Spaces:
Configuration error
Configuration error
File size: 109,481 Bytes
2f5c188 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"from datasets import load_dataset\n",
"import pandas as pd \n",
"from pymongo import MongoClient\n",
"from transformers import BertTokenizer, BertForMaskedLM, DPRContextEncoderTokenizer,DPRContextEncoder;\n",
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
"import numpy as np\n",
"import re\n",
"import pandas as pd\n",
"from nltk.stem import WordNetLemmatizer\n",
"from nltk.corpus import stopwords as nltk_stopwords\n",
"from transformers import BertTokenizer, BertModel, AutoTokenizer\n",
"from sklearn.metrics.pairwise import cosine_similarity\n",
"import torch\n",
"from pymongo import MongoClient\n",
"import torch.nn.functional as F"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2024-08-27 17:58:58 INFO: Checking for updates to resources.json in case models have been updated. Note: this behavior can be turned off with download_method=None or download_method=DownloadMethod.REUSE_RESOURCES\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "8ff25d869f4a47a8b1645d6a09afdb49",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Downloading https://raw.githubusercontent.com/stanfordnlp/stanza-resources/main/resources_1.8.0.json: 0%| …"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"2024-08-27 17:58:58 INFO: Downloaded file to C:\\Users\\info\\stanza_resources\\resources.json\n",
"2024-08-27 17:58:59 INFO: Loading these models for language: tr (Turkish):\n",
"=============================\n",
"| Processor | Package |\n",
"-----------------------------\n",
"| tokenize | imst |\n",
"| mwt | imst |\n",
"| pos | imst_charlm |\n",
"| lemma | imst_nocharlm |\n",
"| depparse | imst_charlm |\n",
"| ner | starlang |\n",
"=============================\n",
"\n",
"2024-08-27 17:58:59 INFO: Using device: cpu\n",
"2024-08-27 17:58:59 INFO: Loading: tokenize\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\tokenization\\trainer.py:82: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" checkpoint = torch.load(filename, lambda storage, loc: storage)\n",
"2024-08-27 17:58:59 INFO: Loading: mwt\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\mwt\\trainer.py:170: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" checkpoint = torch.load(filename, lambda storage, loc: storage)\n",
"2024-08-27 17:58:59 INFO: Loading: pos\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\pos\\trainer.py:139: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" checkpoint = torch.load(filename, lambda storage, loc: storage)\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\common\\pretrain.py:56: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" data = torch.load(self.filename, lambda storage, loc: storage)\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\common\\char_model.py:271: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" state = torch.load(filename, lambda storage, loc: storage)\n",
"2024-08-27 17:58:59 INFO: Loading: lemma\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\lemma\\trainer.py:236: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" checkpoint = torch.load(filename, lambda storage, loc: storage)\n",
"2024-08-27 17:58:59 INFO: Loading: depparse\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\depparse\\trainer.py:194: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" checkpoint = torch.load(filename, lambda storage, loc: storage)\n",
"2024-08-27 17:58:59 INFO: Loading: ner\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\ner\\trainer.py:197: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" checkpoint = torch.load(filename, lambda storage, loc: storage)\n",
"2024-08-27 17:59:00 INFO: Done loading processors!\n"
]
},
{
"ename": "TypeError",
"evalue": "'Document' object is not iterable",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[18], line 94\u001b[0m\n\u001b[0;32m 92\u001b[0m \u001b[38;5;66;03m# ---------------------------------Verilerin kaydedilmesi-------------------------------------\u001b[39;00m\n\u001b[0;32m 93\u001b[0m processor \u001b[38;5;241m=\u001b[39m DataProcessor(input_csv\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtexts_egitim.csv\u001b[39m\u001b[38;5;124m\"\u001b[39m, output_csv\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcleaned_data4.csv\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m---> 94\u001b[0m \u001b[43mprocessor\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmain_pipeline\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
"Cell \u001b[1;32mIn[18], line 74\u001b[0m, in \u001b[0;36mDataProcessor.main_pipeline\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 71\u001b[0m df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mkısaltılmıs_metin\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mmetinler\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mapply(filter_text)\n\u001b[0;32m 73\u001b[0m \u001b[38;5;66;03m# Metinleri kısalt\u001b[39;00m\n\u001b[1;32m---> 74\u001b[0m df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mkısaltılmıs_metin\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[43mdf\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mmetinler\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mapply\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43;01mlambda\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mx\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtruncate_text_meaningful\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_len\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmax_words\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 76\u001b[0m \u001b[38;5;66;03m# Tokenize et ve padding uygula\u001b[39;00m\n\u001b[0;32m 77\u001b[0m padded_tokens \u001b[38;5;241m=\u001b[39m tokenize_and_pad(df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mkısaltılmıs_metin\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mtolist(), model_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel_name)\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\pandas\\core\\series.py:4924\u001b[0m, in \u001b[0;36mSeries.apply\u001b[1;34m(self, func, convert_dtype, args, by_row, **kwargs)\u001b[0m\n\u001b[0;32m 4789\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mapply\u001b[39m(\n\u001b[0;32m 4790\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m 4791\u001b[0m func: AggFuncType,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 4796\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[0;32m 4797\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m DataFrame \u001b[38;5;241m|\u001b[39m Series:\n\u001b[0;32m 4798\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 4799\u001b[0m \u001b[38;5;124;03m Invoke function on values of Series.\u001b[39;00m\n\u001b[0;32m 4800\u001b[0m \n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 4915\u001b[0m \u001b[38;5;124;03m dtype: float64\u001b[39;00m\n\u001b[0;32m 4916\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m 4917\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mSeriesApply\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 4918\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m 4919\u001b[0m \u001b[43m \u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 4920\u001b[0m \u001b[43m \u001b[49m\u001b[43mconvert_dtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconvert_dtype\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 4921\u001b[0m \u001b[43m \u001b[49m\u001b[43mby_row\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mby_row\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 4922\u001b[0m \u001b[43m \u001b[49m\u001b[43margs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 4923\u001b[0m \u001b[43m \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m-> 4924\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mapply\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\pandas\\core\\apply.py:1427\u001b[0m, in \u001b[0;36mSeriesApply.apply\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 1424\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mapply_compat()\n\u001b[0;32m 1426\u001b[0m \u001b[38;5;66;03m# self.func is Callable\u001b[39;00m\n\u001b[1;32m-> 1427\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mapply_standard\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\pandas\\core\\apply.py:1507\u001b[0m, in \u001b[0;36mSeriesApply.apply_standard\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 1501\u001b[0m \u001b[38;5;66;03m# row-wise access\u001b[39;00m\n\u001b[0;32m 1502\u001b[0m \u001b[38;5;66;03m# apply doesn't have a `na_action` keyword and for backward compat reasons\u001b[39;00m\n\u001b[0;32m 1503\u001b[0m \u001b[38;5;66;03m# we need to give `na_action=\"ignore\"` for categorical data.