File size: 29,928 Bytes
7bd8341 db53170 7bd8341 db53170 7bd8341 2e0c701 7bd8341 db53170 7bd8341 db53170 7bd8341 2e0c701 7bd8341 2e0c701 7bd8341 db53170 7bd8341 db53170 7bd8341 db53170 7bd8341 db53170 7bd8341 db53170 7bd8341 2e0c701 7bd8341 2e0c701 7bd8341 2e0c701 7bd8341 db53170 7bd8341 db53170 7bd8341 db53170 7bd8341 db53170 7bd8341 db53170 7bd8341 db53170 7bd8341 2e0c701 7bd8341 2e0c701 7bd8341 db53170 7bd8341 db53170 7bd8341 db53170 7bd8341 db53170 7bd8341 db53170 7bd8341 db53170 7bd8341 2e0c701 7bd8341 2e0c701 7bd8341 db53170 7bd8341 db53170 7bd8341 db53170 7bd8341 db53170 7bd8341 db53170 7bd8341 2e0c701 7bd8341 d0702fa db53170 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 2e0c701 db53170 7bd8341 d0702fa db53170 7bd8341 d0702fa 7bd8341 d0702fa db53170 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa db53170 2e0c701 7bd8341 d0702fa 2e0c701 d0702fa db53170 d0702fa 7bd8341 d0702fa 7bd8341 db53170 d0702fa 7bd8341 2e0c701 7bd8341 2e0c701 7bd8341 d0702fa 7bd8341 2e0c701 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 db53170 d0702fa 7bd8341 2e0c701 7bd8341 2e0c701 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa db53170 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 d0702fa db53170 7bd8341 d0702fa 7bd8341 d0702fa 7bd8341 2e0c701 7bd8341 2e0c701 7bd8341 2e0c701 7bd8341 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import os; os.chdir('..');"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import json"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'Hobbies_and_Leisure': 0,\n",
" 'News': 1,\n",
" 'Science': 2,\n",
" 'Autos_and_Vehicles': 3,\n",
" 'Health': 4,\n",
" 'Pets_and_Animals': 5,\n",
" 'Adult': 6,\n",
" 'Computers_and_Electronics': 7,\n",
" 'Online Communities': 8,\n",
" 'Beauty_and_Fitness': 9,\n",
" 'People_and_Society': 10,\n",
" 'Business_and_Industrial': 11,\n",
" 'Reference': 12,\n",
" 'Shopping': 13,\n",
" 'Travel_and_Transportation': 14,\n",
" 'Food_and_Drink': 15,\n",
" 'Law_and_Government': 16,\n",
" 'Books_and_Literature': 17,\n",
" 'Finance': 18,\n",
" 'Games': 19,\n",
" 'Home_and_Garden': 20,\n",
" 'Jobs_and_Education': 21,\n",
" 'Arts_and_Entertainment': 22,\n",
" 'Sensitive Subjects': 23,\n",
" 'Real Estate': 24,\n",
" 'Internet_and_Telecom': 25,\n",
" 'Sports': 26}"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_cat_dict= json.load(\n",
" open('data/categories_refined.json', 'r')\n",
")\n",
"data_cat_dict"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{0: 'Hobbies_and_Leisure',\n",
" 1: 'News',\n",
" 2: 'Science',\n",
" 3: 'Autos_and_Vehicles',\n",
" 4: 'Health',\n",
" 5: 'Pets_and_Animals',\n",
" 6: 'Adult',\n",
" 7: 'Computers_and_Electronics',\n",
" 8: 'Online Communities',\n",
" 9: 'Beauty_and_Fitness',\n",
" 10: 'People_and_Society',\n",
" 11: 'Business_and_Industrial',\n",
" 12: 'Reference',\n",
" 13: 'Shopping',\n",
" 14: 'Travel_and_Transportation',\n",
" 15: 'Food_and_Drink',\n",
" 16: 'Law_and_Government',\n",
" 17: 'Books_and_Literature',\n",
" 18: 'Finance',\n",
" 19: 'Games',\n",
" 20: 'Home_and_Garden',\n",
" 21: 'Jobs_and_Education',\n",
" 22: 'Arts_and_Entertainment',\n",
" 23: 'Sensitive Subjects',\n",
" 24: 'Real Estate',\n",
" 25: 'Internet_and_Telecom',\n",
" 26: 'Sports'}"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_cat_dict_rev= {}\n",
"for key in data_cat_dict.keys():\n",
" data_cat_dict_rev[data_cat_dict[key]] = key\n",
" \n",
"data_cat_dict_rev"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"data_categories/Hobbies_and_Leisure.csv: True\n",
"data_categories/News.csv: True\n",
"data_categories/Science.csv: True\n",
"data_categories/Autos_and_Vehicles.csv: True\n",
"data_categories/Health.csv: True\n",
