File size: 65,285 Bytes
9894d76 |
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 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 53,
"id": "d3a1f52b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"from dotenv import load_dotenv\n",
"from pathlib import Path\n",
"import json\n",
"\n",
"load_dotenv()"
]
},
{
"cell_type": "code",
"execution_count": 54,
"id": "bca20bcc",
"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>ImageId</th>\n",
" <th>EncodedPixels</th>\n",
" <th>Height</th>\n",
" <th>Width</th>\n",
" <th>ClassId</th>\n",
" <th>AttributesIds</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>00000663ed1ff0c4e0132b9b9ac53f6e</td>\n",
" <td>6068157 7 6073371 20 6078584 34 6083797 48 608...</td>\n",
" <td>5214</td>\n",
" <td>3676</td>\n",
" <td>6</td>\n",
" <td>115,136,143,154,230,295,316,317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>00000663ed1ff0c4e0132b9b9ac53f6e</td>\n",
" <td>6323163 11 6328356 32 6333549 53 6338742 75 63...</td>\n",
" <td>5214</td>\n",
" <td>3676</td>\n",
" <td>0</td>\n",
" <td>115,136,142,146,225,295,316,317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>00000663ed1ff0c4e0132b9b9ac53f6e</td>\n",
" <td>8521389 10 8526585 30 8531789 42 8537002 46 85...</td>\n",
" <td>5214</td>\n",
" <td>3676</td>\n",
" <td>28</td>\n",
" <td>163</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>00000663ed1ff0c4e0132b9b9ac53f6e</td>\n",
" <td>12903854 2 12909064 7 12914275 10 12919485 15 ...</td>\n",
" <td>5214</td>\n",
" <td>3676</td>\n",
" <td>31</td>\n",
" <td>160,204</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>00000663ed1ff0c4e0132b9b9ac53f6e</td>\n",
" <td>10837337 5 10842542 14 10847746 24 10852951 33...</td>\n",
" <td>5214</td>\n",
" <td>3676</td>\n",
" <td>32</td>\n",
" <td>219</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" ImageId \\\n",
"0 00000663ed1ff0c4e0132b9b9ac53f6e \n",
"1 00000663ed1ff0c4e0132b9b9ac53f6e \n",
"2 00000663ed1ff0c4e0132b9b9ac53f6e \n",
"3 00000663ed1ff0c4e0132b9b9ac53f6e \n",
"4 00000663ed1ff0c4e0132b9b9ac53f6e \n",
"\n",
" EncodedPixels Height Width ClassId \\\n",
"0 6068157 7 6073371 20 6078584 34 6083797 48 608... 5214 3676 6 \n",
"1 6323163 11 6328356 32 6333549 53 6338742 75 63... 5214 3676 0 \n",
"2 8521389 10 8526585 30 8531789 42 8537002 46 85... 5214 3676 28 \n",
"3 12903854 2 12909064 7 12914275 10 12919485 15 ... 5214 3676 31 \n",
"4 10837337 5 10842542 14 10847746 24 10852951 33... 5214 3676 32 \n",
"\n",
" AttributesIds \n",
"0 115,136,143,154,230,295,316,317 \n",
"1 115,136,142,146,225,295,316,317 \n",
"2 163 \n",
"3 160,204 \n",
"4 219 "
]
},
"execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Get project root (one level up from notebooks/ if running from notebooks directory)\n",
"current_dir = Path.cwd()\n",
"PROJECT_ROOT = current_dir.parent if current_dir.name == \"notebooks\" else current_dir\n",
"DATA_PATH = PROJECT_ROOT / \"data\"\n",
"\n",
"fashion_df = pd.read_csv(DATA_PATH / \"train.csv\")\n",
"fashion_df.head()\n"
]
},
{
"cell_type": "code",
"execution_count": 55,
"id": "58f4f7b4",
"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>name</th>\n",
" <th>supercategory</th>\n",
" <th>level</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>shirt, blouse</td>\n",
" <td>upperbody</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>top, t-shirt, sweatshirt</td>\n",
" <td>upperbody</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>sweater</td>\n",
" <td>upperbody</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>cardigan</td>\n",
" <td>upperbody</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>jacket</td>\n",
" <td>upperbody</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>5</td>\n",
" <td>vest</td>\n",
" <td>upperbody</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>6</td>\n",
" <td>pants</td>\n",
