Spaces:
Sleeping
Sleeping
File size: 36,478 Bytes
2d4243e |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2023-07-07 17:13:01.457105: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
"To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
]
}
],
"source": [
"import pandas as pd\n",
"import gensim\n",
"import pprint\n",
"from gensim import corpora\n",
"from gensim.utils import simple_preprocess\n",
"from gensim.models import TfidfModel\n",
"from gensim.parsing import strip_tags, strip_numeric, \\\n",
" strip_multiple_whitespaces, stem_text, strip_punctuation, \\\n",
" remove_stopwords, preprocess_string\n",
"import re\n",
"import os\n",
"\n",
"from typing import List\n",
"import spacy"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"transform_to_lower = lambda s: s.lower()\n",
"remove_single_char = lambda s: re.sub(r'\\s+\\w{1}\\s+', '', s)\n",
"\n",
"cleaning_filters = [\n",
" strip_tags,\n",
" strip_numeric,\n",
" strip_punctuation, \n",
" strip_multiple_whitespaces, \n",
" transform_to_lower,\n",
" remove_stopwords,\n",
" remove_single_char\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 95,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_parquet(\"/Users/luis.morales/Desktop/arxiv-paper-recommender/data/processed/reduced_arxiv_papers.parquet.gzip\")"
]
},
{
"cell_type": "code",
"execution_count": 94,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"638707"
]
},
"execution_count": 94,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"int(df.shape[0] * 0.75) "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 73,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_parquet(\"/Users/luis.morales/Desktop/arxiv-paper-recommender/data/processed/reduced_arxiv_papers.parquet.gzip\").sample().reset_index(drop=True)"
]
},
{
"cell_type": "code",
"execution_count": 74,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>id</th>\n",
" <th>submitter</th>\n",
" <th>authors</th>\n",
" <th>title</th>\n",
" <th>comments</th>\n",
" <th>journal-ref</th>\n",
" <th>doi</th>\n",
" <th>report-no</th>\n",
" <th>categories</th>\n",
" <th>license</th>\n",
" <th>abstract</th>\n",
" <th>versions</th>\n",
" <th>update_date</th>\n",
" <th>authors_parsed</th>\n",
" <th>cleaned_abstracts</th>\n",
" <th>len_abstract</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2007.00905</td>\n",
" <td>Song Qingheng</td>\n",
" <td>Qingheng Song, Yong Zeng, Jie Xu, and Shi Jin</td>\n",
" <td>A Survey of Prototype and Experiment for UAV C...</td>\n",
" <td>24 pages, 6 figures</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>cs.IT eess.SP math.IT</td>\n",
" <td>http://creativecommons.org/licenses/by-nc-sa/4.0/</td>\n",
" <td>Unmanned aerial vehicle (UAV) communications...</td>\n",
" <td>[{'created': 'Thu, 2 Jul 2020 06:26:20 GMT', '...</td>\n",
" <td>2020-07-03</td>\n",
" <td>[[Song, Qingheng, ], [Zeng, Yong, ], [Xu, Jie,...</td>\n",
" <td>unmanned aerial vehicle uav communication a...</td>\n",
" <td>865</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2102.04209</td>\n",
" <td>Michael Stuart</td>\n",
" <td>Michael T. Stuart and Markus Kneer</td>\n",
" <td>Guilty Artificial Minds</td>\n",
" <td>20 pages, 4 figures, 1 table</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>cs.CY cs.AI cs.HC</td>\n",
" <td>http://creativecommons.org/licenses/by/4.0/</td>\n",
" <td>The concepts of blameworthiness and wrongnes...</td>\n",
" <td>[{'created': 'Sun, 24 Jan 2021 21:37:35 GMT', ...</td>\n",
" <td>2021-02-09</td>\n",
" <td>[[Stuart, Michael T., ], [Kneer, Markus, ]]</td>\n",
" <td>concept blameworthiness wrongness fundament...</td>\n",
" <td>739</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1201.5796</td>\n",