"data_categories/Pets_and_Animals.csv: True\n",
"data_categories/Adult.csv: True\n",
"data_categories/Computers_and_Electronics.csv: True\n",
"data_categories/Online Communities.csv: True\n",
"data_categories/Beauty_and_Fitness.csv: True\n",
"data_categories/People_and_Society.csv: True\n",
"data_categories/Business_and_Industrial.csv: True\n",
"data_categories/Reference.csv: True\n",
"data_categories/Shopping.csv: True\n",
"data_categories/Travel_and_Transportation.csv: True\n",
"data_categories/Food_and_Drink.csv: True\n",
"data_categories/Law_and_Government.csv: True\n",
"data_categories/Books_and_Literature.csv: True\n",
"data_categories/Finance.csv: True\n",
"data_categories/Games.csv: True\n",
"data_categories/Home_and_Garden.csv: True\n",
"data_categories/Jobs_and_Education.csv: True\n",
"data_categories/Arts_and_Entertainment.csv: True\n",
"data_categories/Sensitive Subjects.csv: True\n",
"data_categories/Real Estate.csv: True\n",
"data_categories/Internet_and_Telecom.csv: True\n",
"data_categories/Sports.csv: True\n"
]
},
{
"data": {
"text/plain": [
"27"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"path_list= []\n",
"for i in data_cat_dict.keys():\n",
" path= os.path.join(\"data_categories\", f'{i}.csv')\n",
" print(f\"{path}: {os.path.exists(path)}\")\n",
" path_list.append(path)\n",
" \n",
"len(path_list)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<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>category</th>\n",
" <th>label</th>\n",
" <th>label_id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Skincare routine</td>\n",
" <td>Hobbies_and_Leisure</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Haircare tips</td>\n",
" <td>Hobbies_and_Leisure</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Makeup tutorials</td>\n",
" <td>Hobbies_and_Leisure</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Fitness workouts</td>\n",
" <td>Hobbies_and_Leisure</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Anti-aging products</td>\n",
" <td>Hobbies_and_Leisure</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" category label label_id\n",
"0 Skincare routine Hobbies_and_Leisure 0\n",
"1 Haircare tips Hobbies_and_Leisure 0\n",
"2 Makeup tutorials Hobbies_and_Leisure 0\n",
"3 Fitness workouts Hobbies_and_Leisure 0\n",
"4 Anti-aging products Hobbies_and_Leisure 0"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df= pd.read_csv(path_list[0])\n",
"df['label']= data_cat_dict_rev[0]\n",
"df['label_id']= data_cat_dict[data_cat_dict_rev[0]]\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<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>category</th>\n",
" <th>label</th>\n",
" <th>label_id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Skincare routine</td>\n",
" <td>Hobbies_and_Leisure</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Haircare tips</td>\n",
" <td>Hobbies_and_Leisure</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Makeup tutorials</td>\n",
" <td>Hobbies_and_Leisure</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Fitness workouts</td>\n",
" <td>Hobbies_and_Leisure</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Anti-aging products</td>\n",
" <td>Hobbies_and_Leisure</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" category label label_id\n",
"0 Skincare routine Hobbies_and_Leisure 0\n",
"1 Haircare tips Hobbies_and_Leisure 0\n",
"2 Makeup tutorials Hobbies_and_Leisure 0\n",
"3 Fitness workouts Hobbies_and_Leisure 0\n",
"4 Anti-aging products Hobbies_and_Leisure 0"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"concat_df= df.copy()\n",
"concat_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"data_categories/News.csv\n",
