Spaces:
Sleeping
Sleeping
File size: 47,412 Bytes
b5cf002 |
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 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"from enum import Enum\n",
"from typing import List, Dict, Any\n",
"from dataclasses import dataclass\n",
"from tqdm import tqdm\n",
"\n",
"import os\n",
"import yaml\n",
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"import pyalex\n",
"from pyalex import Works\n",
"from src.utils.io_utils import PROJECT_ROOT\n",
"from src.dataset.Dataset import *"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Configurations"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"@dataclass\n",
"class ConfigAugmentation:\n",
" \"\"\"Configuration for OpenAlex features\"\"\"\n",
" basic: Dict[str, bool] = None # id, doi, title, etc\n",
" source: Dict[str, bool] = None # journal info\n",
" authors: Dict[str, bool] = None # author details\n",
" metrics: Dict[str, bool] = None # citations, fwci, etc\n",
" classification: Dict[str, bool] = None # topics, concepts\n",
" access: Dict[str, bool] = None # OA status\n",
" related_works: Dict[str, bool] = None # references\n",
" abstract: bool = False"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Dataset Loading "
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"# load the dataset \n",
"\n",
"class DatasetType(Enum):\n",
" FULL_RAW = \"full_raw\"\n",
" PARTIAL_RAW = \"partial_raw\"\n",
" FULL_AUGMENTED = \"full_augmented\"\n",
" PARTIAL_AUGMENTED = \"partial_augmented\""
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"@dataclass\n",
"class Field:\n",
" \"\"\"Field configuration for data extraction\"\"\"\n",
" name: str\n",
" path: List[str]\n",
" default: Any = None\n",
"\n",
"class AlexFields:\n",
" \"\"\"OpenAlex field definitions\"\"\"\n",
" \n",
" BASIC = [\n",
" Field(\"id\", [\"id\"]),\n",
" Field(\"doi\", [\"doi\"]),\n",
" Field(\"title\", [\"title\"]),\n",
" Field(\"display_name\", [\"display_name\"]),\n",
" Field(\"publication_year\", [\"publication_year\"]),\n",
" Field(\"publication_date\", [\"publication_date\"]),\n",
" Field(\"language\", [\"language\"]),\n",
" Field(\"type\", [\"type\"]),\n",
" Field(\"type_crossref\", [\"type_crossref\"])\n",
" ]\n",
" \n",
" SOURCE = [\n",
" Field(\"journal_name\", [\"primary_location\", \"source\", \"display_name\"]),\n",
" Field(\"issn\", [\"primary_location\", \"source\", \"issn\"]),\n",
" Field(\"issn_l\", [\"primary_location\", \"source\", \"issn_l\"]),\n",
" Field(\"publisher\", [\"primary_location\", \"source\", \"host_organization_name\"]),\n",
" Field(\"type\", [\"primary_location\", \"source\", \"type\"])\n",
" ]\n",
"\n",
" METRICS = [\n",
" Field(\"cited_by_count\", [\"cited_by_count\"]),\n",
" Field(\"cited_by_percentile\", [\"citation_normalized_percentile\"]),\n",
" Field(\"is_retracted\", [\"is_retracted\"]),\n",
" Field(\"fwci\", [\"fwci\"]),\n",
" Field(\"referenced_works_count\", [\"referenced_works_count\"])\n",
" ]\n",
"\n",
" ACCESS = [\n",
" Field(\"is_oa\", [\"open_access\", \"is_oa\"]),\n",
" Field(\"oa_status\", [\"open_access\", \"oa_status\"]),\n",
" Field(\"oa_url\", [\"open_access\", \"oa_url\"]),\n",
" Field(\"pdf_url\", [\"primary_location\", \"pdf_url\"]),\n",
" Field(\"license\", [\"primary_location\", \"license\"]) \n",
" ]\n",
"\n",
"def get_nested_value(data: Dict, path: List[str], default: Any = None) -> Any:\n",
" \"\"\"Extract nested value from dictionary using path\"\"\"\n",
" value = data\n",
" for key in path:\n",
" try:\n",
" value = value[key]\n",
" except (KeyError, TypeError):\n",
" return default\n",
" return value\n",
"\n",
"class DataAugmenter:\n",
" \"\"\"Class for augmenting data with OpenAlex features\"\"\"\n",
"\n",
" def __init__(self):\n",
" \"\"\"Initialize augmenter with API credentials\"\"\"\n",
" self.profile = self._load_profile()\n",
" self.email = self.profile[\"email\"]\n",
" self.filters = ConfigAugmentation(\n",
" basic={\n",
" \"id\": True,\n",
" \"doi\": True,\n",
" \"title\": True,\n",
" \"display_name\": True,\n",
" \"publication_year\": True,\n",
" \"publication_date\": True,\n",
" \"language\": True,\n",
" \"type\": True,\n",