\u001b[39;00m\n\u001b[0;32m 1504\u001b[0m \u001b[38;5;66;03m# TODO: remove the `na_action=\"ignore\"` when that default has been changed in\u001b[39;00m\n\u001b[0;32m 1505\u001b[0m \u001b[38;5;66;03m# Categorical (GH51645).\u001b[39;00m\n\u001b[0;32m 1506\u001b[0m action \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(obj\u001b[38;5;241m.\u001b[39mdtype, CategoricalDtype) \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m-> 1507\u001b[0m mapped \u001b[38;5;241m=\u001b[39m \u001b[43mobj\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_map_values\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 1508\u001b[0m \u001b[43m \u001b[49m\u001b[43mmapper\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcurried\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mna_action\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maction\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconvert\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconvert_dtype\u001b[49m\n\u001b[0;32m 1509\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 1511\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(mapped) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(mapped[\u001b[38;5;241m0\u001b[39m], ABCSeries):\n\u001b[0;32m 1512\u001b[0m \u001b[38;5;66;03m# GH#43986 Need to do list(mapped) in order to get treated as nested\u001b[39;00m\n\u001b[0;32m 1513\u001b[0m \u001b[38;5;66;03m# See also GH#25959 regarding EA support\u001b[39;00m\n\u001b[0;32m 1514\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m obj\u001b[38;5;241m.\u001b[39m_constructor_expanddim(\u001b[38;5;28mlist\u001b[39m(mapped), index\u001b[38;5;241m=\u001b[39mobj\u001b[38;5;241m.\u001b[39mindex)\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\pandas\\core\\base.py:921\u001b[0m, in \u001b[0;36mIndexOpsMixin._map_values\u001b[1;34m(self, mapper, na_action, convert)\u001b[0m\n\u001b[0;32m 918\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(arr, ExtensionArray):\n\u001b[0;32m 919\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m arr\u001b[38;5;241m.\u001b[39mmap(mapper, na_action\u001b[38;5;241m=\u001b[39mna_action)\n\u001b[1;32m--> 921\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43malgorithms\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmap_array\u001b[49m\u001b[43m(\u001b[49m\u001b[43marr\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmapper\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mna_action\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mna_action\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconvert\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconvert\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\pandas\\core\\algorithms.py:1743\u001b[0m, in \u001b[0;36mmap_array\u001b[1;34m(arr, mapper, na_action, convert)\u001b[0m\n\u001b[0;32m 1741\u001b[0m values \u001b[38;5;241m=\u001b[39m arr\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mobject\u001b[39m, copy\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[0;32m 1742\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m na_action \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m-> 1743\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mlib\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmap_infer\u001b[49m\u001b[43m(\u001b[49m\u001b[43mvalues\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmapper\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconvert\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconvert\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 1744\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 1745\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mmap_infer_mask(\n\u001b[0;32m 1746\u001b[0m values, mapper, mask\u001b[38;5;241m=\u001b[39misna(values)\u001b[38;5;241m.\u001b[39mview(np\u001b[38;5;241m.\u001b[39muint8), convert\u001b[38;5;241m=\u001b[39mconvert\n\u001b[0;32m 1747\u001b[0m )\n",
"File \u001b[1;32mlib.pyx:2972\u001b[0m, in \u001b[0;36mpandas._libs.lib.map_infer\u001b[1;34m()\u001b[0m\n",
"Cell \u001b[1;32mIn[18], line 74\u001b[0m, in \u001b[0;36mDataProcessor.main_pipeline.<locals>.<lambda>\u001b[1;34m(x)\u001b[0m\n\u001b[0;32m 71\u001b[0m df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mkısaltılmıs_metin\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mmetinler\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mapply(filter_text)\n\u001b[0;32m 73\u001b[0m \u001b[38;5;66;03m# Metinleri kısalt\u001b[39;00m\n\u001b[1;32m---> 74\u001b[0m df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mkısaltılmıs_metin\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mmetinler\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mapply(\u001b[38;5;28;01mlambda\u001b[39;00m x: \u001b[43mtruncate_text_meaningful\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_len\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmax_words\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[0;32m 76\u001b[0m \u001b[38;5;66;03m# Tokenize et ve padding uygula\u001b[39;00m\n\u001b[0;32m 77\u001b[0m padded_tokens \u001b[38;5;241m=\u001b[39m tokenize_and_pad(df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mkısaltılmıs_metin\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mtolist(), model_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel_name)\n",
"Cell \u001b[1;32mIn[18], line 31\u001b[0m, in \u001b[0;36mtruncate_text_meaningful\u001b[1;34m(text, max_len)\u001b[0m\n\u001b[0;32m 28\u001b[0m doc \u001b[38;5;241m=\u001b[39m nlp(text)\n\u001b[0;32m 30\u001b[0m \u001b[38;5;66;03m# Stop kelimeleri ve noktalama işaretlerini kaldır\u001b[39;00m\n\u001b[1;32m---> 31\u001b[0m tokens \u001b[38;5;241m=\u001b[39m [token\u001b[38;5;241m.\u001b[39mlemma_ \u001b[38;5;28;01mfor\u001b[39;00m token \u001b[38;5;129;01min\u001b[39;00m doc \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m token\u001b[38;5;241m.\u001b[39mis_stop \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m token\u001b[38;5;241m.\u001b[39mis_punct]\n\u001b[0;32m 33\u001b[0m \u001b[38;5;66;03m# Belirli bir uzunluktaki metni döndür\u001b[39;00m\n\u001b[0;32m 34\u001b[0m truncated_text \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(tokens[:max_len])\n",
"\u001b[1;31mTypeError\u001b[0m: 'Document' object is not iterable"
]
}
],
"source": [
"import pandas as pd\n",
"import re\n",
"from transformers import AutoTokenizer\n",
"import spacy\n",
"import stanza\n",
"\n",
"# ------------------------Cümlelerin boyutlarını ve stop words'leri tanımladığımız yer-----------------------------\n",
"# Yüklediğiniz modele göre değiştirebilirsiniz\n",
"nlp = stanza.Pipeline('tr')\n",
"\n",
"def preprocess_text(text):\n",
" doc = nlp(text)\n",
" tokens = [token.lemma_ for token in doc if not token.is_stop and not token.is_punct]\n",
" return \" \".join(tokens)\n",
"\n",
"def extract_keywords_and_subheadings(text):\n",
" doc = nlp(text)\n",
" keywords = []\n",
" subheadings = []\n",
" for ent in doc.ents:\n",
" if ent.label_ == \"ORG\" or ent.label_ == \"PERSON\": # Örnek: Kurum veya kişi isimleri\n",
" keywords.append(ent.text)\n",
" elif ent.label_ == \"GPE\": # Örnek: Yer isimleri\n",
" subheadings.append(ent.text)\n",
" return keywords, subheadings\n",
"\n",
"def truncate_text_meaningful(text, max_len=300):\n",
" # Önce metni tokenlere ayır\n",
" doc = nlp(text)\n",
"\n",
" # Stop kelimeleri ve noktalama işaretlerini kaldır\n",
" tokens = [token.lemma_ for token in doc if not token.is_stop and not token.is_punct]\n",
"\n",
" # Belirli bir uzunluktaki metni döndür\n",
" truncated_text = ' '.join(tokens[:max_len])\n",
"\n",
" return truncated_text\n",
"\n",
"# ----------------------------------Tokenize etme fonksiyonu-----------------------------------\n",
"def tokenize_and_pad(data, model_name='bert-base-uncased', max_length=512):\n",
" tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
" encoded_input = tokenizer(data, padding=True, truncation=True, max_length=max_length)\n",