"data_categories/Science.csv\n",
"data_categories/Autos_and_Vehicles.csv\n",
"data_categories/Health.csv\n",
"data_categories/Pets_and_Animals.csv\n",
"data_categories/Adult.csv\n",
"data_categories/Computers_and_Electronics.csv\n",
"data_categories/Online Communities.csv\n",
"data_categories/Beauty_and_Fitness.csv\n",
"data_categories/People_and_Society.csv\n",
"data_categories/Business_and_Industrial.csv\n",
"data_categories/Reference.csv\n",
"data_categories/Shopping.csv\n",
"data_categories/Travel_and_Transportation.csv\n",
"data_categories/Food_and_Drink.csv\n",
"data_categories/Law_and_Government.csv\n",
"data_categories/Books_and_Literature.csv\n",
"data_categories/Finance.csv\n",
"data_categories/Games.csv\n",
"data_categories/Home_and_Garden.csv\n",
"data_categories/Jobs_and_Education.csv\n",
"data_categories/Arts_and_Entertainment.csv\n",
"data_categories/Sensitive Subjects.csv\n",
"data_categories/Real Estate.csv\n",
"data_categories/Internet_and_Telecom.csv\n",
"data_categories/Sports.csv\n"
]
}
],
"source": [
"for i in range(1, 27):\n",
" print(path_list[i])\n",
" df_i= pd.read_csv(path_list[i])\n",
" df_i['label']= data_cat_dict_rev[i]\n",
" df_i['label_id']= data_cat_dict[data_cat_dict_rev[i]]\n",
" concat_df= pd.concat([concat_df, df_i])\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<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>category</th>\n",
" <th>label</th>\n",
" <th>label_id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1201</th>\n",
" <td>Plus-size clothing stores and shops</td>\n",
" <td>Shopping</td>\n",
" <td>13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>853</th>\n",
" <td>Citation context extraction techniques</td>\n",
" <td>Reference</td>\n",
" <td>12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1034</th>\n",
" <td>Cat ear headphones with aux</td>\n",
" <td>Computers_and_Electronics</td>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>632</th>\n",
" <td>promote such behavior</td>\n",
" <td>Sensitive Subjects</td>\n",
" <td>23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>91</th>\n",
" <td>Literature review references</td>\n",
" <td>Reference</td>\n",
" <td>12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>168</th>\n",
" <td>Freedom of speech cases</td>\n",
" <td>Law_and_Government</td>\n",
" <td>16</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1111</th>\n",
" <td>French country kitchen design inspiration DIY</td>\n",
" <td>Home_and_Garden</td>\n",
" <td>20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>492</th>\n",
" <td>Credit score improvement techniques overview</td>\n",
" <td>Finance</td>\n",
" <td>18</td>\n",
" </tr>\n",
" <tr>\n",
" <th>657</th>\n",
" <td>regulated by laws</td>\n",
" <td>Sensitive Subjects</td>\n",
" <td>23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1037</th>\n",
" <td>Health Education for Seniors</td>\n",
" <td>Health</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>109</th>\n",
" <td>Quantum mechanics experiments</td>\n",
" <td>Science</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>538</th>\n",
" <td>Healthcare AI applications</td>\n",
" <td>Science</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1386</th>\n",
" <td>AirPods Pro Case</td>\n",
" <td>Computers_and_Electronics</td>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>844</th>\n",
" <td>DIY home electrical repairs</td>\n",
" <td>Home_and_Garden</td>\n",
" <td>20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>439</th>\n",
" <td>tube sex</td>\n",
" <td>Adult</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>231</th>\n",
" <td>Real estate sales tactics</td>\n",
" <td>Real Estate</td>\n",