" \"type_crossref\": True\n",
" },\n",
" source={\n",
" \"journal_name\": True,\n",
" \"issn\": True,\n",
" \"issn_l\": True,\n",
" \"publisher\": True,\n",
" \"type\": True\n",
" },\n",
" authors={\n",
" \"position\": True,\n",
" \"name\": True,\n",
" \"id\": True,\n",
" \"orcid\": True,\n",
" \"is_corresponding\": True,\n",
" \"affiliations\": False\n",
" },\n",
" metrics={\n",
" \"cited_by_count\": True,\n",
" \"cited_by_percentile\": False,\n",
" \"is_retracted\": True,\n",
" \"fwci\": True,\n",
" \"referenced_works_count\": True\n",
" },\n",
" classification={\n",
" \"primary_topic\": True,\n",
" \"topics\": False,\n",
" \"concepts\": False,\n",
" },\n",
" access={\n",
" \"is_oa\": True,\n",
" \"oa_status\": True,\n",
" \"oa_url\": True,\n",
" \"pdf_url\": True,\n",
" \"license\": True\n",
" },\n",
" related_works={\n",
" \"references\": True,\n",
" \"referenced_by_count\": True,\n",
" \"related\": True\n",
" },\n",
" abstract=True\n",
" )\n",
" \n",
" pyalex.config.email = self.email\n",
" \n",
" def _load_profile(self) -> Dict[str, str]:\n",
" \"\"\"Load API credentials from profile\"\"\"\n",
" profile_path = f\"{PROJECT_ROOT}/user_information/profile.yaml\"\n",
" \n",
" assert str(PROJECT_ROOT).split(\"/\")[-1] == \"MatchingPubs\", \"Please run this script in the github repo folder \"\n",
" assert os.path.exists(profile_path), \"create a profile.yaml with your email (email:) and your api key (api_key:). Go here to get one https://dev.elsevier.com/\"\n",
"\n",
" \n",
" with open(profile_path, \"r\") as f:\n",
" profile = yaml.safe_load(f)\n",
" \n",
" return {\n",
" \"email\": profile[\"email\"]\n",
" }\n",
"\n",
" def get_alex_features(self, doi: str) -> Dict:\n",
" \"\"\"Extract all OpenAlex features for a DOI\"\"\"\n",
" try:\n",
" work = Works()[f\"https://doi.org/{doi}\"]\n",
" result = {}\n",
"\n",
" # Basic metadata\n",
" result[\"basic\"] = {\n",
" field.name: get_nested_value(work, field.path, None)\n",
" for field in AlexFields.BASIC\n",
" }\n",
" \n",
" # Source/journal info\n",
" result[\"source\"] = {\n",
" field.name: get_nested_value(work, field.path, None)\n",
" for field in AlexFields.SOURCE\n",
" }\n",
" \n",
" # Authors with affiliations\n",
" try:\n",
" result[\"authors\"] = [\n",
" {\n",
" \"position\": auth.get(\"author_position\", None),\n",
" \"name\": auth.get(\"author\", {}).get(\"display_name\", None),\n",
" \"id\": auth.get(\"author\", {}).get(\"id\", None),\n",
" \"orcid\": auth.get(\"author\", {}).get(\"orcid\", None),\n",
" \"is_corresponding\": auth.get(\"is_corresponding\", None),\n",
" \"affiliations\": [\n",
" {\n",
" \"name\": inst.get(\"display_name\", None),\n",
" \"id\": inst.get(\"id\", None),\n",
" \"country\": inst.get(\"country_code\", None),\n",
" \"type\": inst.get(\"type\", None),\n",
" \"ror\": inst.get(\"ror\", None)\n",
" }\n",
" for inst in auth.get(\"institutions\", [])\n",
" ]\n",
" }\n",
" for auth in work.get(\"authorships\", [])\n",
" ]\n",
" except:\n",
" result[\"authors\"] = None\n",
"\n",
" # Topics and classifications \n",
" try:\n",
" result[\"classification\"] = {\n",
" \"primary_topic\": {\n",
" \"name\": work.get(\"primary_topic\", {}).get(\"display_name\", None),\n",
" \"score\": work.get(\"primary_topic\", {}).get(\"score\", None),\n",
" \"field\": work.get(\"primary_topic\", {}).get(\"field\", {}).get(\"display_name\", None),\n",
" \"subfield\": work.get(\"primary_topic\", {}).get(\"subfield\", {}).get(\"display_name\", None)\n",
" },\n",
" \"topics\": [\n",
" {\n",
" \"name\": topic.get(\"display_name\", None),\n",
" \"score\": topic.get(\"score\", None),\n",
" \"field\": topic.get(\"field\", {}).get(\"display_name\", None)\n",
" }\n",
" for topic in work.get(\"topics\", [])\n",
" ],\n",
" \"concepts\": [\n",
" {\n",
" \"name\": concept.get(\"display_name\", None),\n",
" \"level\": concept.get(\"level\", None),\n",
" \"score\": concept.get(\"score\", None),\n",
" \"wikidata\": concept.get(\"wikidata\", None)\n",
" }\n",
" for concept in work.get(\"concepts\", [])\n",
" ]\n",
" }\n",
" except:\n",
" result[\"classification\"] = None\n",
"\n",
" # Metrics\n",
" result[\"metrics\"] = {\n",