" <td>Denis Jerome</td>\n",
" <td>Denis Jerome</td>\n",
" <td>Organic Superconductors: when correlations and...</td>\n",
" <td>41 pages, 21 figures to be published in Journa...</td>\n",
" <td>None</td>\n",
" <td>10.1007/s10948-012-1475-7</td>\n",
" <td>None</td>\n",
" <td>cond-mat.supr-con</td>\n",
" <td>http://arxiv.org/licenses/nonexclusive-distrib...</td>\n",
" <td>This survey provides a brief account for the...</td>\n",
" <td>[{'created': 'Fri, 27 Jan 2012 15:24:46 GMT', ...</td>\n",
" <td>2012-02-21</td>\n",
" <td>[[Jerome, Denis, ]]</td>\n",
" <td>survey provide brief account start organic ...</td>\n",
" <td>649</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1511.03076</td>\n",
" <td>Emma Platts Miss</td>\n",
" <td>George F.R. Ellis, Emma Platts, David Sloan an...</td>\n",
" <td>Current observations with a decaying cosmologi...</td>\n",
" <td>23 pages, 11 figures</td>\n",
" <td>None</td>\n",
" <td>10.1088/1475-7516/2016/04/026</td>\n",
" <td>None</td>\n",
" <td>astro-ph.CO gr-qc hep-th</td>\n",
" <td>http://arxiv.org/licenses/nonexclusive-distrib...</td>\n",
" <td>We use the phase plane analysis technique of...</td>\n",
" <td>[{'created': 'Tue, 10 Nov 2015 12:08:23 GMT', ...</td>\n",
" <td>2016-04-27</td>\n",
" <td>[[Ellis, George F. R., ], [Platts, Emma, ], [S...</td>\n",
" <td>use phase plane analysis technique madsen e...</td>\n",
" <td>554</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1710.02954</td>\n",
" <td>Kirk Bansak</td>\n",
" <td>Kirk Bansak</td>\n",
" <td>Estimating Causal Moderation Effects with Rand...</td>\n",
" <td>Forthcoming, Journal of the Royal Statistical ...</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>stat.ME</td>\n",
" <td>http://arxiv.org/licenses/nonexclusive-distrib...</td>\n",
" <td>Researchers are often interested in analyzin...</td>\n",
" <td>[{'created': 'Mon, 9 Oct 2017 06:34:01 GMT', '...</td>\n",
" <td>2020-08-25</td>\n",
" <td>[[Bansak, Kirk, ]]</td>\n",
" <td>researcher interested analyze conditional t...</td>\n",
" <td>799</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>851605</th>\n",
" <td>1301.0707</td>\n",
" <td>Sebastian Klein</td>\n",
" <td>Sebastian Klein</td>\n",
" <td>Chow groups of tensor triangulated categories</td>\n",
" <td>40 pages. The presentation of the article has ...</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>math.AG math.CT math.RT</td>\n",
" <td>http://arxiv.org/licenses/nonexclusive-distrib...</td>\n",
" <td>We recall P. Balmer's definition of tensor t...</td>\n",
" <td>[{'created': 'Fri, 4 Jan 2013 11:06:40 GMT', '...</td>\n",
" <td>2015-10-02</td>\n",
" <td>[[Klein, Sebastian, ]]</td>\n",
" <td>recall p. balmer definition tensor triangul...</td>\n",
" <td>787</td>\n",
" </tr>\n",
" <tr>\n",
" <th>851606</th>\n",
" <td>1707.00341</td>\n",
" <td>Giorgos Anastasiou</td>\n",
" <td>Giorgos Anastasiou, Rodrigo Olea, David Rivera...</td>\n",
" <td>Noether-Wald energy in Critical Gravity</td>\n",
" <td>7 pages, no figures, Final version for PLB</td>\n",
" <td>None</td>\n",
" <td>10.1016/j.physletb.2018.11.021</td>\n",
" <td>None</td>\n",
" <td>hep-th gr-qc</td>\n",
" <td>http://arxiv.org/licenses/nonexclusive-distrib...</td>\n",
" <td>Criticality represents a specific point in t...</td>\n",
" <td>[{'created': 'Sun, 2 Jul 2017 19:52:32 GMT', '...</td>\n",
" <td>2018-11-21</td>\n",
" <td>[[Anastasiou, Giorgos, ], [Olea, Rodrigo, ], [...</td>\n",
" <td>criticality represent specific point parame...</td>\n",
" <td>631</td>\n",
" </tr>\n",
" <tr>\n",
" <th>851607</th>\n",
" <td>1610.08526</td>\n",
" <td>Blagoje Oblak</td>\n",
" <td>Blagoje Oblak</td>\n",
" <td>BMS Particles in Three Dimensions</td>\n",