" <td>24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>610</th>\n",
" <td>Home solar panel cleaning and maintenance</td>\n",
" <td>Home_and_Garden</td>\n",
" <td>20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>422</th>\n",
" <td>Real estate legal issues</td>\n",
" <td>Real Estate</td>\n",
" <td>24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>222</th>\n",
" <td>Film industry news</td>\n",
" <td>Arts_and_Entertainment</td>\n",
" <td>22</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1077</th>\n",
" <td>Cat ear headphones for PS4</td>\n",
" <td>Computers_and_Electronics</td>\n",
" <td>7</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" category \\\n",
"1201 Plus-size clothing stores and shops \n",
"853 Citation context extraction techniques \n",
"1034 Cat ear headphones with aux \n",
"632 promote such behavior \n",
"91 Literature review references \n",
"168 Freedom of speech cases \n",
"1111 French country kitchen design inspiration DIY \n",
"492 Credit score improvement techniques overview \n",
"657 regulated by laws \n",
"1037 Health Education for Seniors \n",
"109 Quantum mechanics experiments \n",
"538 Healthcare AI applications \n",
"1386 AirPods Pro Case \n",
"844 DIY home electrical repairs \n",
"439 tube sex \n",
"231 Real estate sales tactics \n",
"610 Home solar panel cleaning and maintenance \n",
"422 Real estate legal issues \n",
"222 Film industry news \n",
"1077 Cat ear headphones for PS4 \n",
"\n",
" label label_id \n",
"1201 Shopping 13 \n",
"853 Reference 12 \n",
"1034 Computers_and_Electronics 7 \n",
"632 Sensitive Subjects 23 \n",
"91 Reference 12 \n",
"168 Law_and_Government 16 \n",
"1111 Home_and_Garden 20 \n",
"492 Finance 18 \n",
"657 Sensitive Subjects 23 \n",
"1037 Health 4 \n",
"109 Science 2 \n",
"538 Science 2 \n",
"1386 Computers_and_Electronics 7 \n",
"844 Home_and_Garden 20 \n",
"439 Adult 6 \n",
"231 Real Estate 24 \n",
"610 Home_and_Garden 20 \n",
"422 Real Estate 24 \n",
"222 Arts_and_Entertainment 22 \n",
"1077 Computers_and_Electronics 7 "
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"concat_df.sample(20)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"label\n",
"Computers_and_Electronics 1959\n",
"Shopping 1912\n",
"Food_and_Drink 1851\n",
"Reference 1453\n",
"Sports 1399\n",
"Online Communities 1396\n",
"Travel_and_Transportation 1355\n",
"Internet_and_Telecom 1353\n",
"Pets_and_Animals 1324\n",
"Beauty_and_Fitness 1259\n",
"People_and_Society 1250\n",
"Law_and_Government 1226\n",
"Home_and_Garden 1200\n",
"News 1199\n",
"Jobs_and_Education 1188\n",
"Real Estate 1166\n",
"Arts_and_Entertainment 1162\n",
"Business_and_Industrial 1124\n",
"Adult 1100\n",
"Health 1098\n",
"Autos_and_Vehicles 1072\n",
"Science 1055\n",
"Hobbies_and_Leisure 1049\n",
"Books_and_Literature 1000\n",
"Finance 1000\n",
"Sensitive Subjects 762\n",
"Games 700\n",
"Name: count, dtype: int64"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"concat_df.label.value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<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>category</th>\n",
" <th>label</th>\n",
" <th>label_id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Internet usage monitoring</td>\n",
" <td>Internet_and_Telecom</td>\n",
" <td>25</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Food safety guidelines and regulations</td>\n",
" <td>Food_and_Drink</td>\n",
" <td>15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Internet protocols and edge computing in finance</td>\n",
" <td>Internet_and_Telecom</td>\n",
" <td>25</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Online grocery shopping</td>\n",
" <td>Food_and_Drink</td>\n",