" field.name: get_nested_value(work, field.path, None)\n",
" for field in AlexFields.METRICS\n",
" }\n",
"\n",
" # Access info\n",
" result[\"access\"] = {\n",
" field.name: get_nested_value(work, field.path, None)\n",
" for field in AlexFields.ACCESS\n",
" }\n",
"\n",
" # Abstract\n",
" try:\n",
" if \"abstract_inverted_index\" in work:\n",
" abstract_dict = work[\"abstract_inverted_index\"]\n",
" if abstract_dict:\n",
" max_pos = max(max(positions) for positions in abstract_dict.values())\n",
" words = [\"\"] * (max_pos + 1)\n",
" for word, positions in abstract_dict.items():\n",
" for pos in positions:\n",
" words[pos] = word\n",
" result[\"abstract\"] = \" \".join(words)\n",
" else:\n",
" result[\"abstract\"] = None\n",
" else:\n",
" result[\"abstract\"] = None\n",
" except:\n",
" result[\"abstract\"] = None\n",
"\n",
" return result\n",
"\n",
" except Exception as e:\n",
" print(f\"OpenAlex error for DOI {doi}: {e}\")\n",
" return {}\n",
" \n",
" def filter_augmented_data(self, data: Dict[str, Any], config: ConfigAugmentation = None) -> Dict[str, Any]:\n",
" \"\"\"Filter data based on configuration\n",
" \n",
" Args:\n",
" data: Dictionary containing raw data\n",
" config: Configuration specifying which features to include\n",
" \n",
" Returns:\n",
" Filtered dictionary containing only the configured features\n",
" \"\"\"\n",
" config = config or self.filters\n",
" \n",
" def filter_section(section_data: Dict[str, Any], section_config: Dict[str, bool]) -> Dict[str, Any]:\n",
" \"\"\"Filter a section of the data based on the section configuration\"\"\"\n",
" return {k: v for k, v in section_data.items() if k in section_config and section_config[k]}\n",
" \n",
" filtered_data = {}\n",
" \n",
" # Filter OpenAlex data\n",
" alex_filtered = {}\n",
" \n",
" # Basic metadata\n",
" if config.basic:\n",
" alex_filtered[\"basic\"] = filter_section(data.get(\"basic\", {}), config.basic)\n",
" \n",
" # Source/journal info\n",
" if config.source:\n",
" alex_filtered[\"source\"] = filter_section(data.get(\"source\", {}), config.source)\n",
" \n",
" # Authors\n",
" if config.authors:\n",
" authors_data = data.get(\"authors\", [])\n",
" filtered_authors = []\n",
" for author in authors_data:\n",
" filtered_author = filter_section(author, config.authors)\n",
" if config.authors.get(\"affiliations\", False):\n",
" print(author.get(\"affiliations\", []))\n",
" filtered_author[\"affiliations\"] = [\n",
" filter_section(aff, config.authors[\"affiliations\"])\n",
" for aff in author.get(\"affiliations\", [])\n",
" ]\n",
" filtered_authors.append(filtered_author)\n",
" alex_filtered[\"authors\"] = filtered_authors\n",
" \n",
" # Metrics\n",
" if config.metrics:\n",
" alex_filtered[\"metrics\"] = filter_section(data.get(\"metrics\", {}), config.metrics)\n",
" \n",
" # Classification\n",
" if config.classification:\n",
" classification_data = data.get(\"classification\", {})\n",
" alex_filtered[\"classification\"] = {\n",
" k: v for k, v in classification_data.items() if k in config.classification and config.classification[k]\n",
" }\n",
" \n",
" # Access info\n",
" if config.access:\n",
" alex_filtered[\"access\"] = filter_section(data.get(\"access\", {}), config.access)\n",
" \n",
" # Related works\n",
" if config.related_works:\n",
" alex_filtered[\"related_works\"] = filter_section(data.get(\"related_works\", {}), config.related_works)\n",
" \n",
" # Abstract\n",
" if config.abstract and \"abstract\" in data:\n",
" alex_filtered[\"abstract\"] = data[\"abstract\"]\n",
" \n",
" filtered_data = alex_filtered\n",
" \n",
" return filtered_data"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'primary_topic': {'name': 'Gait Analysis and Fall Prevention in Elderly',\n",
" 'score': 0.9994,\n",
" 'field': 'Health Professions',\n",
" 'subfield': 'Physical Therapy, Sports Therapy and Rehabilitation'}}"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"doi = \"10.2196/41082\"\n",
"a = DataAugmenter()\n",
"info = a.get_alex_features(doi)\n",
"filtered_info = a.filter_augmented_data(info)\n",
"filtered_info[\"classification\"]"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"class FullAugmentedDataset: \n",
