
1363 |        "3    0.451999\n",
1364 |        "4    0.622989\n",
1365 |        "5   -0.321537\n",
1366 |        "Name: val2, dtype: float64"
1367 |       ]
1368 |      },
1369 |      "execution_count": 26,
1370 |      "metadata": {},
1371 |      "output_type": "execute_result"
1372 |     }
1373 |    ],
1374 |    "source": [
1375 |     "np.sin(df_new.val2)"
1376 |    ]
1377 |   },
1378 |   {
1379 |    "cell_type": "markdown",
1380 |    "id": "5f8a2091",
1381 |    "metadata": {},
1382 |    "source": [
1383 |     "## Advanced Aggregation Functions:  Apply() Function"
1384 |    ]
1385 |   },
1386 |   {
1387 |    "cell_type": "code",
1388 |    "execution_count": 1,
1389 |    "id": "ffe5d394",
1390 |    "metadata": {},
1391 |    "outputs": [],
1392 |    "source": [
1393 |     "import pandas as pd\n",
1394 |     "import numpy as np"
1395 |    ]
1396 |   },
1397 |   {
1398 |    "cell_type": "code",
1399 |    "execution_count": 2,
1400 |    "id": "9130568c",
1401 |    "metadata": {},
1402 |    "outputs": [],
1403 |    "source": [
1404 |     "df = pd.DataFrame({'groups': ['X', 'Y', 'Z', 'X', 'Y', 'Z'],\n",
1405 |     "                   'val1': [2, 15, 25, 14, 3, 91],\n",
1406 |     "                   'val2': [92,245,325,254,103,961]})"
1407 |    ]
1408 |   },
1409 |   {
1410 |    "cell_type": "code",
1411 |    "execution_count": 3,
1412 |    "id": "6a0b50d2",
1413 |    "metadata": {
1414 |     "scrolled": true
1415 |    },
1416 |    "outputs": [
1417 |     {
1418 |      "data": {
1419 |       "text/html": [
1420 |        "<div>\n",
1421 |        "<style scoped>\n",
1422 |        "    .dataframe tbody tr th:only-of-type {\n",
1423 |        "        vertical-align: middle;\n",
1424 |        "    }\n",
1425 |        "\n",
1426 |        "    .dataframe tbody tr th {\n",
1427 |        "        vertical-align: top;\n",
1428 |        "    }\n",
1429 |        "\n",
1430 |        "    .dataframe thead th {\n",
1431 |        "        text-align: right;\n",
1432 |        "    }\n",
1433 |        "</style>\n",
1434 |        "<table border=\"1\" class=\"dataframe\">\n",
1435 |        "  <thead>\n",
1436 |        "    <tr style=\"text-align: right;\">\n",
1437 |        "      <th></th>\n",
1438 |        "      <th>groups</th>\n",
1439 |        "      <th>val1</th>\n",
1440 |        "      <th>val2</th>\n",
1441 |        "    </tr>\n",
1442 |        "  </thead>\n",
1443 |        "  <tbody>\n",
1444 |        "    <tr>\n",
1445 |        "      <th>0</th>\n",
1446 |        "      <td>X</td>\n",
1447 |        "      <td>2</td>\n",
1448 |        "      <td>92</td>\n",
1449 |        "    </tr>\n",
1450 |        "    <tr>\n",
1451 |        "      <th>1</th>\n",
1452 |        "      <td>Y</td>\n",
1453 |        "      <td>15</td>\n",
1454 |        "      <td>245</td>\n",
1455 |        "    </tr>\n",
1456 |        "    <tr>\n",
1457 |        "      <th>2</th>\n",
1458 |        "      <td>Z</td>\n",
1459 |        "      <td>25</td>\n",
1460 |        "      <td>325</td>\n",
1461 |        "    </tr>\n",
1462 |        "    <tr>\n",
1463 |        "      <th>3</th>\n",
1464 |        "      <td>X</td>\n",
1465 |        "      <td>14</td>\n",
1466 |        "      <td>254</td>\n",
1467 |        "    </tr>\n",
1468 |        "    <tr>\n",
1469 |        "      <th>4</th>\n",
1470 |        "      <td>Y</td>\n",
1471 |        "      <td>3</td>\n",
1472 |        "      <td>103</td>\n",
1473 |        "    </tr>\n",
1474 |        "    <tr>\n",
1475 |        "      <th>5</th>\n",
1476 |        "      <td>Z</td>\n",
1477 |        "      <td>91</td>\n",
1478 |        "      <td>961</td>\n",
1479 |        "    </tr>\n",
1480 |        "  </tbody>\n",
1481 |        "</table>\n",
1482 |        "</div>"
1483 |       ],
1484 |       "text/plain": [
1485 |        "  groups  val1  val2\n",
1486 |        "0      X     2    92\n",
1487 |        "1      Y    15   245\n",
1488 |        "2      Z    25   325\n",
1489 |        "3      X    14   254\n",
1490 |        "4      Y     3   103\n",
1491 |        "5      Z    91   961"
1492 |       ]
1493 |      },
1494 |      "execution_count": 3,
1495 |      "metadata": {},
1496 |      "output_type": "execute_result"
1497 |     }
1498 |    ],
1499 |    "source": [
1500 |     "df"
1501 |    ]
1502 |   },
1503 |   {
1504 |    "cell_type": "code",
1505 |    "execution_count": 4,
1506 |    "id": "263a19dd",
1507 |    "metadata": {},
1508 |    "outputs": [
1509 |     {
1510 |      "data": {
1511 |       "text/plain": [
1512 |        "groups    XYZXYZ\n",
1513 |        "val1         150\n",
1514 |        "val2        1980\n",
1515 |        "dtype: object"
1516 |       ]
1517 |      },
1518 |      "execution_count": 4,
1519 |      "metadata": {},
1520 |      "output_type": "execute_result"
1521 |     }
1522 |    ],
1523 |    "source": [
1524 |     "df.apply(np.sum)"
1525 |    ]
1526 |   },
1527 |   {
1528 |    "cell_type": "code",
1529 |    "execution_count": 5,
1530 |    "id": "c14ca735",
1531 |    "metadata": {},
1532 |    "outputs": [
1533 |     {
1534 |      "ename": "TypeError",
1535 |      "evalue": "Could not convert XYZXYZ to numeric",
1536 |      "output_type": "error",
1537 |      "traceback": [
1538 |       "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
1539 |       "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
1540 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\nanops.py\u001b[0m in \u001b[0;36m_ensure_numeric\u001b[1;34m(x)\u001b[0m\n\u001b[0;32m   1536\u001b[0m         \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1537\u001b[1;33m             \u001b[0mx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mfloat\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1538\u001b[0m         \u001b[1;32mexcept\u001b[0m \u001b[0mValueError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
1541 |       "\u001b[1;31mValueError\u001b[0m: could not convert string to float: 'XYZXYZ'",
1542 |       "\nDuring handling of the above exception, another exception occurred:\n",
1543 |       "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
1544 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\nanops.py\u001b[0m in \u001b[0;36m_ensure_numeric\u001b[1;34m(x)\u001b[0m\n\u001b[0;32m   1540\u001b[0m             \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1541\u001b[1;33m                 \u001b[0mx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcomplex\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1542\u001b[0m             \u001b[1;32mexcept\u001b[0m \u001b[0mValueError\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
1545 |       "\u001b[1;31mValueError\u001b[0m: complex() arg is a malformed string",
1546 |       "\nThe above exception was the direct cause of the following exception:\n",
1547 |       "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
1548 |       "\u001b[1;32m<ipython-input-5-ed42af76af33>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmean\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
1549 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36mapply\u001b[1;34m(self, func, axis, raw, result_type, args, **kwds)\u001b[0m\n\u001b[0;32m   7766\u001b[0m             \u001b[0mkwds\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   7767\u001b[0m         )\n\u001b[1;32m-> 7768\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mop\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_result\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   7769\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   7770\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mapplymap\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mna_action\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mOptional\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mstr\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m->\u001b[0m \u001b[0mDataFrame\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
1550 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\apply.py\u001b[0m in \u001b[0;36mget_result\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    183\u001b[0m             \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_raw\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    184\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 185\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_standard\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    186\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    187\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mapply_empty_result\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
1551 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\apply.py\u001b[0m in \u001b[0;36mapply_standard\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    274\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    275\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mapply_standard\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 276\u001b[1;33m         \u001b[0mresults\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mres_index\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_series_generator\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    277\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    278\u001b[0m         \u001b[1;31m# wrap results\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
1552 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\apply.py\u001b[0m in \u001b[0;36mapply_series_generator\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    288\u001b[0m             \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mv\u001b[0m \u001b[1;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mseries_gen\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    289\u001b[0m                 \u001b[1;31m# ignore SettingWithCopy here in case the user mutates\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 290\u001b[1;33m                 \u001b[0mresults\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mv\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    291\u001b[0m                 \u001b[1;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mresults\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mABCSeries\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    292\u001b[0m                     \u001b[1;31m# If we have a view on v, we need to make a copy because\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
1553 |       "\u001b[1;32m<__array_function__ internals>\u001b[0m in \u001b[0;36mmean\u001b[1;34m(*args, **kwargs)\u001b[0m\n",
1554 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\numpy\\core\\fromnumeric.py\u001b[0m in \u001b[0;36mmean\u001b[1;34m(a, axis, dtype, out, keepdims, where)\u001b[0m\n\u001b[0;32m   3415\u001b[0m             \u001b[1;32mpass\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3416\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3417\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mmean\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mout\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mout\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   3418\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3419\u001b[0m     return _methods._mean(a, axis=axis, dtype=dtype,\n",
1555 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\generic.py\u001b[0m in \u001b[0;36mmean\u001b[1;34m(self, axis, skipna, level, numeric_only, **kwargs)\u001b[0m\n\u001b[0;32m  11116\u001b[0m         )\n\u001b[0;32m  11117\u001b[0m         \u001b[1;32mdef\u001b[0m \u001b[0mmean\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mskipna\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlevel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnumeric_only\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m> 11118\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mNDFrame\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmean\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mskipna\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlevel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnumeric_only\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m  11119\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m  11120\u001b[0m         \u001b[1;31m# pandas\\core\\generic.py:10924: error: Cannot assign to a method\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
1556 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\generic.py\u001b[0m in \u001b[0;36mmean\u001b[1;34m(self, axis, skipna, level, numeric_only, **kwargs)\u001b[0m\n\u001b[0;32m  10724\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m  10725\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mmean\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mskipna\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlevel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnumeric_only\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m> 10726\u001b[1;33m         return self._stat_function(\n\u001b[0m\u001b[0;32m  10727\u001b[0m             \u001b[1;34m\"mean\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnanops\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnanmean\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mskipna\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlevel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnumeric_only\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m  10728\u001b[0m         )\n",
1557 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\generic.py\u001b[0m in \u001b[0;36m_stat_function\u001b[1;34m(self, name, func, axis, skipna, level, numeric_only, **kwargs)\u001b[0m\n\u001b[0;32m  10709\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mlevel\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m  10710\u001b[0m             \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_agg_by_level\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlevel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mlevel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mskipna\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mskipna\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m> 10711\u001b[1;33m         return self._reduce(\n\u001b[0m\u001b[0;32m  10712\u001b[0m             \u001b[0mfunc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mskipna\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mskipna\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnumeric_only\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mnumeric_only\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m  10713\u001b[0m         )\n",
1558 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\series.py\u001b[0m in \u001b[0;36m_reduce\u001b[1;34m(self, op, name, axis, skipna, numeric_only, filter_type, **kwds)\u001b[0m\n\u001b[0;32m   4180\u001b[0m                 )\n\u001b[0;32m   4181\u001b[0m             \u001b[1;32mwith\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0merrstate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mall\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"ignore\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 4182\u001b[1;33m                 \u001b[1;32mreturn\u001b[0m \u001b[0mop\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdelegate\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mskipna\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mskipna\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   4183\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   4184\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m_reindex_indexer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnew_index\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindexer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcopy\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
1559 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\nanops.py\u001b[0m in \u001b[0;36m_f\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m     71\u001b[0m             \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     72\u001b[0m                 \u001b[1;32mwith\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0merrstate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0minvalid\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"ignore\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 73\u001b[1;33m                     \u001b[1;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     74\u001b[0m             \u001b[1;32mexcept\u001b[0m \u001b[0mValueError\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     75\u001b[0m                 \u001b[1;31m# we want to transform an object array\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
1560 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\nanops.py\u001b[0m in \u001b[0;36mf\u001b[1;34m(values, axis, skipna, **kwds)\u001b[0m\n\u001b[0;32m    133\u001b[0m                     \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0malt\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mskipna\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mskipna\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    134\u001b[0m             \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 135\u001b[1;33m                 \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0malt\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mskipna\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mskipna\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    136\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    137\u001b[0m             \u001b[1;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