" <td>15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Writing retreats for poets and novelists</td>\n",
" <td>Books_and_Literature</td>\n",
" <td>17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Unicorn cat ear headphones</td>\n",
" <td>Computers_and_Electronics</td>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Reference citation context tagging techniques</td>\n",
" <td>Reference</td>\n",
" <td>12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>Motorcycle riding tips for beginners gear chec...</td>\n",
" <td>Autos_and_Vehicles</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>Space agency missions</td>\n",
" <td>Science</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>Game streaming self-promotion and growth tactics</td>\n",
" <td>Games</td>\n",
" <td>19</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>sex videos movies</td>\n",
" <td>Adult</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>Citation context organization methods</td>\n",
" <td>Reference</td>\n",
" <td>12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>Healthy office snacks</td>\n",
" <td>Health</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>Indigenous rights advocacy</td>\n",
" <td>People_and_Society</td>\n",
" <td>10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>News talk shows</td>\n",
" <td>News</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>Best facial cleansers</td>\n",
" <td>Hobbies_and_Leisure</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>Letter of recommendation</td>\n",
" <td>Reference</td>\n",
" <td>12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>Fossil preservation techniques</td>\n",
" <td>Science</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>Marriage equality</td>\n",
" <td>People_and_Society</td>\n",
" <td>10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>eSports Game Esports Player Fan Engagement Ini...</td>\n",
" <td>Sports</td>\n",
" <td>26</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" category \\\n",
"0 Internet usage monitoring \n",
"1 Food safety guidelines and regulations \n",
"2 Internet protocols and edge computing in finance \n",
"3 Online grocery shopping \n",
"4 Writing retreats for poets and novelists \n",
"5 Unicorn cat ear headphones \n",
"6 Reference citation context tagging techniques \n",
"7 Motorcycle riding tips for beginners gear chec... \n",
"8 Space agency missions \n",
"9 Game streaming self-promotion and growth tactics \n",
"10 sex videos movies \n",
"11 Citation context organization methods \n",
"12 Healthy office snacks \n",
"13 Indigenous rights advocacy \n",
"14 News talk shows \n",
"15 Best facial cleansers \n",
"16 Letter of recommendation \n",
"17 Fossil preservation techniques \n",
"18 Marriage equality \n",
"19 eSports Game Esports Player Fan Engagement Ini... \n",
"\n",
" label label_id \n",
"0 Internet_and_Telecom 25 \n",
"1 Food_and_Drink 15 \n",
"2 Internet_and_Telecom 25 \n",
"3 Food_and_Drink 15 \n",
"4 Books_and_Literature 17 \n",
"5 Computers_and_Electronics 7 \n",
"6 Reference 12 \n",
"7 Autos_and_Vehicles 3 \n",
"8 Science 2 \n",
"9 Games 19 \n",
"10 Adult 6 \n",
"11 Reference 12 \n",
"12 Health 4 \n",
"13 People_and_Society 10 \n",
"14 News 1 \n",
"15 Hobbies_and_Leisure 0 \n",
"16 Reference 12 \n",
"17 Science 2 \n",
"18 People_and_Society 10 \n",
"19 Sports 26 "
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cdf_shffeled= concat_df.sample(frac=1).reset_index(drop=True)\n",
"cdf_shffeled.head(20)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"cdf_shffeled.to_csv(\n",
" 'data_categories/Final_Category_Data_With_Labels.csv',\n",
" index=False\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|