" <td>437 pages (including index), 33 figures. Appen...</td>\n",
" <td>None</td>\n",
" <td>10.1007/978-3-319-61878-4</td>\n",
" <td>None</td>\n",
" <td>hep-th gr-qc math-ph math.GR math.MP math.RT</td>\n",
" <td>http://arxiv.org/licenses/nonexclusive-distrib...</td>\n",
" <td>This thesis is devoted to the group-theoreti...</td>\n",
" <td>[{'created': 'Wed, 26 Oct 2016 20:00:16 GMT', ...</td>\n",
" <td>2018-01-29</td>\n",
" <td>[[Oblak, Blagoje, ]]</td>\n",
" <td>thesis devoted group theoretic aspect dimen...</td>\n",
" <td>542</td>\n",
" </tr>\n",
" <tr>\n",
" <th>851608</th>\n",
" <td>1211.6629</td>\n",
" <td>Philippe Joyez</td>\n",
" <td>Philippe Joyez</td>\n",
" <td>Self-consistent dynamics of a Josephson juncti...</td>\n",
" <td>7 pages, 1 figure</td>\n",
" <td>None</td>\n",
" <td>10.1103/PhysRevLett.110.217003</td>\n",
" <td>None</td>\n",
" <td>cond-mat.supr-con cond-mat.mes-hall</td>\n",
" <td>http://arxiv.org/licenses/nonexclusive-distrib...</td>\n",
" <td>We derive microscopically the dynamics assoc...</td>\n",
" <td>[{'created': 'Tue, 27 Nov 2012 17:29:04 GMT', ...</td>\n",
" <td>2013-05-29</td>\n",
" <td>[[Joyez, Philippe, ]]</td>\n",
" <td>derive microscopically dynamic associate d....</td>\n",
" <td>558</td>\n",
" </tr>\n",
" <tr>\n",
" <th>851609</th>\n",
" <td>0705.2878</td>\n",
" <td>Benoit Perthame</td>\n",
" <td>Benoit Perthame (DMA), Panagiotis E. Souganidis</td>\n",
" <td>Asymmetric potentials and motor effect: a larg...</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>math.AP</td>\n",
" <td>None</td>\n",
" <td>We provide a mathematical analysis of appear...</td>\n",
" <td>[{'created': 'Sun, 20 May 2007 17:43:39 GMT', ...</td>\n",
" <td>2007-05-23</td>\n",
" <td>[[Perthame, Benoit, , DMA], [Souganidis, Panag...</td>\n",
" <td>provide mathematical analysis appearance co...</td>\n",
" <td>518</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>851610 rows × 16 columns</p>\n",
"</div>"
],
"text/plain": [
" id submitter \n",
"0 2007.00905 Song Qingheng \\\n",
"1 2102.04209 Michael Stuart \n",
"2 1201.5796 Denis Jerome \n",
"3 1511.03076 Emma Platts Miss \n",
"4 1710.02954 Kirk Bansak \n",
"... ... ... \n",
"851605 1301.0707 Sebastian Klein \n",
"851606 1707.00341 Giorgos Anastasiou \n",
"851607 1610.08526 Blagoje Oblak \n",
"851608 1211.6629 Philippe Joyez \n",
"851609 0705.2878 Benoit Perthame \n",
"\n",
" authors \n",
"0 Qingheng Song, Yong Zeng, Jie Xu, and Shi Jin \\\n",
"1 Michael T. Stuart and Markus Kneer \n",
"2 Denis Jerome \n",
"3 George F.R. Ellis, Emma Platts, David Sloan an... \n",
"4 Kirk Bansak \n",
"... ... \n",
"851605 Sebastian Klein \n",
"851606 Giorgos Anastasiou, Rodrigo Olea, David Rivera... \n",
"851607 Blagoje Oblak \n",
"851608 Philippe Joyez \n",
"851609 Benoit Perthame (DMA), Panagiotis E. Souganidis \n",
"\n",
" title \n",
"0 A Survey of Prototype and Experiment for UAV C... \\\n",
"1 Guilty Artificial Minds \n",
"2 Organic Superconductors: when correlations and... \n",
"3 Current observations with a decaying cosmologi... \n",
"4 Estimating Causal Moderation Effects with Rand... \n",
"... ... \n",
"851605 Chow groups of tensor triangulated categories \n",
"851606 Noether-Wald energy in Critical Gravity \n",
"851607 BMS Particles in Three Dimensions \n",
"851608 Self-consistent dynamics of a Josephson juncti... \n",
"851609 Asymmetric potentials and motor effect: a larg... \n",
"\n",
" comments journal-ref \n",
"0 24 pages, 6 figures None \\\n",
"1 20 pages, 4 figures, 1 table None \n",
"2 41 pages, 21 figures to be published in Journa... None \n",
"3 23 pages, 11 figures None \n",
"4 Forthcoming, Journal of the Royal Statistical ... None \n",
"... ... ... \n",