1561 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\nanops.py\u001b[0m in \u001b[0;36mnew_func\u001b[1;34m(values, axis, skipna, mask, **kwargs)\u001b[0m\n\u001b[0;32m    392\u001b[0m             \u001b[0mmask\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0misna\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    393\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 394\u001b[1;33m         \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mskipna\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mskipna\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmask\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmask\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    395\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    396\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mdatetimelike\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
1562 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\nanops.py\u001b[0m in \u001b[0;36mnanmean\u001b[1;34m(values, axis, skipna, mask)\u001b[0m\n\u001b[0;32m    631\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    632\u001b[0m     \u001b[0mcount\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_get_counts\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmask\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdtype_count\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 633\u001b[1;33m     \u001b[0mthe_sum\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_ensure_numeric\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msum\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdtype_sum\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    634\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    635\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0maxis\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mthe_sum\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"ndim\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
1563 |       "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\nanops.py\u001b[0m in \u001b[0;36m_ensure_numeric\u001b[1;34m(x)\u001b[0m\n\u001b[0;32m   1542\u001b[0m             \u001b[1;32mexcept\u001b[0m \u001b[0mValueError\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1543\u001b[0m                 \u001b[1;31m# e.g. \"foo\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1544\u001b[1;33m                 \u001b[1;32mraise\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34mf\"Could not convert {x} to numeric\"\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0merr\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1545\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1546\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
1564 |       "\u001b[1;31mTypeError\u001b[0m: Could not convert XYZXYZ to numeric"
1565 |      ]
1566 |     }
1567 |    ],
1568 |    "source": [
1569 |     "df.apply(np.mean)"
1570 |    ]
1571 |   },
1572 |   {
1573 |    "cell_type": "code",
1574 |    "execution_count": 6,
1575 |    "id": "e3de4789",
1576 |    "metadata": {},
1577 |    "outputs": [],
1578 |    "source": [
1579 |     "df_new = df.loc[:, \"val1\":\"val2\"]"
1580 |    ]
1581 |   },
1582 |   {
1583 |    "cell_type": "code",
1584 |    "execution_count": 7,
1585 |    "id": "7157fc82",
1586 |    "metadata": {},
1587 |    "outputs": [
1588 |     {
1589 |      "data": {
1590 |       "text/html": [
1591 |        "<div>\n",
1592 |        "<style scoped>\n",
1593 |        "    .dataframe tbody tr th:only-of-type {\n",
1594 |        "        vertical-align: middle;\n",
1595 |        "    }\n",
1596 |        "\n",
1597 |        "    .dataframe tbody tr th {\n",
1598 |        "        vertical-align: top;\n",
1599 |        "    }\n",
1600 |        "\n",
1601 |        "    .dataframe thead th {\n",
1602 |        "        text-align: right;\n",
1603 |        "    }\n",
1604 |        "</style>\n",
1605 |        "<table border=\"1\" class=\"dataframe\">\n",
1606 |        "  <thead>\n",
1607 |        "    <tr style=\"text-align: right;\">\n",
1608 |        "      <th></th>\n",
1609 |        "      <th>val1</th>\n",
1610 |        "      <th>val2</th>\n",
1611 |        "    </tr>\n",
1612 |        "  </thead>\n",
1613 |        "  <tbody>\n",
1614 |        "    <tr>\n",
1615 |        "      <th>0</th>\n",
1616 |        "      <td>2</td>\n",
1617 |        "      <td>92</td>\n",
1618 |        "    </tr>\n",
1619 |        "    <tr>\n",
1620 |        "      <th>1</th>\n",
1621 |        "      <td>15</td>\n",
1622 |        "      <td>245</td>\n",
1623 |        "    </tr>\n",
1624 |        "    <tr>\n",
1625 |        "      <th>2</th>\n",
1626 |        "      <td>25</td>\n",
1627 |        "      <td>325</td>\n",
1628 |        "    </tr>\n",
1629 |        "    <tr>\n",
1630 |        "      <th>3</th>\n",
1631 |        "      <td>14</td>\n",
1632 |        "      <td>254</td>\n",
1633 |        "    </tr>\n",
1634 |        "    <tr>\n",
1635 |        "      <th>4</th>\n",
1636 |        "      <td>3</td>\n",
1637 |        "      <td>103</td>\n",
1638 |        "    </tr>\n",
1639 |        "    <tr>\n",
1640 |        "      <th>5</th>\n",
1641 |        "      <td>91</td>\n",
1642 |        "      <td>961</td>\n",
1643 |        "    </tr>\n",
1644 |        "  </tbody>\n",
1645 |        "</table>\n",
1646 |        "</div>"
1647 |       ],
1648 |       "text/plain": [
1649 |        "   val1  val2\n",
1650 |        "0     2    92\n",
1651 |        "1    15   245\n",
1652 |        "2    25   325\n",
1653 |        "3    14   254\n",
1654 |        "4     3   103\n",
1655 |        "5    91   961"
1656 |       ]
1657 |      },
1658 |      "execution_count": 7,
1659 |      "metadata": {},
1660 |      "output_type": "execute_result"
1661 |     }
1662 |    ],
1663 |    "source": [
1664 |     "df_new"
1665 |    ]
1666 |   },
1667 |   {
1668 |    "cell_type": "code",
1669 |    "execution_count": 8,
1670 |    "id": "7999e9ec",
1671 |    "metadata": {
1672 |     "scrolled": true
1673 |    },
1674 |    "outputs": [
1675 |     {
1676 |      "data": {
1677 |       "text/plain": [
1678 |        "val1     25.0\n",
1679 |        "val2    330.0\n",
1680 |        "dtype: float64"
1681 |       ]
1682 |      },
1683 |      "execution_count": 8,
1684 |      "metadata": {},
1685 |      "output_type": "execute_result"
1686 |     }
1687 |    ],
1688 |    "source": [
1689 |     "df_new.apply(np.mean)"
1690 |    ]
1691 |   },
1692 |   {
1693 |    "cell_type": "code",
1694 |    "execution_count": 33,
1695 |    "id": "38093ea4",
1696 |    "metadata": {},
1697 |    "outputs": [
1698 |     {
1699 |      "data": {
1700 |       "text/plain": [
1701 |        "330.0"
1702 |       ]
1703 |      },
1704 |      "execution_count": 33,
1705 |      "metadata": {},
1706 |      "output_type": "execute_result"
1707 |     }
1708 |    ],
1709 |    "source": [
1710 |     "df_new[\"val2\"].mean()"
1711 |    ]
1712 |   },
1713 |   {
1714 |    "cell_type": "code",
1715 |    "execution_count": 34,
1716 |    "id": "f9a05aaa",
1717 |    "metadata": {},
1718 |    "outputs": [
1719 |     {
1720 |      "data": {
1721 |       "text/plain": [
1722 |        "0     47.0\n",
1723 |        "1    130.0\n",
1724 |        "2    175.0\n",
1725 |        "3    134.0\n",
1726 |        "4     53.0\n",
1727 |        "5    526.0\n",
1728 |        "dtype: float64"
1729 |       ]
1730 |      },
1731 |      "execution_count": 34,
1732 |      "metadata": {},
1733 |      "output_type": "execute_result"
1734 |     }
1735 |    ],
1736 |    "source": [
1737 |     "df_new.apply(np.mean, axis = 1)"
1738 |    ]
1739 |   },
1740 |   {
1741 |    "cell_type": "code",
1742 |    "execution_count": 35,
1743 |    "id": "7b431561",
1744 |    "metadata": {},
1745 |    "outputs": [
1746 |     {
1747 |      "data": {
1748 |       "text/html": [
1749 |        "<div>\n",
1750 |        "<style scoped>\n",
1751 |        "    .dataframe tbody tr th:only-of-type {\n",
1752 |        "        vertical-align: middle;\n",
1753 |        "    }\n",
1754 |        "\n",
1755 |        "    .dataframe tbody tr th {\n",
1756 |        "        vertical-align: top;\n",
1757 |        "    }\n",
1758 |        "\n",
1759 |        "    .dataframe thead th {\n",
1760 |        "        text-align: right;\n",
1761 |        "    }\n",
1762 |        "</style>\n",
1763 |        "<table border=\"1\" class=\"dataframe\">\n",
1764 |        "  <thead>\n",
1765 |        "    <tr style=\"text-align: right;\">\n",
1766 |        "      <th></th>\n",
1767 |        "      <th>val1</th>\n",
1768 |        "      <th>val2</th>\n",
1769 |        "    </tr>\n",
1770 |        "    <tr>\n",
1771 |        "      <th>groups</th>\n",
1772 |        "      <th></th>\n",
1773 |        "      <th></th>\n",
1774 |        "    </tr>\n",
1775 |        "  </thead>\n",
1776 |        "  <tbody>\n",
1777 |        "    <tr>\n",
1778 |        "      <th>X</th>\n",
1779 |        "      <td>8.0</td>\n",
1780 |        "      <td>173.0</td>\n",
1781 |        "    </tr>\n",
1782 |        "    <tr>\n",
1783 |        "      <th>Y</th>\n",
1784 |        "      <td>9.0</td>\n",
1785 |        "      <td>174.0</td>\n",
1786 |        "    </tr>\n",
1787 |        "    <tr>\n",
1788 |        "      <th>Z</th>\n",
1789 |        "      <td>58.0</td>\n",
1790 |        "      <td>643.0</td>\n",
1791 |        "    </tr>\n",
1792 |        "  </tbody>\n",
1793 |        "</table>\n",
1794 |        "</div>"
1795 |       ],
1796 |       "text/plain": [
1797 |        "        val1   val2\n",
1798 |        "groups             \n",
1799 |        "X        8.0  173.0\n",
1800 |        "Y        9.0  174.0\n",
1801 |        "Z       58.0  643.0"
1802 |       ]
1803 |      },
1804 |      "execution_count": 35,
1805 |      "metadata": {},
1806 |      "output_type": "execute_result"
1807 |     }
1808 |    ],
1809 |    "source": [
1810 |     "df.groupby(\"groups\").apply(np.mean)"
1811 |    ]
1812 |   },
1813 |   {
1814 |    "cell_type": "code",
1815 |    "execution_count": 36,
1816 |    "id": "fe0671f9",
1817 |    "metadata": {
1818 |     "scrolled": true
1819 |    },
1820 |    "outputs": [],
1821 |    "source": [
1822 |     "df2 = pd.DataFrame({'val1':[2, 4, 6, 8, 10], 'val2':['Turkey', 'UK', 'Australia','Philippines', 'Egypt']})"
1823 |    ]
1824 |   },
1825 |   {
1826 |    "cell_type": "code",
1827 |    "execution_count": 37,
1828 |    "id": "99c1f576",
1829 |    "metadata": {
1830 |     "scrolled": true
1831 |    },
1832 |    "outputs": [
1833 |     {
1834 |      "data": {
1835 |       "text/html": [
1836 |        "<div>\n",
1837 |        "<style scoped>\n",
1838 |        "    .dataframe tbody tr th:only-of-type {\n",
1839 |        "        vertical-align: middle;\n",
1840 |        "    }\n",
1841 |        "\n",
1842 |        "    .dataframe tbody tr th {\n",
1843 |        "        vertical-align: top;\n",
1844 |        "    }\n",
1845 |        "\n",
1846 |        "    .dataframe thead th {\n",
1847 |        "        text-align: right;\n",
1848 |        "    }\n",
1849 |        "</style>\n",
1850 |        "<table border=\"1\" class=\"dataframe\">\n",
1851 |        "  <thead>\n",
1852 |        "    <tr style=\"text-align: right;\">\n",
1853 |        "      <th></th>\n",
1854 |        "      <th>val1</th>\n",
1855 |        "      <th>val2</th>\n",
1856 |        "    </tr>\n",
1857 |        "  </thead>\n",
1858 |        "  <tbody>\n",
1859 |        "    <tr>\n",
1860 |        "      <th>0</th>\n",
1861 |        "      <td>2</td>\n",
1862 |        "      <td>Turkey</td>\n",
1863 |        "    </tr>\n",
1864 |        "    <tr>\n",
1865 |        "      <th>1</th>\n",
1866 |        "      <td>4</td>\n",
1867 |        "      <td>UK</td>\n",
1868 |        "    </tr>\n",
1869 |        "    <tr>\n",
1870 |        "      <th>2</th>\n",
1871 |        "      <td>6</td>\n",
1872 |        "      <td>Australia</td>\n",
1873 |        "    </tr>\n",
1874 |        "    <tr>\n",
1875 |        "      <th>3</th>\n",
1876 |        "      <td>8</td>\n",
1877 |        "      <td>Philippines</td>\n",
1878 |        "    </tr>\n",
1879 |        "    <tr>\n",
1880 |        "      <th>4</th>\n",
1881 |        "      <td>10</td>\n",
1882 |        "      <td>Egypt</td>\n",
1883 |        "    </tr>\n",
1884 |        "  </tbody>\n",
1885 |        "</table>\n",
1886 |        "</div>"
1887 |       ],
1888 |       "text/plain": [
1889 |        "   val1         val2\n",
1890 |        "0     2       Turkey\n",
1891 |        "1     4           UK\n",
1892 |        "2     6    Australia\n",
1893 |        "3     8  Philippines\n",
1894 |        "4    10        Egypt"
1895 |       ]
1896 |      },
1897 |      "execution_count": 37,
1898 |      "metadata": {},
1899 |      "output_type": "execute_result"
1900 |     }
1901 |    ],
1902 |    "source": [
1903 |     "df2"
1904 |    ]
1905 |   },
1906 |   {
1907 |    "cell_type": "code",
1908 |    "execution_count": 38,
1909 |    "id": "a9ead634",
1910 |    "metadata": {},
1911 |    "outputs": [],
1912 |    "source": [
1913 |     "def cube(x):\n",
1914 |     "    return x ** 3"
1915 |    ]
1916 |   },
1917 |   {
1918 |    "cell_type": "code",
1919 |    "execution_count": 39,
1920 |    "id": "8b5e0492",
1921 |    "metadata": {
1922 |     "scrolled": true
1923 |    },
1924 |    "outputs": [
1925 |     {
1926 |      "data": {
1927 |       "text/plain": [
1928 |        "0       8\n",
1929 |        "1      64\n",
1930 |        "2     216\n",
1931 |        "3     512\n",
1932 |        "4    1000\n",
1933 |        "Name: val1, dtype: int64"
1934 |       ]
1935 |      },
1936 |      "execution_count": 39,
1937 |      "metadata": {},
1938 |      "output_type": "execute_result"
1939 |     }
1940 |    ],
1941 |    "source": [
1942 |     "df2.val1.apply(cube)"
1943 |    ]
1944 |   },
1945 |   {
1946 |    "cell_type": "code",
1947 |    "execution_count": 40,
1948 |    "id": "4cd9e724",
1949 |    "metadata": {},
1950 |    "outputs": [
1951 |     {
1952 |      "data": {
1953 |       "text/plain": [
1954 |        "0     6\n",
1955 |        "1     2\n",
1956 |        "2     9\n",
1957 |        "3    11\n",
1958 |        "4     5\n",
1959 |        "Name: val2, dtype: int64"
1960 |       ]
1961 |      },
1962 |      "execution_count": 40,
1963 |      "metadata": {},
1964 |      "output_type": "execute_result"
1965 |     }
1966 |    ],
1967 |    "source": [
1968 |     "df2.val2.apply(len)"
1969 |    ]
1970 |   },
1971 |   {
1972 |    "cell_type": "markdown",
1973 |    "id": "d99b9023",
1974 |    "metadata": {},
1975 |    "source": [
1976 |     "## Examining the Data Set 3"
1977 |    ]
1978 |   },
1979 |   {
1980 |    "cell_type": "code",
1981 |    "execution_count": 41,
1982 |    "id": "ebf223a1",
1983 |    "metadata": {},
1984 |    "outputs": [],
1985 |    "source": [
1986 |     "import pandas as pd\n",
1987 |     "import seaborn as sns\n",
1988 |     "import numpy as np"
1989 |    ]
1990 |   },
1991 |   {
1992 |    "cell_type": "code",
1993 |    "execution_count": 42,
1994 |    "id": "af020fef",
1995 |    "metadata": {},
1996 |    "outputs": [],
1997 |    "source": [
1998 |     "df = sns.load_dataset(\"titanic\")"
1999 |    ]
2000 |   },
2001 |   {
2002 |    "cell_type": "code",
2003 |    "execution_count": 43,
2004 |    "id": "51bcc364",
2005 |    "metadata": {
2006 |     "scrolled": false
2007 |    },
2008 |    "outputs": [
2009 |     {
2010 |      "data": {
2011 |       "text/html": [
2012 |        "<div>\n",
2013 |        "<style scoped>\n",
2014 |        "    .dataframe tbody tr th:only-of-type {\n",
2015 |        "        vertical-align: middle;\n",
2016 |        "    }\n",
2017 |        "\n",
2018 |        "    .dataframe tbody tr th {\n",
2019 |        "        vertical-align: top;\n",
2020 |        "    }\n",
2021 |        "\n",
2022 |        "    .dataframe thead th {\n",
2023 |        "        text-align: right;\n",
2024 |        "    }\n",
2025 |        "</style>\n",
2026 |        "<table border=\"1\" class=\"dataframe\">\n",
2027 |        "  <thead>\n",
2028 |        "    <tr style=\"text-align: right;\">\n",
2029 |        "      <th></th>\n",
2030 |        "      <th>survived</th>\n",
2031 |        "      <th>pclass</th>\n",
2032 |        "      <th>sex</th>\n",
2033 |        "      <th>age</th>\n",
2034 |        "      <th>sibsp</th>\n",
2035 |        "      <th>parch</th>\n",
2036 |        "      <th>fare</th>\n",
2037 |        "      <th>embarked</th>\n",
2038 |        "      <th>class</th>\n",
2039 |        "      <th>who</th>\n",
2040 |        "      <th>adult_male</th>\n",
2041 |        "      <th>deck</th>\n",
2042 |        "      <th>embark_town</th>\n",
2043 |        "      <th>alive</th>\n",
2044 |        "      <th>alone</th>\n",
2045 |        "    </tr>\n",
2046 |        "  </thead>\n",
2047 |        "  <tbody>\n",
2048 |        "    <tr>\n",
2049 |        "      <th>0</th>\n",
2050 |        "      <td>0</td>\n",
2051 |        "      <td>3</td>\n",
2052 |        "      <td>male</td>\n",
2053 |        "      <td>22.0</td>\n",
2054 |        "      <td>1</td>\n",
2055 |        "      <td>0</td>\n",
2056 |        "      <td>7.2500</td>\n",
2057 |        "      <td>S</td>\n",
2058 |        "      <td>Third</td>\n",
2059 |        "      <td>man</td>\n",
2060 |        "      <td>True</td>\n",
2061 |        "      <td>NaN</td>\n",
2062 |        "      <td>Southampton</td>\n",
2063 |        "      <td>no</td>\n",
2064 |        "      <td>False</td>\n",
2065 |        "    </tr>\n",
2066 |        "    <tr>\n",
2067 |        "      <th>1</th>\n",
