Spaces:
Sleeping
Sleeping
File size: 55,416 Bytes
edaf37d |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 49,
"id": "b33d3892",
"metadata": {},
"outputs": [
{
"ename": "ModuleNotFoundError",
"evalue": "No module named 'pandarallel'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
"Input \u001b[0;32mIn [49]\u001b[0m, in \u001b[0;36m<cell line: 12>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 9\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mnltk\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mstem\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mporter\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m PorterStemmer\n\u001b[1;32m 10\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpattern\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mtext\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01men\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m singularize\n\u001b[0;32m---> 12\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpandarallel\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m pandarallel \u001b[38;5;66;03m# Parallel workers on pandas dataframe\u001b[39;00m\n\u001b[1;32m 14\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01munidecode\u001b[39;00m\n\u001b[1;32m 15\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mre\u001b[39;00m \n",
"\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'pandarallel'"
]
}
],
"source": [
"import numpy as np # linear algebra\n",
"import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
"import matplotlib.pyplot as plt # Used to do plots\n",
"%matplotlib inline\n",
"\n",
"import nltk \n",
"from nltk.corpus import stopwords # Stopwords \n",
"from nltk.tokenize import word_tokenize # Word_tokenizer\n",
"from nltk.stem.porter import PorterStemmer\n",
"from pattern.text.en import singularize\n",
"\n",
"from pandarallel import pandarallel # Parallel workers on pandas dataframe\n",
"\n",
"import unidecode\n",
"import re \n",
"import time\n",
"import string\n",
"import statistics\n",
"\n",
"from datetime import datetime"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "d1ef5e57",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting pattern\n",
" Downloading Pattern-3.6.0.tar.gz (22.2 MB)\n",
"\u001b[2K \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m22.2/22.2 MB\u001b[0m \u001b[31m201.5 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mm eta \u001b[36m0:00:01\u001b[0m[36m0:00:03\u001b[0m\n",
"\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25hRequirement already satisfied: future in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from pattern) (0.18.2)\n",
"Collecting backports.csv (from pattern)\n",
" Downloading backports.csv-1.0.7-py2.py3-none-any.whl.metadata (4.0 kB)\n",
"Collecting mysqlclient (from pattern)\n",
" Downloading mysqlclient-2.2.4.tar.gz (90 kB)\n",
"\u001b[2K \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m90.4/90.4 kB\u001b[0m \u001b[31m339.8 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m1m362.1 kB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25h Installing build dependencies ... \u001b[?25ldone\n",
"\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
"\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
"\u001b[?25hRequirement already satisfied: beautifulsoup4 in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from pattern) (4.11.1)\n",
"Requirement already satisfied: lxml in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from pattern) (4.9.1)\n",
"Collecting feedparser (from pattern)\n",
" Downloading feedparser-6.0.11-py3-none-any.whl.metadata (2.4 kB)\n",
"Collecting pdfminer.six (from pattern)\n",
" Downloading pdfminer.six-20240706-py3-none-any.whl.metadata (4.1 kB)\n",
"Requirement already satisfied: numpy in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from pattern) (1.24.3)\n",
"Requirement already satisfied: scipy in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from pattern) (1.9.1)\n",
"Requirement already satisfied: nltk in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from pattern) (3.8.1)\n",
"Collecting python-docx (from pattern)\n",
" Downloading python_docx-1.1.2-py3-none-any.whl.metadata (2.0 kB)\n",
"Collecting cherrypy (from pattern)\n",