"851605 40 pages. The presentation of the article has ... None \n",
"851606 7 pages, no figures, Final version for PLB None \n",
"851607 437 pages (including index), 33 figures. Appen... None \n",
"851608 7 pages, 1 figure None \n",
"851609 None None \n",
"\n",
" doi report-no \n",
"0 None None \\\n",
"1 None None \n",
"2 10.1007/s10948-012-1475-7 None \n",
"3 10.1088/1475-7516/2016/04/026 None \n",
"4 None None \n",
"... ... ... \n",
"851605 None None \n",
"851606 10.1016/j.physletb.2018.11.021 None \n",
"851607 10.1007/978-3-319-61878-4 None \n",
"851608 10.1103/PhysRevLett.110.217003 None \n",
"851609 None None \n",
"\n",
" categories \n",
"0 cs.IT eess.SP math.IT \\\n",
"1 cs.CY cs.AI cs.HC \n",
"2 cond-mat.supr-con \n",
"3 astro-ph.CO gr-qc hep-th \n",
"4 stat.ME \n",
"... ... \n",
"851605 math.AG math.CT math.RT \n",
"851606 hep-th gr-qc \n",
"851607 hep-th gr-qc math-ph math.GR math.MP math.RT \n",
"851608 cond-mat.supr-con cond-mat.mes-hall \n",
"851609 math.AP \n",
"\n",
" license \n",
"0 http://creativecommons.org/licenses/by-nc-sa/4.0/ \\\n",
"1 http://creativecommons.org/licenses/by/4.0/ \n",
"2 http://arxiv.org/licenses/nonexclusive-distrib... \n",
"3 http://arxiv.org/licenses/nonexclusive-distrib... \n",
"4 http://arxiv.org/licenses/nonexclusive-distrib... \n",
"... ... \n",
"851605 http://arxiv.org/licenses/nonexclusive-distrib... \n",
"851606 http://arxiv.org/licenses/nonexclusive-distrib... \n",
"851607 http://arxiv.org/licenses/nonexclusive-distrib... \n",
"851608 http://arxiv.org/licenses/nonexclusive-distrib... \n",
"851609 None \n",
"\n",
" abstract \n",
"0 Unmanned aerial vehicle (UAV) communications... \\\n",
"1 The concepts of blameworthiness and wrongnes... \n",
"2 This survey provides a brief account for the... \n",
"3 We use the phase plane analysis technique of... \n",
"4 Researchers are often interested in analyzin... \n",
"... ... \n",
"851605 We recall P. Balmer's definition of tensor t... \n",
"851606 Criticality represents a specific point in t... \n",
"851607 This thesis is devoted to the group-theoreti... \n",
"851608 We derive microscopically the dynamics assoc... \n",
"851609 We provide a mathematical analysis of appear... \n",
"\n",
" versions update_date \n",
"0 [{'created': 'Thu, 2 Jul 2020 06:26:20 GMT', '... 2020-07-03 \\\n",
"1 [{'created': 'Sun, 24 Jan 2021 21:37:35 GMT', ... 2021-02-09 \n",
"2 [{'created': 'Fri, 27 Jan 2012 15:24:46 GMT', ... 2012-02-21 \n",
"3 [{'created': 'Tue, 10 Nov 2015 12:08:23 GMT', ... 2016-04-27 \n",
"4 [{'created': 'Mon, 9 Oct 2017 06:34:01 GMT', '... 2020-08-25 \n",
"... ... ... \n",
"851605 [{'created': 'Fri, 4 Jan 2013 11:06:40 GMT', '... 2015-10-02 \n",
"851606 [{'created': 'Sun, 2 Jul 2017 19:52:32 GMT', '... 2018-11-21 \n",
"851607 [{'created': 'Wed, 26 Oct 2016 20:00:16 GMT', ... 2018-01-29 \n",
"851608 [{'created': 'Tue, 27 Nov 2012 17:29:04 GMT', ... 2013-05-29 \n",
"851609 [{'created': 'Sun, 20 May 2007 17:43:39 GMT', ... 2007-05-23 \n",
"\n",
" authors_parsed \n",
"0 [[Song, Qingheng, ], [Zeng, Yong, ], [Xu, Jie,... \\\n",
"1 [[Stuart, Michael T., ], [Kneer, Markus, ]] \n",
"2 [[Jerome, Denis, ]] \n",
"3 [[Ellis, George F. R., ], [Platts, Emma, ], [S... \n",
"4 [[Bansak, Kirk, ]] \n",
"... ... \n",
"851605 [[Klein, Sebastian, ]] \n",
"851606 [[Anastasiou, Giorgos, ], [Olea, Rodrigo, ], [... \n",
"851607 [[Oblak, Blagoje, ]] \n",
"851608 [[Joyez, Philippe, ]] \n",
"851609 [[Perthame, Benoit, , DMA], [Souganidis, Panag... \n",
"\n",
" cleaned_abstracts len_abstract \n",
"0 unmanned aerial vehicle uav communication a... 865 \n",
"1 concept blameworthiness wrongness fundament... 739 \n",
"2 survey provide brief account start organic ... 649 \n",