"\n",
" def __init__(self):\n",
" self.augmenter = DataAugmenter()\n",
" self.full_raw_dataset = self._load_the_dataset()\n",
"\n",
" def _load_the_dataset(self, type: DatasetType = DatasetType.FULL_RAW) -> pd.DataFrame:\n",
" \"\"\"Load as csv file one of the datasets for training.\"\"\"\n",
" assert str(PROJECT_ROOT).split(\"/\")[-1] == \"MatchingPubs\", \"Please run this script in the github repo folder \"\n",
" \n",
" if type == DatasetType.FULL_RAW:\n",
" return pd.read_csv(f\"{PROJECT_ROOT}/data/crossref-preprint-article-relationships-Aug-2023.csv\")\n",
"\n",
" def retrieve_dois_couple(self, len: int = 1, random: bool = False, seed: bool = None, full: bool = False):\n",
" \"\"\"Retrieve two DOIs from the dataset\"\"\"\n",
" if random:\n",
" dois = self.full_raw_dataset.sample(n=len, random_state=seed)[[\"preprint_doi\", \"article_doi\"]]\n",
" else:\n",
" dois = self.full_raw_dataset.head(len)[[\"preprint_doi\", \"article_doi\"]]\n",
" if full:\n",
" dois = self.full_raw_dataset[[\"preprint_doi\", \"article_doi\"]]\n",
" return dois.to_numpy()\n",
" \n",
" @staticmethod\n",
" def _flatten_list(lst):\n",
" \"\"\"\n",
" Flattens a nested list into a single list. If the input is not nested, it returns the original list.\n",
" Handles cases where some elements are lists and others are not.\n",
" \"\"\"\n",
" if not isinstance(lst, list): # Ensure the input is a list\n",
" raise ValueError(\"Input must be a list\")\n",
"\n",
" def _flatten(sublist):\n",
" for item in sublist:\n",
" if isinstance(item, list): # Check if the item is a list\n",
" yield from _flatten(item) # Recursively flatten the list\n",
" else:\n",
" yield item # Yield the non-list item\n",
"\n",
" return list(_flatten(lst))\n",
" \n",
" def _augmented_data_to_row(self, filtered_data: Dict[str, Any], preprint: bool = True) -> pd.Series:\n",
" \"\"\"Transform filtered augmented data into a pandas Series\n",
" \n",
" Args:\n",
" filtered_data: Dictionary containing filtered OpenAlex and Elsevier data\n",
" preprint: If True, use prpnt_ prefix, else use article_ prefix\n",
" \n",
" Returns:\n",
" pd.Series: Flattened data as a single row\n",
" \"\"\"\n",
"\n",
" additional_part = FullAugmentedDataset.filter_author(filtered_data.get(\"authors\",{}))\n",
" # modify the key of additional part by adding authors_ at the beginning\n",
" additional_part = {f\"authors_{k}\": v for k, v in additional_part.items()} \n",
" # remove authos key from filtreed_info\n",
" filtered_data.pop(\"authors\")\n",
" # append the additional part to the filtered_info\n",
" filtered_data.update(additional_part)\n",
" final_dictionary = FullAugmentedDataset.flatten_dict(filtered_data, preprint=preprint)\n",
"\n",
" for k, v in final_dictionary.items():\n",
" final_dictionary[k] = \"$@$\".join(map(str, FullAugmentedDataset._flatten_list(v))) if isinstance(v, list) else [v]\n",
"\n",
" return pd.DataFrame(final_dictionary)\n",
"\n",
" @staticmethod\n",
" def filter_author(authors_info : list) -> dict:\n",
"\n",
" try:\n",
" relevant_keys = authors_info[0].keys()\n",
" new_dict = {}\n",
" for key in relevant_keys:\n",
" new_dict[key] = [author[key] for author in authors_info]\n",
" return new_dict\n",
" except:\n",
" return {}\n",
" \n",
" @staticmethod\n",
" def flatten_dict(d: dict, parent_key: str = '', sep: str = '_', preprint = True) -> dict:\n",
" \"\"\"Flatten a nested dictionary.\n",
" \n",
" Args:\n",
" d (dict): The dictionary to flatten.\n",
" parent_key (str): The base key string to use for the flattened keys.\n",
" sep (str): The separator to use between parent and child keys.\n",
" \n",
" Returns:\n",
" dict: The flattened dictionary.\n",
" \"\"\"\n",
" addition = \"prpnt_\" if preprint else \"article_\"\n",
" def _flatten_dict(d: dict, parent_key: str = '', sep: str = '_') -> dict:\n",
" items = []\n",
" for k, v in d.items():\n",
" new_key = f\"{parent_key}{sep}{k}\" if parent_key else k\n",
" if isinstance(v, dict):\n",
" items.extend(_flatten_dict(v, new_key, sep=sep).items())\n",
" else:\n",
" items.append((new_key, v))\n",
" return dict(items)\n",