" <td>lowerbody</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>7</td>\n",
" <td>shorts</td>\n",
" <td>lowerbody</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>8</td>\n",
" <td>skirt</td>\n",
" <td>lowerbody</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>9</td>\n",
" <td>coat</td>\n",
" <td>wholebody</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>10</td>\n",
" <td>dress</td>\n",
" <td>wholebody</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>11</td>\n",
" <td>jumpsuit</td>\n",
" <td>wholebody</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>12</td>\n",
" <td>cape</td>\n",
" <td>wholebody</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>13</td>\n",
" <td>glasses</td>\n",
" <td>head</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>14</td>\n",
" <td>hat</td>\n",
" <td>head</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>15</td>\n",
" <td>headband, head covering, hair accessory</td>\n",
" <td>head</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>16</td>\n",
" <td>tie</td>\n",
" <td>neck</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>17</td>\n",
" <td>glove</td>\n",
" <td>arms and hands</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>18</td>\n",
" <td>watch</td>\n",
" <td>arms and hands</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>19</td>\n",
" <td>belt</td>\n",
" <td>waist</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>20</td>\n",
" <td>leg warmer</td>\n",
" <td>legs and feet</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>21</td>\n",
" <td>tights, stockings</td>\n",
" <td>legs and feet</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>22</td>\n",
" <td>sock</td>\n",
" <td>legs and feet</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>23</td>\n",
" <td>shoe</td>\n",
" <td>legs and feet</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>24</td>\n",
" <td>bag, wallet</td>\n",
" <td>others</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>25</td>\n",
" <td>scarf</td>\n",
" <td>others</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>26</td>\n",
" <td>umbrella</td>\n",
" <td>others</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>27</td>\n",
" <td>hood</td>\n",
" <td>garment parts</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>28</td>\n",
" <td>collar</td>\n",
" <td>garment parts</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>29</td>\n",
" <td>lapel</td>\n",
" <td>garment parts</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>30</td>\n",
" <td>epaulette</td>\n",
" <td>garment parts</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>31</td>\n",
" <td>sleeve</td>\n",
" <td>garment parts</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>32</td>\n",
" <td>pocket</td>\n",
" <td>garment parts</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>33</td>\n",
" <td>neckline</td>\n",
" <td>garment parts</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>34</th>\n",
" <td>34</td>\n",
" <td>buckle</td>\n",
" <td>closures</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>35</th>\n",
" <td>35</td>\n",
" <td>zipper</td>\n",
" <td>closures</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>36</td>\n",
" <td>applique</td>\n",
" <td>decorations</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37</th>\n",
" <td>37</td>\n",
" <td>bead</td>\n",
" <td>decorations</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>38</th>\n",
" <td>38</td>\n",
" <td>bow</td>\n",
" <td>decorations</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>39</td>\n",
" <td>flower</td>\n",
" <td>decorations</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>40</th>\n",
" <td>40</td>\n",
" <td>fringe</td>\n",
" <td>decorations</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>41</th>\n",
" <td>41</td>\n",