"3 use phase plane analysis technique madsen e... 554 \n",
"4 researcher interested analyze conditional t... 799 \n",
"... ... ... \n",
"851605 recall p. balmer definition tensor triangul... 787 \n",
"851606 criticality represent specific point parame... 631 \n",
"851607 thesis devoted group theoretic aspect dimen... 542 \n",
"851608 derive microscopically dynamic associate d.... 558 \n",
"851609 provide mathematical analysis appearance co... 518 \n",
"\n",
"[851610 rows x 16 columns]"
]
},
"execution_count": 74,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 75,
"metadata": {},
"outputs": [],
"source": [
"corpus = df['cleaned_abstracts'].to_list()\n"
]
},
{
"cell_type": "code",
"execution_count": 76,
"metadata": {},
"outputs": [],
"source": [
"def gensim_tokenizer(docs: List[str]):\n",
" tokenized_docs = list()\n",
" for doc in docs:\n",
" processed_words = preprocess_string(doc, cleaning_filters)\n",
" tokenized_docs.append(processed_words)\n",
" \n",
" return tokenized_docs\n",
"\n",
"tokenized_corpus = gensim_tokenizer(corpus)"
]
},
{
"cell_type": "code",
"execution_count": 77,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"851610"
]
},
"execution_count": 77,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(tokenized_corpus)"
]
},
{
"cell_type": "code",
"execution_count": 55,
"metadata": {},
"outputs": [],
"source": [
"def cleaning_pipe(document):\n",
" # Invoking gensim.parsing.preprocess_string method with set of filters\n",
" processed_words = preprocess_string(document, cleaning_filters)\n",
" return processed_words"
]
},
{
"cell_type": "code",
"execution_count": 78,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"/Users/luis.morales/Desktop/arxiv-paper-recommender/models\n",
"/Users/luis.morales/Desktop/arxiv-paper-recommender\n"
]
},
{
"data": {
"text/plain": [
"False"
]
},
"execution_count": 78,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def validate_if_dictionary_exists(dictionaty_name: str) -> bool:\n",
" dicts_folder = \"models/nlp_dictionaries\"\n",
" current_dir = os.getcwd()\n",
" parent_dir = os.path.dirname(current_dir)\n",
" dict_path = f\"{parent_dir}/{dicts_folder}/{dictionaty_name}\"\n",
" print(current_dir)\n",
" print(parent_dir)\n",
" return os.path.isfile(dict_path)\n",
" \n",
"\n",
"validate_if_dictionary_exists('30ktokens.dict') "
]
},
{
"cell_type": "code",
"execution_count": 79,
"metadata": {},
"outputs": [],
"source": [
"def get_gensim_dictionary(tokenized_docs: List[str], dict_name: str = \"corpus\", save_dict: bool = False):\n",
" \"\"\"\n",
" Create dictionary of words in preprocessed corpus and saves the dict object\n",
" \"\"\"\n",
" dictionary = corpora.Dictionary(tokenized_docs)\n",
" if save_dict: \n",
" dict_lenght = len(tokenized_corpus)\n",
" parent_folder = \"/Users/luis.morales/Desktop/arxiv-paper-recommender/models/dictionaries\"\n",
" #if validate_if_dictionary_exists('30ktokens.dict'):\n",
" dictionary.save(f'{parent_folder}/{dict_name}.dict')\n",
" \n",
" return dictionary\n",
"\n",
"dictionary = get_gensim_dictionary(tokenized_docs=tokenized_corpus, dict_name=\"TextualTango\", save_dict=True)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"# def get_gensim_dictionary(tokenized_docs: List[str], dict_name: str = \"corpus\", save_dict: bool = False):\n",
"# \"\"\"\n",
"# Create dictionary of words in preprocessed corpus and saves the dict object\n",
"# \"\"\"\n",
"# dictionary = corpora.Dictionary(tokenized_docs)\n",
"# if save_dict: \n",
"# dict_lenght = len(tokenized_corpus)\n",
"# parent_folder = \"/Users/luis.morales/Desktop/arxiv-paper-recommender/models/nlp_dictionaries\"\n",
"# if validate_if_dictionary_exists('30ktokens.dict'):\n",