2068 |        "      <td>1</td>\n",
2069 |        "      <td>1</td>\n",
2070 |        "      <td>female</td>\n",
2071 |        "      <td>38.0</td>\n",
2072 |        "      <td>1</td>\n",
2073 |        "      <td>0</td>\n",
2074 |        "      <td>71.2833</td>\n",
2075 |        "      <td>C</td>\n",
2076 |        "      <td>First</td>\n",
2077 |        "      <td>woman</td>\n",
2078 |        "      <td>False</td>\n",
2079 |        "      <td>C</td>\n",
2080 |        "      <td>Cherbourg</td>\n",
2081 |        "      <td>yes</td>\n",
2082 |        "      <td>False</td>\n",
2083 |        "    </tr>\n",
2084 |        "    <tr>\n",
2085 |        "      <th>2</th>\n",
2086 |        "      <td>1</td>\n",
2087 |        "      <td>3</td>\n",
2088 |        "      <td>female</td>\n",
2089 |        "      <td>26.0</td>\n",
2090 |        "      <td>0</td>\n",
2091 |        "      <td>0</td>\n",
2092 |        "      <td>7.9250</td>\n",
2093 |        "      <td>S</td>\n",
2094 |        "      <td>Third</td>\n",
2095 |        "      <td>woman</td>\n",
2096 |        "      <td>False</td>\n",
2097 |        "      <td>NaN</td>\n",
2098 |        "      <td>Southampton</td>\n",
2099 |        "      <td>yes</td>\n",
2100 |        "      <td>True</td>\n",
2101 |        "    </tr>\n",
2102 |        "    <tr>\n",
2103 |        "      <th>3</th>\n",
2104 |        "      <td>1</td>\n",
2105 |        "      <td>1</td>\n",
2106 |        "      <td>female</td>\n",
2107 |        "      <td>35.0</td>\n",
2108 |        "      <td>1</td>\n",
2109 |        "      <td>0</td>\n",
2110 |        "      <td>53.1000</td>\n",
2111 |        "      <td>S</td>\n",
2112 |        "      <td>First</td>\n",
2113 |        "      <td>woman</td>\n",
2114 |        "      <td>False</td>\n",
2115 |        "      <td>C</td>\n",
2116 |        "      <td>Southampton</td>\n",
2117 |        "      <td>yes</td>\n",
2118 |        "      <td>False</td>\n",
2119 |        "    </tr>\n",
2120 |        "    <tr>\n",
2121 |        "      <th>4</th>\n",
2122 |        "      <td>0</td>\n",
2123 |        "      <td>3</td>\n",
2124 |        "      <td>male</td>\n",
2125 |        "      <td>35.0</td>\n",
2126 |        "      <td>0</td>\n",
2127 |        "      <td>0</td>\n",
2128 |        "      <td>8.0500</td>\n",
2129 |        "      <td>S</td>\n",
2130 |        "      <td>Third</td>\n",
2131 |        "      <td>man</td>\n",
2132 |        "      <td>True</td>\n",
2133 |        "      <td>NaN</td>\n",
2134 |        "      <td>Southampton</td>\n",
2135 |        "      <td>no</td>\n",
2136 |        "      <td>True</td>\n",
2137 |        "    </tr>\n",
2138 |        "  </tbody>\n",
2139 |        "</table>\n",
2140 |        "</div>"
2141 |       ],
2142 |       "text/plain": [
2143 |        "   survived  pclass     sex   age  sibsp  parch     fare embarked  class  \\\n",
2144 |        "0         0       3    male  22.0      1      0   7.2500        S  Third   \n",
2145 |        "1         1       1  female  38.0      1      0  71.2833        C  First   \n",
2146 |        "2         1       3  female  26.0      0      0   7.9250        S  Third   \n",
2147 |        "3         1       1  female  35.0      1      0  53.1000        S  First   \n",
2148 |        "4         0       3    male  35.0      0      0   8.0500        S  Third   \n",
2149 |        "\n",
2150 |        "     who  adult_male deck  embark_town alive  alone  \n",
2151 |        "0    man        True  NaN  Southampton    no  False  \n",
2152 |        "1  woman       False    C    Cherbourg   yes  False  \n",
2153 |        "2  woman       False  NaN  Southampton   yes   True  \n",
2154 |        "3  woman       False    C  Southampton   yes  False  \n",
2155 |        "4    man        True  NaN  Southampton    no   True  "
2156 |       ]
2157 |      },
2158 |      "execution_count": 43,
2159 |      "metadata": {},
2160 |      "output_type": "execute_result"
2161 |     }
2162 |    ],
2163 |    "source": [
2164 |     "df.head()"
2165 |    ]
2166 |   },
2167 |   {
2168 |    "cell_type": "code",
2169 |    "execution_count": 44,
2170 |    "id": "45902a00",
2171 |    "metadata": {
2172 |     "scrolled": false
2173 |    },
2174 |    "outputs": [
2175 |     {
2176 |      "name": "stdout",
2177 |      "output_type": "stream",
2178 |      "text": [
2179 |       "<class 'pandas.core.frame.DataFrame'>\n",
2180 |       "RangeIndex: 891 entries, 0 to 890\n",
2181 |       "Data columns (total 15 columns):\n",
2182 |       " #   Column       Non-Null Count  Dtype   \n",
2183 |       "---  ------       --------------  -----   \n",
2184 |       " 0   survived     891 non-null    int64   \n",
2185 |       " 1   pclass       891 non-null    int64   \n",
2186 |       " 2   sex          891 non-null    object  \n",
2187 |       " 3   age          714 non-null    float64 \n",
2188 |       " 4   sibsp        891 non-null    int64   \n",
2189 |       " 5   parch        891 non-null    int64   \n",
2190 |       " 6   fare         891 non-null    float64 \n",
2191 |       " 7   embarked     889 non-null    object  \n",
2192 |       " 8   class        891 non-null    category\n",
2193 |       " 9   who          891 non-null    object  \n",
2194 |       " 10  adult_male   891 non-null    bool    \n",
2195 |       " 11  deck         203 non-null    category\n",
2196 |       " 12  embark_town  889 non-null    object  \n",
2197 |       " 13  alive        891 non-null    object  \n",
2198 |       " 14  alone        891 non-null    bool    \n",
2199 |       "dtypes: bool(2), category(2), float64(2), int64(4), object(5)\n",
2200 |       "memory usage: 80.7+ KB\n"
2201 |      ]
2202 |     }
2203 |    ],
2204 |    "source": [
2205 |     "df.info()"
2206 |    ]
2207 |   },
2208 |   {
2209 |    "cell_type": "markdown",
2210 |    "id": "0de1ad71",
2211 |    "metadata": {},
2212 |    "source": [
2213 |     "## Pivot Tables in Pandas Library"
2214 |    ]
2215 |   },
2216 |   {
2217 |    "cell_type": "code",
2218 |    "execution_count": 45,
2219 |    "id": "9b80afdf",
2220 |    "metadata": {},
2221 |    "outputs": [],
2222 |    "source": [
2223 |     "import pandas as pd\n",
2224 |     "import seaborn as sns\n",
2225 |     "import numpy as np"
2226 |    ]
2227 |   },
2228 |   {
2229 |    "cell_type": "code",
2230 |    "execution_count": 46,
2231 |    "id": "933388ab",
2232 |    "metadata": {},
2233 |    "outputs": [],
2234 |    "source": [
2235 |     "df = sns.load_dataset(\"titanic\")"
2236 |    ]
2237 |   },
2238 |   {
2239 |    "cell_type": "code",
2240 |    "execution_count": 47,
2241 |    "id": "2faa9a4a",
2242 |    "metadata": {},
2243 |    "outputs": [
2244 |     {
2245 |      "data": {
2246 |       "text/html": [
2247 |        "<div>\n",
2248 |        "<style scoped>\n",
2249 |        "    .dataframe tbody tr th:only-of-type {\n",
2250 |        "        vertical-align: middle;\n",
2251 |        "    }\n",
2252 |        "\n",
2253 |        "    .dataframe tbody tr th {\n",
2254 |        "        vertical-align: top;\n",
2255 |        "    }\n",
2256 |        "\n",
2257 |        "    .dataframe thead th {\n",
2258 |        "        text-align: right;\n",
2259 |        "    }\n",
2260 |        "</style>\n",
2261 |        "<table border=\"1\" class=\"dataframe\">\n",
2262 |        "  <thead>\n",
2263 |        "    <tr style=\"text-align: right;\">\n",
2264 |        "      <th></th>\n",
2265 |        "      <th>survived</th>\n",
2266 |        "      <th>pclass</th>\n",
2267 |        "      <th>sex</th>\n",
2268 |        "      <th>age</th>\n",
2269 |        "      <th>sibsp</th>\n",
2270 |        "      <th>parch</th>\n",
2271 |        "      <th>fare</th>\n",
2272 |        "      <th>embarked</th>\n",
2273 |        "      <th>class</th>\n",
2274 |        "      <th>who</th>\n",
2275 |        "      <th>adult_male</th>\n",
2276 |        "      <th>deck</th>\n",
2277 |        "      <th>embark_town</th>\n",
2278 |        "      <th>alive</th>\n",
2279 |        "      <th>alone</th>\n",
2280 |        "    </tr>\n",
2281 |        "  </thead>\n",
2282 |        "  <tbody>\n",
2283 |        "    <tr>\n",
2284 |        "      <th>0</th>\n",
2285 |        "      <td>0</td>\n",
2286 |        "      <td>3</td>\n",
2287 |        "      <td>male</td>\n",
2288 |        "      <td>22.0</td>\n",
2289 |        "      <td>1</td>\n",
2290 |        "      <td>0</td>\n",
2291 |        "      <td>7.2500</td>\n",
2292 |        "      <td>S</td>\n",
2293 |        "      <td>Third</td>\n",
2294 |        "      <td>man</td>\n",
2295 |        "      <td>True</td>\n",
2296 |        "      <td>NaN</td>\n",
2297 |        "      <td>Southampton</td>\n",
2298 |        "      <td>no</td>\n",
2299 |        "      <td>False</td>\n",
2300 |        "    </tr>\n",
2301 |        "    <tr>\n",
2302 |        "      <th>1</th>\n",
2303 |        "      <td>1</td>\n",
2304 |        "      <td>1</td>\n",
2305 |        "      <td>female</td>\n",
2306 |        "      <td>38.0</td>\n",
2307 |        "      <td>1</td>\n",
2308 |        "      <td>0</td>\n",
2309 |        "      <td>71.2833</td>\n",
2310 |        "      <td>C</td>\n",
2311 |        "      <td>First</td>\n",
2312 |        "      <td>woman</td>\n",
2313 |        "      <td>False</td>\n",
2314 |        "      <td>C</td>\n",
2315 |        "      <td>Cherbourg</td>\n",
2316 |        "      <td>yes</td>\n",
2317 |        "      <td>False</td>\n",
2318 |        "    </tr>\n",
2319 |        "    <tr>\n",
2320 |        "      <th>2</th>\n",
2321 |        "      <td>1</td>\n",
2322 |        "      <td>3</td>\n",
2323 |        "      <td>female</td>\n",
2324 |        "      <td>26.0</td>\n",
2325 |        "      <td>0</td>\n",
2326 |        "      <td>0</td>\n",
2327 |        "      <td>7.9250</td>\n",
2328 |        "      <td>S</td>\n",
2329 |        "      <td>Third</td>\n",
2330 |        "      <td>woman</td>\n",
2331 |        "      <td>False</td>\n",
2332 |        "      <td>NaN</td>\n",
2333 |        "      <td>Southampton</td>\n",
2334 |        "      <td>yes</td>\n",
2335 |        "      <td>True</td>\n",
2336 |        "    </tr>\n",
2337 |        "    <tr>\n",
2338 |        "      <th>3</th>\n",
2339 |        "      <td>1</td>\n",
2340 |        "      <td>1</td>\n",
2341 |        "      <td>female</td>\n",
2342 |        "      <td>35.0</td>\n",
2343 |        "      <td>1</td>\n",
2344 |        "      <td>0</td>\n",
2345 |        "      <td>53.1000</td>\n",
2346 |        "      <td>S</td>\n",
2347 |        "      <td>First</td>\n",
2348 |        "      <td>woman</td>\n",
2349 |        "      <td>False</td>\n",
2350 |        "      <td>C</td>\n",
2351 |        "      <td>Southampton</td>\n",
2352 |        "      <td>yes</td>\n",
2353 |        "      <td>False</td>\n",
2354 |        "    </tr>\n",
2355 |        "    <tr>\n",
2356 |        "      <th>4</th>\n",
2357 |        "      <td>0</td>\n",
2358 |        "      <td>3</td>\n",
2359 |        "      <td>male</td>\n",
2360 |        "      <td>35.0</td>\n",
2361 |        "      <td>0</td>\n",
2362 |        "      <td>0</td>\n",
2363 |        "      <td>8.0500</td>\n",
2364 |        "      <td>S</td>\n",
2365 |        "      <td>Third</td>\n",
2366 |        "      <td>man</td>\n",
2367 |        "      <td>True</td>\n",
2368 |        "      <td>NaN</td>\n",
2369 |        "      <td>Southampton</td>\n",
2370 |        "      <td>no</td>\n",
2371 |        "      <td>True</td>\n",
2372 |        "    </tr>\n",
2373 |        "  </tbody>\n",
2374 |        "</table>\n",
2375 |        "</div>"
2376 |       ],
2377 |       "text/plain": [
2378 |        "   survived  pclass     sex   age  sibsp  parch     fare embarked  class  \\\n",
2379 |        "0         0       3    male  22.0      1      0   7.2500        S  Third   \n",
2380 |        "1         1       1  female  38.0      1      0  71.2833        C  First   \n",
2381 |        "2         1       3  female  26.0      0      0   7.9250        S  Third   \n",
2382 |        "3         1       1  female  35.0      1      0  53.1000        S  First   \n",
2383 |        "4         0       3    male  35.0      0      0   8.0500        S  Third   \n",
2384 |        "\n",
2385 |        "     who  adult_male deck  embark_town alive  alone  \n",
2386 |        "0    man        True  NaN  Southampton    no  False  \n",
2387 |        "1  woman       False    C    Cherbourg   yes  False  \n",
2388 |        "2  woman       False  NaN  Southampton   yes   True  \n",
2389 |        "3  woman       False    C  Southampton   yes  False  \n",
2390 |        "4    man        True  NaN  Southampton    no   True  "
2391 |       ]
2392 |      },
2393 |      "execution_count": 47,
2394 |      "metadata": {},
2395 |      "output_type": "execute_result"
2396 |     }
2397 |    ],
2398 |    "source": [
2399 |     "df.head()"
2400 |    ]
2401 |   },
2402 |   {
2403 |    "cell_type": "code",
2404 |    "execution_count": 48,
2405 |    "id": "90071115",
2406 |    "metadata": {
2407 |     "scrolled": true
2408 |    },
2409 |    "outputs": [
2410 |     {
2411 |      "data": {
2412 |       "text/html": [
2413 |        "<div>\n",
2414 |        "<style scoped>\n",
2415 |        "    .dataframe tbody tr th:only-of-type {\n",
2416 |        "        vertical-align: middle;\n",
2417 |        "    }\n",
2418 |        "\n",
2419 |        "    .dataframe tbody tr th {\n",
2420 |        "        vertical-align: top;\n",
2421 |        "    }\n",
2422 |        "\n",
2423 |        "    .dataframe thead th {\n",
2424 |        "        text-align: right;\n",
2425 |        "    }\n",
2426 |        "</style>\n",
2427 |        "<table border=\"1\" class=\"dataframe\">\n",
2428 |        "  <thead>\n",
2429 |        "    <tr style=\"text-align: right;\">\n",
2430 |        "      <th></th>\n",
2431 |        "      <th>survived</th>\n",
2432 |        "    </tr>\n",
2433 |        "    <tr>\n",
2434 |        "      <th>sex</th>\n",
2435 |        "      <th></th>\n",
2436 |        "    </tr>\n",
2437 |        "  </thead>\n",
2438 |        "  <tbody>\n",
2439 |        "    <tr>\n",
2440 |        "      <th>female</th>\n",
2441 |        "      <td>0.742038</td>\n",
2442 |        "    </tr>\n",
2443 |        "    <tr>\n",
2444 |        "      <th>male</th>\n",
2445 |        "      <td>0.188908</td>\n",
2446 |        "    </tr>\n",
2447 |        "  </tbody>\n",
2448 |        "</table>\n",
2449 |        "</div>"
2450 |       ],
2451 |       "text/plain": [
2452 |        "        survived\n",
2453 |        "sex             \n",
2454 |        "female  0.742038\n",
2455 |        "male    0.188908"
2456 |       ]
2457 |      },
2458 |      "execution_count": 48,
2459 |      "metadata": {},
2460 |      "output_type": "execute_result"
2461 |     }
2462 |    ],
2463 |    "source": [
2464 |     "df.groupby(\"sex\")[[\"survived\"]].mean()"
2465 |    ]
2466 |   },
2467 |   {
2468 |    "cell_type": "code",
2469 |    "execution_count": 49,
2470 |    "id": "7754e53f",
2471 |    "metadata": {
2472 |     "scrolled": false
2473 |    },
2474 |    "outputs": [
2475 |     {
2476 |      "data": {
2477 |       "text/html": [
2478 |        "<div>\n",
2479 |        "<style scoped>\n",
2480 |        "    .dataframe tbody tr th:only-of-type {\n",
2481 |        "        vertical-align: middle;\n",
2482 |        "    }\n",
2483 |        "\n",
2484 |        "    .dataframe tbody tr th {\n",
2485 |        "        vertical-align: top;\n",
2486 |        "    }\n",
2487 |        "\n",
2488 |        "    .dataframe thead th {\n",
2489 |        "        text-align: right;\n",
2490 |        "    }\n",
2491 |        "</style>\n",
2492 |        "<table border=\"1\" class=\"dataframe\">\n",
2493 |        "  <thead>\n",
2494 |        "    <tr style=\"text-align: right;\">\n",
2495 |        "      <th></th>\n",
2496 |        "      <th></th>\n",
2497 |        "      <th>survived</th>\n",
2498 |        "    </tr>\n",
2499 |        "    <tr>\n",
2500 |        "      <th>sex</th>\n",
2501 |        "      <th>embark_town</th>\n",
2502 |        "      <th></th>\n",
2503 |        "    </tr>\n",
2504 |        "  </thead>\n",
2505 |        "  <tbody>\n",
2506 |        "    <tr>\n",
2507 |        "      <th rowspan=\"3\" valign=\"top\">female</th>\n",
2508 |        "      <th>Cherbourg</th>\n",
2509 |        "      <td>0.876712</td>\n",
2510 |        "    </tr>\n",
2511 |        "    <tr>\n",
2512 |        "      <th>Queenstown</th>\n",
2513 |        "      <td>0.750000</td>\n",
2514 |        "    </tr>\n",
2515 |        "    <tr>\n",
2516 |        "      <th>Southampton</th>\n",
2517 |        "      <td>0.689655</td>\n",
2518 |        "    </tr>\n",
2519 |        "    <tr>\n",
2520 |        "      <th rowspan=\"3\" valign=\"top\">male</th>\n",
2521 |        "      <th>Cherbourg</th>\n",
2522 |        "      <td>0.305263</td>\n",
2523 |        "    </tr>\n",
2524 |        "    <tr>\n",
2525 |        "      <th>Queenstown</th>\n",
2526 |        "      <td>0.073171</td>\n",
2527 |        "    </tr>\n",
2528 |        "    <tr>\n",
2529 |        "      <th>Southampton</th>\n",
2530 |        "      <td>0.174603</td>\n",
2531 |        "    </tr>\n",
2532 |        "  </tbody>\n",
2533 |        "</table>\n",
2534 |        "</div>"
2535 |       ],
2536 |       "text/plain": [
2537 |        "                    survived\n",
2538 |        "sex    embark_town          \n",
2539 |        "female Cherbourg    0.876712\n",
2540 |        "       Queenstown   0.750000\n",
2541 |        "       Southampton  0.689655\n",
2542 |        "male   Cherbourg    0.305263\n",
2543 |        "       Queenstown   0.073171\n",