" return encoded_input\n",
"\n",
"class DataProcessor:\n",
" def __init__(self, input_csv, output_csv, max_words=300, model_name='dbmdz/distilbert-base-turkish-cased'):\n",
" self.input_csv = input_csv\n",
" self.output_csv = output_csv\n",
" self.max_words = max_words\n",
" self.model_name = model_name\n",
"\n",
" def main_pipeline(self):\n",
" def filter_text(text):\n",
" # Dış bağlantılar ve kaynakçaları kaldır\n",
" text = re.sub(r'http\\S+|https\\S+|\\b(?:www\\.)?\\S+\\.\\w{2,4}\\b', '', text)\n",
" # Tarih ve sayıları kaldır\n",
" text = re.sub(r'\\d{4}-\\d{2}-\\d{2}|\\d{2}/\\d{2}/\\d{4}|\\d+', '', text)\n",
" # Sayıları kaldır\n",
" text = re.sub(r'\\d+', '', text)\n",
" # Kısa veya uzun kelimeleri kaldır\n",
" words = text.split()\n",
" words = [word for word in words if 2 <= len(word) <= 20]\n",
" return ' '.join(words)\n",
" \n",
" # UTF-8 encoding ile dosyayı okuyun\n",
" df = pd.read_csv(self.input_csv, encoding='utf-8')\n",
" \n",
" # Metinlerin sütun adını kontrol edin\n",
" if 'metinler' not in df.columns:\n",
" raise ValueError(\"CSV dosyasında 'metinler' adlı bir sütun bulunamadı. Lütfen sütun adını kontrol edin.\")\n",
" \n",
" df['kısaltılmıs_metin'] = df['metinler'].apply(filter_text)\n",
"\n",
" # Metinleri kısalt\n",
" df['kısaltılmıs_metin'] = df['metinler'].apply(lambda x: truncate_text_meaningful(x, max_len=self.max_words))\n",
"\n",
" # Tokenize et ve padding uygula\n",
" padded_tokens = tokenize_and_pad(df['kısaltılmıs_metin'].tolist(), model_name=self.model_name)\n",
" df['padded_tokens'] = padded_tokens['input_ids']\n",
"\n",
" print(\"Kısaltılmış metinler:\")\n",
" print(df['kısaltılmıs_metin'].head())\n",
" print(\"Tokenize edilmiş ve padding uygulanmış veriler:\")\n",
" print(df[['kısaltılmıs_metin', 'padded_tokens']].head())\n",
"\n",
" # Veriyi kaydet\n",
" self.save_cleaned_data(df)\n",
" \n",
" def save_cleaned_data(self, df):\n",
" df.to_csv(self.output_csv, index=False, encoding='utf-8')\n",
" print(f\"Temizlenmiş veri '{self.output_csv}' dosyasına kaydedildi.\")\n",
"\n",
"# ---------------------------------Verilerin kaydedilmesi-------------------------------------\n",
"processor = DataProcessor(input_csv=\"texts_egitim.csv\", output_csv=\"cleaned_data4.csv\")\n",
"processor.main_pipeline()\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"ename": "ValueError",
"evalue": "The language 'turkish' is not supported.",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[4], line 6\u001b[0m\n\u001b[0;32m 3\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;01msnowball\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m SnowballStemmer\n\u001b[0;32m 5\u001b[0m \u001b[38;5;66;03m# Türkçe stemmer\u001b[39;00m\n\u001b[1;32m----> 6\u001b[0m stemmer \u001b[38;5;241m=\u001b[39m \u001b[43mSnowballStemmer\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mturkish\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[0;32m 8\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mstem_text\u001b[39m(text):\n\u001b[0;32m 9\u001b[0m words \u001b[38;5;241m=\u001b[39m text\u001b[38;5;241m.\u001b[39msplit()\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\nltk\\stem\\snowball.py:106\u001b[0m, in \u001b[0;36mSnowballStemmer.__init__\u001b[1;34m(self, language, ignore_stopwords)\u001b[0m\n\u001b[0;32m 104\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__init__\u001b[39m(\u001b[38;5;28mself\u001b[39m, language, ignore_stopwords\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[0;32m 105\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m language \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlanguages:\n\u001b[1;32m--> 106\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThe language \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mlanguage\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m is not supported.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 107\u001b[0m stemmerclass \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mglobals\u001b[39m()[language\u001b[38;5;241m.\u001b[39mcapitalize() \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mStemmer\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[0;32m 108\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstemmer \u001b[38;5;241m=\u001b[39m stemmerclass(ignore_stopwords)\n",
"\u001b[1;31mValueError\u001b[0m: The language 'turkish' is not supported."
]
}
],
"source": [
"import re\n",
"import pandas as pd\n",
"from nltk.stem.snowball import SnowballStemmer\n",
"\n",
"# Türkçe stemmer\n",
"stemmer = SnowballStemmer(\"turkish\")\n",
"\n",
"def stem_text(text):\n",
" words = text.split()\n",
" stemmed_words = [stemmer.stem(word) for word in words]\n",
" return ' '.join(stemmed_words)\n",
"\n",
"class DataProcessor:\n",
" def __init__(self, input_csv, output_csv, max_words=300, model_name='dbmdz/distilbert-base-turkish-cased'):\n",
" self.input_csv = input_csv\n",
" self.output_csv = output_csv\n",
" self.max_words = max_words\n",
" self.model_name = model_name\n",
"\n",
" def main_pipeline(self):\n",
" def filter_text(text):\n",
" # Dış bağlantılar ve kaynakçaları kaldır\n",
" text = re.sub(r'http\\S+|https\\S+|\\b(?:www\\.)?\\S+\\.\\w{2,4}\\b', '', text)\n",
" # Tarih ve sayıları kaldır\n",
" text = re.sub(r'\\d{4}-\\d{2}-\\d{2}|\\d{2}/\\d{2}/\\d{4}|\\d+', '', text)\n",
" # Sayıları kaldır\n",
" text = re.sub(r'\\d+', '', text)\n",
" # Kısa veya uzun kelimeleri kaldır\n",
" words = text.split()\n",
" words = [word for word in words if 2 <= len(word) <= 20]\n",
" return ' '.join(words)\n",
" \n",
" # UTF-8 encoding ile dosyayı okuyun\n",
" df = pd.read_csv(self.input_csv, encoding='utf-8')\n",
"\n",
" # Metinleri filtrele\n",
" df['filtered_text'] = df['metinler'].apply(filter_text)\n",
"\n",
" # Filtrelenmiş metinleri stem (kök) yap\n",
" df['stemmed_text'] = df['filtered_text'].apply(stem_text)\n",
"\n",
" # Sonuçları yeni bir CSV dosyasına kaydet\n",
" df.to_csv(self.output_csv, index=False, encoding='utf-8')\n",
"\n",
"# Kullanım örneği\n",
"processor = DataProcessor(input_csv='texts_egitim.csv', output_csv='cleaned_data4.csv')\n",
"processor.main_pipeline()\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2024-08-28 11:26:01 INFO: Checking for updates to resources.json in case models have been updated. Note: this behavior can be turned off with download_method=None or download_method=DownloadMethod.REUSE_RESOURCES\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "2af6508a7b6c48619ba0d6b3ce69e73b",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Downloading https://raw.githubusercontent.com/stanfordnlp/stanza-resources/main/resources_1.8.0.json: 0%| …"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"2024-08-28 11:26:02 INFO: Downloaded file to C:\\Users\\info\\stanza_resources\\resources.json\n",
"2024-08-28 11:26:02 INFO: Loading these models for language: tr (Turkish):\n",
"=============================\n",
"| Processor | Package |\n",
"-----------------------------\n",
"| tokenize | imst |\n",
"| mwt | imst |\n",
"| pos | imst_charlm |\n",
"| lemma | imst_nocharlm |\n",
"| ner | starlang |\n",
"=============================\n",
"\n",
"2024-08-28 11:26:02 INFO: Using device: cpu\n",
"2024-08-28 11:26:02 INFO: Loading: tokenize\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\tokenization\\trainer.py:82: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" checkpoint = torch.load(filename, lambda storage, loc: storage)\n",
"2024-08-28 11:26:02 INFO: Loading: mwt\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\mwt\\trainer.py:170: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" checkpoint = torch.load(filename, lambda storage, loc: storage)\n",
"2024-08-28 11:26:02 INFO: Loading: pos\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\pos\\trainer.py:139: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" checkpoint = torch.load(filename, lambda storage, loc: storage)\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\common\\pretrain.py:56: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" data = torch.load(self.filename, lambda storage, loc: storage)\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\common\\char_model.py:271: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" state = torch.load(filename, lambda storage, loc: storage)\n",