" return {f\"{addition}{k}\": v for k, v in _flatten_dict(d, parent_key, sep).items()}\n",
"\n",
" def process_pair(self, dois) -> pd.DataFrame:\n",
" \"\"\"Process a pair of DOIs and return combined rows as a DataFrame\"\"\"\n",
" assert len(dois) > 0\n",
" rows = []\n",
" for preprint_doi, article_doi in tqdm(dois):\n",
" # Get preprint features\n",
" preprint_features = self.augmenter.get_alex_features(preprint_doi) # augment with all the features\n",
" preprint_filtered = self.augmenter.filter_augmented_data(preprint_features) # filter the relevant features\n",
" preprint_row = self._augmented_data_to_row(preprint_filtered, True)\n",
"\n",
" # Get article features\n",
" article_features = self.augmenter.get_alex_features(article_doi) # augment with all the features\n",
" article_filtered = self.augmenter.filter_augmented_data(article_features)\n",
" article_row = self._augmented_data_to_row(article_filtered, False)\n",
"\n",
" # print(article_row.columns)\n",
" # print(len(preprint_row.columns))\n",
"\n",
" # combined_row = pd.concat([preprint_row, article_row], axis=1)\n",
" # rows.append(combined_row)\n",
" rows.append([preprint_row, article_row])\n",
"\n",
" return rows\n",
"\n",
" @staticmethod\n",
" def transform_array(input_array, factor):\n",
" output_list = []\n",
" \n",
" for i, row in enumerate(input_array):\n",
" other_indices = np.array([j for j in range(len(input_array)) if j != i])\n",
" sampled_indices = np.random.choice(other_indices, size=factor, replace=False)\n",
" sampled_rows = [input_array[j] for j in sampled_indices]\n",
"\n",
" output_list.append(pd.concat([row[0], row[1], pd.DataFrame(data=[1], columns=['label'])], axis=1))\n",
" for B in sampled_rows:\n",
" output_list.append(pd.concat([row[0], B[1], pd.DataFrame(data=[0], columns=['label'])], axis=1))\n",
"\n",
" return pd.concat(output_list).reset_index(drop=True)\n",
"\n",
" def get_full_dataset(self, len: int = 1, random: bool = True, seed: int = 42, full: bool = True) -> pd.DataFrame:\n",
" \"\"\"Process all DOI pairs and return full dataset\"\"\"\n",
" dois = self.retrieve_dois_couple(len, random, seed, full)\n",
" self.augmented_df = FullAugmentedDataset.transform_array(self.process_pair(dois), factor=3)\n",
" return self.augmented_df"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# TRYING STUFF"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"# Create dataset with new configs\n",
"dataset = FullAugmentedDataset()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(5, 2)"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dois = dataset.retrieve_dois_couple(5, random = True, seed = 42)\n",
"dois.shape"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"info = dataset.augmenter.get_alex_features(dois[0][0]) # augment with all the features"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'basic': {'id': 'https://openalex.org/W4213260597',\n",
" 'doi': 'https://doi.org/10.31234/osf.io/6fps2',\n",
" 'title': 'Distance perception in virtual reality: A meta-analysis of the effect of head-mounted display characteristics',\n",
" 'display_name': 'Distance perception in virtual reality: A meta-analysis of the effect of head-mounted display characteristics',\n",
" 'publication_year': 2022,\n",
" 'publication_date': '2022-02-12',\n",
" 'language': 'en',\n",
" 'type': 'preprint',\n",
" 'type_crossref': 'posted-content'},\n",
" 'source': {'journal_name': None,\n",
" 'issn': None,\n",
" 'issn_l': None,\n",
" 'publisher': None,\n",
" 'type': None},\n",
" 'authors': [{'position': 'first',\n",
" 'name': 'Jonathan W. Kelly',\n",
" 'id': 'https://openalex.org/A5011931977',\n",
" 'orcid': 'https://orcid.org/0000-0002-4317-273X',\n",
" 'is_corresponding': True,\n",
" 'affiliations': [{'name': 'Iowa State University',\n",
" 'id': 'https://openalex.org/I173911158',\n",
" 'country': 'US',\n",
" 'type': 'education',\n",
" 'ror': 'https://ror.org/04rswrd78'}]}],\n",
" 'classification': {'primary_topic': {'name': 'Virtual Presence and Embodiment in VR Research',\n",
" 'score': 0.9982,\n",
" 'field': 'Computer Science',\n",
" 'subfield': 'Human-Computer Interaction'},\n",