2544 |        "       Southampton  0.174603"
2545 |       ]
2546 |      },
2547 |      "execution_count": 49,
2548 |      "metadata": {},
2549 |      "output_type": "execute_result"
2550 |     }
2551 |    ],
2552 |    "source": [
2553 |     "df.groupby([\"sex\", \"embark_town\"])[[\"survived\"]].mean()"
2554 |    ]
2555 |   },
2556 |   {
2557 |    "cell_type": "code",
2558 |    "execution_count": 50,
2559 |    "id": "f0133d55",
2560 |    "metadata": {},
2561 |    "outputs": [
2562 |     {
2563 |      "data": {
2564 |       "text/html": [
2565 |        "<div>\n",
2566 |        "<style scoped>\n",
2567 |        "    .dataframe tbody tr th:only-of-type {\n",
2568 |        "        vertical-align: middle;\n",
2569 |        "    }\n",
2570 |        "\n",
2571 |        "    .dataframe tbody tr th {\n",
2572 |        "        vertical-align: top;\n",
2573 |        "    }\n",
2574 |        "\n",
2575 |        "    .dataframe thead tr th {\n",
2576 |        "        text-align: left;\n",
2577 |        "    }\n",
2578 |        "\n",
2579 |        "    .dataframe thead tr:last-of-type th {\n",
2580 |        "        text-align: right;\n",
2581 |        "    }\n",
2582 |        "</style>\n",
2583 |        "<table border=\"1\" class=\"dataframe\">\n",
2584 |        "  <thead>\n",
2585 |        "    <tr>\n",
2586 |        "      <th></th>\n",
2587 |        "      <th colspan=\"3\" halign=\"left\">survived</th>\n",
2588 |        "    </tr>\n",
2589 |        "    <tr>\n",
2590 |        "      <th>embark_town</th>\n",
2591 |        "      <th>Cherbourg</th>\n",
2592 |        "      <th>Queenstown</th>\n",
2593 |        "      <th>Southampton</th>\n",
2594 |        "    </tr>\n",
2595 |        "    <tr>\n",
2596 |        "      <th>sex</th>\n",
2597 |        "      <th></th>\n",
2598 |        "      <th></th>\n",
2599 |        "      <th></th>\n",
2600 |        "    </tr>\n",
2601 |        "  </thead>\n",
2602 |        "  <tbody>\n",
2603 |        "    <tr>\n",
2604 |        "      <th>female</th>\n",
2605 |        "      <td>0.876712</td>\n",
2606 |        "      <td>0.750000</td>\n",
2607 |        "      <td>0.689655</td>\n",
2608 |        "    </tr>\n",
2609 |        "    <tr>\n",
2610 |        "      <th>male</th>\n",
2611 |        "      <td>0.305263</td>\n",
2612 |        "      <td>0.073171</td>\n",
2613 |        "      <td>0.174603</td>\n",
2614 |        "    </tr>\n",
2615 |        "  </tbody>\n",
2616 |        "</table>\n",
2617 |        "</div>"
2618 |       ],
2619 |       "text/plain": [
2620 |        "             survived                       \n",
2621 |        "embark_town Cherbourg Queenstown Southampton\n",
2622 |        "sex                                         \n",
2623 |        "female       0.876712   0.750000    0.689655\n",
2624 |        "male         0.305263   0.073171    0.174603"
2625 |       ]
2626 |      },
2627 |      "execution_count": 50,
2628 |      "metadata": {},
2629 |      "output_type": "execute_result"
2630 |     }
2631 |    ],
2632 |    "source": [
2633 |     "df.groupby([\"sex\", \"embark_town\"])[[\"survived\"]].mean().unstack()"
2634 |    ]
2635 |   },
2636 |   {
2637 |    "cell_type": "code",
2638 |    "execution_count": 51,
2639 |    "id": "9855d1e6",
2640 |    "metadata": {},
2641 |    "outputs": [
2642 |     {
2643 |      "data": {
2644 |       "text/html": [
2645 |        "<div>\n",
2646 |        "<style scoped>\n",
2647 |        "    .dataframe tbody tr th:only-of-type {\n",
2648 |        "        vertical-align: middle;\n",
2649 |        "    }\n",
2650 |        "\n",
2651 |        "    .dataframe tbody tr th {\n",
2652 |        "        vertical-align: top;\n",
2653 |        "    }\n",
2654 |        "\n",
2655 |        "    .dataframe thead th {\n",
2656 |        "        text-align: right;\n",
2657 |        "    }\n",
2658 |        "</style>\n",
2659 |        "<table border=\"1\" class=\"dataframe\">\n",
2660 |        "  <thead>\n",
2661 |        "    <tr style=\"text-align: right;\">\n",
2662 |        "      <th>embark_town</th>\n",
2663 |        "      <th>Cherbourg</th>\n",
2664 |        "      <th>Queenstown</th>\n",
2665 |        "      <th>Southampton</th>\n",
2666 |        "    </tr>\n",
2667 |        "    <tr>\n",
2668 |        "      <th>sex</th>\n",
2669 |        "      <th></th>\n",
2670 |        "      <th></th>\n",
2671 |        "      <th></th>\n",
2672 |        "    </tr>\n",
2673 |        "  </thead>\n",
2674 |        "  <tbody>\n",
2675 |        "    <tr>\n",
2676 |        "      <th>female</th>\n",
2677 |        "      <td>0.876712</td>\n",
2678 |        "      <td>0.750000</td>\n",
2679 |        "      <td>0.689655</td>\n",
2680 |        "    </tr>\n",
2681 |        "    <tr>\n",
2682 |        "      <th>male</th>\n",
2683 |        "      <td>0.305263</td>\n",
2684 |        "      <td>0.073171</td>\n",
2685 |        "      <td>0.174603</td>\n",
2686 |        "    </tr>\n",
2687 |        "  </tbody>\n",
2688 |        "</table>\n",
2689 |        "</div>"
2690 |       ],
2691 |       "text/plain": [
2692 |        "embark_town  Cherbourg  Queenstown  Southampton\n",
2693 |        "sex                                            \n",
2694 |        "female        0.876712    0.750000     0.689655\n",
2695 |        "male          0.305263    0.073171     0.174603"
2696 |       ]
2697 |      },
2698 |      "execution_count": 51,
2699 |      "metadata": {},
2700 |      "output_type": "execute_result"
2701 |     }
2702 |    ],
2703 |    "source": [
2704 |     "df.pivot_table(\"survived\", index = \"sex\", columns = \"embark_town\")"
2705 |    ]
2706 |   },
2707 |   {
2708 |    "cell_type": "code",
2709 |    "execution_count": 52,
2710 |    "id": "04e050d2",
2711 |    "metadata": {
2712 |     "scrolled": true
2713 |    },
2714 |    "outputs": [
2715 |     {
2716 |      "data": {
2717 |       "text/html": [
2718 |        "<div>\n",
2719 |        "<style scoped>\n",
2720 |        "    .dataframe tbody tr th:only-of-type {\n",
2721 |        "        vertical-align: middle;\n",
2722 |        "    }\n",
2723 |        "\n",
2724 |        "    .dataframe tbody tr th {\n",
2725 |        "        vertical-align: top;\n",
2726 |        "    }\n",
2727 |        "\n",
2728 |        "    .dataframe thead tr th {\n",
2729 |        "        text-align: left;\n",
2730 |        "    }\n",
2731 |        "\n",
2732 |        "    .dataframe thead tr:last-of-type th {\n",
2733 |        "        text-align: right;\n",
2734 |        "    }\n",
2735 |        "</style>\n",
2736 |        "<table border=\"1\" class=\"dataframe\">\n",
2737 |        "  <thead>\n",
2738 |        "    <tr>\n",
2739 |        "      <th></th>\n",
2740 |        "      <th colspan=\"3\" halign=\"left\">sum</th>\n",
2741 |        "      <th colspan=\"3\" halign=\"left\">mean</th>\n",
2742 |        "      <th colspan=\"3\" halign=\"left\">std</th>\n",
2743 |        "    </tr>\n",
2744 |        "    <tr>\n",
2745 |        "      <th>embark_town</th>\n",
2746 |        "      <th>Cherbourg</th>\n",
2747 |        "      <th>Queenstown</th>\n",
2748 |        "      <th>Southampton</th>\n",
2749 |        "      <th>Cherbourg</th>\n",
2750 |        "      <th>Queenstown</th>\n",
2751 |        "      <th>Southampton</th>\n",
2752 |        "      <th>Cherbourg</th>\n",
2753 |        "      <th>Queenstown</th>\n",
2754 |        "      <th>Southampton</th>\n",
2755 |        "    </tr>\n",
2756 |        "    <tr>\n",
2757 |        "      <th>sex</th>\n",
2758 |        "      <th></th>\n",
2759 |        "      <th></th>\n",
2760 |        "      <th></th>\n",
2761 |        "      <th></th>\n",
2762 |        "      <th></th>\n",
2763 |        "      <th></th>\n",
2764 |        "      <th></th>\n",
2765 |        "      <th></th>\n",
2766 |        "      <th></th>\n",
2767 |        "    </tr>\n",
2768 |        "  </thead>\n",
2769 |        "  <tbody>\n",
2770 |        "    <tr>\n",
2771 |        "      <th>female</th>\n",
2772 |        "      <td>64</td>\n",
2773 |        "      <td>27</td>\n",
2774 |        "      <td>140</td>\n",
2775 |        "      <td>0.876712</td>\n",
2776 |        "      <td>0.750000</td>\n",
2777 |        "      <td>0.689655</td>\n",
2778 |        "      <td>0.331042</td>\n",
2779 |        "      <td>0.439155</td>\n",
2780 |        "      <td>0.463778</td>\n",
2781 |        "    </tr>\n",
2782 |        "    <tr>\n",
2783 |        "      <th>male</th>\n",
2784 |        "      <td>29</td>\n",
2785 |        "      <td>3</td>\n",
2786 |        "      <td>77</td>\n",
2787 |        "      <td>0.305263</td>\n",
2788 |        "      <td>0.073171</td>\n",
2789 |        "      <td>0.174603</td>\n",
2790 |        "      <td>0.462962</td>\n",
2791 |        "      <td>0.263652</td>\n",
2792 |        "      <td>0.380058</td>\n",
2793 |        "    </tr>\n",
2794 |        "  </tbody>\n",
2795 |        "</table>\n",
2796 |        "</div>"
2797 |       ],
2798 |       "text/plain": [
2799 |        "                  sum                             mean                         \\\n",
2800 |        "embark_town Cherbourg Queenstown Southampton Cherbourg Queenstown Southampton   \n",
2801 |        "sex                                                                             \n",
2802 |        "female             64         27         140  0.876712   0.750000    0.689655   \n",
2803 |        "male               29          3          77  0.305263   0.073171    0.174603   \n",
2804 |        "\n",
2805 |        "                  std                         \n",
2806 |        "embark_town Cherbourg Queenstown Southampton  \n",
2807 |        "sex                                           \n",
2808 |        "female       0.331042   0.439155    0.463778  \n",
2809 |        "male         0.462962   0.263652    0.380058  "
2810 |       ]
2811 |      },
2812 |      "execution_count": 52,
2813 |      "metadata": {},
2814 |      "output_type": "execute_result"
2815 |     }
2816 |    ],
2817 |    "source": [
2818 |     "df.pivot_table(\"survived\", index = \"sex\", columns = \"embark_town\", aggfunc = [\"sum\", \"mean\", \"std\"])"
2819 |    ]
2820 |   },
2821 |   {
2822 |    "cell_type": "code",
2823 |    "execution_count": 53,
2824 |    "id": "9985ede3",
2825 |    "metadata": {},
2826 |    "outputs": [
2827 |     {
2828 |      "data": {
2829 |       "text/html": [
2830 |        "<div>\n",
2831 |        "<style scoped>\n",
2832 |        "    .dataframe tbody tr th:only-of-type {\n",
2833 |        "        vertical-align: middle;\n",
2834 |        "    }\n",
2835 |        "\n",
2836 |        "    .dataframe tbody tr th {\n",
2837 |        "        vertical-align: top;\n",
2838 |        "    }\n",
2839 |        "\n",
2840 |        "    .dataframe thead tr th {\n",
2841 |        "        text-align: left;\n",
2842 |        "    }\n",
2843 |        "\n",
2844 |        "    .dataframe thead tr:last-of-type th {\n",
2845 |        "        text-align: right;\n",
2846 |        "    }\n",
2847 |        "</style>\n",
2848 |        "<table border=\"1\" class=\"dataframe\">\n",
2849 |        "  <thead>\n",
2850 |        "    <tr>\n",
2851 |        "      <th></th>\n",
2852 |        "      <th></th>\n",
2853 |        "      <th colspan=\"3\" halign=\"left\">sum</th>\n",
2854 |        "      <th colspan=\"3\" halign=\"left\">mean</th>\n",
2855 |        "      <th colspan=\"3\" halign=\"left\">std</th>\n",
2856 |        "    </tr>\n",
2857 |        "    <tr>\n",
2858 |        "      <th></th>\n",
2859 |        "      <th>embark_town</th>\n",
2860 |        "      <th>Cherbourg</th>\n",
2861 |        "      <th>Queenstown</th>\n",
2862 |        "      <th>Southampton</th>\n",
2863 |        "      <th>Cherbourg</th>\n",
2864 |        "      <th>Queenstown</th>\n",
2865 |        "      <th>Southampton</th>\n",
2866 |        "      <th>Cherbourg</th>\n",
2867 |        "      <th>Queenstown</th>\n",
2868 |        "      <th>Southampton</th>\n",
2869 |        "    </tr>\n",
2870 |        "    <tr>\n",
2871 |        "      <th>sex</th>\n",
2872 |        "      <th>class</th>\n",
2873 |        "      <th></th>\n",
2874 |        "      <th></th>\n",
2875 |        "      <th></th>\n",
2876 |        "      <th></th>\n",
2877 |        "      <th></th>\n",
2878 |        "      <th></th>\n",
2879 |        "      <th></th>\n",
2880 |        "      <th></th>\n",
2881 |        "      <th></th>\n",
2882 |        "    </tr>\n",
2883 |        "  </thead>\n",
2884 |        "  <tbody>\n",
2885 |        "    <tr>\n",
2886 |        "      <th rowspan=\"3\" valign=\"top\">female</th>\n",
2887 |        "      <th>First</th>\n",
2888 |        "      <td>42</td>\n",
2889 |        "      <td>1</td>\n",
2890 |        "      <td>46</td>\n",
2891 |        "      <td>0.976744</td>\n",
2892 |        "      <td>1.000000</td>\n",
2893 |        "      <td>0.958333</td>\n",
2894 |        "      <td>0.152499</td>\n",
2895 |        "      <td>NaN</td>\n",
2896 |        "      <td>0.201941</td>\n",
2897 |        "    </tr>\n",
2898 |        "    <tr>\n",
2899 |        "      <th>Second</th>\n",
2900 |        "      <td>7</td>\n",
2901 |        "      <td>2</td>\n",
2902 |        "      <td>61</td>\n",
2903 |        "      <td>1.000000</td>\n",
2904 |        "      <td>1.000000</td>\n",
2905 |        "      <td>0.910448</td>\n",
2906 |        "      <td>0.000000</td>\n",
2907 |        "      <td>0.000000</td>\n",
2908 |        "      <td>0.287694</td>\n",
2909 |        "    </tr>\n",
2910 |        "    <tr>\n",
2911 |        "      <th>Third</th>\n",
2912 |        "      <td>15</td>\n",
2913 |        "      <td>24</td>\n",
2914 |        "      <td>33</td>\n",
2915 |        "      <td>0.652174</td>\n",
2916 |        "      <td>0.727273</td>\n",
2917 |        "      <td>0.375000</td>\n",
2918 |        "      <td>0.486985</td>\n",
2919 |        "      <td>0.452267</td>\n",
2920 |        "      <td>0.486897</td>\n",
2921 |        "    </tr>\n",
2922 |        "    <tr>\n",
2923 |        "      <th rowspan=\"3\" valign=\"top\">male</th>\n",
2924 |        "      <th>First</th>\n",
2925 |        "      <td>17</td>\n",
2926 |        "      <td>0</td>\n",
2927 |        "      <td>28</td>\n",
2928 |        "      <td>0.404762</td>\n",
2929 |        "      <td>0.000000</td>\n",
2930 |        "      <td>0.354430</td>\n",
2931 |        "      <td>0.496796</td>\n",
2932 |        "      <td>NaN</td>\n",
2933 |        "      <td>0.481397</td>\n",
2934 |        "    </tr>\n",
2935 |        "    <tr>\n",
2936 |        "      <th>Second</th>\n",
2937 |        "      <td>2</td>\n",
2938 |        "      <td>0</td>\n",
2939 |        "      <td>15</td>\n",
2940 |        "      <td>0.200000</td>\n",
2941 |        "      <td>0.000000</td>\n",
2942 |        "      <td>0.154639</td>\n",
2943 |        "      <td>0.421637</td>\n",
2944 |        "      <td>NaN</td>\n",
2945 |        "      <td>0.363439</td>\n",
2946 |        "    </tr>\n",
2947 |        "    <tr>\n",
2948 |        "      <th>Third</th>\n",
2949 |        "      <td>10</td>\n",
2950 |        "      <td>3</td>\n",
2951 |        "      <td>34</td>\n",
2952 |        "      <td>0.232558</td>\n",
2953 |        "      <td>0.076923</td>\n",
2954 |        "      <td>0.128302</td>\n",
2955 |        "      <td>0.427463</td>\n",
2956 |        "      <td>0.269953</td>\n",
2957 |        "      <td>0.335058</td>\n",
2958 |        "    </tr>\n",
2959 |        "  </tbody>\n",
2960 |        "</table>\n",
2961 |        "</div>"
2962 |       ],
2963 |       "text/plain": [
2964 |        "                    sum                             mean             \\\n",
2965 |        "embark_town   Cherbourg Queenstown Southampton Cherbourg Queenstown   \n",
2966 |        "sex    class                                                          \n",
2967 |        "female First         42          1          46  0.976744   1.000000   \n",
2968 |        "       Second         7          2          61  1.000000   1.000000   \n",
2969 |        "       Third         15         24          33  0.652174   0.727273   \n",
2970 |        "male   First         17          0          28  0.404762   0.000000   \n",
2971 |        "       Second         2          0          15  0.200000   0.000000   \n",
2972 |        "       Third         10          3          34  0.232558   0.076923   \n",
2973 |        "\n",
2974 |        "                                std                         \n",
2975 |        "embark_town   Southampton Cherbourg Queenstown Southampton  \n",
2976 |        "sex    class                                                \n",
2977 |        "female First     0.958333  0.152499        NaN    0.201941  \n",
2978 |        "       Second    0.910448  0.000000   0.000000    0.287694  \n",
2979 |        "       Third     0.375000  0.486985   0.452267    0.486897  \n",
2980 |        "male   First     0.354430  0.496796        NaN    0.481397  \n",
2981 |        "       Second    0.154639  0.421637        NaN    0.363439  \n",
2982 |        "       Third     0.128302  0.427463   0.269953    0.335058  "
2983 |       ]
2984 |      },
2985 |      "execution_count": 53,
2986 |      "metadata": {},
2987 |      "output_type": "execute_result"
2988 |     }
2989 |    ],
2990 |    "source": [
2991 |     "df.pivot_table(\"survived\", index = [\"sex\", \"class\"], columns = \"embark_town\", aggfunc = [\"sum\", \"mean\", \"std\"])"
2992 |    ]
2993 |   },
2994 |   {
2995 |    "cell_type": "markdown",
2996 |    "id": "6266834b",
2997 |    "metadata": {},
2998 |    "source": [
2999 |     "## External Data Entry to Pandas Library"