"2024-08-28 11:26:02 INFO: Loading: lemma\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\lemma\\trainer.py:236: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" checkpoint = torch.load(filename, lambda storage, loc: storage)\n",
"2024-08-28 11:26:02 INFO: Loading: ner\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\stanza\\models\\ner\\trainer.py:197: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" checkpoint = torch.load(filename, lambda storage, loc: storage)\n",
"2024-08-28 11:26:03 INFO: Done loading processors!\n"
]
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n",
"\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n",
"\u001b[1;31mClick <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. \n",
"\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
]
}
],
"source": [
"import pandas as pd\n",
"import re\n",
"from transformers import AutoTokenizer\n",
"import spacy\n",
"import stanza\n",
"\n",
"# ------------------------ Cümlelerin boyutlarını ve stop words'leri tanımladığımız yer -----------------------------\n",
"nlp = stanza.Pipeline('tr', processors='tokenize,mwt,pos,lemma,ner')\n",
"\n",
"def preprocess_text(text, stopwords):\n",
" doc = nlp(text)\n",
" tokens = [\n",
" word.lemma if word.lemma is not None else word.text\n",
" for sentence in doc.sentences\n",
" for word in sentence.words\n",
" if word.text.lower() not in stopwords\n",
" ]\n",
" return \" \".join(tokens)\n",
"\n",
"def extract_keywords_and_subheadings(text):\n",
" doc = nlp(text)\n",
" keywords = []\n",
" subheadings = []\n",
" for ent in doc.ents:\n",
" if ent.label_ == \"ORG\" or ent.label_ == \"PERSON\": # Örnek: Kurum veya kişi isimleri\n",
" keywords.append(ent.text)\n",
" elif ent.label_ == \"GPE\": # Örnek: Yer isimleri\n",
" subheadings.append(ent.text)\n",
" return keywords, subheadings\n",
"\n",
"def truncate_text_meaningful(text, max_len=300):\n",
" doc = nlp(text)\n",
" tokens = [word.lemma if word.lemma is not None else word.text for word in doc.words]\n",
" truncated_text = ' '.join(tokens[:max_len])\n",
" return truncated_text\n",
"\n",
"def tokenize_and_pad(data, model_name='bert-base-uncased', max_length=512):\n",
" tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
" encoded_input = tokenizer(data, padding=True, truncation=True, max_length=max_length)\n",
" return encoded_input\n",
"\n",
"class DataProcessor:\n",
" def __init__(self, input_csv, output_csv, stopword_file, max_words=300, model_name='dbmdz/distilbert-base-turkish-cased'):\n",
" self.input_csv = input_csv\n",
" self.output_csv = output_csv\n",
" self.stopword_file = stopword_file\n",
" self.max_words = max_words\n",
" self.model_name = model_name\n",
" self.stopwords = self.load_stopwords()\n",
"\n",
" def load_stopwords(self):\n",
" with open(self.stopword_file, 'r', encoding='utf-8') as file:\n",
" stopwords = set(file.read().split())\n",
" return stopwords\n",
"\n",
" def main_pipeline(self):\n",
" def filter_text(text):\n",
" text = re.sub(r'http\\S+|https\\S+|\\b(?:www\\.)?\\S+\\.\\w{2,4}\\b', '', text)\n",
" text = re.sub(r'\\d{4}-\\d{2}-\\d{2}|\\d{2}/\\d{2}/\\d{4}|\\d+', '', text)\n",
" text = re.sub(r'\\d+', '', text)\n",
" words = text.split()\n",
" words = [word for word in words if 2 <= len(word) <= 20]\n",
" return ' '.join(words)\n",
" \n",
" df = pd.read_csv(self.input_csv, encoding='utf-8')\n",
" \n",
" if 'metinler' not in df.columns:\n",
" raise ValueError(\"CSV dosyasında 'metinler' adlı bir sütun bulunamadı. Lütfen sütun adını kontrol edin.\")\n",
" \n",
" df['kısaltılmıs_metin'] = df['metinler'].apply(lambda x: preprocess_text(x, self.stopwords))\n",
" df['kısaltılmıs_metin'] = df['kısaltılmıs_metin'].apply(lambda x: truncate_text_meaningful(x, max_len=self.max_words))\n",
"\n",
" padded_tokens = tokenize_and_pad(df['kısaltılmıs_metin'].tolist(), model_name=self.model_name)\n",
" df['padded_tokens'] = padded_tokens['input_ids']\n",
"\n",
" print(\"Kısaltılmış metinler:\")\n",
" print(df['kısaltılmıs_metin'].head())\n",
" print(\"Tokenize edilmiş ve padding uygulanmış veriler:\")\n",
" print(df[['kısaltılmıs_metin', 'padded_tokens']].head())\n",
"\n",
" self.save_cleaned_data(df)\n",
" \n",
" def save_cleaned_data(self, df):\n",
" df.to_csv(self.output_csv, index=False, encoding='utf-8')\n",
" print(f\"Temizlenmiş veri '{self.output_csv}' dosyasına kaydedildi.\")\n",
"\n",
"processor = DataProcessor(input_csv=\"texts_egitim.csv\", output_csv=\"cleaned_data4.csv\", stopword_file=\"gereksiz_kelimeler.txt\")\n",
"processor.main_pipeline()\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from transformers import AutoModel, AutoTokenizer\n",
"import torch\n",
"from sklearn.metrics.pairwise import cosine_similarity\n",
"\n",
"# Model ve tokenizer'ı yükleme\n",
"model_name = 'dbmdz/distilbert-base-turkish-cased'\n",
"tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
"model = AutoModel.from_pretrained(model_name)\n",
"\n",
"def get_embeddings(text):\n",
" inputs = tokenizer(text, return_tensors='pt', truncation=True, padding=True)\n",
" with torch.no_grad():\n",
" outputs = model(**inputs)\n",
" # İlk özniteliklerin ortalamasını alarak vektör elde etme\n",
" embeddings = outputs.last_hidden_state.mean(dim=1).squeeze()\n",
" return embeddings\n",
"\n",
"def generate_subheadings(title, keywords, top_n=5):\n",
" title_embedding = get_embeddings(title)\n",
" keyword_embeddings = [get_embeddings(keyword) for keyword in keywords]\n",
"\n",
" similarities = [cosine_similarity(title_embedding.unsqueeze(0), keyword_embedding.unsqueeze(0))[0][0] for keyword_embedding in keyword_embeddings]\n",
" sorted_indices = sorted(range(len(similarities)), key=lambda i: similarities[i], reverse=True)\n",
"\n",
" # Benzerliklere göre anahtar kelimelerden alt başlıklar oluşturma\n",
" subheadings = [keywords[i] for i in sorted_indices[:top_n]]\n",
" return subheadings\n",
"\n",
"# Örnek veri\n",
"title = \"Veri Bilimi Nedir?\"\n",
"keywords = [\"Makine Öğrenmesi\", \"Büyük Veri\", \"Yapay Zeka\", \"1936\", \"Veri Madenciliği\", \"Derin Öğrenme\", \"Doğal Dil İşleme\", \"1982\", \"Yapay Sinir Ağları\", \"Kümeleme\"]\n",
"\n",
"# Alt başlıkları oluşturma\n",
"subheadings = generate_subheadings(title, keywords)\n",
"print(\"Alt Başlıklar:\")\n",
"for subheading in subheadings:\n",
" print(f\"- {subheading}\")\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" kısaltılmıs_metin\n",
"0 W F 295–596 P N 82 3–211 78 pp 137–146 5–537 \"...\n",
"1 Pasaportunun Ama 1934 Balıkesir'de Doktoru Pro...\n",
"2 hesaplamalar ortalarına 2 II Bu kümesi İlk II ...\n",
"3 1 20 14 19 12 14 Yazın Türkçedir Zaman geçirmi...\n",
"4 \" ) inşasıyla ilgilenir \"Ters mühendislik, müh...\n",
"... ...\n",
"104103 Xenocicerina, Cicerininae altfamilyasına cinsi...\n",
"104104 Paracicerina, Cicerininae altfamilyasına cinsi...\n",
"104105 Lig futbolcuları Yasin Güreler (d Lig futbolcu...\n",
"104106 Elvertia, Kalyptorhynchia seksiyonuna cinsidir...\n",
"104107 Kaynakça Ek Hartcher New York: HarperCollins M...\n",
"\n",
"[104108 rows x 1 columns]\n"
]
},
{
"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>kısaltılmıs_metin</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>W F 295–596 P N 82 3–211 78 pp 137–146 5–537 \"...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Pasaportunun Ama 1934 Balıkesir'de Doktoru Pro...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>hesaplamalar ortalarına 2 II Bu kümesi İlk II ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1 20 14 19 12 14 Yazın Türkçedir Zaman geçirmi...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>\" ) inşasıyla ilgilenir \"Ters mühendislik, müh...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104103</th>\n",
" <td>Xenocicerina, Cicerininae altfamilyasına cinsi...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104104</th>\n",
" <td>Paracicerina, Cicerininae altfamilyasına cinsi...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104105</th>\n",
" <td>Lig futbolcuları Yasin Güreler (d Lig futbolcu...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104106</th>\n",
" <td>Elvertia, Kalyptorhynchia seksiyonuna cinsidir...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104107</th>\n",
" <td>Kaynakça Ek Hartcher New York: HarperCollins M...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>104108 rows × 1 columns</p>\n",
"</div>"
],
"text/plain": [
" kısaltılmıs_metin\n",