"# dictionary.save(f'{parent_folder}/{dict_name}.dict')\n",
" \n",
"# return dictionary\n",
"\n",
"# dictionary = get_gensim_dictionary(tokenized_docs=tokenized_corpus, dict_name=\"300Ktokens\", save_dict=True)"
]
},
{
"cell_type": "code",
"execution_count": 80,
"metadata": {},
"outputs": [],
"source": [
"BoW_corpus = [dictionary.doc2bow(doc, allow_update=True) for doc in tokenized_corpus]"
]
},
{
"cell_type": "code",
"execution_count": 81,
"metadata": {},
"outputs": [],
"source": [
"tfidf_model = TfidfModel(BoW_corpus)"
]
},
{
"cell_type": "code",
"execution_count": 82,
"metadata": {},
"outputs": [],
"source": [
"tfidf_model.save(\"/Users/luis.morales/Desktop/arxiv-paper-recommender/models/tfidf/TextualTango.model\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Test model"
]
},
{
"cell_type": "code",
"execution_count": 83,
"metadata": {},
"outputs": [],
"source": [
"# index the tfidf vector of corpus as sparse matrix\n",
"from gensim import similarities\n",
"index = similarities.SparseMatrixSimilarity(tfidf_model[BoW_corpus], num_features=len(dictionary))"
]
},
{
"cell_type": "code",
"execution_count": 84,
"metadata": {},
"outputs": [],
"source": [
"index.save(\"/Users/luis.morales/Desktop/arxiv-paper-recommender/models/similarities_matrix/TextualTangoSimilarities/TextualTango\")"
]
},
{
"cell_type": "code",
"execution_count": 67,
"metadata": {},
"outputs": [],
"source": [
"def get_closest_n(query, n):\n",
" '''get the top matching docs as per cosine similarity\n",
" between tfidf vector of query and all docs'''\n",
" query_document = cleaning_pipe(query)\n",
" query_bow = dictionary.doc2bow(query_document)\n",
" sims = index[tfidf_model[query_bow]]\n",
" top_idx = sims.argsort()[-1*n:][::-1]\n",
" return top_idx"
]
},
{
"cell_type": "code",
"execution_count": 85,
"metadata": {},
"outputs": [],
"source": [
"def get_recomendations_metadata(query: str, n: int, df: pd.DataFrame):\n",
" recommendations_idxs = get_closest_n(query, n)\n",
" return df.iloc[recommendations_idxs].reset_index(drop=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 91,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"User Request ---- : \n",
" Which papers discuss the use of statistical models and Bayesian inference for uncertainty quantification and risk assessment in engineering systems?\n",
"User Request ---- : \n",
" \n",
"Title: A framework for benchmarking uncertainty in deep regression\n",
"Abstract: We propose a framework for the assessment of uncertainty quantification in\n",
"deep regression. The framework is based on regression problems where the\n",
"regression function is a linear combination of nonlinear functions. Basically,\n",
"any level of complexity can be realized through the choice of the nonlinear\n",
"functions and the dimensionality of their domain. Results of an uncertainty\n",
"quantification for deep regression are compared against those obtained by a\n",
"statistical reference method. The reference method utilizes knowledge of the\n",
"underlying nonlinear functions and is based on a Bayesian linear regression\n",
"using a reference prior. Reliability of uncertainty quantification is assessed\n",
"in terms of coverage probabilities, and accuracy through the size of calculated\n",
"uncertainties. We illustrate the proposed framework by applying it to current\n",
"approaches for uncertainty quantification in deep regression. The flexibility,\n",
"together with the availability of a reference solution, makes the framework\n",
"suitable for defining benchmark sets for uncertainty quantification.\n",
"\n",
"\n",
"--------------------------\n",
"User Request ---- : \n",
