File size: 35,141 Bytes
f61d311 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 |
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "code",
"execution_count": 82,
"metadata": {
"cellView": "form",
"id": "AXI2uCSkxx7m"
},
"outputs": [],
"source": [
"#@title Setup\n",
"\n",
"%%capture\n",
"!pip install networkx pulp numpy pandas\n",
"\n",
"!rm -rf ./data/\n",
"!mkdir -p ./data/\n",
"!wget -c -O ./data/lastfm_asia.zip \"https://snap.stanford.edu/data/lastfm_asia.zip\"\n",
"!unzip -q ./data/lastfm_asia.zip -d ./data/"
]
},
{
"cell_type": "code",
"source": [
"#@title Problem 3: Linear Programming\n",
"\n",
"\n",
"from pulp import *\n",
"from IPython.display import HTML, display\n",
"\n",
"def display_table(table):\n",
" display(HTML(\n",
" '<table><tr>{}</tr></table>'.format(\n",
" '</tr><tr>'.join(\n",
" '<td>{}</td>'.format('</td><td>'.join(str(_) for _ in row)) for row in table)\n",
" )\n",
" ))\n",
"\n",
"problem = LpProblem(\"MSML_602_Midterm_Q3\", LpMaximize)\n",
"\n",
"X = LpVariable(\"X\", cat=\"Integer\")\n",
"Y = LpVariable(\"Y\", cat=\"Integer\")\n",
"\n",
"problem += (5 * X) + (3 * Y), \"Objective\"\n",
"problem += X + (2 * Y) <= 14, \"Constraint 1\"\n",
"problem += (3* X) - Y >= 0, \"Constraint 2\"\n",
"problem += X - Y <= 2, \"Constraint 3\"\n",
"\n",
"problem.solve()\n",
"print(\"Solution:\\n\")\n",
"\n",
"data = [[\"Variable\", \"Value\"]] + [[v.name, v.varValue] for v in problem.variables()]\n",
"data += [[\"Max value for objective function: \", problem.objective.value()]]\n",
"display_table(data)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 140
},
"cellView": "form",
"id": "ALmlZnbcx-9e",
"outputId": "45e2c507-3265-4b22-e21a-2d6dbd72f05f"
},
"execution_count": 83,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Solution:\n",
"\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"<table><tr><td>Variable</td><td>Value</td></tr><tr><td>X</td><td>6.0</td></tr><tr><td>Y</td><td>4.0</td></tr><tr><td>Max value for objective function: </td><td>42.0</td></tr></table>"
]
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"source": [
"#@title Problem 5: Graph Metrics\n",
"\n",
"import pandas as pd \n",
"import networkx as nx\n",
"import matplotlib.pyplot as plt\n",
"\n",
"df = pd.read_csv(\"/content/data/lasftm_asia/lastfm_asia_edges.csv\")\n",
"G = nx.from_pandas_edgelist(df, source=\"node_1\", target=\"node_2\")\n",
"shortest_path = nx.shortest_path_length(G, 0)\n",
"del shortest_path[0]\n",
"num = len(shortest_path)\n",
"total_length = sum([shortest_path[k] for k in shortest_path])\n",
"avg_shortest_path = total_length / num\n",
"print(f\"The average shortest path length from node 0 to all other nodes is: {avg_shortest_path}\")"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"cellView": "form",
"id": "87mMC-B1yJoq",
"outputId": "83ff28ec-7d51-4f6a-ced6-358538a58f83"
},
"execution_count": 84,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"The average shortest path length from node 0 to all other nodes is: 5.651974288337925\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"## Problem 6: Extracting Webpage Data"
],
"metadata": {
"id": "mAiJRhb5iW5O"
}
},
{
"cell_type": "code",
"source": [
"#@title Scraping result\n",
"\n",
"import requests\n",
"from bs4 import BeautifulSoup\n",
"import pandas as pd \n",
"import numpy as np\n",
"\n",
"page = requests.get(\"https://www.worldometers.info/coronavirus/#countries\")\n",
"html = page.content\n",
"\n",
"soup = BeautifulSoup(html, 'html.parser')\n",
"table = soup.find(\"table\", {\"id\": \"main_table_countries_today\"})\n",
"\n",
"cols = [\n",
" '#', 'Country', 'TotalCases', 'NewCases', 'TotalDeaths', 'NewDeaths', 'TotalRecovered',\n",
" 'NewRecovered','ActiveCases','Serious,Critical','TotalCases/1M pop','Deaths/1M pop', \n",
" 'TotalTests', 'Tests/1M pop', 'Population', 'Continent', '1 Case every X ppl', '1 Death every X ppl',\n",