3000 |    ]
3001 |   },
3002 |   {
3003 |    "cell_type": "markdown",
3004 |    "id": "58c0393a",
3005 |    "metadata": {},
3006 |    "source": [
3007 |     "##  Data Entry with Csv and Txt Files"
3008 |    ]
3009 |   },
3010 |   {
3011 |    "cell_type": "code",
3012 |    "execution_count": 1,
3013 |    "id": "9c6f4bd4",
3014 |    "metadata": {},
3015 |    "outputs": [],
3016 |    "source": [
3017 |     "import pandas as pd"
3018 |    ]
3019 |   },
3020 |   {
3021 |    "cell_type": "code",
3022 |    "execution_count": 2,
3023 |    "id": "c31e005e",
3024 |    "metadata": {
3025 |     "scrolled": true
3026 |    },
3027 |    "outputs": [
3028 |     {
3029 |      "data": {
3030 |       "text/html": [
3031 |        "<div>\n",
3032 |        "<style scoped>\n",
3033 |        "    .dataframe tbody tr th:only-of-type {\n",
3034 |        "        vertical-align: middle;\n",
3035 |        "    }\n",
3036 |        "\n",
3037 |        "    .dataframe tbody tr th {\n",
3038 |        "        vertical-align: top;\n",
3039 |        "    }\n",
3040 |        "\n",
3041 |        "    .dataframe thead th {\n",
3042 |        "        text-align: right;\n",
3043 |        "    }\n",
3044 |        "</style>\n",
3045 |        "<table border=\"1\" class=\"dataframe\">\n",
3046 |        "  <thead>\n",
3047 |        "    <tr style=\"text-align: right;\">\n",
3048 |        "      <th></th>\n",
3049 |        "      <th>VAL1</th>\n",
3050 |        "      <th>VAL2</th>\n",
3051 |        "      <th>VAL3</th>\n",
3052 |        "      <th>VAL4</th>\n",
3053 |        "      <th>VAL5</th>\n",
3054 |        "    </tr>\n",
3055 |        "  </thead>\n",
3056 |        "  <tbody>\n",
3057 |        "    <tr>\n",
3058 |        "      <th>0</th>\n",
3059 |        "      <td>2.706850</td>\n",
3060 |        "      <td>0.628133</td>\n",
3061 |        "      <td>0.907969</td>\n",
3062 |        "      <td>0.503826</td>\n",
3063 |        "      <td>0.651118</td>\n",
3064 |        "    </tr>\n",
3065 |        "    <tr>\n",
3066 |        "      <th>1</th>\n",
3067 |        "      <td>-0.319318</td>\n",
3068 |        "      <td>-0.848077</td>\n",
3069 |        "      <td>0.605965</td>\n",
3070 |        "      <td>-2.018168</td>\n",
3071 |        "      <td>0.740122</td>\n",
3072 |        "    </tr>\n",
3073 |        "    <tr>\n",
3074 |        "      <th>2</th>\n",
3075 |        "      <td>0.528813</td>\n",
3076 |        "      <td>-0.589001</td>\n",
3077 |        "      <td>0.188695</td>\n",
3078 |        "      <td>-0.758872</td>\n",
3079 |        "      <td>-0.933237</td>\n",
3080 |        "    </tr>\n",
3081 |        "    <tr>\n",
3082 |        "      <th>3</th>\n",
3083 |        "      <td>0.955057</td>\n",
3084 |        "      <td>0.190794</td>\n",
3085 |        "      <td>1.978757</td>\n",
3086 |        "      <td>2.605967</td>\n",
3087 |        "      <td>0.683509</td>\n",
3088 |        "    </tr>\n",
3089 |        "    <tr>\n",
3090 |        "      <th>4</th>\n",
3091 |        "      <td>0.302665</td>\n",
3092 |        "      <td>1.693723</td>\n",
3093 |        "      <td>-1.706086</td>\n",
3094 |        "      <td>-1.159119</td>\n",
3095 |        "      <td>-0.134841</td>\n",
3096 |        "    </tr>\n",
3097 |        "    <tr>\n",
3098 |        "      <th>5</th>\n",
3099 |        "      <td>0.390528</td>\n",
3100 |        "      <td>0.166905</td>\n",
3101 |        "      <td>0.184502</td>\n",
3102 |        "      <td>0.807706</td>\n",
3103 |        "      <td>0.072960</td>\n",
3104 |        "    </tr>\n",
3105 |        "  </tbody>\n",
3106 |        "</table>\n",
3107 |        "</div>"
3108 |       ],
3109 |       "text/plain": [
3110 |        "       VAL1      VAL2      VAL3      VAL4      VAL5\n",
3111 |        "0  2.706850  0.628133  0.907969  0.503826  0.651118\n",
3112 |        "1 -0.319318 -0.848077  0.605965 -2.018168  0.740122\n",
3113 |        "2  0.528813 -0.589001  0.188695 -0.758872 -0.933237\n",
3114 |        "3  0.955057  0.190794  1.978757  2.605967  0.683509\n",
3115 |        "4  0.302665  1.693723 -1.706086 -1.159119 -0.134841\n",
3116 |        "5  0.390528  0.166905  0.184502  0.807706  0.072960"
3117 |       ]
3118 |      },
3119 |      "execution_count": 2,
3120 |      "metadata": {},
3121 |      "output_type": "execute_result"
3122 |     }
3123 |    ],
3124 |    "source": [
3125 |     "pd.read_csv(\"pandas\\csv_example_data.csv\")"
3126 |    ]
3127 |   },
3128 |   {
3129 |    "cell_type": "code",
3130 |    "execution_count": 3,
3131 |    "id": "a310c007",
3132 |    "metadata": {},
3133 |    "outputs": [
3134 |     {
3135 |      "data": {
3136 |       "text/html": [
3137 |        "<div>\n",
3138 |        "<style scoped>\n",
3139 |        "    .dataframe tbody tr th:only-of-type {\n",
3140 |        "        vertical-align: middle;\n",
3141 |        "    }\n",
3142 |        "\n",
3143 |        "    .dataframe tbody tr th {\n",
3144 |        "        vertical-align: top;\n",
3145 |        "    }\n",
3146 |        "\n",
3147 |        "    .dataframe thead th {\n",
3148 |        "        text-align: right;\n",
3149 |        "    }\n",
3150 |        "</style>\n",
3151 |        "<table border=\"1\" class=\"dataframe\">\n",
3152 |        "  <thead>\n",
3153 |        "    <tr style=\"text-align: right;\">\n",
3154 |        "      <th></th>\n",
3155 |        "      <th>employee;department;Year</th>\n",
3156 |        "    </tr>\n",
3157 |        "  </thead>\n",
3158 |        "  <tbody>\n",
3159 |        "    <tr>\n",
3160 |        "      <th>0</th>\n",
3161 |        "      <td>Julia;Data Science;2005</td>\n",
3162 |        "    </tr>\n",
3163 |        "    <tr>\n",
3164 |        "      <th>1</th>\n",
3165 |        "      <td>Marie;Web Development;2008</td>\n",
3166 |        "    </tr>\n",
3167 |        "    <tr>\n",
3168 |        "      <th>2</th>\n",
3169 |        "      <td>Adam;Data Science;2011</td>\n",
3170 |        "    </tr>\n",
3171 |        "    <tr>\n",
3172 |        "      <th>3</th>\n",
3173 |        "      <td>Nicole;Cyber Security;2002</td>\n",
3174 |        "    </tr>\n",
3175 |        "    <tr>\n",
3176 |        "      <th>4</th>\n",
3177 |        "      <td>Joseph;App Developer;2007</td>\n",
3178 |        "    </tr>\n",
3179 |        "    <tr>\n",
3180 |        "      <th>5</th>\n",
3181 |        "      <td>Kayra;Data Science;2008</td>\n",
3182 |        "    </tr>\n",
3183 |        "  </tbody>\n",
3184 |        "</table>\n",
3185 |        "</div>"
3186 |       ],
3187 |       "text/plain": [
3188 |        "     employee;department;Year\n",
3189 |        "0     Julia;Data Science;2005\n",
3190 |        "1  Marie;Web Development;2008\n",
3191 |        "2      Adam;Data Science;2011\n",
3192 |        "3  Nicole;Cyber Security;2002\n",
3193 |        "4   Joseph;App Developer;2007\n",
3194 |        "5     Kayra;Data Science;2008"
3195 |       ]
3196 |      },
3197 |      "execution_count": 3,
3198 |      "metadata": {},
3199 |      "output_type": "execute_result"
3200 |     }
3201 |    ],
3202 |    "source": [
3203 |     "pd.read_csv(\"pandas\\csv_example_data_2.csv\")"
3204 |    ]
3205 |   },
3206 |   {
3207 |    "cell_type": "code",
3208 |    "execution_count": 4,
3209 |    "id": "04d1b1a0",
3210 |    "metadata": {},
3211 |    "outputs": [
3212 |     {
3213 |      "data": {
3214 |       "text/html": [
3215 |        "<div>\n",
3216 |        "<style scoped>\n",
3217 |        "    .dataframe tbody tr th:only-of-type {\n",
3218 |        "        vertical-align: middle;\n",
3219 |        "    }\n",
3220 |        "\n",
3221 |        "    .dataframe tbody tr th {\n",
3222 |        "        vertical-align: top;\n",
3223 |        "    }\n",
3224 |        "\n",
3225 |        "    .dataframe thead th {\n",
3226 |        "        text-align: right;\n",
3227 |        "    }\n",
3228 |        "</style>\n",
3229 |        "<table border=\"1\" class=\"dataframe\">\n",
3230 |        "  <thead>\n",
3231 |        "    <tr style=\"text-align: right;\">\n",
3232 |        "      <th></th>\n",
3233 |        "      <th>employee</th>\n",
3234 |        "      <th>department</th>\n",
3235 |        "      <th>Year</th>\n",
3236 |        "    </tr>\n",
3237 |        "  </thead>\n",
3238 |        "  <tbody>\n",
3239 |        "    <tr>\n",
3240 |        "      <th>0</th>\n",
3241 |        "      <td>Julia</td>\n",
3242 |        "      <td>Data Science</td>\n",
3243 |        "      <td>2005</td>\n",
3244 |        "    </tr>\n",
3245 |        "    <tr>\n",
3246 |        "      <th>1</th>\n",
3247 |        "      <td>Marie</td>\n",
3248 |        "      <td>Web Development</td>\n",
3249 |        "      <td>2008</td>\n",
3250 |        "    </tr>\n",
3251 |        "    <tr>\n",
3252 |        "      <th>2</th>\n",
3253 |        "      <td>Adam</td>\n",
3254 |        "      <td>Data Science</td>\n",
3255 |        "      <td>2011</td>\n",
3256 |        "    </tr>\n",
3257 |        "    <tr>\n",
3258 |        "      <th>3</th>\n",
3259 |        "      <td>Nicole</td>\n",
3260 |        "      <td>Cyber Security</td>\n",
3261 |        "      <td>2002</td>\n",
3262 |        "    </tr>\n",
3263 |        "    <tr>\n",
3264 |        "      <th>4</th>\n",
3265 |        "      <td>Joseph</td>\n",
3266 |        "      <td>App Developer</td>\n",
3267 |        "      <td>2007</td>\n",
3268 |        "    </tr>\n",
3269 |        "    <tr>\n",
3270 |        "      <th>5</th>\n",
3271 |        "      <td>Kayra</td>\n",
3272 |        "      <td>Data Science</td>\n",
3273 |        "      <td>2008</td>\n",
3274 |        "    </tr>\n",
3275 |        "  </tbody>\n",
3276 |        "</table>\n",
3277 |        "</div>"
3278 |       ],
3279 |       "text/plain": [
3280 |        "  employee       department  Year\n",
3281 |        "0    Julia     Data Science  2005\n",
3282 |        "1    Marie  Web Development  2008\n",
3283 |        "2     Adam     Data Science  2011\n",
3284 |        "3   Nicole   Cyber Security  2002\n",
3285 |        "4   Joseph    App Developer  2007\n",
3286 |        "5    Kayra     Data Science  2008"
3287 |       ]
3288 |      },
3289 |      "execution_count": 4,
3290 |      "metadata": {},
3291 |      "output_type": "execute_result"
3292 |     }
3293 |    ],
3294 |    "source": [
3295 |     "pd.read_csv(\"pandas\\csv_example_data_2.csv\", sep = \";\")"
3296 |    ]
3297 |   },
3298 |   {
3299 |    "cell_type": "code",
3300 |    "execution_count": 5,
3301 |    "id": "3b93f8a8",
3302 |    "metadata": {
3303 |     "scrolled": false
3304 |    },
3305 |    "outputs": [
3306 |     {
3307 |      "data": {
3308 |       "text/html": [
3309 |        "<div>\n",
3310 |        "<style scoped>\n",
3311 |        "    .dataframe tbody tr th:only-of-type {\n",
3312 |        "        vertical-align: middle;\n",
3313 |        "    }\n",
3314 |        "\n",
3315 |        "    .dataframe tbody tr th {\n",
3316 |        "        vertical-align: top;\n",
3317 |        "    }\n",
3318 |        "\n",
3319 |        "    .dataframe thead th {\n",
3320 |        "        text-align: right;\n",
3321 |        "    }\n",
3322 |        "</style>\n",
3323 |        "<table border=\"1\" class=\"dataframe\">\n",
3324 |        "  <thead>\n",
3325 |        "    <tr style=\"text-align: right;\">\n",
3326 |        "      <th></th>\n",
3327 |        "      <th>employee</th>\n",
3328 |        "      <th>department</th>\n",
3329 |        "      <th>Year</th>\n",
3330 |        "    </tr>\n",
3331 |        "  </thead>\n",
3332 |        "  <tbody>\n",
3333 |        "    <tr>\n",
3334 |        "      <th>0</th>\n",
3335 |        "      <td>Julia</td>\n",
3336 |        "      <td>Data Science</td>\n",
3337 |        "      <td>2005</td>\n",
3338 |        "    </tr>\n",
3339 |        "    <tr>\n",
3340 |        "      <th>1</th>\n",
3341 |        "      <td>Marie</td>\n",
3342 |        "      <td>Web Development</td>\n",
3343 |        "      <td>2008</td>\n",
3344 |        "    </tr>\n",
3345 |        "    <tr>\n",
3346 |        "      <th>2</th>\n",
3347 |        "      <td>Adam</td>\n",
3348 |        "      <td>Data Science</td>\n",
3349 |        "      <td>2011</td>\n",
3350 |        "    </tr>\n",
3351 |        "    <tr>\n",
3352 |        "      <th>3</th>\n",
3353 |        "      <td>Nicole</td>\n",
3354 |        "      <td>Cyber Security</td>\n",
3355 |        "      <td>2002</td>\n",
3356 |        "    </tr>\n",
3357 |        "    <tr>\n",
3358 |        "      <th>4</th>\n",
3359 |        "      <td>Joseph</td>\n",
3360 |        "      <td>App Developer</td>\n",
3361 |        "      <td>2007</td>\n",
3362 |        "    </tr>\n",
3363 |        "    <tr>\n",
3364 |        "      <th>5</th>\n",
3365 |        "      <td>Kayra</td>\n",
3366 |        "      <td>Data Science</td>\n",
3367 |        "      <td>2008</td>\n",
3368 |        "    </tr>\n",
3369 |        "  </tbody>\n",
3370 |        "</table>\n",
3371 |        "</div>"
3372 |       ],
3373 |       "text/plain": [
3374 |        "  employee       department  Year\n",
3375 |        "0    Julia     Data Science  2005\n",
3376 |        "1    Marie  Web Development  2008\n",
3377 |        "2     Adam     Data Science  2011\n",
3378 |        "3   Nicole   Cyber Security  2002\n",
3379 |        "4   Joseph    App Developer  2007\n",
3380 |        "5    Kayra     Data Science  2008"
3381 |       ]
3382 |      },
3383 |      "execution_count": 5,
3384 |      "metadata": {},
3385 |      "output_type": "execute_result"
3386 |     }
3387 |    ],
3388 |    "source": [
3389 |     "pd.read_csv(\"pandas\\csv_example_data_2.csv\", delimiter = \";\")"
3390 |    ]
3391 |   },
3392 |   {
3393 |    "cell_type": "code",
3394 |    "execution_count": 59,
3395 |    "id": "168c3b9b",
3396 |    "metadata": {},
3397 |    "outputs": [
3398 |     {
3399 |      "data": {
3400 |       "text/html": [
3401 |        "<div>\n",
3402 |        "<style scoped>\n",
3403 |        "    .dataframe tbody tr th:only-of-type {\n",
3404 |        "        vertical-align: middle;\n",
3405 |        "    }\n",
3406 |        "\n",
3407 |        "    .dataframe tbody tr th {\n",
3408 |        "        vertical-align: top;\n",
3409 |        "    }\n",
3410 |        "\n",
3411 |        "    .dataframe thead th {\n",
3412 |        "        text-align: right;\n",
3413 |        "    }\n",
3414 |        "</style>\n",
3415 |        "<table border=\"1\" class=\"dataframe\">\n",
3416 |        "  <thead>\n",
3417 |        "    <tr style=\"text-align: right;\">\n",
3418 |        "      <th></th>\n",
3419 |        "      <th>Unnamed: 0</th>\n",
3420 |        "      <th>employee</th>\n",
3421 |        "      <th>department</th>\n",
3422 |        "      <th>Year</th>\n",
3423 |        "    </tr>\n",
3424 |        "  </thead>\n",
3425 |        "  <tbody>\n",
3426 |        "    <tr>\n",
3427 |        "      <th>0</th>\n",
3428 |        "      <td>0</td>\n",
3429 |        "      <td>Julia</td>\n",
3430 |        "      <td>Data Science</td>\n",
3431 |        "      <td>2005</td>\n",
3432 |        "    </tr>\n",
3433 |        "    <tr>\n",
3434 |        "      <th>1</th>\n",
3435 |        "      <td>1</td>\n",
3436 |        "      <td>Marie</td>\n",
3437 |        "      <td>Web Development</td>\n",
3438 |        "      <td>2008</td>\n",
3439 |        "    </tr>\n",
3440 |        "    <tr>\n",
3441 |        "      <th>2</th>\n",
3442 |        "      <td>2</td>\n",
3443 |        "      <td>Adam</td>\n",
3444 |        "      <td>Data Science</td>\n",
3445 |        "      <td>2011</td>\n",
3446 |        "    </tr>\n",
3447 |        "    <tr>\n",
3448 |        "      <th>3</th>\n",
3449 |        "      <td>3</td>\n",
3450 |        "      <td>Nicole</td>\n",
3451 |        "      <td>Cyber Security</td>\n",
3452 |        "      <td>2002</td>\n",
3453 |        "    </tr>\n",
3454 |        "    <tr>\n",
3455 |        "      <th>4</th>\n",
3456 |        "      <td>4</td>\n",
3457 |        "      <td>Joseph</td>\n",
3458 |        "      <td>App Developer</td>\n",
3459 |        "      <td>2007</td>\n",
3460 |        "    </tr>\n",
3461 |        "    <tr>\n",
3462 |        "      <th>5</th>\n",
3463 |        "      <td>5</td>\n",
3464 |        "      <td>Kayra</td>\n",
3465 |        "      <td>Data Science</td>\n",
3466 |        "      <td>2008</td>\n",
3467 |        "    </tr>\n",
3468 |        "  </tbody>\n",
3469 |        "</table>\n",
3470 |        "</div>"
3471 |       ],
3472 |       "text/plain": [
3473 |        "   Unnamed: 0 employee       department  Year\n",
3474 |        "0           0    Julia     Data Science  2005\n",
3475 |        "1           1    Marie  Web Development  2008\n",
3476 |        "2           2     Adam     Data Science  2011\n",
3477 |        "3           3   Nicole   Cyber Security  2002\n",
3478 |        "4           4   Joseph    App Developer  2007\n",
3479 |        "5           5    Kayra     Data Science  2008"
3480 |       ]
3481 |      },
3482 |      "execution_count": 59,
3483 |      "metadata": {},
3484 |      "output_type": "execute_result"
3485 |     }
3486 |    ],
3487 |    "source": [
3488 |     "pd.read_csv(\"pandas\\csv_example_data_3.csv\")"
3489 |    ]
3490 |   },
3491 |   {
3492 |    "cell_type": "code",
3493 |    "execution_count": 60,
3494 |    "id": "a3818718",
3495 |    "metadata": {
3496 |     "scrolled": true
3497 |    },
3498 |    "outputs": [
3499 |     {
3500 |      "data": {
3501 |       "text/html": [
3502 |        "<div>\n",
3503 |        "<style scoped>\n",
3504 |        "    .dataframe tbody tr th:only-of-type {\n",
3505 |        "        vertical-align: middle;\n",
3506 |        "    }\n",
3507 |        "\n",