"0 W F 295–596 P N 82 3–211 78 pp 137–146 5–537 \"...\n",
"1 Pasaportunun Ama 1934 Balıkesir'de Doktoru Pro...\n",
"2 hesaplamalar ortalarına 2 II Bu kümesi İlk II ...\n",
"3 1 20 14 19 12 14 Yazın Türkçedir Zaman geçirmi...\n",
"4 \" ) inşasıyla ilgilenir \"Ters mühendislik, müh...\n",
"... ...\n",
"104103 Xenocicerina, Cicerininae altfamilyasına cinsi...\n",
"104104 Paracicerina, Cicerininae altfamilyasına cinsi...\n",
"104105 Lig futbolcuları Yasin Güreler (d Lig futbolcu...\n",
"104106 Elvertia, Kalyptorhynchia seksiyonuna cinsidir...\n",
"104107 Kaynakça Ek Hartcher New York: HarperCollins M...\n",
"\n",
"[104108 rows x 1 columns]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import pandas as pd\n",
"\n",
"# CSV dosyasını oku\n",
"df = pd.read_csv('cleaned_data.csv')\n",
"\n",
"# Görmek istediğiniz üç sütunu seçin\n",
"selected_columns = df[['kısaltılmıs_metin']]\n",
"\n",
"# Seçilen sütunları tablo olarak görüntüle\n",
"print(selected_columns)\n",
"\n",
"# Eğer Jupyter Notebook kullanıyorsanız, daha güzel görüntü için display() fonksiyonunu kullanabilirsiniz:\n",
"from IPython.display import display\n",
"display(selected_columns)\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" padded_tokens\n",
"0 [2, 59, 42, 4550, 1092, 550, 8528, 1062, 52, 5...\n",
"1 [2, 7722, 11428, 2297, 2742, 7395, 1119, 10491...\n",
"2 [2, 16306, 1980, 3008, 2431, 22, 6477, 2123, 2...\n",
"3 [2, 21, 2146, 3226, 2401, 2836, 3226, 27718, 5...\n",
"4 [2, 6, 13, 29132, 2218, 5999, 1977, 6, 24444, ...\n",
"... ...\n",
"104103 [2, 60, 1975, 2370, 6546, 4689, 1006, 16, 39, ...\n",
"104104 [2, 8149, 2329, 5790, 3930, 16, 39, 6546, 4689...\n",
"104105 [2, 5379, 17315, 1048, 19661, 5646, 2070, 12, ...\n",
"104106 [2, 3026, 11411, 4475, 16, 3771, 1032, 6728, 1...\n",
"104107 [2, 7934, 2548, 2951, 3698, 1023, 14059, 5510,...\n",
"\n",
"[104108 rows x 1 columns]\n"
]
},
{
"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>padded_tokens</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>[2, 59, 42, 4550, 1092, 550, 8528, 1062, 52, 5...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>[2, 7722, 11428, 2297, 2742, 7395, 1119, 10491...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>[2, 16306, 1980, 3008, 2431, 22, 6477, 2123, 2...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>[2, 21, 2146, 3226, 2401, 2836, 3226, 27718, 5...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>[2, 6, 13, 29132, 2218, 5999, 1977, 6, 24444, ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104103</th>\n",
" <td>[2, 60, 1975, 2370, 6546, 4689, 1006, 16, 39, ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104104</th>\n",
" <td>[2, 8149, 2329, 5790, 3930, 16, 39, 6546, 4689...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104105</th>\n",
" <td>[2, 5379, 17315, 1048, 19661, 5646, 2070, 12, ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104106</th>\n",
" <td>[2, 3026, 11411, 4475, 16, 3771, 1032, 6728, 1...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104107</th>\n",
" <td>[2, 7934, 2548, 2951, 3698, 1023, 14059, 5510,...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>104108 rows × 1 columns</p>\n",
"</div>"
],
"text/plain": [
" padded_tokens\n",
"0 [2, 59, 42, 4550, 1092, 550, 8528, 1062, 52, 5...\n",
"1 [2, 7722, 11428, 2297, 2742, 7395, 1119, 10491...\n",
"2 [2, 16306, 1980, 3008, 2431, 22, 6477, 2123, 2...\n",
"3 [2, 21, 2146, 3226, 2401, 2836, 3226, 27718, 5...\n",
"4 [2, 6, 13, 29132, 2218, 5999, 1977, 6, 24444, ...\n",
"... ...\n",
"104103 [2, 60, 1975, 2370, 6546, 4689, 1006, 16, 39, ...\n",
"104104 [2, 8149, 2329, 5790, 3930, 16, 39, 6546, 4689...\n",
"104105 [2, 5379, 17315, 1048, 19661, 5646, 2070, 12, ...\n",
"104106 [2, 3026, 11411, 4475, 16, 3771, 1032, 6728, 1...\n",
"104107 [2, 7934, 2548, 2951, 3698, 1023, 14059, 5510,...\n",
"\n",
"[104108 rows x 1 columns]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import pandas as pd\n",
"\n",
"# CSV dosyasını oku\n",
"df = pd.read_csv('cleaned_data.csv')\n",
"\n",
"# Görmek istediğiniz üç sütunu seçin\n",
"selected_columns = df[['padded_tokens']]\n",
"\n",
"# Seçilen sütunları tablo olarak görüntüle\n",
"print(selected_columns)\n",
"\n",
"# Eğer Jupyter Notebook kullanıyorsanız, daha güzel görüntü için display() fonksiyonunu kullanabilirsiniz:\n",
"from IPython.display import display\n",
"display(selected_columns)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from gensim import corpora\n",
"from gensim.models import LdaMulticore\n",
"import pandas as pd\n",
"\n",
"# CSV dosyasını okuma\n",
"df = pd.read_csv('cleaned_data3.csv')\n",
"\n",
"# Verinin bir alt kümesini seçme\n",
"df_sample = df.sample(n=10000, random_state=100)\n",
"\n",
"# Kelimeleri token'lara ayırma\n",
"tokenized_text = [text.split() for text in df_sample['kısaltılmıs_metin']]\n",
"\n",
"# Dictionary ve Corpus oluşturma\n",
"id2word = corpora.Dictionary(tokenized_text)\n",
"corpus = [id2word.doc2bow(text) for text in tokenized_text]\n",
"\n",
"# LDA Modelini Eğitme\n",
"lda_model = LdaMulticore(\n",
" corpus=corpus,\n",
" id2word=id2word,\n",
" num_topics=5,\n",
" random_state=100,\n",
" chunksize=50,\n",
" passes=5,\n",
" alpha='symmetric',\n",
" eta='auto',\n",
" per_word_topics=True,\n",
" workers=4 # Paralel iş parçacıkları kullanarak performansı artırır\n",
")\n",
"\n",
"# Sonuçları görüntüleme\n",
"for idx, topic in lda_model.print_topics(-1):\n",
" print(f\"Topic: {idx}\\nWords: {topic}\\n\")\n",
"\n",
"# Alt kümesini kaydetme\n",
"df_sample.to_csv('cleaned_processed_data.csv', index=False)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Subheadings belirleme "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\sentence_transformers\\cross_encoder\\CrossEncoder.py:11: TqdmExperimentalWarning: Using `tqdm.autonotebook.tqdm` in notebook mode. Use `tqdm.tqdm` instead to force console mode (e.g. in jupyter console)\n",
" from tqdm.autonotebook import tqdm, trange\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\utils\\generic.py:441: FutureWarning: `torch.utils._pytree._register_pytree_node` is deprecated. Please use `torch.utils._pytree.register_pytree_node` instead.\n",
" _torch_pytree._register_pytree_node(\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\utils\\generic.py:309: FutureWarning: `torch.utils._pytree._register_pytree_node` is deprecated. Please use `torch.utils._pytree.register_pytree_node` instead.\n",
" _torch_pytree._register_pytree_node(\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\huggingface_hub\\file_download.py:1150: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
" warnings.warn(\n",
"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\utils\\generic.py:309: FutureWarning: `torch.utils._pytree._register_pytree_node` is deprecated. Please use `torch.utils._pytree.register_pytree_node` instead.\n",
" _torch_pytree._register_pytree_node(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Batch 1 işlenip kaydedildi.\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[1], line 71\u001b[0m\n\u001b[0;32m 68\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mSubheadings başarıyla \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124msubheadings.csv\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m dosyasına kaydedildi.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 70\u001b[0m \u001b[38;5;66;03m# CSV'ye yazma işlemini başlatma\u001b[39;00m\n\u001b[1;32m---> 71\u001b[0m \u001b[43mprocess_documents\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
"Cell \u001b[1;32mIn[1], line 54\u001b[0m, in \u001b[0;36mprocess_documents\u001b[1;34m(batch_size, top_n_subheadings)\u001b[0m\n\u001b[0;32m 51\u001b[0m keywords \u001b[38;5;241m=\u001b[39m doc[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mkeywords\u001b[39m\u001b[38;5;124m'\u001b[39m]\n\u001b[0;32m 52\u001b[0m text \u001b[38;5;241m=\u001b[39m doc[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtext\u001b[39m\u001b[38;5;124m'\u001b[39m]\n\u001b[1;32m---> 54\u001b[0m top_subheadings \u001b[38;5;241m=\u001b[39m \u001b[43mget_top_subheadings\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtitle\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkeywords\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtext\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 56\u001b[0m \u001b[38;5;66;03m# Verileri listeye ekleyin\u001b[39;00m\n\u001b[0;32m 57\u001b[0m data\u001b[38;5;241m.\u001b[39mappend({\n\u001b[0;32m 58\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mTitle\u001b[39m\u001b[38;5;124m'\u001b[39m: title,\n\u001b[0;32m 59\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mKeywords\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m, \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(keywords),\n\u001b[0;32m 60\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mSubheadings\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m; \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(top_subheadings)\n\u001b[0;32m 61\u001b[0m })\n",