" 'topics': [{'name': 'Virtual Presence and Embodiment in VR Research',\n",
" 'score': 0.9982,\n",
" 'field': 'Computer Science'},\n",
" {'name': 'Neural Mechanisms of Visual Perception and Processing',\n",
" 'score': 0.9906,\n",
" 'field': 'Neuroscience'},\n",
" {'name': 'Spatial Ability for STEM Domains',\n",
" 'score': 0.9727,\n",
" 'field': 'Engineering'}],\n",
" 'concepts': [{'name': 'Virtual reality',\n",
" 'level': 2,\n",
" 'score': 0.74525213,\n",
" 'wikidata': 'https://www.wikidata.org/wiki/Q170519'},\n",
" {'name': 'Perception',\n",
" 'level': 2,\n",
" 'score': 0.69497585,\n",
" 'wikidata': 'https://www.wikidata.org/wiki/Q160402'},\n",
" {'name': 'Optical head-mounted display',\n",
" 'level': 2,\n",
" 'score': 0.64143133,\n",
" 'wikidata': 'https://www.wikidata.org/wiki/Q17105103'},\n",
" {'name': 'Computer science',\n",
" 'level': 0,\n",
" 'score': 0.4773505,\n",
" 'wikidata': 'https://www.wikidata.org/wiki/Q21198'},\n",
" {'name': 'Psychology',\n",
" 'level': 0,\n",
" 'score': 0.3757282,\n",
" 'wikidata': 'https://www.wikidata.org/wiki/Q9418'},\n",
" {'name': 'Computer vision',\n",
" 'level': 1,\n",
" 'score': 0.3722988,\n",
" 'wikidata': 'https://www.wikidata.org/wiki/Q844240'},\n",
" {'name': 'Artificial intelligence',\n",
" 'level': 1,\n",
" 'score': 0.35102686,\n",
" 'wikidata': 'https://www.wikidata.org/wiki/Q11660'},\n",
" {'name': 'Neuroscience',\n",
" 'level': 1,\n",
" 'score': 0.0,\n",
" 'wikidata': 'https://www.wikidata.org/wiki/Q207011'}]},\n",
" 'metrics': {'cited_by_count': 6,\n",
" 'cited_by_percentile': {'value': 0.997093,\n",
" 'is_in_top_1_percent': True,\n",
" 'is_in_top_10_percent': True},\n",
" 'is_retracted': False,\n",
" 'fwci': None,\n",
" 'referenced_works_count': 89},\n",
" 'access': {'is_oa': True,\n",
" 'oa_status': 'green',\n",
" 'oa_url': 'https://psyarxiv.com/6fps2/download',\n",
" 'pdf_url': 'https://psyarxiv.com/6fps2/download',\n",
" 'license': None},\n",
" 'abstract': 'Distances are commonly underperceived in virtual reality (VR), and this finding has been documented repeatedly over more than two decades of research. Yet, there is evidence that perceived distance is more accurate in modern compared to older head-mounted displays (HMDs). This meta-analysis of 131 studies describes egocentric distance perception across 20 HMDs, and also examines the relationship between perceived distance and technical HMD characteristics. Judged distance was positively associated with HMD field of view (FOV), positively associated with HMD resolution, and negatively associated with HMD weight. The effects of FOV and resolution were more pronounced among heavier HMDs. These findings suggest that future improvements in these technical characteristics may be central to resolving the problem of distance underperception in VR.'}"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"info"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"filtered_info = dataset.augmenter.filter_augmented_data(info)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"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>prpnt_basic_id</th>\n",
" <th>prpnt_basic_doi</th>\n",
" <th>prpnt_basic_title</th>\n",
" <th>prpnt_basic_display_name</th>\n",
" <th>prpnt_basic_publication_year</th>\n",
" <th>prpnt_basic_publication_date</th>\n",
" <th>prpnt_basic_language</th>\n",
" <th>prpnt_basic_type</th>\n",
" <th>prpnt_basic_type_crossref</th>\n",
" <th>prpnt_source_journal_name</th>\n",
" <th>...</th>\n",
" <th>prpnt_access_oa_status</th>\n",
" <th>prpnt_access_oa_url</th>\n",
" <th>prpnt_access_pdf_url</th>\n",
" <th>prpnt_access_license</th>\n",
" <th>prpnt_abstract</th>\n",
" <th>prpnt_authors_position</th>\n",
" <th>prpnt_authors_name</th>\n",
" <th>prpnt_authors_id</th>\n",
" <th>prpnt_authors_orcid</th>\n",
" <th>prpnt_authors_is_corresponding</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>https://openalex.org/W4213260597</td>\n",
" <td>https://doi.org/10.31234/osf.io/6fps2</td>\n",
" <td>Distance perception in virtual reality: A meta...</td>\n",
" <td>Distance perception in virtual reality: A meta...</td>\n",
" <td>2022</td>\n",
" <td>2022-02-12</td>\n",
" <td>en</td>\n",