" Downloading CherryPy-18.10.0-py3-none-any.whl.metadata (8.7 kB)\n",
"Requirement already satisfied: requests in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from pattern) (2.28.1)\n",
"Requirement already satisfied: soupsieve>1.2 in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from beautifulsoup4->pattern) (2.3.1)\n",
"Collecting cheroot>=8.2.1 (from cherrypy->pattern)\n",
" Downloading cheroot-10.0.1-py3-none-any.whl.metadata (7.1 kB)\n",
"Collecting portend>=2.1.1 (from cherrypy->pattern)\n",
" Downloading portend-3.2.0-py3-none-any.whl.metadata (3.6 kB)\n",
"Collecting more-itertools (from cherrypy->pattern)\n",
" Downloading more_itertools-10.4.0-py3-none-any.whl.metadata (36 kB)\n",
"Collecting zc.lockfile (from cherrypy->pattern)\n",
" Downloading zc.lockfile-3.0.post1-py3-none-any.whl.metadata (6.2 kB)\n",
"Collecting jaraco.collections (from cherrypy->pattern)\n",
" Downloading jaraco.collections-5.0.1-py3-none-any.whl.metadata (3.8 kB)\n",
"Collecting sgmllib3k (from feedparser->pattern)\n",
" Downloading sgmllib3k-1.0.0.tar.gz (5.8 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25hRequirement already satisfied: click in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from nltk->pattern) (8.0.4)\n",
"Requirement already satisfied: joblib in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from nltk->pattern) (1.3.2)\n",
"Requirement already satisfied: regex>=2021.8.3 in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from nltk->pattern) (2022.7.9)\n",
"Requirement already satisfied: tqdm in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from nltk->pattern) (4.64.1)\n",
"Requirement already satisfied: charset-normalizer>=2.0.0 in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from pdfminer.six->pattern) (2.0.4)\n",
"Requirement already satisfied: cryptography>=36.0.0 in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from pdfminer.six->pattern) (37.0.1)\n",
"Collecting typing-extensions>=4.9.0 (from python-docx->pattern)\n",
" Downloading typing_extensions-4.12.2-py3-none-any.whl.metadata (3.0 kB)\n",
"Requirement already satisfied: idna<4,>=2.5 in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from requests->pattern) (3.3)\n",
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from requests->pattern) (1.26.11)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from requests->pattern) (2023.7.22)\n",
"Collecting jaraco.functools (from cheroot>=8.2.1->cherrypy->pattern)\n",
" Downloading jaraco.functools-4.0.2-py3-none-any.whl.metadata (2.8 kB)\n",
"Requirement already satisfied: cffi>=1.12 in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from cryptography>=36.0.0->pdfminer.six->pattern) (1.15.1)\n",
"Collecting tempora>=1.8 (from portend>=2.1.1->cherrypy->pattern)\n",
" Downloading tempora-5.7.0-py3-none-any.whl.metadata (3.2 kB)\n",
"Collecting jaraco.text (from jaraco.collections->cherrypy->pattern)\n",
" Downloading jaraco.text-4.0.0-py3-none-any.whl.metadata (3.7 kB)\n",
"Requirement already satisfied: setuptools in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from zc.lockfile->cherrypy->pattern) (63.4.1)\n",
"Requirement already satisfied: pycparser in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from cffi>=1.12->cryptography>=36.0.0->pdfminer.six->pattern) (2.21)\n",
"Requirement already satisfied: python-dateutil in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from tempora>=1.8->portend>=2.1.1->cherrypy->pattern) (2.8.2)\n",
"Collecting jaraco.context>=4.1 (from jaraco.text->jaraco.collections->cherrypy->pattern)\n",
" Downloading jaraco.context-5.3.0-py3-none-any.whl.metadata (4.0 kB)\n",
"Collecting autocommand (from jaraco.text->jaraco.collections->cherrypy->pattern)\n",
" Downloading autocommand-2.2.2-py3-none-any.whl.metadata (15 kB)\n",
"Collecting backports.tarfile (from jaraco.context>=4.1->jaraco.text->jaraco.collections->cherrypy->pattern)\n",
" Downloading backports.tarfile-1.2.0-py3-none-any.whl.metadata (2.0 kB)\n",
"Requirement already satisfied: six>=1.5 in /Users/ramtin/anaconda3/envs/py39/lib/python3.9/site-packages (from python-dateutil->tempora>=1.8->portend>=2.1.1->cherrypy->pattern) (1.16.0)\n",
"Downloading backports.csv-1.0.7-py2.py3-none-any.whl (12 kB)\n",