" <td>ribbon</td>\n",
" <td>decorations</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
" <td>42</td>\n",
" <td>rivet</td>\n",
" <td>decorations</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>43</th>\n",
" <td>43</td>\n",
" <td>ruffle</td>\n",
" <td>decorations</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
" <td>44</td>\n",
" <td>sequin</td>\n",
" <td>decorations</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>45</td>\n",
" <td>tassel</td>\n",
" <td>decorations</td>\n",
" <td>2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id name supercategory level\n",
"0 0 shirt, blouse upperbody 2\n",
"1 1 top, t-shirt, sweatshirt upperbody 2\n",
"2 2 sweater upperbody 2\n",
"3 3 cardigan upperbody 2\n",
"4 4 jacket upperbody 2\n",
"5 5 vest upperbody 2\n",
"6 6 pants lowerbody 2\n",
"7 7 shorts lowerbody 2\n",
"8 8 skirt lowerbody 2\n",
"9 9 coat wholebody 2\n",
"10 10 dress wholebody 2\n",
"11 11 jumpsuit wholebody 2\n",
"12 12 cape wholebody 2\n",
"13 13 glasses head 2\n",
"14 14 hat head 2\n",
"15 15 headband, head covering, hair accessory head 2\n",
"16 16 tie neck 2\n",
"17 17 glove arms and hands 2\n",
"18 18 watch arms and hands 2\n",
"19 19 belt waist 2\n",
"20 20 leg warmer legs and feet 2\n",
"21 21 tights, stockings legs and feet 2\n",
"22 22 sock legs and feet 2\n",
"23 23 shoe legs and feet 2\n",
"24 24 bag, wallet others 2\n",
"25 25 scarf others 2\n",
"26 26 umbrella others 2\n",
"27 27 hood garment parts 2\n",
"28 28 collar garment parts 2\n",
"29 29 lapel garment parts 2\n",
"30 30 epaulette garment parts 2\n",
"31 31 sleeve garment parts 2\n",
"32 32 pocket garment parts 2\n",
"33 33 neckline garment parts 2\n",
"34 34 buckle closures 2\n",
"35 35 zipper closures 2\n",
"36 36 applique decorations 2\n",
"37 37 bead decorations 2\n",
"38 38 bow decorations 2\n",
"39 39 flower decorations 2\n",
"40 40 fringe decorations 2\n",
"41 41 ribbon decorations 2\n",
"42 42 rivet decorations 2\n",
"43 43 ruffle decorations 2\n",
"44 44 sequin decorations 2\n",
"45 45 tassel decorations 2"
]
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"label_descriptions = json.load(open(DATA_PATH / \"label_descriptions.json\"))\n",
"\n",
"categories_df = pd.DataFrame(label_descriptions[\"categories\"])\n",
"categories_df"
]
},
{
"cell_type": "code",
"execution_count": 56,
"id": "48d7ab2b",
"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>name</th>\n",
" <th>supercategory</th>\n",
" <th>level</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>classic (t-shirt)</td>\n",
" <td>nickname</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>polo (shirt)</td>\n",
" <td>nickname</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>undershirt</td>\n",
" <td>nickname</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>henley (shirt)</td>\n",
" <td>nickname</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>ringer (t-shirt)</td>\n",
" <td>nickname</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>289</th>\n",
" <td>336</td>\n",
" <td>peacock</td>\n",
" <td>animal</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>290</th>\n",
" <td>337</td>\n",
" <td>zebra</td>\n",
" <td>animal</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>291</th>\n",
" <td>338</td>\n",
" <td>giraffe</td>\n",
" <td>animal</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>292</th>\n",
" <td>339</td>\n",
" <td>toile de jouy</td>\n",
" <td>textile pattern</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>293</th>\n",
" <td>340</td>\n",
" <td>plant</td>\n",
" <td>textile pattern</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>294 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" id name supercategory level\n",
"0 0 classic (t-shirt) nickname 1\n",
"1 1 polo (shirt) nickname 1\n",
"2 2 undershirt nickname 1\n",
"3 3 henley (shirt) nickname 1\n",