"Cell \u001b[1;32mIn[1], line 32\u001b[0m, in \u001b[0;36mget_top_subheadings\u001b[1;34m(title, keywords, text, top_n)\u001b[0m\n\u001b[0;32m 30\u001b[0m keywords_embedding \u001b[38;5;241m=\u001b[39m embed_text(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(keywords))\n\u001b[0;32m 31\u001b[0m subheadings \u001b[38;5;241m=\u001b[39m extract_subheadings(text)\n\u001b[1;32m---> 32\u001b[0m subheadings_embeddings \u001b[38;5;241m=\u001b[39m [embed_text(sub) \u001b[38;5;28;01mfor\u001b[39;00m sub \u001b[38;5;129;01min\u001b[39;00m subheadings]\n\u001b[0;32m 34\u001b[0m scores \u001b[38;5;241m=\u001b[39m [cosine_similarity([title_embedding], [embedding])[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;241m0\u001b[39m] \u001b[38;5;241m+\u001b[39m \n\u001b[0;32m 35\u001b[0m cosine_similarity([keywords_embedding], [embedding])[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m 36\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m embedding \u001b[38;5;129;01min\u001b[39;00m subheadings_embeddings]\n\u001b[0;32m 38\u001b[0m top_indices \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39margsort(scores)[\u001b[38;5;241m-\u001b[39mtop_n:]\n",
"Cell \u001b[1;32mIn[1], line 32\u001b[0m, in \u001b[0;36m<listcomp>\u001b[1;34m(.0)\u001b[0m\n\u001b[0;32m 30\u001b[0m keywords_embedding \u001b[38;5;241m=\u001b[39m embed_text(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(keywords))\n\u001b[0;32m 31\u001b[0m subheadings \u001b[38;5;241m=\u001b[39m extract_subheadings(text)\n\u001b[1;32m---> 32\u001b[0m subheadings_embeddings \u001b[38;5;241m=\u001b[39m [\u001b[43membed_text\u001b[49m\u001b[43m(\u001b[49m\u001b[43msub\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m sub \u001b[38;5;129;01min\u001b[39;00m subheadings]\n\u001b[0;32m 34\u001b[0m scores \u001b[38;5;241m=\u001b[39m [cosine_similarity([title_embedding], [embedding])[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;241m0\u001b[39m] \u001b[38;5;241m+\u001b[39m \n\u001b[0;32m 35\u001b[0m cosine_similarity([keywords_embedding], [embedding])[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m 36\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m embedding \u001b[38;5;129;01min\u001b[39;00m subheadings_embeddings]\n\u001b[0;32m 38\u001b[0m top_indices \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39margsort(scores)[\u001b[38;5;241m-\u001b[39mtop_n:]\n",
"Cell \u001b[1;32mIn[1], line 25\u001b[0m, in \u001b[0;36membed_text\u001b[1;34m(text)\u001b[0m\n\u001b[0;32m 24\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21membed_text\u001b[39m(text):\n\u001b[1;32m---> 25\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\sentence_transformers\\SentenceTransformer.py:517\u001b[0m, in \u001b[0;36mSentenceTransformer.encode\u001b[1;34m(self, sentences, prompt_name, prompt, batch_size, show_progress_bar, output_value, precision, convert_to_numpy, convert_to_tensor, device, normalize_embeddings)\u001b[0m\n\u001b[0;32m 514\u001b[0m features\u001b[38;5;241m.\u001b[39mupdate(extra_features)\n\u001b[0;32m 516\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mno_grad():\n\u001b[1;32m--> 517\u001b[0m out_features \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mforward\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfeatures\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 518\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdevice\u001b[38;5;241m.\u001b[39mtype \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhpu\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[0;32m 519\u001b[0m out_features \u001b[38;5;241m=\u001b[39m copy\u001b[38;5;241m.\u001b[39mdeepcopy(out_features)\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\container.py:219\u001b[0m, in \u001b[0;36mSequential.forward\u001b[1;34m(self, input)\u001b[0m\n\u001b[0;32m 217\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m):\n\u001b[0;32m 218\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m module \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m:\n\u001b[1;32m--> 219\u001b[0m \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[43mmodule\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[0;32m 220\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28minput\u001b[39m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\module.py:1553\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1551\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m 1552\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1553\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1557\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m 1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m 1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m 1560\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m 1561\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1562\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m 1565\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\sentence_transformers\\models\\Transformer.py:118\u001b[0m, in \u001b[0;36mTransformer.forward\u001b[1;34m(self, features)\u001b[0m\n\u001b[0;32m 115\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtoken_type_ids\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m features:\n\u001b[0;32m 116\u001b[0m trans_features[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtoken_type_ids\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m features[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtoken_type_ids\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m--> 118\u001b[0m output_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mauto_model(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mtrans_features, return_dict\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[0;32m 119\u001b[0m output_tokens \u001b[38;5;241m=\u001b[39m output_states[\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m 121\u001b[0m features\u001b[38;5;241m.\u001b[39mupdate({\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtoken_embeddings\u001b[39m\u001b[38;5;124m\"\u001b[39m: output_tokens, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mattention_mask\u001b[39m\u001b[38;5;124m\"\u001b[39m: features[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mattention_mask\u001b[39m\u001b[38;5;124m\"\u001b[39m]})\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\module.py:1553\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1551\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m 1552\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1553\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1557\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m 1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m 1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m 1560\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m 1561\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1562\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m 1565\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\models\\bert\\modeling_bert.py:1013\u001b[0m, in \u001b[0;36mBertModel.forward\u001b[1;34m(self, input_ids, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, encoder_hidden_states, encoder_attention_mask, past_key_values, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[0;32m 1004\u001b[0m head_mask \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mget_head_mask(head_mask, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39mnum_hidden_layers)\n\u001b[0;32m 1006\u001b[0m embedding_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39membeddings(\n\u001b[0;32m 1007\u001b[0m input_ids\u001b[38;5;241m=\u001b[39minput_ids,\n\u001b[0;32m 1008\u001b[0m position_ids\u001b[38;5;241m=\u001b[39mposition_ids,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 