"Downloading CherryPy-18.10.0-py3-none-any.whl (349 kB)\n",
"\u001b[2K \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m349.8/349.8 kB\u001b[0m \u001b[31m308.8 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m1m336.8 kB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading feedparser-6.0.11-py3-none-any.whl (81 kB)\n",
"\u001b[2K \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m81.3/81.3 kB\u001b[0m \u001b[31m352.7 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m kB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading pdfminer.six-20240706-py3-none-any.whl (5.6 MB)\n",
"\u001b[2K \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.6/5.6 MB\u001b[0m \u001b[31m219.0 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mm eta \u001b[36m0:00:01\u001b[0m[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading python_docx-1.1.2-py3-none-any.whl (244 kB)\n",
"\u001b[2K \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m244.3/244.3 kB\u001b[0m \u001b[31m220.7 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m1m216.4 kB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading cheroot-10.0.1-py3-none-any.whl (104 kB)\n",
"\u001b[2K \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m104.8/104.8 kB\u001b[0m \u001b[31m185.9 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m kB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m:01\u001b[0m\n",
"\u001b[?25hDownloading more_itertools-10.4.0-py3-none-any.whl (60 kB)\n",
"\u001b[2K \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.9/60.9 kB\u001b[0m \u001b[31m204.1 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m1m177.4 kB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading portend-3.2.0-py3-none-any.whl (5.3 kB)\n",
"Downloading typing_extensions-4.12.2-py3-none-any.whl (37 kB)\n",
"Downloading jaraco.collections-5.0.1-py3-none-any.whl (10 kB)\n",
"Downloading zc.lockfile-3.0.post1-py3-none-any.whl (9.8 kB)\n",
"Downloading tempora-5.7.0-py3-none-any.whl (13 kB)\n",
"Downloading jaraco.functools-4.0.2-py3-none-any.whl (9.9 kB)\n",
"Downloading jaraco.text-4.0.0-py3-none-any.whl (11 kB)\n",
"Downloading jaraco.context-5.3.0-py3-none-any.whl (6.5 kB)\n",
"Downloading autocommand-2.2.2-py3-none-any.whl (19 kB)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Downloading backports.tarfile-1.2.0-py3-none-any.whl (30 kB)\n",
"Building wheels for collected packages: pattern, mysqlclient, sgmllib3k\n",
" Building wheel for pattern (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Created wheel for pattern: filename=Pattern-3.6-py3-none-any.whl size=22332702 sha256=87d88aa6ebbfcb7d72318a2a3f803172542546b39356f04a9963ee0f84e0b5d9\n",
" Stored in directory: /Users/ramtin/Library/Caches/pip/wheels/50/33/f3/ea00b80d50c09f210588bda15ec60bdb38b289b452577cd5c3\n",
" Building wheel for mysqlclient (pyproject.toml) ... \u001b[?25ldone\n",
"\u001b[?25h Created wheel for mysqlclient: filename=mysqlclient-2.2.4-cp39-cp39-macosx_11_0_arm64.whl size=73775 sha256=486b18a9927e86835857d7cd65ca1488f7324577c97c4f1c9d6d8c90b2926cbb\n",
" Stored in directory: /Users/ramtin/Library/Caches/pip/wheels/df/23/68/faa07b93488a130b3295ca4e91574e85a9dc4764cd463bc152\n",
" Building wheel for sgmllib3k (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Created wheel for sgmllib3k: filename=sgmllib3k-1.0.0-py3-none-any.whl size=6048 sha256=1143b02b589d8d7c77c44e86a44ce647e51698927b9243e3964e0562e3ef887d\n",
" Stored in directory: /Users/ramtin/Library/Caches/pip/wheels/65/7a/a7/78c287f64e401255dff4c13fdbc672fed5efbfd21c530114e1\n",
"Successfully built pattern mysqlclient sgmllib3k\n",
"Installing collected packages: sgmllib3k, backports.csv, zc.lockfile, typing-extensions, mysqlclient, more-itertools, feedparser, backports.tarfile, autocommand, python-docx, jaraco.functools, jaraco.context, tempora, pdfminer.six, jaraco.text, cheroot, portend, jaraco.collections, cherrypy, pattern\n",
" Attempting uninstall: typing-extensions\n",
" Found existing installation: typing_extensions 4.8.0\n",
" Uninstalling typing_extensions-4.8.0:\n",
" Successfully uninstalled typing_extensions-4.8.0\n",