"4 4 ringer (t-shirt) nickname 1\n",
".. ... ... ... ...\n",
"289 336 peacock animal 2\n",
"290 337 zebra animal 2\n",
"291 338 giraffe animal 2\n",
"292 339 toile de jouy textile pattern 1\n",
"293 340 plant textile pattern 1\n",
"\n",
"[294 rows x 4 columns]"
]
},
"execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"attributes_df = pd.DataFrame(label_descriptions[\"attributes\"])\n",
"attributes_df\n"
]
},
{
"cell_type": "code",
"execution_count": 57,
"id": "b178ce00",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Found 0 potentially SUGGESTIVE categories\n",
"Found 4 potentially SUGGESTIVE attributes\n",
"\n",
"============================================================\n",
"POTENTIALLY SUGGESTIVE CATEGORIES:\n",
"============================================================\n",
"Empty DataFrame\n",
"Columns: [id, name, supercategory]\n",
"Index: []\n",
"\n",
"============================================================\n",
"POTENTIALLY SUGGESTIVE ATTRIBUTES:\n",
"============================================================\n",
" id name supercategory\n",
" 51 booty (shorts) nickname\n",
"106 bodycon (dress) nickname\n",
"148 micro (length) length\n",
"192 plunging (neckline) neckline type\n"
]
}
],
"source": [
"# ULTRA-RESTRICTIVE criteria for UNCERTAIN SUGGESTIVE content\n",
"# Only items that are clearly and unambiguously SUGGESTIVE/revealing\n",
"# Removed: crop tops, halter tops, tube tops, mini length, tight fit, etc. - too many false positives\n",
"\n",
"# Only the most obviously SUGGESTIVE items\n",
"revealing_keywords = {\n",
" 'categories': [\n",
" # Only inherently revealing categories - removed most as they had false positives\n",
" # 'booty', # removed - checking attribute instead\n",
" # 'bodycon', # removed - checking attribute instead\n",
" ],\n",
" 'attributes': [\n",
" # ONLY the most clearly SUGGESTIVE items\n",
" 'booty (shorts)', # very specific and clearly SUGGESTIVE\n",
" 'bodycon (dress)', # form-fitting, often revealing\n",
" # Removed: crop (top), halter (top), tube (top), camisole, slip (dress) - too many false positives\n",
" ]\n",
"}\n",
"\n",
"# Only the most revealing patterns\n",
"revealing_patterns = {\n",
" 'length': [\n",
" # Removed: mini (length) - too broad, many modest mini skirts\n",
" 'micro (length)', # only very short - but still might have false positives\n",
" ],\n",
" 'neckline type': [\n",
" 'plunging (neckline)', # only the most revealing neckline\n",
" # Removed: off-the-shoulder, one shoulder - can be modest\n",
" ],\n",
" 'silhouette': [\n",
" # Removed: tight (fit) - way too broad, many normal clothes are tight\n",
" ],\n",
" 'nickname': [\n",
" # Only the most clearly SUGGESTIVE\n",
" 'booty (shorts)',\n",
" 'bodycon (dress)',\n",
" ]\n",
"}\n",
"\n",
"def is_potentially_SUGGESTIVE(name: str, supercategory: str = None) -> bool:\n",
" \"\"\"Check if a category or attribute name suggests potentially SUGGESTIVE content.\n",
" ULTRA-RESTRICTIVE: Only matches clearly SUGGESTIVE items to avoid false positives.\"\"\"\n",
" name_lower = name.lower()\n",
" \n",
" # Special case: check for \"booty\" in any context (shorts) - very specific\n",
" if 'booty' in name_lower:\n",
" return True\n",
" \n",
" # Check for revealing patterns by supercategory - very restrictive\n",
" if supercategory:\n",
" if supercategory == 'length':\n",
" # Only micro length (very short) - removed mini as too broad\n",
" if 'micro (length)' in name_lower:\n",
" return True\n",
" elif supercategory == 'neckline type':\n",
" # Only plunging neckline - most revealing\n",
" if 'plunging (neckline)' in name_lower:\n",
" return True\n",
" elif supercategory == 'nickname':\n",
" # Only the most clearly SUGGESTIVE styles\n",
" for pattern in revealing_patterns['nickname']:\n",
" if pattern.lower() in name_lower:\n",