" '1 Test every X ppl', 'New Cases/1M pop', 'New Deaths/1M pop', 'Active Cases/1M pop'\n",
"]\n",
"\n",
"tbody = table.find(\"tbody\")\n",
"rows = tbody.find_all(\"tr\")\n",
"\n",
"data = []\n",
"for row in rows:\n",
" cells = row.find_all(\"td\")\n",
" values = [c.text for c in cells]\n",
" data.append(values)\n",
"\n",
"def sanitize_country_number(row):\n",
" val = row[\"#\"]\n",
" if not val.strip():\n",
" return np.NaN\n",
" else:\n",
" return val\n",
"\n",
"def fill_active_cases(row):\n",
" val = row[\"ActiveCases\"]\n",
" if not np.isnan(val):\n",
" return val\n",
" active_per_1_mil = row[\"Active Cases/1M pop\"]\n",
" if np.isnan(active_per_1_mil):\n",
" return np.nan\n",
" population = row[\"Population\"]\n",
" return (active_per_1_mil/1000000) * population\n",
"\n",
"def to_float(col):\n",
" def mapper(row):\n",
" if row[col] == \"N/A\":\n",
" return np.NaN\n",
" val = row[col]\n",
" val = val.replace(\",\", \"\").strip()\n",
" if not val:\n",
" return np.NaN\n",
" return float(val)\n",
" return mapper \n",
"\n",
"df = pd.DataFrame(data, columns=cols)\n",
"df.replace(r\"\\n\", \"\", regex=True, inplace=True)\n",
"\n",
"df.head()\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 386
},
"cellView": "form",
"id": "Ay-ceRkkzcVg",
"outputId": "3b1e8535-f211-45ba-9b90-85c279e522ec"
},
"execution_count": 85,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" # Country TotalCases NewCases TotalDeaths NewDeaths \\\n",
"0 North America 118,308,960 +16,354 1,557,219 +76 \n",
"1 Asia 195,343,819 +168,618 1,491,630 +230 \n",
"2 Europe 235,496,414 +41,389 1,948,669 +165 \n",
"3 South America 64,557,158 +10,126 1,333,737 +79 \n",
"4 Oceania 12,691,699 +3,057 21,779 +9 \n",
"\n",
" TotalRecovered NewRecovered ActiveCases Serious,Critical ... TotalTests \\\n",
"0 113,762,872 +16,362 2,988,869 7,881 ... \n",
"1 188,186,652 +78,736 5,665,537 9,159 ... \n",
"2 229,427,346 +175,758 4,120,399 7,685 ... \n",
"3 62,884,992 +7,699 338,429 10,119 ... \n",
"4 12,512,305 157,615 97 ... \n",
"\n",
" Tests/1M pop Population Continent 1 Case every X ppl \\\n",
"0 North America \n",
"1 Asia \n",
"2 Europe \n",
"3 South America \n",
"4 Australia/Oceania \n",
"\n",
" 1 Death every X ppl 1 Test every X ppl New Cases/1M pop New Deaths/1M pop \\\n",
"0 \n",
"1 \n",
"2 \n",
"3 \n",
"4 \n",
"\n",
" Active Cases/1M pop \n",
"0 \n",
"1 \n",
"2 \n",
"3 \n",
"4 \n",
"\n",
"[5 rows x 22 columns]"
],
"text/html": [
"\n",
" <div id=\"df-ba4843e7-ab30-4f7d-ab50-7ddf8afb1bbb\">\n",
" <div class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>#</th>\n",
" <th>Country</th>\n",
" <th>TotalCases</th>\n",
" <th>NewCases</th>\n",
" <th>TotalDeaths</th>\n",
" <th>NewDeaths</th>\n",
" <th>TotalRecovered</th>\n",
" <th>NewRecovered</th>\n",
" <th>ActiveCases</th>\n",
" <th>Serious,Critical</th>\n",
" <th>...</th>\n",
" <th>TotalTests</th>\n",
" <th>Tests/1M pop</th>\n",
" <th>Population</th>\n",
" <th>Continent</th>\n",
" <th>1 Case every X ppl</th>\n",
" <th>1 Death every X ppl</th>\n",
" <th>1 Test every X ppl</th>\n",
" <th>New Cases/1M pop</th>\n",
" <th>New Deaths/1M pop</th>\n",
" <th>Active Cases/1M pop</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td></td>\n",
" <td>North America</td>\n",
" <td>118,308,960</td>\n",
" <td>+16,354</td>\n",
" <td>1,557,219</td>\n",
" <td>+76</td>\n",
" <td>113,762,872</td>\n",
" <td>+16,362</td>\n",
" <td>2,988,869</td>\n",
" <td>7,881</td>\n",
" <td>...</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>North America</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td></td>\n",
" <td>Asia</td>\n",
" <td>195,343,819</td>\n",
" <td>+168,618</td>\n",
" <td>1,491,630</td>\n",
" <td>+230</td>\n",
" <td>188,186,652</td>\n",
" <td>+78,736</td>\n",
" <td>5,665,537</td>\n",
" <td>9,159</td>\n",
" <td>...</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>Asia</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td></td>\n",