"Successfully installed autocommand-2.2.2 backports.csv-1.0.7 backports.tarfile-1.2.0 cheroot-10.0.1 cherrypy-18.10.0 feedparser-6.0.11 jaraco.collections-5.0.1 jaraco.context-5.3.0 jaraco.functools-4.0.2 jaraco.text-4.0.0 more-itertools-10.4.0 mysqlclient-2.2.4 pattern-3.6 pdfminer.six-20240706 portend-3.2.0 python-docx-1.1.2 sgmllib3k-1.0.0 tempora-5.7.0 typing-extensions-4.12.2 zc.lockfile-3.0.post1\n",
"\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m24.0\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.2\u001b[0m\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
]
}
],
"source": [
"!pip install pattern"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "cde34094",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"User reviews shape: (573913, 7)\n"
]
}
],
"source": [
"df_reviews = pd.read_json('kaggle/input/IMDB_reviews.json', lines=True) \n",
"print('User reviews shape: ', df_reviews.shape)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "94060a02",
"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>review_date</th>\n",
" <th>movie_id</th>\n",
" <th>user_id</th>\n",
" <th>is_spoiler</th>\n",
" <th>review_text</th>\n",
" <th>rating</th>\n",
" <th>review_summary</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>10 February 2006</td>\n",
" <td>tt0111161</td>\n",
" <td>ur1898687</td>\n",
" <td>True</td>\n",
" <td>In its Oscar year, Shawshank Redemption (writt...</td>\n",
" <td>10</td>\n",
" <td>A classic piece of unforgettable film-making.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>6 September 2000</td>\n",
" <td>tt0111161</td>\n",
" <td>ur0842118</td>\n",
" <td>True</td>\n",
" <td>The Shawshank Redemption is without a doubt on...</td>\n",
" <td>10</td>\n",
" <td>Simply amazing. The best film of the 90's.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3 August 2001</td>\n",
" <td>tt0111161</td>\n",
" <td>ur1285640</td>\n",
" <td>True</td>\n",
" <td>I believe that this film is the best story eve...</td>\n",
" <td>8</td>\n",
" <td>The best story ever told on film</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1 September 2002</td>\n",
" <td>tt0111161</td>\n",
" <td>ur1003471</td>\n",
" <td>True</td>\n",
" <td>**Yes, there are SPOILERS here**This film has ...</td>\n",
" <td>10</td>\n",
" <td>Busy dying or busy living?</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>20 May 2004</td>\n",
" <td>tt0111161</td>\n",
" <td>ur0226855</td>\n",
" <td>True</td>\n",
" <td>At the heart of this extraordinary movie is a ...</td>\n",
" <td>8</td>\n",
" <td>Great story, wondrously told and acted</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" review_date movie_id user_id is_spoiler \\\n",
"0 10 February 2006 tt0111161 ur1898687 True \n",
"1 6 September 2000 tt0111161 ur0842118 True \n",
"2 3 August 2001 tt0111161 ur1285640 True \n",
"3 1 September 2002 tt0111161 ur1003471 True \n",
"4 20 May 2004 tt0111161 ur0226855 True \n",
"\n",
" review_text rating \\\n",
"0 In its Oscar year, Shawshank Redemption (writt... 10 \n",
"1 The Shawshank Redemption is without a doubt on... 10 \n",
"2 I believe that this film is the best story eve... 8 \n",
"3 **Yes, there are SPOILERS here**This film has ... 10 \n",
"4 At the heart of this extraordinary movie is a ... 8 \n",
"\n",
" review_summary \n",
"0 A classic piece of unforgettable film-making. \n",
"1 Simply amazing. The best film of the 90's. \n",
"2 The best story ever told on film \n",
"3 Busy dying or busy living? \n",
"4 Great story, wondrously told and acted "
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_reviews.head()"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "da5a873c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 573913 entries, 0 to 573912\n",
"Data columns (total 7 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 review_date 573913 non-null object\n",
" 1 movie_id 573913 non-null object\n",
" 2 user_id 573913 non-null object\n",
" 3 is_spoiler 573913 non-null bool \n",
" 4 review_text 573913 non-null object\n",
" 5 rating 573913 non-null int64 \n",
" 6 review_summary 573913 non-null object\n",
"dtypes: bool(1), int64(1), object(5)\n",
"memory usage: 26.8+ MB\n"
]
}
],
"source": [
"df_reviews.info()"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "b9fd9dad",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"User reviews shape: (1572, 7)\n"