1011\u001b[0m past_key_values_length\u001b[38;5;241m=\u001b[39mpast_key_values_length,\n\u001b[0;32m 1012\u001b[0m )\n\u001b[1;32m-> 1013\u001b[0m encoder_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoder\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 1014\u001b[0m \u001b[43m \u001b[49m\u001b[43membedding_output\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1015\u001b[0m \u001b[43m \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextended_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1016\u001b[0m \u001b[43m \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mhead_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1017\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1018\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoder_attention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoder_extended_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1019\u001b[0m \u001b[43m \u001b[49m\u001b[43mpast_key_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1020\u001b[0m \u001b[43m \u001b[49m\u001b[43muse_cache\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_cache\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1021\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1022\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1023\u001b[0m \u001b[43m \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_dict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1024\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 1025\u001b[0m sequence_output \u001b[38;5;241m=\u001b[39m encoder_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m 1026\u001b[0m pooled_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpooler(sequence_output) \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpooler \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\module.py:1553\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1551\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m 1552\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1553\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1557\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m 1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m 1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m 1560\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m 1561\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1562\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m 1565\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\models\\bert\\modeling_bert.py:607\u001b[0m, in \u001b[0;36mBertEncoder.forward\u001b[1;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_values, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[0;32m 596\u001b[0m layer_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_gradient_checkpointing_func(\n\u001b[0;32m 597\u001b[0m layer_module\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__call__\u001b[39m,\n\u001b[0;32m 598\u001b[0m hidden_states,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 604\u001b[0m output_attentions,\n\u001b[0;32m 605\u001b[0m )\n\u001b[0;32m 606\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 607\u001b[0m layer_outputs \u001b[38;5;241m=\u001b[39m \u001b[43mlayer_module\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 608\u001b[0m \u001b[43m \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 609\u001b[0m \u001b[43m \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 610\u001b[0m \u001b[43m \u001b[49m\u001b[43mlayer_head_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 611\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 612\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoder_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 613\u001b[0m \u001b[43m \u001b[49m\u001b[43mpast_key_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 614\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 615\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 617\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m layer_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m 618\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m use_cache:\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\module.py:1553\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1551\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m 1552\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1553\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1557\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m 1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m 1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m 1560\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m 1561\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1562\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m 1565\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\models\\bert\\modeling_bert.py:497\u001b[0m, in \u001b[0;36mBertLayer.forward\u001b[1;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_value, output_attentions)\u001b[0m\n\u001b[0;32m 485\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\n\u001b[0;32m 486\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m 487\u001b[0m hidden_states: torch\u001b[38;5;241m.\u001b[39mTensor,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 494\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tuple[torch\u001b[38;5;241m.\u001b[39mTensor]:\n\u001b[0;32m 495\u001b[0m \u001b[38;5;66;03m# decoder uni-directional self-attention cached key/values tuple is at positions 1,2\u001b[39;00m\n\u001b[0;32m 496\u001b[0m self_attn_past_key_value \u001b[38;5;241m=\u001b[39m past_key_value[:\u001b[38;5;241m2\u001b[39m] \u001b[38;5;28;01mif\u001b[39;00m past_key_value \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m--> 497\u001b[0m self_attention_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mattention\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 498\u001b[0m \u001b[43m \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 499\u001b[0m \u001b[43m \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 500\u001b[0m \u001b[43m \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 501\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 502\u001b[0m \u001b[43m \u001b[49m\u001b[43mpast_key_value\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mself_attn_past_key_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 503\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 504\u001b[0m attention_output \u001b[38;5;241m=\u001b[39m self_attention_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m 506\u001b[0m \u001b[38;5;66;03m# if decoder, the last output is tuple of self-attn cache\u001b[39;00m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\module.py:1553\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1551\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m 1552\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1553\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1557\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m 1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m 1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m 1560\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m 1561\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1562\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m 1565\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\models\\bert\\modeling_bert.py:427\u001b[0m, in \u001b[0;36mBertAttention.forward\u001b[1;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_value, output_attentions)\u001b[0m\n\u001b[0;32m 417\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\n\u001b[0;32m 418\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m 419\u001b[0m hidden_states: torch\u001b[38;5;241m.\u001b[39mTensor,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 425\u001b[0m output_attentions: Optional[\u001b[38;5;28mbool\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m 426\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tuple[torch\u001b[38;5;241m.