" <td>Europe</td>\n",
" <td>235,496,414</td>\n",
" <td>+41,389</td>\n",
" <td>1,948,669</td>\n",
" <td>+165</td>\n",
" <td>229,427,346</td>\n",
" <td>+175,758</td>\n",
" <td>4,120,399</td>\n",
" <td>7,685</td>\n",
" <td>...</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>Europe</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td></td>\n",
" <td>South America</td>\n",
" <td>64,557,158</td>\n",
" <td>+10,126</td>\n",
" <td>1,333,737</td>\n",
" <td>+79</td>\n",
" <td>62,884,992</td>\n",
" <td>+7,699</td>\n",
" <td>338,429</td>\n",
" <td>10,119</td>\n",
" <td>...</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>South America</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td></td>\n",
" <td>Oceania</td>\n",
" <td>12,691,699</td>\n",
" <td>+3,057</td>\n",
" <td>21,779</td>\n",
" <td>+9</td>\n",
" <td>12,512,305</td>\n",
" <td></td>\n",
" <td>157,615</td>\n",
" <td>97</td>\n",
" <td>...</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>Australia/Oceania</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 22 columns</p>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-ba4843e7-ab30-4f7d-ab50-7ddf8afb1bbb')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-ba4843e7-ab30-4f7d-ab50-7ddf8afb1bbb button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-ba4843e7-ab30-4f7d-ab50-7ddf8afb1bbb');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
]
},
"metadata": {},
"execution_count": 85
}
]
},
{
"cell_type": "code",
"source": [
"#@title Data sanitization / generation\n",
"\n",
"#@markdown Some of the countries (actually ships, in this case) did not have any population data, so I excluded those records from the dataset.\n",
"\n",
"#@markdown Some countries didn't have data for exact active cases, but had data for **active cases per 1 million population**. \n",
"#@markdown For these countries, I calculated their active cases by using the active cases per 1 million population data as follows: \n",
"\n",
"#@markdown ```Active Cases = (Active cases per 1 million population / 1,000,000) * Population```\n",
"\n",
"df[\"country_number\"] = df.apply(sanitize_country_number, axis=1)\n",
"\n",
"data_by_country = df[df[\"country_number\"].notna()].copy()\n",
"data_by_country[\"ActiveCases\"] = data_by_country.apply(to_float(\"ActiveCases\"), axis=1)\n",
"data_by_country[\"Active Cases/1M pop\"] = data_by_country.apply(to_float(\"Active Cases/1M pop\"), axis=1)\n",
"data_by_country[\"Population\"] = data_by_country.apply(to_float(\"Population\"), axis=1)\n",
"data_by_country[\"ActiveCases\"] = data_by_country.apply(fill_active_cases, axis=1)\n",
"data_by_country[data_by_country[\"ActiveCases\"] == \"N/A\"].head(20)\n",
"aggregated = data_by_country.groupby(\"Country\").agg({'ActiveCases':'mean', 'Population':'sum'}, as_index=False)\n",
"aggregated.reset_index(inplace=True)\n",
"dropped_countries = aggregated[aggregated[\"Population\"] == 0 ]\n",
"aggregated = aggregated[aggregated[\"Population\"] != 0 ]\n",
"aggregated[\"PercentageInfected\"] = aggregated.apply(lambda x: x[\"ActiveCases\"]/x[\"Population\"], axis=1)\n",
"aggregated.sort_values([\"PercentageInfected\"], ascending=False, inplace=True)\n",
"\n",
"print(\"These were the countries(ships) that didn't have population data:\\n\")\n",
"print(dropped_countries)\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"cellView": "form",
"id": "Roitzj22-VO5",
"outputId": "5dc61fa2-31c9-4fa4-828c-c9f88fb449e2"
},
"execution_count": 86,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"These were the countries(ships) that didn't have population data:\n",
"\n",
" Country ActiveCases Population\n",
"56 Diamond Princess 0.0 0.0\n",
"120 MS Zaandam 0.0 0.0\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"#@title Average active cases & the proportion of the total population affected\n",
"\n",