" <td>preprint</td>\n",
" <td>posted-content</td>\n",
" <td>None</td>\n",
" <td>...</td>\n",
" <td>green</td>\n",
" <td>https://psyarxiv.com/6fps2/download</td>\n",
" <td>https://psyarxiv.com/6fps2/download</td>\n",
" <td>None</td>\n",
" <td>Distances are commonly underperceived in virtu...</td>\n",
" <td>first</td>\n",
" <td>Jonathan W. Kelly</td>\n",
" <td>https://openalex.org/A5011931977</td>\n",
" <td>https://orcid.org/0000-0002-4317-273X</td>\n",
" <td>True</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1 rows × 33 columns</p>\n",
"</div>"
],
"text/plain": [
" prpnt_basic_id prpnt_basic_doi \\\n",
"0 https://openalex.org/W4213260597 https://doi.org/10.31234/osf.io/6fps2 \n",
"\n",
" prpnt_basic_title \\\n",
"0 Distance perception in virtual reality: A meta... \n",
"\n",
" prpnt_basic_display_name \\\n",
"0 Distance perception in virtual reality: A meta... \n",
"\n",
" prpnt_basic_publication_year prpnt_basic_publication_date \\\n",
"0 2022 2022-02-12 \n",
"\n",
" prpnt_basic_language prpnt_basic_type prpnt_basic_type_crossref \\\n",
"0 en preprint posted-content \n",
"\n",
" prpnt_source_journal_name ... prpnt_access_oa_status \\\n",
"0 None ... green \n",
"\n",
" prpnt_access_oa_url prpnt_access_pdf_url \\\n",
"0 https://psyarxiv.com/6fps2/download https://psyarxiv.com/6fps2/download \n",
"\n",
" prpnt_access_license prpnt_abstract \\\n",
"0 None Distances are commonly underperceived in virtu... \n",
"\n",
" prpnt_authors_position prpnt_authors_name \\\n",
"0 first Jonathan W. Kelly \n",
"\n",
" prpnt_authors_id prpnt_authors_orcid \\\n",
"0 https://openalex.org/A5011931977 https://orcid.org/0000-0002-4317-273X \n",
"\n",
" prpnt_authors_is_corresponding \n",
"0 True \n",
"\n",
"[1 rows x 33 columns]"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"row = dataset._augmented_data_to_row(filtered_info)\n",
"row"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 5/5 [00:04<00:00, 1.02it/s]\n",
"/var/folders/kp/b80wd80s53l95yjb77jn_l0r0000gn/T/ipykernel_17064/485421214.py:140: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
" return pd.concat(output_list).reset_index(drop=True)\n"
]
}
],
"source": [
"df = dataset.get_full_dataset(5, full=False)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[['10.31234/osf.io/6fps2' '10.1109/tvcg.2022.3196606']\n",
" ['10.5194/acpd-11-3071-2011' '10.5194/acp-12-3837-2012']\n",
" ['10.1101/2020.08.07.241687' '10.1021/acscentsci.1c00703']\n",
" ['10.21203/rs.3.rs-62250/v1' '10.1016/j.vetpar.2021.109373']\n",
" ['10.21203/rs.3.rs-2640242/v1' '10.1007/s10499-023-01047-1']]\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>prpnt_basic_doi</th>\n",
" <th>article_basic_doi</th>\n",
" <th>label</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>https://doi.org/10.31234/osf.io/6fps2</td>\n",
" <td>https://doi.org/10.1109/tvcg.2022.3196606</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>https://doi.org/10.31234/osf.io/6fps2</td>\n",
" <td>https://doi.org/10.1007/s10499-023-01047-1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>https://doi.org/10.31234/osf.io/6fps2</td>\n",
" <td>https://doi.org/10.5194/acp-12-3837-2012</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>https://doi.org/10.31234/osf.io/6fps2</td>\n",
" <td>https://doi.org/10.1016/j.vetpar.2021.109373</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>https://doi.org/10.5194/acpd-11-3071-2011</td>\n",
" <td>https://doi.org/10.5194/acp-12-3837-2012</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>https://doi.org/10.5194/acpd-11-3071-2011</td>\n",
" <td>https://doi.org/10.1016/j.vetpar.2021.109373</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>https://doi.org/10.5194/acpd-11-3071-2011</td>\n",
" <td>https://doi.org/10.1109/tvcg.2022.3196606</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>https://doi.org/10.5194/acpd-11-3071-2011</td>\n",
" <td>https://doi.org/10.1007/s10499-023-01047-1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>https://doi.org/10.1101/2020.08.07.241687</td>\n",
" <td>https://doi.org/10.1021/acscentsci.1c00703</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>https://doi.org/10.1101/2020.08.07.241687</td>\n",