]
}
],
"source": [
"df_details = pd.read_json('kaggle/input/IMDB_movie_details.json', lines=True) \n",
"print('User reviews shape: ', df_details.shape)"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "9ea16b9c",
"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>movie_id</th>\n",
" <th>plot_summary</th>\n",
" <th>duration</th>\n",
" <th>genre</th>\n",
" <th>rating</th>\n",
" <th>release_date</th>\n",
" <th>plot_synopsis</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>tt0105112</td>\n",
" <td>Former CIA analyst, Jack Ryan is in England wi...</td>\n",
" <td>1h 57min</td>\n",
" <td>[Action, Thriller]</td>\n",
" <td>6.9</td>\n",
" <td>1992-06-05</td>\n",
" <td>Jack Ryan (Ford) is on a \"working vacation\" in...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>tt1204975</td>\n",
" <td>Billy (Michael Douglas), Paddy (Robert De Niro...</td>\n",
" <td>1h 45min</td>\n",
" <td>[Comedy]</td>\n",
" <td>6.6</td>\n",
" <td>2013-11-01</td>\n",
" <td>Four boys around the age of 10 are friends in ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>tt0243655</td>\n",
" <td>The setting is Camp Firewood, the year 1981. I...</td>\n",
" <td>1h 37min</td>\n",
" <td>[Comedy, Romance]</td>\n",
" <td>6.7</td>\n",
" <td>2002-04-11</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>tt0040897</td>\n",
" <td>Fred C. Dobbs and Bob Curtin, both down on the...</td>\n",
" <td>2h 6min</td>\n",
" <td>[Adventure, Drama, Western]</td>\n",
" <td>8.3</td>\n",
" <td>1948-01-24</td>\n",
" <td>Fred Dobbs (Humphrey Bogart) and Bob Curtin (T...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>tt0126886</td>\n",
" <td>Tracy Flick is running unopposed for this year...</td>\n",
" <td>1h 43min</td>\n",
" <td>[Comedy, Drama, Romance]</td>\n",
" <td>7.3</td>\n",
" <td>1999-05-07</td>\n",
" <td>Jim McAllister (Matthew Broderick) is a much-a...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" movie_id plot_summary duration \\\n",
"0 tt0105112 Former CIA analyst, Jack Ryan is in England wi... 1h 57min \n",
"1 tt1204975 Billy (Michael Douglas), Paddy (Robert De Niro... 1h 45min \n",
"2 tt0243655 The setting is Camp Firewood, the year 1981. I... 1h 37min \n",
"3 tt0040897 Fred C. Dobbs and Bob Curtin, both down on the... 2h 6min \n",
"4 tt0126886 Tracy Flick is running unopposed for this year... 1h 43min \n",
"\n",
" genre rating release_date \\\n",
"0 [Action, Thriller] 6.9 1992-06-05 \n",
"1 [Comedy] 6.6 2013-11-01 \n",
"2 [Comedy, Romance] 6.7 2002-04-11 \n",
"3 [Adventure, Drama, Western] 8.3 1948-01-24 \n",
"4 [Comedy, Drama, Romance] 7.3 1999-05-07 \n",
"\n",
" plot_synopsis \n",
"0 Jack Ryan (Ford) is on a \"working vacation\" in... \n",
"1 Four boys around the age of 10 are friends in ... \n",
"2 \n",
"3 Fred Dobbs (Humphrey Bogart) and Bob Curtin (T... \n",
"4 Jim McAllister (Matthew Broderick) is a much-a... "
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_details.head()"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "a7591d12",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 1572 entries, 0 to 1571\n",
"Data columns (total 7 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 movie_id 1572 non-null object \n",
" 1 plot_summary 1572 non-null object \n",
" 2 duration 1572 non-null object \n",
" 3 genre 1572 non-null object \n",
" 4 rating 1572 non-null float64\n",
" 5 release_date 1572 non-null object \n",
" 6 plot_synopsis 1572 non-null object \n",
"dtypes: float64(1), object(6)\n",
"memory usage: 86.1+ KB\n"
]
}
],
"source": [
"df_details.info()"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "0e45373d",
"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>review_date</th>\n",
" <th>movie_id</th>\n",
" <th>user_id</th>\n",
" <th>is_spoiler</th>\n",
" <th>review_text</th>\n",
" <th>rating</th>\n",
" <th>review_summary</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>10 February 2006</td>\n",
" <td>tt0111161</td>\n",
" <td>ur1898687</td>\n",
" <td>True</td>\n",
" <td>In its Oscar year, Shawshank Redemption (writt...</td>\n",
" <td>10</td>\n",
" <td>A classic piece of unforgettable film-making.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>6 September 2000</td>\n",
" <td>tt0111161</td>\n",
" <td>ur0842118</td>\n",