3508 |        "    .dataframe tbody tr th {\n",
3509 |        "        vertical-align: top;\n",
3510 |        "    }\n",
3511 |        "\n",
3512 |        "    .dataframe thead th {\n",
3513 |        "        text-align: right;\n",
3514 |        "    }\n",
3515 |        "</style>\n",
3516 |        "<table border=\"1\" class=\"dataframe\">\n",
3517 |        "  <thead>\n",
3518 |        "    <tr style=\"text-align: right;\">\n",
3519 |        "      <th></th>\n",
3520 |        "      <th>employee</th>\n",
3521 |        "      <th>department</th>\n",
3522 |        "      <th>Year</th>\n",
3523 |        "    </tr>\n",
3524 |        "  </thead>\n",
3525 |        "  <tbody>\n",
3526 |        "    <tr>\n",
3527 |        "      <th>0</th>\n",
3528 |        "      <td>Julia</td>\n",
3529 |        "      <td>Data Science</td>\n",
3530 |        "      <td>2005</td>\n",
3531 |        "    </tr>\n",
3532 |        "    <tr>\n",
3533 |        "      <th>1</th>\n",
3534 |        "      <td>Marie</td>\n",
3535 |        "      <td>Web Development</td>\n",
3536 |        "      <td>2008</td>\n",
3537 |        "    </tr>\n",
3538 |        "    <tr>\n",
3539 |        "      <th>2</th>\n",
3540 |        "      <td>Adam</td>\n",
3541 |        "      <td>Data Science</td>\n",
3542 |        "      <td>2011</td>\n",
3543 |        "    </tr>\n",
3544 |        "    <tr>\n",
3545 |        "      <th>3</th>\n",
3546 |        "      <td>Nicole</td>\n",
3547 |        "      <td>Cyber Security</td>\n",
3548 |        "      <td>2002</td>\n",
3549 |        "    </tr>\n",
3550 |        "    <tr>\n",
3551 |        "      <th>4</th>\n",
3552 |        "      <td>Joseph</td>\n",
3553 |        "      <td>App Developer</td>\n",
3554 |        "      <td>2007</td>\n",
3555 |        "    </tr>\n",
3556 |        "    <tr>\n",
3557 |        "      <th>5</th>\n",
3558 |        "      <td>Kayra</td>\n",
3559 |        "      <td>Data Science</td>\n",
3560 |        "      <td>2008</td>\n",
3561 |        "    </tr>\n",
3562 |        "  </tbody>\n",
3563 |        "</table>\n",
3564 |        "</div>"
3565 |       ],
3566 |       "text/plain": [
3567 |        "  employee       department  Year\n",
3568 |        "0    Julia     Data Science  2005\n",
3569 |        "1    Marie  Web Development  2008\n",
3570 |        "2     Adam     Data Science  2011\n",
3571 |        "3   Nicole   Cyber Security  2002\n",
3572 |        "4   Joseph    App Developer  2007\n",
3573 |        "5    Kayra     Data Science  2008"
3574 |       ]
3575 |      },
3576 |      "execution_count": 60,
3577 |      "metadata": {},
3578 |      "output_type": "execute_result"
3579 |     }
3580 |    ],
3581 |    "source": [
3582 |     "pd.read_csv(\"pandas\\csv_example_data_3.csv\", index_col=0)"
3583 |    ]
3584 |   },
3585 |   {
3586 |    "cell_type": "code",
3587 |    "execution_count": 61,
3588 |    "id": "8c831319",
3589 |    "metadata": {},
3590 |    "outputs": [],
3591 |    "source": [
3592 |     "df = pd.read_csv(\"pandas\\csv_example_data_3.csv\", index_col=0)"
3593 |    ]
3594 |   },
3595 |   {
3596 |    "cell_type": "code",
3597 |    "execution_count": 62,
3598 |    "id": "e5ebe664",
3599 |    "metadata": {},
3600 |    "outputs": [
3601 |     {
3602 |      "data": {
3603 |       "text/html": [
3604 |        "<div>\n",
3605 |        "<style scoped>\n",
3606 |        "    .dataframe tbody tr th:only-of-type {\n",
3607 |        "        vertical-align: middle;\n",
3608 |        "    }\n",
3609 |        "\n",
3610 |        "    .dataframe tbody tr th {\n",
3611 |        "        vertical-align: top;\n",
3612 |        "    }\n",
3613 |        "\n",
3614 |        "    .dataframe thead th {\n",
3615 |        "        text-align: right;\n",
3616 |        "    }\n",
3617 |        "</style>\n",
3618 |        "<table border=\"1\" class=\"dataframe\">\n",
3619 |        "  <thead>\n",
3620 |        "    <tr style=\"text-align: right;\">\n",
3621 |        "      <th></th>\n",
3622 |        "      <th>employee</th>\n",
3623 |        "      <th>department</th>\n",
3624 |        "      <th>Year</th>\n",
3625 |        "    </tr>\n",
3626 |        "  </thead>\n",
3627 |        "  <tbody>\n",
3628 |        "    <tr>\n",
3629 |        "      <th>0</th>\n",
3630 |        "      <td>Julia</td>\n",
3631 |        "      <td>Data Science</td>\n",
3632 |        "      <td>2005</td>\n",
3633 |        "    </tr>\n",
3634 |        "    <tr>\n",
3635 |        "      <th>1</th>\n",
3636 |        "      <td>Marie</td>\n",
3637 |        "      <td>Web Development</td>\n",
3638 |        "      <td>2008</td>\n",
3639 |        "    </tr>\n",
3640 |        "    <tr>\n",
3641 |        "      <th>2</th>\n",
3642 |        "      <td>Adam</td>\n",
3643 |        "      <td>Data Science</td>\n",
3644 |        "      <td>2011</td>\n",
3645 |        "    </tr>\n",
3646 |        "    <tr>\n",
3647 |        "      <th>3</th>\n",
3648 |        "      <td>Nicole</td>\n",
3649 |        "      <td>Cyber Security</td>\n",
3650 |        "      <td>2002</td>\n",
3651 |        "    </tr>\n",
3652 |        "    <tr>\n",
3653 |        "      <th>4</th>\n",
3654 |        "      <td>Joseph</td>\n",
3655 |        "      <td>App Developer</td>\n",
3656 |        "      <td>2007</td>\n",
3657 |        "    </tr>\n",
3658 |        "  </tbody>\n",
3659 |        "</table>\n",
3660 |        "</div>"
3661 |       ],
3662 |       "text/plain": [
3663 |        "  employee       department  Year\n",
3664 |        "0    Julia     Data Science  2005\n",
3665 |        "1    Marie  Web Development  2008\n",
3666 |        "2     Adam     Data Science  2011\n",
3667 |        "3   Nicole   Cyber Security  2002\n",
3668 |        "4   Joseph    App Developer  2007"
3669 |       ]
3670 |      },
3671 |      "execution_count": 62,
3672 |      "metadata": {},
3673 |      "output_type": "execute_result"
3674 |     }
3675 |    ],
3676 |    "source": [
3677 |     "df.head()"
3678 |    ]
3679 |   },
3680 |   {
3681 |    "cell_type": "code",
3682 |    "execution_count": 63,
3683 |    "id": "494c7b2c",
3684 |    "metadata": {},
3685 |    "outputs": [],
3686 |    "source": [
3687 |     "df2 = pd.read_csv(\"pandas\\example_text_data.txt\")"
3688 |    ]
3689 |   },
3690 |   {
3691 |    "cell_type": "code",
3692 |    "execution_count": 64,
3693 |    "id": "15c903f2",
3694 |    "metadata": {},
3695 |    "outputs": [
3696 |     {
3697 |      "data": {
3698 |       "text/html": [
3699 |        "<div>\n",
3700 |        "<style scoped>\n",
3701 |        "    .dataframe tbody tr th:only-of-type {\n",
3702 |        "        vertical-align: middle;\n",
3703 |        "    }\n",
3704 |        "\n",
3705 |        "    .dataframe tbody tr th {\n",
3706 |        "        vertical-align: top;\n",
3707 |        "    }\n",
3708 |        "\n",
3709 |        "    .dataframe thead th {\n",
3710 |        "        text-align: right;\n",
3711 |        "    }\n",
3712 |        "</style>\n",
3713 |        "<table border=\"1\" class=\"dataframe\">\n",
3714 |        "  <thead>\n",
3715 |        "    <tr style=\"text-align: right;\">\n",
3716 |        "      <th></th>\n",
3717 |        "      <th>VAL1 VAL2</th>\n",
3718 |        "    </tr>\n",
3719 |        "  </thead>\n",
3720 |        "  <tbody>\n",
3721 |        "    <tr>\n",
3722 |        "      <th>0</th>\n",
3723 |        "      <td>10 100</td>\n",
3724 |        "    </tr>\n",
3725 |        "    <tr>\n",
3726 |        "      <th>1</th>\n",
3727 |        "      <td>25 250</td>\n",
3728 |        "    </tr>\n",
3729 |        "    <tr>\n",
3730 |        "      <th>2</th>\n",
3731 |        "      <td>30 300</td>\n",
3732 |        "    </tr>\n",
3733 |        "    <tr>\n",
3734 |        "      <th>3</th>\n",
3735 |        "      <td>5 50</td>\n",
3736 |        "    </tr>\n",
3737 |        "    <tr>\n",
3738 |        "      <th>4</th>\n",
3739 |        "      <td>8 80</td>\n",
3740 |        "    </tr>\n",
3741 |        "    <tr>\n",
3742 |        "      <th>5</th>\n",
3743 |        "      <td>3 30</td>\n",
3744 |        "    </tr>\n",
3745 |        "    <tr>\n",
3746 |        "      <th>6</th>\n",
3747 |        "      <td>15 150</td>\n",
3748 |        "    </tr>\n",
3749 |        "    <tr>\n",
3750 |        "      <th>7</th>\n",
3751 |        "      <td>7 70</td>\n",
3752 |        "    </tr>\n",
3753 |        "    <tr>\n",
3754 |        "      <th>8</th>\n",
3755 |        "      <td>6 60</td>\n",
3756 |        "    </tr>\n",
3757 |        "  </tbody>\n",
3758 |        "</table>\n",
3759 |        "</div>"
3760 |       ],
3761 |       "text/plain": [
3762 |        "  VAL1 VAL2\n",
3763 |        "0    10 100\n",
3764 |        "1    25 250\n",
3765 |        "2    30 300\n",
3766 |        "3      5 50\n",
3767 |        "4      8 80\n",
3768 |        "5      3 30\n",
3769 |        "6    15 150\n",
3770 |        "7      7 70\n",
3771 |        "8      6 60"
3772 |       ]
3773 |      },
3774 |      "execution_count": 64,
3775 |      "metadata": {},
3776 |      "output_type": "execute_result"
3777 |     }
3778 |    ],
3779 |    "source": [
3780 |     "df2"
3781 |    ]
3782 |   },
3783 |   {
3784 |    "cell_type": "code",
3785 |    "execution_count": 65,
3786 |    "id": "1f11d542",
3787 |    "metadata": {},
3788 |    "outputs": [],
3789 |    "source": [
3790 |     "df3 = pd.read_csv(\"pandas\\example_text_data.txt\", delimiter = \" \")"
3791 |    ]
3792 |   },
3793 |   {
3794 |    "cell_type": "code",
3795 |    "execution_count": 66,
3796 |    "id": "2650f64f",
3797 |    "metadata": {},
3798 |    "outputs": [
3799 |     {
3800 |      "data": {
3801 |       "text/html": [
3802 |        "<div>\n",
3803 |        "<style scoped>\n",
3804 |        "    .dataframe tbody tr th:only-of-type {\n",
3805 |        "        vertical-align: middle;\n",
3806 |        "    }\n",
3807 |        "\n",
3808 |        "    .dataframe tbody tr th {\n",
3809 |        "        vertical-align: top;\n",
3810 |        "    }\n",
3811 |        "\n",
3812 |        "    .dataframe thead th {\n",
3813 |        "        text-align: right;\n",
3814 |        "    }\n",
3815 |        "</style>\n",
3816 |        "<table border=\"1\" class=\"dataframe\">\n",
3817 |        "  <thead>\n",
3818 |        "    <tr style=\"text-align: right;\">\n",
3819 |        "      <th></th>\n",
3820 |        "      <th>VAL1</th>\n",
3821 |        "      <th>VAL2</th>\n",
3822 |        "    </tr>\n",
3823 |        "  </thead>\n",
3824 |        "  <tbody>\n",
3825 |        "    <tr>\n",
3826 |        "      <th>0</th>\n",
3827 |        "      <td>10</td>\n",
3828 |        "      <td>100</td>\n",
3829 |        "    </tr>\n",
3830 |        "    <tr>\n",
3831 |        "      <th>1</th>\n",
3832 |        "      <td>25</td>\n",
3833 |        "      <td>250</td>\n",
3834 |        "    </tr>\n",
3835 |        "    <tr>\n",
3836 |        "      <th>2</th>\n",
3837 |        "      <td>30</td>\n",
3838 |        "      <td>300</td>\n",
3839 |        "    </tr>\n",
3840 |        "    <tr>\n",
3841 |        "      <th>3</th>\n",
3842 |        "      <td>5</td>\n",
3843 |        "      <td>50</td>\n",
3844 |        "    </tr>\n",
3845 |        "    <tr>\n",
3846 |        "      <th>4</th>\n",
3847 |        "      <td>8</td>\n",
3848 |        "      <td>80</td>\n",
3849 |        "    </tr>\n",
3850 |        "    <tr>\n",
3851 |        "      <th>5</th>\n",
3852 |        "      <td>3</td>\n",
3853 |        "      <td>30</td>\n",
3854 |        "    </tr>\n",
3855 |        "    <tr>\n",
3856 |        "      <th>6</th>\n",
3857 |        "      <td>15</td>\n",
3858 |        "      <td>150</td>\n",
3859 |        "    </tr>\n",
3860 |        "    <tr>\n",
3861 |        "      <th>7</th>\n",
3862 |        "      <td>7</td>\n",
3863 |        "      <td>70</td>\n",
3864 |        "    </tr>\n",
3865 |        "    <tr>\n",
3866 |        "      <th>8</th>\n",
3867 |        "      <td>6</td>\n",
3868 |        "      <td>60</td>\n",
3869 |        "    </tr>\n",
3870 |        "  </tbody>\n",
3871 |        "</table>\n",
3872 |        "</div>"
3873 |       ],
3874 |       "text/plain": [
3875 |        "   VAL1  VAL2\n",
3876 |        "0    10   100\n",
3877 |        "1    25   250\n",
3878 |        "2    30   300\n",
3879 |        "3     5    50\n",
3880 |        "4     8    80\n",
3881 |        "5     3    30\n",
3882 |        "6    15   150\n",
3883 |        "7     7    70\n",
3884 |        "8     6    60"
3885 |       ]
3886 |      },
3887 |      "execution_count": 66,
3888 |      "metadata": {},
3889 |      "output_type": "execute_result"
3890 |     }
3891 |    ],
3892 |    "source": [
3893 |     "df3"
3894 |    ]
3895 |   },
3896 |   {
3897 |    "cell_type": "markdown",
3898 |    "id": "f2534fab",
3899 |    "metadata": {},
3900 |    "source": [
3901 |     "## Data Entry with Excel Files"
3902 |    ]
3903 |   },
3904 |   {
3905 |    "cell_type": "code",
3906 |    "execution_count": 67,
3907 |    "id": "5d70e36b",
3908 |    "metadata": {},
3909 |    "outputs": [],
3910 |    "source": [
3911 |     "import pandas as pd"
3912 |    ]
3913 |   },
3914 |   {
3915 |    "cell_type": "code",
3916 |    "execution_count": 68,
3917 |    "id": "79833759",
3918 |    "metadata": {},
3919 |    "outputs": [],
3920 |    "source": [
3921 |     "df1 = pd.read_excel(\"pandas\\excel_example_data.xlsx\")"
3922 |    ]
3923 |   },
3924 |   {
3925 |    "cell_type": "code",
3926 |    "execution_count": 69,
3927 |    "id": "d2b1a127",
3928 |    "metadata": {},
3929 |    "outputs": [
3930 |     {
3931 |      "data": {
3932 |       "text/html": [
3933 |        "<div>\n",
3934 |        "<style scoped>\n",
3935 |        "    .dataframe tbody tr th:only-of-type {\n",
3936 |        "        vertical-align: middle;\n",
3937 |        "    }\n",
3938 |        "\n",
3939 |        "    .dataframe tbody tr th {\n",
3940 |        "        vertical-align: top;\n",
3941 |        "    }\n",
3942 |        "\n",
3943 |        "    .dataframe thead th {\n",
3944 |        "        text-align: right;\n",
3945 |        "    }\n",
3946 |        "</style>\n",
3947 |        "<table border=\"1\" class=\"dataframe\">\n",
3948 |        "  <thead>\n",
3949 |        "    <tr style=\"text-align: right;\">\n",
3950 |        "      <th></th>\n",
3951 |        "      <th>employee</th>\n",
3952 |        "      <th>department</th>\n",
3953 |        "      <th>Year</th>\n",
3954 |        "    </tr>\n",
3955 |        "  </thead>\n",
3956 |        "  <tbody>\n",
3957 |        "    <tr>\n",
3958 |        "      <th>0</th>\n",
3959 |        "      <td>Julia</td>\n",
3960 |        "      <td>Data Science</td>\n",
3961 |        "      <td>2005</td>\n",
3962 |        "    </tr>\n",
3963 |        "    <tr>\n",
3964 |        "      <th>1</th>\n",
3965 |        "      <td>Marie</td>\n",
3966 |        "      <td>Web Development</td>\n",
3967 |        "      <td>2008</td>\n",
3968 |        "    </tr>\n",
3969 |        "    <tr>\n",
3970 |        "      <th>2</th>\n",
3971 |        "      <td>Adam</td>\n",
3972 |        "      <td>Data Science</td>\n",
3973 |        "      <td>2011</td>\n",
3974 |        "    </tr>\n",
3975 |        "    <tr>\n",
3976 |        "      <th>3</th>\n",
3977 |        "      <td>Nicole</td>\n",
3978 |        "      <td>Cyber Security</td>\n",
3979 |        "      <td>2002</td>\n",
3980 |        "    </tr>\n",
3981 |        "    <tr>\n",
3982 |        "      <th>4</th>\n",
3983 |        "      <td>Joseph</td>\n",
3984 |        "      <td>App Developer</td>\n",
3985 |        "      <td>2007</td>\n",
3986 |        "    </tr>\n",
3987 |        "    <tr>\n",
3988 |        "      <th>5</th>\n",
3989 |        "      <td>Kayra</td>\n",
3990 |        "      <td>Data Science</td>\n",
3991 |        "      <td>2008</td>\n",
3992 |        "    </tr>\n",
3993 |        "  </tbody>\n",
3994 |        "</table>\n",
3995 |        "</div>"
3996 |       ],
3997 |       "text/plain": [
3998 |        "  employee       department  Year\n",
3999 |        "0    Julia     Data Science  2005\n",
4000 |        "1    Marie  Web Development  2008\n",
4001 |        "2     Adam     Data Science  2011\n",
4002 |        "3   Nicole   Cyber Security  2002\n",
4003 |        "4   Joseph    App Developer  2007\n",
4004 |        "5    Kayra     Data Science  2008"
4005 |       ]
4006 |      },
4007 |      "execution_count": 69,
4008 |      "metadata": {},
4009 |      "output_type": "execute_result"
4010 |     }
4011 |    ],
4012 |    "source": [
4013 |     "df1"
4014 |    ]
4015 |   },
4016 |   {
4017 |    "cell_type": "code",
4018 |    "execution_count": 70,
4019 |    "id": "6e0fa9ef",
4020 |    "metadata": {},
4021 |    "outputs": [],
4022 |    "source": [
4023 |     "df2 = pd.read_excel(\"pandas\\excel_example_data.xlsx\", sheet_name = \"Sheet2\")"
4024 |    ]
4025 |   },
4026 |   {
4027 |    "cell_type": "code",
4028 |    "execution_count": 71,
4029 |    "id": "440e2492",
4030 |    "metadata": {},
4031 |    "outputs": [
4032 |     {
4033 |      "data": {
4034 |       "text/html": [
4035 |        "<div>\n",
4036 |        "<style scoped>\n",
4037 |        "    .dataframe tbody tr th:only-of-type {\n",
4038 |        "        vertical-align: middle;\n",
4039 |        "    }\n",
4040 |        "\n",
4041 |        "    .dataframe tbody tr th {\n",
4042 |        "        vertical-align: top;\n",
4043 |        "    }\n",
4044 |        "\n",
4045 |        "    .dataframe thead th {\n",
4046 |        "        text-align: right;\n",
4047 |        "    }\n",
4048 |        "</style>\n",
4049 |        "<table border=\"1\" class=\"dataframe\">\n",
4050 |        "  <thead>\n",