\u001b[39mTensor]:\n\u001b[1;32m--> 427\u001b[0m self_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mself\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 428\u001b[0m \u001b[43m \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 429\u001b[0m \u001b[43m \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 430\u001b[0m \u001b[43m \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 431\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 432\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoder_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 433\u001b[0m \u001b[43m \u001b[49m\u001b[43mpast_key_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 434\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 435\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 436\u001b[0m attention_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput(self_outputs[\u001b[38;5;241m0\u001b[39m], hidden_states)\n\u001b[0;32m 437\u001b[0m outputs \u001b[38;5;241m=\u001b[39m (attention_output,) \u001b[38;5;241m+\u001b[39m self_outputs[\u001b[38;5;241m1\u001b[39m:] \u001b[38;5;66;03m# add attentions if we output them\u001b[39;00m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\module.py:1553\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1551\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m 1552\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1553\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1557\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m 1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m 1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m 1560\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m 1561\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1562\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m 1565\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\models\\bert\\modeling_bert.py:308\u001b[0m, in \u001b[0;36mBertSelfAttention.forward\u001b[1;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_value, output_attentions)\u001b[0m\n\u001b[0;32m 306\u001b[0m value_layer \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mcat([past_key_value[\u001b[38;5;241m1\u001b[39m], value_layer], dim\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m2\u001b[39m)\n\u001b[0;32m 307\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 308\u001b[0m key_layer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtranspose_for_scores(\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mkey\u001b[49m\u001b[43m(\u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[0;32m 309\u001b[0m value_layer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtranspose_for_scores(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvalue(hidden_states))\n\u001b[0;32m 311\u001b[0m query_layer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtranspose_for_scores(mixed_query_layer)\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\module.py:1553\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1551\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m 1552\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1553\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1557\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m 1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m 1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m 1560\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m 1561\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1562\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m 1565\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
"File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\nn\\modules\\linear.py:117\u001b[0m, in \u001b[0;36mLinear.forward\u001b[1;34m(self, input)\u001b[0m\n\u001b[0;32m 116\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[1;32m--> 117\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlinear\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbias\u001b[49m\u001b[43m)\u001b[49m\n",
"\u001b[1;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"from pymongo import MongoClient\n",
"from sentence_transformers import SentenceTransformer\n",
"import numpy as np \n",
"from sklearn.metrics.pairwise import cosine_similarity\n",
"import spacy\n",
"import pandas as pd\n",
"\n",
"# Model ve NLP yükleme\n",
"model = SentenceTransformer('sentence-transformers/paraphrase-MiniLM-L6-v2')\n",
"nlp = spacy.load('en_core_web_sm')\n",
"\n",
"# MongoDB bağlantısı\n",
"client = MongoClient(\"mongodb://localhost:27017/\") \n",
"db = client['EgitimDatabase'] \n",
"collection = db['test']\n",
"\n",
"# Subheading'leri çıkarma\n",
"def extract_subheadings(text):\n",
" doc = nlp(text)\n",
" sentences = [sent.text for sent in doc.sents]\n",
" return sentences\n",
"\n",
"# Metinleri gömme (embedding) işlemi\n",
"def embed_text(text):\n",
" return model.encode(text)\n",
"\n",
"# En iyi subheading'leri seçme\n",
"def get_top_subheadings(title, keywords, text, top_n=5):\n",
" title_embedding = embed_text(title)\n",
" keywords_embedding = embed_text(' '.join(keywords))\n",
" subheadings = extract_subheadings(text)\n",
" subheadings_embeddings = [embed_text(sub) for sub in subheadings]\n",
" \n",
" scores = [cosine_similarity([title_embedding], [embedding])[0][0] + \n",
" cosine_similarity([keywords_embedding], [embedding])[0][0]\n",
" for embedding in subheadings_embeddings]\n",
" \n",
" top_indices = np.argsort(scores)[-top_n:]\n",
" top_subheadings = [subheadings[i] for i in top_indices]\n",
"\n",
" return top_subheadings\n",
"\n",
"# Verileri işleme ve CSV'ye yazma\n",
"def process_documents(batch_size=1000, top_n_subheadings=5):\n",
" data = []\n",
" total_documents = 10000\n",
" for skip in range(0, total_documents, batch_size):\n",
" documents = collection.find({}, {'keywords': 1, 'title': 1, 'text': 1}).skip(skip).limit(batch_size)\n",
" for doc in documents:\n",
" title = doc['title']\n",
" keywords = doc['keywords']\n",
" text = doc['text']\n",
" \n",
" top_subheadings = get_top_subheadings(title, keywords, text)\n",
" \n",
" # Verileri listeye ekleyin\n",
" data.append({\n",
" 'Title': title,\n",
" 'Keywords': ', '.join(keywords),\n",
" 'Subheadings': '; '.join(top_subheadings)\n",
" })\n",
" \n",
" # Her batch sonrası CSV dosyasına kaydetme\n",
" df = pd.DataFrame(data)\n",
" df.to_csv('subheadings.csv', index=False, mode='a', header=not bool(skip))\n",
" print(f\"Batch {skip // batch_size + 1} işlenip kaydedildi.\")\n",
" \n",
" print(\"Subheadings başarıyla 'subheadings.csv' dosyasına kaydedildi.\")\n",
"\n",
"# CSV'ye yazma işlemini başlatma\n",
"process_documents()\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"\n",
"def generate_ngrams(text, n):\n",
" tokens = word_tokenize(text) #[\"this\",\"is\",\"a\",\"test\"]\n",
" n_grams = ngrams(tokens, n) #kelime gruplarına böler\n",
" return [' '.join(gram) for gram in n_grams]\n",
"\n",
"def get_important_ngrams(text, n, top_n=5):\n",
" n_grams = generate_ngrams(text, n)\n",
" ngram_freq = Counter(n_grams)\n",
" most_common_ngrams = [ngram for ngram, _ in ngram_freq.most_common(top_n)]\n",
" return most_common_ngrams\n",
"\n",
"def get_similar_bigrams(text, n=2, similarity_threshold=0.8):\n",
" # Bigramları oluştur\n",
" bigrams = generate_ngrams(text, n)\n",
" \n",
" # Bigramları embedding vektörlerine dönüştür\n",
" bigram_embeddings = [embed_text(bigram) for bigram in bigrams]\n",
" \n",
" # Benzer bigramları listelemek için boş bir liste oluştur\n",
" similar_bigrams = []\n",
" \n",
" # Bigramlar arasındaki benzerlikleri kontrol et\n",
" for i in range(len(bigrams)):\n",
" for j in range(i + 1, len(bigrams)):\n",
" similarity = cosine_similarity([bigram_embeddings[i]], [bigram_embeddings[j]])[0][0]\n",
" if similarity >= similarity_threshold:\n",
" similar_bigrams.append((bigrams[i], bigrams[j], similarity))\n",
" \n",
" return similar_bigrams\n",
"\n",
"similar_bigrams = get_similar_bigrams(text, n=2, similarity_threshold=0.8)\n",
"# Benzer bigramları yazdır\n",
"for bigram1, bigram2, similarity in similar_bigrams:\n",
" print(f\"Bigram 1: {bigram1}, Bigram 2: {bigram2}, Similarity: {similarity:.2f}\")\n",
"\n",
"def generate_subheadings(text, num_headings=5):\n",
" # Metni spaCy ile işleyin\n",
" doc = nlp(text)\n",
" \n",
" # Biagram ve triagramları oluşturun\n",
" bigrams = get_important_ngrams(text, 2, top_n=num_headings)\n",
" trigrams = get_important_ngrams(text, 3, top_n=num_headings)\n",
" \n",
" # Subheadings'leri birleştirin\n",
" headings = list(set(bigrams + trigrams))\n",
" \n",
" return headings"
]
}
],
"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": "3.10.11"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|