" <td>True</td>\n",
" <td>The Shawshank Redemption is without a doubt on...</td>\n",
" <td>10</td>\n",
" <td>Simply amazing. The best film of the 90's.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3 August 2001</td>\n",
" <td>tt0111161</td>\n",
" <td>ur1285640</td>\n",
" <td>True</td>\n",
" <td>I believe that this film is the best story eve...</td>\n",
" <td>8</td>\n",
" <td>The best story ever told on film</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1 September 2002</td>\n",
" <td>tt0111161</td>\n",
" <td>ur1003471</td>\n",
" <td>True</td>\n",
" <td>**Yes, there are SPOILERS here**This film has ...</td>\n",
" <td>10</td>\n",
" <td>Busy dying or busy living?</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>20 May 2004</td>\n",
" <td>tt0111161</td>\n",
" <td>ur0226855</td>\n",
" <td>True</td>\n",
" <td>At the heart of this extraordinary movie is a ...</td>\n",
" <td>8</td>\n",
" <td>Great story, wondrously told and acted</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" review_date movie_id user_id is_spoiler \\\n",
"0 10 February 2006 tt0111161 ur1898687 True \n",
"1 6 September 2000 tt0111161 ur0842118 True \n",
"2 3 August 2001 tt0111161 ur1285640 True \n",
"3 1 September 2002 tt0111161 ur1003471 True \n",
"4 20 May 2004 tt0111161 ur0226855 True \n",
"\n",
" review_text rating \\\n",
"0 In its Oscar year, Shawshank Redemption (writt... 10 \n",
"1 The Shawshank Redemption is without a doubt on... 10 \n",
"2 I believe that this film is the best story eve... 8 \n",
"3 **Yes, there are SPOILERS here**This film has ... 10 \n",
"4 At the heart of this extraordinary movie is a ... 8 \n",
"\n",
" review_summary \n",
"0 A classic piece of unforgettable film-making. \n",
"1 Simply amazing. The best film of the 90's. \n",
"2 The best story ever told on film \n",
"3 Busy dying or busy living? \n",
"4 Great story, wondrously told and acted "
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_analysed_reviews = df_reviews.copy()\n",
"df_analysed_reviews.head()"
]
},
{
"cell_type": "code",
"execution_count": 52,
"id": "2c2a0ffe",
"metadata": {},
"outputs": [],
"source": [
"stop_words = list(set(stopwords.words('english')))\n",
"len_1 = []\n",
"for w in word_tokenize(df_reviews.iloc[0][4]):\n",
" if len(w) == 1:\n",
" len_1.append(w)\n",
" \n",
"for sym in len_1:\n",
" stop_words.append(sym)\n",
"stop_words = set(stop_words)"
]
},
{
"cell_type": "code",
"execution_count": 53,
"id": "296ea26b",
"metadata": {},
"outputs": [],
"source": [
"ps = PorterStemmer()"
]
},
{
"cell_type": "code",
"execution_count": 56,
"id": "c494a8a3",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['cheat', 'die', 'kill']"
]
},
"execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"bad_words = [\"die\", \"dying\", \"died\", \"kill\", \"killed\", \"killing\", \"cheat\", \"cheating\", \"cheated\"]\n",
"bad_words = set([ps.stem(w) for w in bad_words])\n",
"bad_words = list(bad_words)\n",
"bad_words"
]
},
{
"cell_type": "code",
"execution_count": 57,
"id": "b69e8e62",
"metadata": {},
"outputs": [],
"source": [
"df_analysed_reviews[\"bad_flag\"] = [any([y.lower() in bad_words\n",
" for y in [ps.stem(w) for w in word_tokenize(x[4]) if not w.lower() in stop_words]])\n",
" for x in df_reviews.values]"
]
},
{
"cell_type": "code",
"execution_count": 58,
"id": "534fee23",
"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>review_date</th>\n",
" <th>movie_id</th>\n",
" <th>user_id</th>\n",
" <th>is_spoiler</th>\n",
" <th>review_text</th>\n",
" <th>rating</th>\n",
" <th>review_summary</th>\n",
" <th>bad_flag</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>10 February 2006</td>\n",
" <td>tt0111161</td>\n",
" <td>ur1898687</td>\n",
" <td>True</td>\n",
" <td>In its Oscar year, Shawshank Redemption (writt...</td>\n",
" <td>10</td>\n",
" <td>A classic piece of unforgettable film-making.</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>6 September 2000</td>\n",
" <td>tt0111161</td>\n",
" <td>ur0842118</td>\n",
" <td>True</td>\n",
" <td>The Shawshank Redemption is without a doubt on...</td>\n",
" <td>10</td>\n",
" <td>Simply amazing. The best film of the 90's.</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3 August 2001</td>\n",
" <td>tt0111161</td>\n",