4051 |        "    <tr style=\"text-align: right;\">\n",
4052 |        "      <th></th>\n",
4053 |        "      <th>employee</th>\n",
4054 |        "      <th>age</th>\n",
4055 |        "    </tr>\n",
4056 |        "  </thead>\n",
4057 |        "  <tbody>\n",
4058 |        "    <tr>\n",
4059 |        "      <th>0</th>\n",
4060 |        "      <td>Julia</td>\n",
4061 |        "      <td>35</td>\n",
4062 |        "    </tr>\n",
4063 |        "    <tr>\n",
4064 |        "      <th>1</th>\n",
4065 |        "      <td>Marie</td>\n",
4066 |        "      <td>40</td>\n",
4067 |        "    </tr>\n",
4068 |        "    <tr>\n",
4069 |        "      <th>2</th>\n",
4070 |        "      <td>Adam</td>\n",
4071 |        "      <td>38</td>\n",
4072 |        "    </tr>\n",
4073 |        "    <tr>\n",
4074 |        "      <th>3</th>\n",
4075 |        "      <td>Nicole</td>\n",
4076 |        "      <td>33</td>\n",
4077 |        "    </tr>\n",
4078 |        "    <tr>\n",
4079 |        "      <th>4</th>\n",
4080 |        "      <td>Joseph</td>\n",
4081 |        "      <td>29</td>\n",
4082 |        "    </tr>\n",
4083 |        "    <tr>\n",
4084 |        "      <th>5</th>\n",
4085 |        "      <td>Kayra</td>\n",
4086 |        "      <td>27</td>\n",
4087 |        "    </tr>\n",
4088 |        "  </tbody>\n",
4089 |        "</table>\n",
4090 |        "</div>"
4091 |       ],
4092 |       "text/plain": [
4093 |        "  employee  age\n",
4094 |        "0    Julia   35\n",
4095 |        "1    Marie   40\n",
4096 |        "2     Adam   38\n",
4097 |        "3   Nicole   33\n",
4098 |        "4   Joseph   29\n",
4099 |        "5    Kayra   27"
4100 |       ]
4101 |      },
4102 |      "execution_count": 71,
4103 |      "metadata": {},
4104 |      "output_type": "execute_result"
4105 |     }
4106 |    ],
4107 |    "source": [
4108 |     "df2"
4109 |    ]
4110 |   },
4111 |   {
4112 |    "cell_type": "code",
4113 |    "execution_count": 72,
4114 |    "id": "831b0c23",
4115 |    "metadata": {},
4116 |    "outputs": [],
4117 |    "source": [
4118 |     "df3 = pd.merge(df1, df2)"
4119 |    ]
4120 |   },
4121 |   {
4122 |    "cell_type": "code",
4123 |    "execution_count": 73,
4124 |    "id": "b5914a5f",
4125 |    "metadata": {},
4126 |    "outputs": [
4127 |     {
4128 |      "data": {
4129 |       "text/html": [
4130 |        "<div>\n",
4131 |        "<style scoped>\n",
4132 |        "    .dataframe tbody tr th:only-of-type {\n",
4133 |        "        vertical-align: middle;\n",
4134 |        "    }\n",
4135 |        "\n",
4136 |        "    .dataframe tbody tr th {\n",
4137 |        "        vertical-align: top;\n",
4138 |        "    }\n",
4139 |        "\n",
4140 |        "    .dataframe thead th {\n",
4141 |        "        text-align: right;\n",
4142 |        "    }\n",
4143 |        "</style>\n",
4144 |        "<table border=\"1\" class=\"dataframe\">\n",
4145 |        "  <thead>\n",
4146 |        "    <tr style=\"text-align: right;\">\n",
4147 |        "      <th></th>\n",
4148 |        "      <th>employee</th>\n",
4149 |        "      <th>department</th>\n",
4150 |        "      <th>Year</th>\n",
4151 |        "      <th>age</th>\n",
4152 |        "    </tr>\n",
4153 |        "  </thead>\n",
4154 |        "  <tbody>\n",
4155 |        "    <tr>\n",
4156 |        "      <th>0</th>\n",
4157 |        "      <td>Julia</td>\n",
4158 |        "      <td>Data Science</td>\n",
4159 |        "      <td>2005</td>\n",
4160 |        "      <td>35</td>\n",
4161 |        "    </tr>\n",
4162 |        "    <tr>\n",
4163 |        "      <th>1</th>\n",
4164 |        "      <td>Marie</td>\n",
4165 |        "      <td>Web Development</td>\n",
4166 |        "      <td>2008</td>\n",
4167 |        "      <td>40</td>\n",
4168 |        "    </tr>\n",
4169 |        "    <tr>\n",
4170 |        "      <th>2</th>\n",
4171 |        "      <td>Adam</td>\n",
4172 |        "      <td>Data Science</td>\n",
4173 |        "      <td>2011</td>\n",
4174 |        "      <td>38</td>\n",
4175 |        "    </tr>\n",
4176 |        "    <tr>\n",
4177 |        "      <th>3</th>\n",
4178 |        "      <td>Nicole</td>\n",
4179 |        "      <td>Cyber Security</td>\n",
4180 |        "      <td>2002</td>\n",
4181 |        "      <td>33</td>\n",
4182 |        "    </tr>\n",
4183 |        "    <tr>\n",
4184 |        "      <th>4</th>\n",
4185 |        "      <td>Joseph</td>\n",
4186 |        "      <td>App Developer</td>\n",
4187 |        "      <td>2007</td>\n",
4188 |        "      <td>29</td>\n",
4189 |        "    </tr>\n",
4190 |        "    <tr>\n",
4191 |        "      <th>5</th>\n",
4192 |        "      <td>Kayra</td>\n",
4193 |        "      <td>Data Science</td>\n",
4194 |        "      <td>2008</td>\n",
4195 |        "      <td>27</td>\n",
4196 |        "    </tr>\n",
4197 |        "  </tbody>\n",
4198 |        "</table>\n",
4199 |        "</div>"
4200 |       ],
4201 |       "text/plain": [
4202 |        "  employee       department  Year  age\n",
4203 |        "0    Julia     Data Science  2005   35\n",
4204 |        "1    Marie  Web Development  2008   40\n",
4205 |        "2     Adam     Data Science  2011   38\n",
4206 |        "3   Nicole   Cyber Security  2002   33\n",
4207 |        "4   Joseph    App Developer  2007   29\n",
4208 |        "5    Kayra     Data Science  2008   27"
4209 |       ]
4210 |      },
4211 |      "execution_count": 73,
4212 |      "metadata": {},
4213 |      "output_type": "execute_result"
4214 |     }
4215 |    ],
4216 |    "source": [
4217 |     "df3"
4218 |    ]
4219 |   },
4220 |   {
4221 |    "cell_type": "markdown",
4222 |    "id": "15ed8aa4",
4223 |    "metadata": {},
4224 |    "source": [
4225 |     "## Data Output with Pandas Library\n",
4226 |     "## Output of File with CSV Extension\n",
4227 |     " "
4228 |    ]
4229 |   },
4230 |   {
4231 |    "cell_type": "code",
4232 |    "execution_count": 76,
4233 |    "id": "7c6654da",
4234 |    "metadata": {},
4235 |    "outputs": [],
4236 |    "source": [
4237 |     "import pandas as pd"
4238 |    ]
4239 |   },
4240 |   {
4241 |    "cell_type": "code",
4242 |    "execution_count": 77,
4243 |    "id": "08742a87",
4244 |    "metadata": {},
4245 |    "outputs": [],
4246 |    "source": [
4247 |     "df1 = pd.DataFrame({'employee': ['Julia', 'Marie', 'Adam', 'Nicole'],\n",
4248 |     "                     'department': ['Data Science', 'Web Development', 'Data Science', 'Cyber Security'],\n",
4249 |     "                     'Year': ['2005', '2008', '2011', '2002']})\n",
4250 |     "   \n",
4251 |     "df2 = pd.DataFrame({'employee': ['Nicole', 'Adam', 'Julia', 'Marie'],\n",
4252 |     "                          'country': ['Canada', 'England', 'USA', 'Germany'],\n",
4253 |     "                          'salary': ['22000', '16000', '20000', '17500']})  "
4254 |    ]
4255 |   },
4256 |   {
4257 |    "cell_type": "code",
4258 |    "execution_count": 78,
4259 |    "id": "03759175",
4260 |    "metadata": {
4261 |     "scrolled": true
4262 |    },
4263 |    "outputs": [
4264 |     {
4265 |      "data": {
4266 |       "text/html": [
4267 |        "<div>\n",
4268 |        "<style scoped>\n",
4269 |        "    .dataframe tbody tr th:only-of-type {\n",
4270 |        "        vertical-align: middle;\n",
4271 |        "    }\n",
4272 |        "\n",
4273 |        "    .dataframe tbody tr th {\n",
4274 |        "        vertical-align: top;\n",
4275 |        "    }\n",
4276 |        "\n",
4277 |        "    .dataframe thead th {\n",
4278 |        "        text-align: right;\n",
4279 |        "    }\n",
4280 |        "</style>\n",
4281 |        "<table border=\"1\" class=\"dataframe\">\n",
4282 |        "  <thead>\n",
4283 |        "    <tr style=\"text-align: right;\">\n",
4284 |        "      <th></th>\n",
4285 |        "      <th>employee</th>\n",
4286 |        "      <th>department</th>\n",
4287 |        "      <th>Year</th>\n",
4288 |        "    </tr>\n",
4289 |        "  </thead>\n",
4290 |        "  <tbody>\n",
4291 |        "    <tr>\n",
4292 |        "      <th>0</th>\n",
4293 |        "      <td>Julia</td>\n",
4294 |        "      <td>Data Science</td>\n",
4295 |        "      <td>2005</td>\n",
4296 |        "    </tr>\n",
4297 |        "    <tr>\n",
4298 |        "      <th>1</th>\n",
4299 |        "      <td>Marie</td>\n",
4300 |        "      <td>Web Development</td>\n",
4301 |        "      <td>2008</td>\n",
4302 |        "    </tr>\n",
4303 |        "    <tr>\n",
4304 |        "      <th>2</th>\n",
4305 |        "      <td>Adam</td>\n",
4306 |        "      <td>Data Science</td>\n",
4307 |        "      <td>2011</td>\n",
4308 |        "    </tr>\n",
4309 |        "    <tr>\n",
4310 |        "      <th>3</th>\n",
4311 |        "      <td>Nicole</td>\n",
4312 |        "      <td>Cyber Security</td>\n",
4313 |        "      <td>2002</td>\n",
4314 |        "    </tr>\n",
4315 |        "  </tbody>\n",
4316 |        "</table>\n",
4317 |        "</div>"
4318 |       ],
4319 |       "text/plain": [
4320 |        "  employee       department  Year\n",
4321 |        "0    Julia     Data Science  2005\n",
4322 |        "1    Marie  Web Development  2008\n",
4323 |        "2     Adam     Data Science  2011\n",
4324 |        "3   Nicole   Cyber Security  2002"
4325 |       ]
4326 |      },
4327 |      "execution_count": 78,
4328 |      "metadata": {},
4329 |      "output_type": "execute_result"
4330 |     }
4331 |    ],
4332 |    "source": [
4333 |     "df1"
4334 |    ]
4335 |   },
4336 |   {
4337 |    "cell_type": "code",
4338 |    "execution_count": 79,
4339 |    "id": "8951838a",
4340 |    "metadata": {
4341 |     "scrolled": true
4342 |    },
4343 |    "outputs": [
4344 |     {
4345 |      "data": {
4346 |       "text/html": [
4347 |        "<div>\n",
4348 |        "<style scoped>\n",
4349 |        "    .dataframe tbody tr th:only-of-type {\n",
4350 |        "        vertical-align: middle;\n",
4351 |        "    }\n",
4352 |        "\n",
4353 |        "    .dataframe tbody tr th {\n",
4354 |        "        vertical-align: top;\n",
4355 |        "    }\n",
4356 |        "\n",
4357 |        "    .dataframe thead th {\n",
4358 |        "        text-align: right;\n",
4359 |        "    }\n",
4360 |        "</style>\n",
4361 |        "<table border=\"1\" class=\"dataframe\">\n",
4362 |        "  <thead>\n",
4363 |        "    <tr style=\"text-align: right;\">\n",
4364 |        "      <th></th>\n",
4365 |        "      <th>employee</th>\n",
4366 |        "      <th>country</th>\n",
4367 |        "      <th>salary</th>\n",
4368 |        "    </tr>\n",
4369 |        "  </thead>\n",
4370 |        "  <tbody>\n",
4371 |        "    <tr>\n",
4372 |        "      <th>0</th>\n",
4373 |        "      <td>Nicole</td>\n",
4374 |        "      <td>Canada</td>\n",
4375 |        "      <td>22000</td>\n",
4376 |        "    </tr>\n",
4377 |        "    <tr>\n",
4378 |        "      <th>1</th>\n",
4379 |        "      <td>Adam</td>\n",
4380 |        "      <td>England</td>\n",
4381 |        "      <td>16000</td>\n",
4382 |        "    </tr>\n",
4383 |        "    <tr>\n",
4384 |        "      <th>2</th>\n",
4385 |        "      <td>Julia</td>\n",
4386 |        "      <td>USA</td>\n",
4387 |        "      <td>20000</td>\n",
4388 |        "    </tr>\n",
4389 |        "    <tr>\n",
4390 |        "      <th>3</th>\n",
4391 |        "      <td>Marie</td>\n",
4392 |        "      <td>Germany</td>\n",
4393 |        "      <td>17500</td>\n",
4394 |        "    </tr>\n",
4395 |        "  </tbody>\n",
4396 |        "</table>\n",
4397 |        "</div>"
4398 |       ],
4399 |       "text/plain": [
4400 |        "  employee  country salary\n",
4401 |        "0   Nicole   Canada  22000\n",
4402 |        "1     Adam  England  16000\n",
4403 |        "2    Julia      USA  20000\n",
4404 |        "3    Marie  Germany  17500"
4405 |       ]
4406 |      },
4407 |      "execution_count": 79,
4408 |      "metadata": {},
4409 |      "output_type": "execute_result"
4410 |     }
4411 |    ],
4412 |    "source": [
4413 |     "df2"
4414 |    ]
4415 |   },
4416 |   {
4417 |    "cell_type": "code",
4418 |    "execution_count": 80,
4419 |    "id": "affaebf0",
4420 |    "metadata": {},
4421 |    "outputs": [],
4422 |    "source": [
4423 |     "df3 = pd.merge(df1, df2)"
4424 |    ]
4425 |   },
4426 |   {
4427 |    "cell_type": "code",
4428 |    "execution_count": 81,
4429 |    "id": "c7b86528",
4430 |    "metadata": {},
4431 |    "outputs": [
4432 |     {
4433 |      "data": {
4434 |       "text/html": [
4435 |        "<div>\n",
4436 |        "<style scoped>\n",
4437 |        "    .dataframe tbody tr th:only-of-type {\n",
4438 |        "        vertical-align: middle;\n",
4439 |        "    }\n",
4440 |        "\n",
4441 |        "    .dataframe tbody tr th {\n",
4442 |        "        vertical-align: top;\n",
4443 |        "    }\n",
4444 |        "\n",
4445 |        "    .dataframe thead th {\n",
4446 |        "        text-align: right;\n",
4447 |        "    }\n",
4448 |        "</style>\n",
4449 |        "<table border=\"1\" class=\"dataframe\">\n",
4450 |        "  <thead>\n",
4451 |        "    <tr style=\"text-align: right;\">\n",
4452 |        "      <th></th>\n",
4453 |        "      <th>employee</th>\n",
4454 |        "      <th>department</th>\n",
4455 |        "      <th>Year</th>\n",
4456 |        "      <th>country</th>\n",
4457 |        "      <th>salary</th>\n",
4458 |        "    </tr>\n",
4459 |        "  </thead>\n",
4460 |        "  <tbody>\n",
4461 |        "    <tr>\n",
4462 |        "      <th>0</th>\n",
4463 |        "      <td>Julia</td>\n",
4464 |        "      <td>Data Science</td>\n",
4465 |        "      <td>2005</td>\n",
4466 |        "      <td>USA</td>\n",
4467 |        "      <td>20000</td>\n",
4468 |        "    </tr>\n",
4469 |        "    <tr>\n",
4470 |        "      <th>1</th>\n",
4471 |        "      <td>Marie</td>\n",
4472 |        "      <td>Web Development</td>\n",
4473 |        "      <td>2008</td>\n",
4474 |        "      <td>Germany</td>\n",
4475 |        "      <td>17500</td>\n",
4476 |        "    </tr>\n",
4477 |        "    <tr>\n",
4478 |        "      <th>2</th>\n",
4479 |        "      <td>Adam</td>\n",
4480 |        "      <td>Data Science</td>\n",
4481 |        "      <td>2011</td>\n",
4482 |        "      <td>England</td>\n",
4483 |        "      <td>16000</td>\n",
4484 |        "    </tr>\n",
4485 |        "    <tr>\n",
4486 |        "      <th>3</th>\n",
4487 |        "      <td>Nicole</td>\n",
4488 |        "      <td>Cyber Security</td>\n",
4489 |        "      <td>2002</td>\n",
4490 |        "      <td>Canada</td>\n",
4491 |        "      <td>22000</td>\n",
4492 |        "    </tr>\n",
4493 |        "  </tbody>\n",
4494 |        "</table>\n",
4495 |        "</div>"
4496 |       ],
4497 |       "text/plain": [
4498 |        "  employee       department  Year  country salary\n",
4499 |        "0    Julia     Data Science  2005      USA  20000\n",
4500 |        "1    Marie  Web Development  2008  Germany  17500\n",
4501 |        "2     Adam     Data Science  2011  England  16000\n",
4502 |        "3   Nicole   Cyber Security  2002   Canada  22000"
4503 |       ]
4504 |      },
4505 |      "execution_count": 81,
4506 |      "metadata": {},
4507 |      "output_type": "execute_result"
4508 |     }
4509 |    ],
4510 |    "source": [
4511 |     "df3"
4512 |    ]
4513 |   },
4514 |   {
4515 |    "cell_type": "code",
4516 |    "execution_count": 82,
4517 |    "id": "20772126",
4518 |    "metadata": {},
4519 |    "outputs": [],
4520 |    "source": [
4521 |     "df3.to_csv(\"new_data_set.csv\")"
4522 |    ]
4523 |   },
4524 |   {
4525 |    "cell_type": "code",
4526 |    "execution_count": 83,
4527 |    "id": "39ff724c",
4528 |    "metadata": {},
4529 |    "outputs": [],
4530 |    "source": [
4531 |     "df4 = pd.read_csv(\"new_data_set.csv\")"
4532 |    ]
4533 |   },
4534 |   {
4535 |    "cell_type": "code",
4536 |    "execution_count": 84,
4537 |    "id": "24ffa12c",
4538 |    "metadata": {
4539 |     "scrolled": true
4540 |    },
4541 |    "outputs": [
4542 |     {
4543 |      "data": {
4544 |       "text/html": [
4545 |        "<div>\n",
4546 |        "<style scoped>\n",
4547 |        "    .dataframe tbody tr th:only-of-type {\n",
4548 |        "        vertical-align: middle;\n",
4549 |        "    }\n",
4550 |        "\n",
4551 |        "    .dataframe tbody tr th {\n",
4552 |        "        vertical-align: top;\n",
4553 |        "    }\n",
4554 |        "\n",
4555 |        "    .dataframe thead th {\n",
4556 |        "        text-align: right;\n",
4557 |        "    }\n",
4558 |        "</style>\n",
4559 |        "<table border=\"1\" class=\"dataframe\">\n",
4560 |        "  <thead>\n",
4561 |        "    <tr style=\"text-align: right;\">\n",
4562 |        "      <th></th>\n",
4563 |        "      <th>Unnamed: 0</th>\n",
4564 |        "      <th>employee</th>\n",
4565 |        "      <th>department</th>\n",
4566 |        "      <th>Year</th>\n",
4567 |        "      <th>country</th>\n",
4568 |        "      <th>salary</th>\n",
4569 |        "    </tr>\n",
4570 |        "  </thead>\n",
4571 |        "  <tbody>\n",
4572 |        "    <tr>\n",
4573 |        "      <th>0</th>\n",
4574 |        "      <td>0</td>\n",
4575 |        "      <td>Julia</td>\n",
4576 |        "      <td>Data Science</td>\n",
4577 |        "      <td>2005</td>\n",
4578 |        "      <td>USA</td>\n",
4579 |        "      <td>20000</td>\n",
4580 |        "    </tr>\n",
4581 |        "    <tr>\n",
4582 |        "      <th>1</th>\n",