"from IPython.display import HTML, display\n",
"\n",
"def display_table(table):\n",
" display(HTML(\n",
" '<table><tr>{}</tr></table>'.format(\n",
" '</tr><tr>'.join(\n",
" '<td>{}</td>'.format('</td><td>'.join(str(_) for _ in row)) for row in table)\n",
" )\n",
" ))\n",
"\n",
"avg_active_cases = aggregated[\"ActiveCases\"].mean()\n",
"\n",
"aggr = aggregated.agg({\"ActiveCases\": \"sum\", \"Population\": \"sum\"}, as_index=False)\n",
"final_df = aggr.to_frame().T\n",
"final_df[\"PercentageInfected\"] = final_df.apply(lambda x: (x[\"ActiveCases\"]/x[\"Population\"]) * 100, axis=1)\n",
"percentage_infected = final_df[\"PercentageInfected\"].to_numpy()[0]\n",
"\n",
"display(HTML(\n",
" \"\"\"\n",
" <h3>Result:</h3>\n",
" <br>\n",
" <table border=\"1\">\n",
" <tr>\n",
" <th align=\"left\">Average active cases:</th>\n",
" <td>{0:.2f}</td>\n",
" </tr>\n",
" <tr>\n",
" <th align=\"left\">Proportion of total <br>population currently infected:</th>\n",
" <td>{1:.2f}%</td>\n",
" </tr>\n",
" </table>\n",
" <br>\n",
" \"\"\".format(avg_active_cases, percentage_infected))\n",
")\n",
"\n",
"\n",
"print(\"\"\"\n",
"I was unsure whether the problem wanted the percentage of the population\n",
"affected for each country, so I have included the percentage for each country \n",
"as well, just in case:\n",
"\"\"\")\n",
"aggregated.head()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 439
},
"cellView": "form",
"id": "lRtwSfqSAPAY",
"outputId": "a7037d5d-fbd6-48b3-e47b-32090720dfd1"
},
"execution_count": 87,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"\n",
" <h3>Result:</h3>\n",
" <br>\n",
" <table border=\"1\">\n",
" <tr>\n",
" <th align=\"left\">Average active cases:</th>\n",
" <td>60038.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th align=\"left\">Proportion of total <br>population currently infected:</th>\n",
" <td>0.17%</td>\n",
" </tr>\n",
" </table>\n",
" <br>\n",
" "
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
"I was unsure whether the problem wanted the percentage of the population\n",
"affected for each country, so I have included the percentage for each country \n",
"as well, just in case:\n",
"\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
" Country ActiveCases Population PercentageInfected\n",
"129 Martinique 222576.901869 374087.0 0.594987\n",
"68 Faeroe Islands 26936.998989 49233.0 0.547133\n",
"195 St. Barth 4854.999825 9945.0 0.488185\n",
"84 Guadeloupe 193026.939904 399794.0 0.482816\n",
"93 Iceland 130899.111498 345393.0 0.378986"
],
"text/html": [
"\n",
" <div id=\"df-5b3415ae-443b-4212-be42-19efc6bff309\">\n",
" <div class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Country</th>\n",
" <th>ActiveCases</th>\n",
" <th>Population</th>\n",
" <th>PercentageInfected</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>129</th>\n",
" <td>Martinique</td>\n",
" <td>222576.901869</td>\n",
" <td>374087.0</td>\n",
" <td>0.594987</td>\n",
" </tr>\n",
" <tr>\n",
" <th>68</th>\n",
" <td>Faeroe Islands</td>\n",
" <td>26936.998989</td>\n",
" <td>49233.0</td>\n",
" <td>0.547133</td>\n",
" </tr>\n",
" <tr>\n",
" <th>195</th>\n",
" <td>St. Barth</td>\n",
" <td>4854.999825</td>\n",
" <td>9945.0</td>\n",
" <td>0.488185</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84</th>\n",
" <td>Guadeloupe</td>\n",
" <td>193026.939904</td>\n",
" <td>399794.0</td>\n",
" <td>0.482816</td>\n",
" </tr>\n",
" <tr>\n",
" <th>93</th>\n",
" <td>Iceland</td>\n",
" <td>130899.111498</td>\n",
" <td>345393.0</td>\n",
" <td>0.378986</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-5b3415ae-443b-4212-be42-19efc6bff309')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-5b3415ae-443b-4212-be42-19efc6bff309 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-5b3415ae-443b-4212-be42-19efc6bff309');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
]
},
"metadata": {},
"execution_count": 87
}
]
}
]
} |