" <td>ur1285640</td>\n",
" <td>True</td>\n",
" <td>I believe that this film is the best story eve...</td>\n",
" <td>8</td>\n",
" <td>The best story ever told on film</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1 September 2002</td>\n",
" <td>tt0111161</td>\n",
" <td>ur1003471</td>\n",
" <td>True</td>\n",
" <td>**Yes, there are SPOILERS here**This film has ...</td>\n",
" <td>10</td>\n",
" <td>Busy dying or busy living?</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>20 May 2004</td>\n",
" <td>tt0111161</td>\n",
" <td>ur0226855</td>\n",
" <td>True</td>\n",
" <td>At the heart of this extraordinary movie is a ...</td>\n",
" <td>8</td>\n",
" <td>Great story, wondrously told and acted</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" review_date movie_id user_id is_spoiler \\\n",
"0 10 February 2006 tt0111161 ur1898687 True \n",
"1 6 September 2000 tt0111161 ur0842118 True \n",
"2 3 August 2001 tt0111161 ur1285640 True \n",
"3 1 September 2002 tt0111161 ur1003471 True \n",
"4 20 May 2004 tt0111161 ur0226855 True \n",
"\n",
" review_text rating \\\n",
"0 In its Oscar year, Shawshank Redemption (writt... 10 \n",
"1 The Shawshank Redemption is without a doubt on... 10 \n",
"2 I believe that this film is the best story eve... 8 \n",
"3 **Yes, there are SPOILERS here**This film has ... 10 \n",
"4 At the heart of this extraordinary movie is a ... 8 \n",
"\n",
" review_summary bad_flag \n",
"0 A classic piece of unforgettable film-making. True \n",
"1 Simply amazing. The best film of the 90's. False \n",
"2 The best story ever told on film True \n",
"3 Busy dying or busy living? True \n",
"4 Great story, wondrously told and acted False "
]
},
"execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_analysed_reviews.head()"
]
},
{
"cell_type": "code",
"execution_count": 50,
"id": "bcf1a542",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Percentage distribution in the dataset of spoilers and not spoilers \n",
"\n",
"False 73.7\n",
"True 26.3\n",
"Name: is_spoiler, dtype: float64\n"
]
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"print('Percentage distribution in the dataset of spoilers and not spoilers \\n')\n",
"\n",
"# Compute distribution between classes\n",
"print(round(df_reviews.is_spoiler.value_counts(normalize=True)*100,2)) \n",
"# Plot distribution between classes \n",
"round(df_reviews.is_spoiler.value_counts(normalize=True)*100,2).plot(kind='bar')\n",
"\n",
"plt.title('Distributions')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 60,
"id": "345b9a57",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'The Shawshank Redemption is without a doubt one of the most brilliant movies I have ever seen. Similar to The Green Mile in many respects (and better than it in almost all of them), these two movies have shown us that Stephen King is a master not only of horror but also of prose that shakes the soul and moves the heart. The plot is average, but King did great things with it in his novella that are only furthered by the direction, and the acting is so top-rate it\\'s almost scary.Tim Robbins plays Andy Dufrane, wrongly imprisoned for 20 years for the murder of his wife. The story focuses on Andy\\'s relationship with \"Red\" Redding (Morgan Freeman, in probably his best role) and his attempts to escape from Shawshank. Bob Gunton is positively evil and frightening as Warden Norton, and there are great performances and cameos all around; the most prominent one being Gil Bellows (late as Billy of Ally McBeal) as Tommy, a fellow inmate of Andy\\'s who suffers under the iron will of Norton.If you haven\\'t seen this movie, GO AND RENT IT NOW. You will not be disappointed. It is positively the best movie of the \\'90\\'s, and one of my Top 3 of all time. This movie is a spectacle to move the mind, soul, and heart. 10/10'"
]
},
"execution_count": 60,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_analysed_reviews.iloc[1][4]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b45e2e8e",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.9.13 64-bit ('py39': conda)",
"language": "python",
"name": "python3913jvsc74a57bd0536dd8d7cef9e0a7a3a0f6a92439f3a8950a5c8454fb0f4b78046b15afdc533f"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|