" <td>https://doi.org/10.1007/s10499-023-01047-1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>https://doi.org/10.1101/2020.08.07.241687</td>\n",
" <td>https://doi.org/10.1109/tvcg.2022.3196606</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>https://doi.org/10.1101/2020.08.07.241687</td>\n",
" <td>https://doi.org/10.1016/j.vetpar.2021.109373</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>https://doi.org/10.21203/rs.3.rs-62250/v1</td>\n",
" <td>https://doi.org/10.1016/j.vetpar.2021.109373</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>https://doi.org/10.21203/rs.3.rs-62250/v1</td>\n",
" <td>https://doi.org/10.5194/acp-12-3837-2012</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>https://doi.org/10.21203/rs.3.rs-62250/v1</td>\n",
" <td>https://doi.org/10.1109/tvcg.2022.3196606</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>https://doi.org/10.21203/rs.3.rs-62250/v1</td>\n",
" <td>https://doi.org/10.1021/acscentsci.1c00703</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>https://doi.org/10.21203/rs.3.rs-2640242/v1</td>\n",
" <td>https://doi.org/10.1007/s10499-023-01047-1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>https://doi.org/10.21203/rs.3.rs-2640242/v1</td>\n",
" <td>https://doi.org/10.5194/acp-12-3837-2012</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>https://doi.org/10.21203/rs.3.rs-2640242/v1</td>\n",
" <td>https://doi.org/10.1016/j.vetpar.2021.109373</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>https://doi.org/10.21203/rs.3.rs-2640242/v1</td>\n",
" <td>https://doi.org/10.1021/acscentsci.1c00703</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" prpnt_basic_doi \\\n",
"0 https://doi.org/10.31234/osf.io/6fps2 \n",
"1 https://doi.org/10.31234/osf.io/6fps2 \n",
"2 https://doi.org/10.31234/osf.io/6fps2 \n",
"3 https://doi.org/10.31234/osf.io/6fps2 \n",
"4 https://doi.org/10.5194/acpd-11-3071-2011 \n",
"5 https://doi.org/10.5194/acpd-11-3071-2011 \n",
"6 https://doi.org/10.5194/acpd-11-3071-2011 \n",
"7 https://doi.org/10.5194/acpd-11-3071-2011 \n",
"8 https://doi.org/10.1101/2020.08.07.241687 \n",
"9 https://doi.org/10.1101/2020.08.07.241687 \n",
"10 https://doi.org/10.1101/2020.08.07.241687 \n",
"11 https://doi.org/10.1101/2020.08.07.241687 \n",
"12 https://doi.org/10.21203/rs.3.rs-62250/v1 \n",
"13 https://doi.org/10.21203/rs.3.rs-62250/v1 \n",
"14 https://doi.org/10.21203/rs.3.rs-62250/v1 \n",
"15 https://doi.org/10.21203/rs.3.rs-62250/v1 \n",
"16 https://doi.org/10.21203/rs.3.rs-2640242/v1 \n",
"17 https://doi.org/10.21203/rs.3.rs-2640242/v1 \n",
"18 https://doi.org/10.21203/rs.3.rs-2640242/v1 \n",
"19 https://doi.org/10.21203/rs.3.rs-2640242/v1 \n",
"\n",
" article_basic_doi label \n",
"0 https://doi.org/10.1109/tvcg.2022.3196606 1 \n",
"1 https://doi.org/10.1007/s10499-023-01047-1 0 \n",
"2 https://doi.org/10.5194/acp-12-3837-2012 0 \n",
"3 https://doi.org/10.1016/j.vetpar.2021.109373 0 \n",
"4 https://doi.org/10.5194/acp-12-3837-2012 1 \n",
"5 https://doi.org/10.1016/j.vetpar.2021.109373 0 \n",
"6 https://doi.org/10.1109/tvcg.2022.3196606 0 \n",
"7 https://doi.org/10.1007/s10499-023-01047-1 0 \n",
"8 https://doi.org/10.1021/acscentsci.1c00703 1 \n",
"9 https://doi.org/10.1007/s10499-023-01047-1 0 \n",
"10 https://doi.org/10.1109/tvcg.2022.3196606 0 \n",
"11 https://doi.org/10.1016/j.vetpar.2021.109373 0 \n",
"12 https://doi.org/10.1016/j.vetpar.2021.109373 1 \n",
"13 https://doi.org/10.5194/acp-12-3837-2012 0 \n",
"14 https://doi.org/10.1109/tvcg.2022.3196606 0 \n",
"15 https://doi.org/10.1021/acscentsci.1c00703 0 \n",
"16 https://doi.org/10.1007/s10499-023-01047-1 1 \n",
"17 https://doi.org/10.5194/acp-12-3837-2012 0 \n",
"18 https://doi.org/10.1016/j.vetpar.2021.109373 0 \n",
"19 https://doi.org/10.1021/acscentsci.1c00703 0 "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"print(dois)\n",
"display(df[['prpnt_basic_doi', 'article_basic_doi', 'label']])"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "dl",
"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": "3.9.6"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|