" return True\n",
" \n",
" # Check categories for inherently revealing items\n",
" for keyword in revealing_keywords['categories']:\n",
" if keyword.lower() in name_lower:\n",
" return True\n",
" \n",
" # Check attributes for inherently revealing items\n",
" for keyword in revealing_keywords['attributes']:\n",
" if keyword.lower() in name_lower:\n",
" return True\n",
" \n",
" return False\n",
"\n",
"# Filter categories\n",
"SUGGESTIVE_categories = categories_df[\n",
" categories_df['name'].apply(lambda x: is_potentially_SUGGESTIVE(x))\n",
"].copy()\n",
"\n",
"# Filter attributes\n",
"SUGGESTIVE_attributes = attributes_df[\n",
" attributes_df.apply(lambda row: is_potentially_SUGGESTIVE(row['name'], row['supercategory']), axis=1)\n",
"].copy()\n",
"\n",
"print(f\"Found {len(SUGGESTIVE_categories)} potentially SUGGESTIVE categories\")\n",
"print(f\"Found {len(SUGGESTIVE_attributes)} potentially SUGGESTIVE attributes\")\n",
"print(\"\\n\" + \"=\"*60)\n",
"print(\"POTENTIALLY SUGGESTIVE CATEGORIES:\")\n",
"print(\"=\"*60)\n",
"print(SUGGESTIVE_categories[['id', 'name', 'supercategory']].to_string(index=False))\n",
"print(\"\\n\" + \"=\"*60)\n",
"print(\"POTENTIALLY SUGGESTIVE ATTRIBUTES:\")\n",
"print(\"=\"*60)\n",
"print(SUGGESTIVE_attributes[['id', 'name', 'supercategory']].to_string(index=False))\n"
]
},
{
"cell_type": "code",
"execution_count": 58,
"id": "7ff15a1c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"============================================================\n",
"BREAKDOWN BY SUPERCATEGORY:\n",
"============================================================\n",
"\n",
"Attributes by supercategory:\n",
"supercategory\n",
"nickname 2\n",
"length 1\n",
"neckline type 1\n",
"dtype: int64\n",
"\n",
"Detailed attribute breakdown:\n",
"\n",
"nickname:\n",
" - booty (shorts) (id: 51)\n",
" - bodycon (dress) (id: 106)\n",
"\n",
"length:\n",
" - micro (length) (id: 148)\n",
"\n",
"neckline type:\n",
" - plunging (neckline) (id: 192)\n",
"\n",
"============================================================\n",
"SUMMARY DATAFRAME (for export):\n",
"============================================================\n",
" type id name supercategory\n",
"0 attribute 51 booty (shorts) nickname\n",
"1 attribute 106 bodycon (dress) nickname\n",
"2 attribute 148 micro (length) length\n",
"3 attribute 192 plunging (neckline) neckline type\n"
]
}
],
"source": [
"# Create a detailed breakdown by supercategory\n",
"print(\"=\"*60)\n",
"print(\"BREAKDOWN BY SUPERCATEGORY:\")\n",
"print(\"=\"*60)\n",
"\n",
"if len(SUGGESTIVE_attributes) > 0:\n",
" print(\"\\nAttributes by supercategory:\")\n",
" print(SUGGESTIVE_attributes.groupby('supercategory').size().sort_values(ascending=False))\n",
" \n",
" print(\"\\nDetailed attribute breakdown:\")\n",
" for supercat in SUGGESTIVE_attributes['supercategory'].unique():\n",
" print(f\"\\n{supercat}:\")\n",
" subset = SUGGESTIVE_attributes[SUGGESTIVE_attributes['supercategory'] == supercat]\n",
" for _, row in subset.iterrows():\n",
" print(f\" - {row['name']} (id: {row['id']})\")\n",
"\n",
"# Create summary DataFrames for export\n",
"SUGGESTIVE_summary = {\n",
" 'type': ['category'] * len(SUGGESTIVE_categories) + ['attribute'] * len(SUGGESTIVE_attributes),\n",
" 'id': list(SUGGESTIVE_categories['id']) + list(SUGGESTIVE_attributes['id']),\n",
" 'name': list(SUGGESTIVE_categories['name']) + list(SUGGESTIVE_attributes['name']),\n",
" 'supercategory': list(SUGGESTIVE_categories['supercategory']) + list(SUGGESTIVE_attributes['supercategory'])\n",
"}\n",
"\n",
"SUGGESTIVE_summary_df = pd.DataFrame(SUGGESTIVE_summary)\n",
"print(\"\\n\" + \"=\"*60)\n",
"print(\"SUMMARY DATAFRAME (for export):\")\n",
"print(\"=\"*60)\n",
"print(SUGGESTIVE_summary_df)\n",
"\n",
"# Optionally save to CSV\n",
"# SUGGESTIVE_summary_df.to_csv(DATA_PATH / \"SUGGESTIVE_labels.csv\", index=False)\n"