4583 |        "      <td>1</td>\n",
4584 |        "      <td>Marie</td>\n",
4585 |        "      <td>Web Development</td>\n",
4586 |        "      <td>2008</td>\n",
4587 |        "      <td>Germany</td>\n",
4588 |        "      <td>17500</td>\n",
4589 |        "    </tr>\n",
4590 |        "    <tr>\n",
4591 |        "      <th>2</th>\n",
4592 |        "      <td>2</td>\n",
4593 |        "      <td>Adam</td>\n",
4594 |        "      <td>Data Science</td>\n",
4595 |        "      <td>2011</td>\n",
4596 |        "      <td>England</td>\n",
4597 |        "      <td>16000</td>\n",
4598 |        "    </tr>\n",
4599 |        "    <tr>\n",
4600 |        "      <th>3</th>\n",
4601 |        "      <td>3</td>\n",
4602 |        "      <td>Nicole</td>\n",
4603 |        "      <td>Cyber Security</td>\n",
4604 |        "      <td>2002</td>\n",
4605 |        "      <td>Canada</td>\n",
4606 |        "      <td>22000</td>\n",
4607 |        "    </tr>\n",
4608 |        "  </tbody>\n",
4609 |        "</table>\n",
4610 |        "</div>"
4611 |       ],
4612 |       "text/plain": [
4613 |        "   Unnamed: 0 employee       department  Year  country  salary\n",
4614 |        "0           0    Julia     Data Science  2005      USA   20000\n",
4615 |        "1           1    Marie  Web Development  2008  Germany   17500\n",
4616 |        "2           2     Adam     Data Science  2011  England   16000\n",
4617 |        "3           3   Nicole   Cyber Security  2002   Canada   22000"
4618 |       ]
4619 |      },
4620 |      "execution_count": 84,
4621 |      "metadata": {},
4622 |      "output_type": "execute_result"
4623 |     }
4624 |    ],
4625 |    "source": [
4626 |     "df4"
4627 |    ]
4628 |   },
4629 |   {
4630 |    "cell_type": "code",
4631 |    "execution_count": 85,
4632 |    "id": "da56db67",
4633 |    "metadata": {},
4634 |    "outputs": [],
4635 |    "source": [
4636 |     "df5 = pd.read_csv(\"new_data_set.csv\", index_col = 0)"
4637 |    ]
4638 |   },
4639 |   {
4640 |    "cell_type": "code",
4641 |    "execution_count": 86,
4642 |    "id": "d76351a3",
4643 |    "metadata": {},
4644 |    "outputs": [
4645 |     {
4646 |      "data": {
4647 |       "text/html": [
4648 |        "<div>\n",
4649 |        "<style scoped>\n",
4650 |        "    .dataframe tbody tr th:only-of-type {\n",
4651 |        "        vertical-align: middle;\n",
4652 |        "    }\n",
4653 |        "\n",
4654 |        "    .dataframe tbody tr th {\n",
4655 |        "        vertical-align: top;\n",
4656 |        "    }\n",
4657 |        "\n",
4658 |        "    .dataframe thead th {\n",
4659 |        "        text-align: right;\n",
4660 |        "    }\n",
4661 |        "</style>\n",
4662 |        "<table border=\"1\" class=\"dataframe\">\n",
4663 |        "  <thead>\n",
4664 |        "    <tr style=\"text-align: right;\">\n",
4665 |        "      <th></th>\n",
4666 |        "      <th>employee</th>\n",
4667 |        "      <th>department</th>\n",
4668 |        "      <th>Year</th>\n",
4669 |        "      <th>country</th>\n",
4670 |        "      <th>salary</th>\n",
4671 |        "    </tr>\n",
4672 |        "  </thead>\n",
4673 |        "  <tbody>\n",
4674 |        "    <tr>\n",
4675 |        "      <th>0</th>\n",
4676 |        "      <td>Julia</td>\n",
4677 |        "      <td>Data Science</td>\n",
4678 |        "      <td>2005</td>\n",
4679 |        "      <td>USA</td>\n",
4680 |        "      <td>20000</td>\n",
4681 |        "    </tr>\n",
4682 |        "    <tr>\n",
4683 |        "      <th>1</th>\n",
4684 |        "      <td>Marie</td>\n",
4685 |        "      <td>Web Development</td>\n",
4686 |        "      <td>2008</td>\n",
4687 |        "      <td>Germany</td>\n",
4688 |        "      <td>17500</td>\n",
4689 |        "    </tr>\n",
4690 |        "    <tr>\n",
4691 |        "      <th>2</th>\n",
4692 |        "      <td>Adam</td>\n",
4693 |        "      <td>Data Science</td>\n",
4694 |        "      <td>2011</td>\n",
4695 |        "      <td>England</td>\n",
4696 |        "      <td>16000</td>\n",
4697 |        "    </tr>\n",
4698 |        "    <tr>\n",
4699 |        "      <th>3</th>\n",
4700 |        "      <td>Nicole</td>\n",
4701 |        "      <td>Cyber Security</td>\n",
4702 |        "      <td>2002</td>\n",
4703 |        "      <td>Canada</td>\n",
4704 |        "      <td>22000</td>\n",
4705 |        "    </tr>\n",
4706 |        "  </tbody>\n",
4707 |        "</table>\n",
4708 |        "</div>"
4709 |       ],
4710 |       "text/plain": [
4711 |        "  employee       department  Year  country  salary\n",
4712 |        "0    Julia     Data Science  2005      USA   20000\n",
4713 |        "1    Marie  Web Development  2008  Germany   17500\n",
4714 |        "2     Adam     Data Science  2011  England   16000\n",
4715 |        "3   Nicole   Cyber Security  2002   Canada   22000"
4716 |       ]
4717 |      },
4718 |      "execution_count": 86,
4719 |      "metadata": {},
4720 |      "output_type": "execute_result"
4721 |     }
4722 |    ],
4723 |    "source": [
4724 |     "df5"
4725 |    ]
4726 |   },
4727 |   {
4728 |    "cell_type": "code",
4729 |    "execution_count": 87,
4730 |    "id": "ba2c642e",
4731 |    "metadata": {},
4732 |    "outputs": [],
4733 |    "source": [
4734 |     "df3.to_csv(\"new_data_set2.csv\", index = False)"
4735 |    ]
4736 |   },
4737 |   {
4738 |    "cell_type": "code",
4739 |    "execution_count": 88,
4740 |    "id": "37c53d52",
4741 |    "metadata": {},
4742 |    "outputs": [],
4743 |    "source": [
4744 |     "df6 = pd.read_csv(\"new_data_set2.csv\")"
4745 |    ]
4746 |   },
4747 |   {
4748 |    "cell_type": "code",
4749 |    "execution_count": 89,
4750 |    "id": "cdeac636",
4751 |    "metadata": {
4752 |     "scrolled": true
4753 |    },
4754 |    "outputs": [
4755 |     {
4756 |      "data": {
4757 |       "text/html": [
4758 |        "<div>\n",
4759 |        "<style scoped>\n",
4760 |        "    .dataframe tbody tr th:only-of-type {\n",
4761 |        "        vertical-align: middle;\n",
4762 |        "    }\n",
4763 |        "\n",
4764 |        "    .dataframe tbody tr th {\n",
4765 |        "        vertical-align: top;\n",
4766 |        "    }\n",
4767 |        "\n",
4768 |        "    .dataframe thead th {\n",
4769 |        "        text-align: right;\n",
4770 |        "    }\n",
4771 |        "</style>\n",
4772 |        "<table border=\"1\" class=\"dataframe\">\n",
4773 |        "  <thead>\n",
4774 |        "    <tr style=\"text-align: right;\">\n",
4775 |        "      <th></th>\n",
4776 |        "      <th>employee</th>\n",
4777 |        "      <th>department</th>\n",
4778 |        "      <th>Year</th>\n",
4779 |        "      <th>country</th>\n",
4780 |        "      <th>salary</th>\n",
4781 |        "    </tr>\n",
4782 |        "  </thead>\n",
4783 |        "  <tbody>\n",
4784 |        "    <tr>\n",
4785 |        "      <th>0</th>\n",
4786 |        "      <td>Julia</td>\n",
4787 |        "      <td>Data Science</td>\n",
4788 |        "      <td>2005</td>\n",
4789 |        "      <td>USA</td>\n",
4790 |        "      <td>20000</td>\n",
4791 |        "    </tr>\n",
4792 |        "    <tr>\n",
4793 |        "      <th>1</th>\n",
4794 |        "      <td>Marie</td>\n",
4795 |        "      <td>Web Development</td>\n",
4796 |        "      <td>2008</td>\n",
4797 |        "      <td>Germany</td>\n",
4798 |        "      <td>17500</td>\n",
4799 |        "    </tr>\n",
4800 |        "    <tr>\n",
4801 |        "      <th>2</th>\n",
4802 |        "      <td>Adam</td>\n",
4803 |        "      <td>Data Science</td>\n",
4804 |        "      <td>2011</td>\n",
4805 |        "      <td>England</td>\n",
4806 |        "      <td>16000</td>\n",
4807 |        "    </tr>\n",
4808 |        "    <tr>\n",
4809 |        "      <th>3</th>\n",
4810 |        "      <td>Nicole</td>\n",
4811 |        "      <td>Cyber Security</td>\n",
4812 |        "      <td>2002</td>\n",
4813 |        "      <td>Canada</td>\n",
4814 |        "      <td>22000</td>\n",
4815 |        "    </tr>\n",
4816 |        "  </tbody>\n",
4817 |        "</table>\n",
4818 |        "</div>"
4819 |       ],
4820 |       "text/plain": [
4821 |        "  employee       department  Year  country  salary\n",
4822 |        "0    Julia     Data Science  2005      USA   20000\n",
4823 |        "1    Marie  Web Development  2008  Germany   17500\n",
4824 |        "2     Adam     Data Science  2011  England   16000\n",
4825 |        "3   Nicole   Cyber Security  2002   Canada   22000"
4826 |       ]
4827 |      },
4828 |      "execution_count": 89,
4829 |      "metadata": {},
4830 |      "output_type": "execute_result"
4831 |     }
4832 |    ],
4833 |    "source": [
4834 |     "df6"
4835 |    ]
4836 |   },
4837 |   {
4838 |    "cell_type": "markdown",
4839 |    "id": "3b7e4e3b",
4840 |    "metadata": {},
4841 |    "source": [
4842 |     "## Outputting as an Excel File"
4843 |    ]
4844 |   },
4845 |   {
4846 |    "cell_type": "code",
4847 |    "execution_count": 90,
4848 |    "id": "40e30ce6",
4849 |    "metadata": {},
4850 |    "outputs": [],
4851 |    "source": [
4852 |     "import pandas as pd"
4853 |    ]
4854 |   },
4855 |   {
4856 |    "cell_type": "code",
4857 |    "execution_count": 91,
4858 |    "id": "ecaaf3fc",
4859 |    "metadata": {},
4860 |    "outputs": [],
4861 |    "source": [
4862 |     "df1 = pd.DataFrame({'employee': ['Julia', 'Marie', 'Adam', 'Nicole'],\n",
4863 |     "                     'department': ['Data Science', 'Web Development', 'Data Science', 'Cyber Security'],\n",
4864 |     "                     'Year': ['2005', '2008', '2011', '2002']})\n",
4865 |     "   \n",
4866 |     "df2 = pd.DataFrame({'employee': ['Nicole', 'Adam', 'Julia', 'Marie'],\n",
4867 |     "                          'country': ['Canada', 'England', 'USA', 'Germany'],\n",
4868 |     "                          'salary': ['22000', '16000', '20000', '17500']})  "
4869 |    ]
4870 |   },
4871 |   {
4872 |    "cell_type": "code",
4873 |    "execution_count": 92,
4874 |    "id": "6bd6a284",
4875 |    "metadata": {},
4876 |    "outputs": [],
4877 |    "source": [
4878 |     "df3 = pd.merge(df1, df2)"
4879 |    ]
4880 |   },
4881 |   {
4882 |    "cell_type": "code",
4883 |    "execution_count": 93,
4884 |    "id": "fe73506a",
4885 |    "metadata": {},
4886 |    "outputs": [
4887 |     {
4888 |      "data": {
4889 |       "text/html": [
4890 |        "<div>\n",
4891 |        "<style scoped>\n",
4892 |        "    .dataframe tbody tr th:only-of-type {\n",
4893 |        "        vertical-align: middle;\n",
4894 |        "    }\n",
4895 |        "\n",
4896 |        "    .dataframe tbody tr th {\n",
4897 |        "        vertical-align: top;\n",
4898 |        "    }\n",
4899 |        "\n",
4900 |        "    .dataframe thead th {\n",
4901 |        "        text-align: right;\n",
4902 |        "    }\n",
4903 |        "</style>\n",
4904 |        "<table border=\"1\" class=\"dataframe\">\n",
4905 |        "  <thead>\n",
4906 |        "    <tr style=\"text-align: right;\">\n",
4907 |        "      <th></th>\n",
4908 |        "      <th>employee</th>\n",
4909 |        "      <th>department</th>\n",
4910 |        "      <th>Year</th>\n",
4911 |        "      <th>country</th>\n",
4912 |        "      <th>salary</th>\n",
4913 |        "    </tr>\n",
4914 |        "  </thead>\n",
4915 |        "  <tbody>\n",
4916 |        "    <tr>\n",
4917 |        "      <th>0</th>\n",
4918 |        "      <td>Julia</td>\n",
4919 |        "      <td>Data Science</td>\n",
4920 |        "      <td>2005</td>\n",
4921 |        "      <td>USA</td>\n",
4922 |        "      <td>20000</td>\n",
4923 |        "    </tr>\n",
4924 |        "    <tr>\n",
4925 |        "      <th>1</th>\n",
4926 |        "      <td>Marie</td>\n",
4927 |        "      <td>Web Development</td>\n",
4928 |        "      <td>2008</td>\n",
4929 |        "      <td>Germany</td>\n",
4930 |        "      <td>17500</td>\n",
4931 |        "    </tr>\n",
4932 |        "    <tr>\n",
4933 |        "      <th>2</th>\n",
4934 |        "      <td>Adam</td>\n",
4935 |        "      <td>Data Science</td>\n",
4936 |        "      <td>2011</td>\n",
4937 |        "      <td>England</td>\n",
4938 |        "      <td>16000</td>\n",
4939 |        "    </tr>\n",
4940 |        "    <tr>\n",
4941 |        "      <th>3</th>\n",
4942 |        "      <td>Nicole</td>\n",
4943 |        "      <td>Cyber Security</td>\n",
4944 |        "      <td>2002</td>\n",
4945 |        "      <td>Canada</td>\n",
4946 |        "      <td>22000</td>\n",
4947 |        "    </tr>\n",
4948 |        "  </tbody>\n",
4949 |        "</table>\n",
4950 |        "</div>"
4951 |       ],
4952 |       "text/plain": [
4953 |        "  employee       department  Year  country salary\n",
4954 |        "0    Julia     Data Science  2005      USA  20000\n",
4955 |        "1    Marie  Web Development  2008  Germany  17500\n",
4956 |        "2     Adam     Data Science  2011  England  16000\n",
4957 |        "3   Nicole   Cyber Security  2002   Canada  22000"
4958 |       ]
4959 |      },
4960 |      "execution_count": 93,
4961 |      "metadata": {},
4962 |      "output_type": "execute_result"
4963 |     }
4964 |    ],
4965 |    "source": [
4966 |     "df3"
4967 |    ]
4968 |   },
4969 |   {
4970 |    "cell_type": "code",
4971 |    "execution_count": 94,
4972 |    "id": "c8142a9c",
4973 |    "metadata": {},
4974 |    "outputs": [],
4975 |    "source": [
4976 |     "df3.to_excel(\"excel_sample.xlsx\", sheet_name = \"new_sheet1\", index = False)"
4977 |    ]
4978 |   },
4979 |   {
4980 |    "cell_type": "code",
4981 |    "execution_count": 95,
4982 |    "id": "00497451",
4983 |    "metadata": {},
4984 |    "outputs": [],
4985 |    "source": [
4986 |     "df4 = pd.read_excel(\"excel_sample.xlsx\")"
4987 |    ]
4988 |   },
4989 |   {
4990 |    "cell_type": "code",
4991 |    "execution_count": 96,
4992 |    "id": "7c8c0584",
4993 |    "metadata": {},
4994 |    "outputs": [
4995 |     {
4996 |      "data": {
4997 |       "text/html": [
4998 |        "<div>\n",
4999 |        "<style scoped>\n",
5000 |        "    .dataframe tbody tr th:only-of-type {\n",
5001 |        "        vertical-align: middle;\n",
5002 |        "    }\n",
5003 |        "\n",
5004 |        "    .dataframe tbody tr th {\n",
5005 |        "        vertical-align: top;\n",
5006 |        "    }\n",
5007 |        "\n",
5008 |        "    .dataframe thead th {\n",
5009 |        "        text-align: right;\n",
5010 |        "    }\n",
5011 |        "</style>\n",
5012 |        "<table border=\"1\" class=\"dataframe\">\n",
5013 |        "  <thead>\n",
5014 |        "    <tr style=\"text-align: right;\">\n",
5015 |        "      <th></th>\n",
5016 |        "      <th>employee</th>\n",
5017 |        "      <th>department</th>\n",
5018 |        "      <th>Year</th>\n",
5019 |        "      <th>country</th>\n",
5020 |        "      <th>salary</th>\n",
5021 |        "    </tr>\n",
5022 |        "  </thead>\n",
5023 |        "  <tbody>\n",
5024 |        "    <tr>\n",
5025 |        "      <th>0</th>\n",
5026 |        "      <td>Julia</td>\n",
5027 |        "      <td>Data Science</td>\n",
5028 |        "      <td>2005</td>\n",
5029 |        "      <td>USA</td>\n",
5030 |        "      <td>20000</td>\n",
5031 |        "    </tr>\n",
5032 |        "    <tr>\n",
5033 |        "      <th>1</th>\n",
5034 |        "      <td>Marie</td>\n",
5035 |        "      <td>Web Development</td>\n",
5036 |        "      <td>2008</td>\n",
5037 |        "      <td>Germany</td>\n",
5038 |        "      <td>17500</td>\n",
5039 |        "    </tr>\n",
5040 |        "    <tr>\n",
5041 |        "      <th>2</th>\n",
5042 |        "      <td>Adam</td>\n",
5043 |        "      <td>Data Science</td>\n",
5044 |        "      <td>2011</td>\n",
5045 |        "      <td>England</td>\n",
5046 |        "      <td>16000</td>\n",
5047 |        "    </tr>\n",
5048 |        "    <tr>\n",
5049 |        "      <th>3</th>\n",
5050 |        "      <td>Nicole</td>\n",
5051 |        "      <td>Cyber Security</td>\n",
5052 |        "      <td>2002</td>\n",
5053 |        "      <td>Canada</td>\n",
5054 |        "      <td>22000</td>\n",
5055 |        "    </tr>\n",
5056 |        "  </tbody>\n",
5057 |        "</table>\n",
5058 |        "</div>"
5059 |       ],
5060 |       "text/plain": [
5061 |        "  employee       department  Year  country  salary\n",
5062 |        "0    Julia     Data Science  2005      USA   20000\n",
5063 |        "1    Marie  Web Development  2008  Germany   17500\n",
5064 |        "2     Adam     Data Science  2011  England   16000\n",
5065 |        "3   Nicole   Cyber Security  2002   Canada   22000"
5066 |       ]
5067 |      },
5068 |      "execution_count": 96,
5069 |      "metadata": {},
5070 |      "output_type": "execute_result"
5071 |     }
5072 |    ],
5073 |    "source": [
5074 |     "df4"
5075 |    ]
5076 |   }
5077 |  ],
5078 |  "metadata": {
5079 |   "kernelspec": {
5080 |    "display_name": "Python 3",
5081 |    "language": "python",
5082 |    "name": "python3"
5083 |   },
5084 |   "language_info": {
5085 |    "codemirror_mode": {
5086 |     "name": "ipython",
5087 |     "version": 3
5088 |    },
5089 |    "file_extension": ".py",
5090 |    "mimetype": "text/x-python",
5091 |    "name": "python",
5092 |    "nbconvert_exporter": "python",
5093 |    "pygments_lexer": "ipython3",
5094 |    "version": "3.8.8"
5095 |   }
5096 |  },
5097 |  "nbformat": 4,
5098 |  "nbformat_minor": 5
5099 | }
5100 | 


--------------------------------------------------------------------------------