" Which papers discuss the use of statistical models and Bayesian inference for uncertainty quantification and risk assessment in engineering systems?\n",
"User Request ---- : \n",
" \n",
"Title: Generative Parameter Sampler For Scalable Uncertainty Quantification\n",
"Abstract: Uncertainty quantification has been a core of the statistical machine\n",
"learning, but its computational bottleneck has been a serious challenge for\n",
"both Bayesians and frequentists. We propose a model-based framework in\n",
"quantifying uncertainty, called predictive-matching Generative Parameter\n",
"Sampler (GPS). This procedure considers an Uncertainty Quantification (UQ)\n",
"distribution on the targeted parameter, which matches the corresponding\n",
"predictive distribution to the observed data. This framework adopts a\n",
"hierarchical modeling perspective such that each observation is modeled by an\n",
"individual parameter. This individual parameterization permits the resulting\n",
"inference to be computationally scalable and robust to outliers. Our approach\n",
"is illustrated for linear models, Poisson processes, and deep neural networks\n",
"for classification. The results show that the GPS is successful in providing\n",
"uncertainty quantification as well as additional flexibility beyond what is\n",
"allowed by classical statistical procedures under the postulated statistical\n",
"models.\n",
"\n",
"\n",
"--------------------------\n",
"User Request ---- : \n",
" Which papers discuss the use of statistical models and Bayesian inference for uncertainty quantification and risk assessment in engineering systems?\n",
"User Request ---- : \n",
" \n",
"Title: Recent Advances in Uncertainty Quantification Methods for Engineering\n",
" Problems\n",
"Abstract: In the last few decades, uncertainty quantification (UQ) methods have been\n",
"used widely to ensure the robustness of engineering designs. This chapter aims\n",
"to detail recent advances in popular uncertainty quantification methods used in\n",
"engineering applications. This chapter describes the two most popular\n",
"meta-modeling methods for uncertainty quantification suitable for engineering\n",
"applications (Polynomial Chaos Method and Gaussian Process). Further, the UQ\n",
"methods are applied to an engineering test problem under multiple\n",
"uncertainties. The test problem considered here is a supersonic nozzle under\n",
"operational uncertainties. For the deterministic solution, an open-source\n",
"computational fluid dynamics (CFD) solver SU2 is used. The UQ methods are\n",
"developed in Matlab and are further combined with SU2 for the uncertainty and\n",
"sensitivity estimates. The results are presented in terms of the mean and\n",
"standard deviation of the output quantities.\n",
"\n",
"\n",
"--------------------------\n"
]
}
],
"source": [
"_input = \"Which papers discuss the use of statistical models and Bayesian inference for uncertainty quantification and risk assessment in engineering systems?\"\n",
"results_df = get_recomendations_metadata(query=_input, df=df, n=3)\n",
"\n",
"\n",
"for abstract in list(zip(results_df['abstract'].to_list(), results_df['title'].to_list())):\n",
" print(f\"User Request ---- : \\n {_input}\")\n",
" print(f\"User Request ---- : \\n \")\n",
" print(f\"Title: {abstract[1]}\")\n",
" print(f\"Abstract: {abstract[0]}\\n\")\n",
" print(f\"--------------------------\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.11.4 ('arxiv-env': 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": "3.11.4"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "aae17c2ae2f38cc6f211be9b71a2aa280701d8462782cbc1f67caa83a1603363"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|