]
},
{
"cell_type": "code",
"execution_count": 59,
"id": "a46d616c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"SUGGESTIVE category IDs: set()\n",
"SUGGESTIVE attribute IDs: {192, 106, 51, 148}\n",
"\n",
"Total unique SUGGESTIVE category IDs: 0\n",
"Total unique SUGGESTIVE attribute IDs: 4\n",
"\n",
"============================================================\n",
"FILTERING RESULTS:\n",
"============================================================\n",
"Total images in fashion_df: 333401\n",
"Images with SUGGESTIVE content: 5218\n",
"Percentage: 1.57%\n",
"\n",
"Breakdown:\n",
" - Matched by category only: 0\n",
" - Matched by attribute only: 5218\n",
" - Matched by both: 0\n",
"\n",
"============================================================\n",
"SAMPLE OF SUGGESTIVE IMAGES (first 10 rows):\n",
"============================================================\n",
" ImageId ClassId \\\n",
"49 000b3a87508b0fa185fbd53ecbe2e4c6 33 \n",
"147 001a66b16b12f12dc45e2bba40e04683 10 \n",
"180 00211c06b1fe730097dde122cd4d3f8c 7 \n",
"304 003ae3da258f7ba7267af5f159dd3502 10 \n",
"369 0048f6c47de85cc4dc263912bd0ff6f5 33 \n",
"372 0048f6c47de85cc4dc263912bd0ff6f5 7 \n",
"445 005380bd939eb68085af3f804d387824 10 \n",
"456 0054564ae183ad9a1b152eef0bc11e1d 10 \n",
"465 0055347a114b215f8f469fec9e38c272 10 \n",
"526 005e9b75edcee7d655c390ea5416641d 33 \n",
"\n",
" AttributesIds \n",
"49 192 \n",
"147 106,115,127,142,149,229,295,316 \n",
"180 50,115,136,142,148,230,295,300,317 \n",
"304 106,127,141,150,295,316,317 \n",
"369 192 \n",
"372 50,115,136,142,148,317 \n",
"445 106,114,127,142,150,229,295,311,317 \n",
"456 106,115,127,142,149,229,295,316,317 \n",
"465 106,115,127,142,149,229,295,316,317 \n",
"526 192 \n"
]
}
],
"source": [
"# Get IDs of SUGGESTIVE categories and attributes\n",
"SUGGESTIVE_category_ids = set(SUGGESTIVE_categories['id'].tolist())\n",
"SUGGESTIVE_attribute_ids = set(SUGGESTIVE_attributes['id'].tolist())\n",
"\n",
"print(f\"SUGGESTIVE category IDs: {SUGGESTIVE_category_ids}\")\n",
"print(f\"SUGGESTIVE attribute IDs: {SUGGESTIVE_attribute_ids}\")\n",
"print(f\"\\nTotal unique SUGGESTIVE category IDs: {len(SUGGESTIVE_category_ids)}\")\n",
"print(f\"Total unique SUGGESTIVE attribute IDs: {len(SUGGESTIVE_attribute_ids)}\")\n",
"\n",
"# Function to check if AttributesIds string contains any SUGGESTIVE attribute ID\n",
"def has_SUGGESTIVE_attribute(attributes_str: str) -> bool:\n",
" \"\"\"Check if the comma-separated attributes string contains any SUGGESTIVE attribute ID.\"\"\"\n",
" if pd.isna(attributes_str) or attributes_str == '':\n",
" return False\n",
" # Parse comma-separated string and convert to integers\n",
" try:\n",
" attr_ids = [int(x.strip()) for x in str(attributes_str).split(',')]\n",
" return bool(SUGGESTIVE_attribute_ids.intersection(set(attr_ids)))\n",
" except (ValueError, AttributeError):\n",
" return False\n",
"\n",
"# Filter fashion_df for SUGGESTIVE images\n",
"# An image is SUGGESTIVE if:\n",
"# 1. Its ClassId matches a SUGGESTIVE category, OR\n",
"# 2. Its AttributesIds contains any SUGGESTIVE attribute ID\n",
"\n",
"SUGGESTIVE_mask = (\n",
" fashion_df['ClassId'].isin(SUGGESTIVE_category_ids) |\n",
" fashion_df['AttributesIds'].apply(has_SUGGESTIVE_attribute)\n",
")\n",
"\n",
"SUGGESTIVE_fashion_df = fashion_df[SUGGESTIVE_mask].copy()\n",
"\n",
"print(\"\\n\" + \"=\"*60)\n",
"print(\"FILTERING RESULTS:\")\n",
"print(\"=\"*60)\n",
"print(f\"Total images in fashion_df: {len(fashion_df)}\")\n",
"print(f\"Images with SUGGESTIVE content: {len(SUGGESTIVE_fashion_df)}\")\n",
"print(f\"Percentage: {len(SUGGESTIVE_fashion_df) / len(fashion_df) * 100:.2f}%\")\n",
"\n",
"# Show breakdown by type of match\n",
"category_matches = fashion_df['ClassId'].isin(SUGGESTIVE_category_ids).sum()\n",
"attribute_matches = fashion_df['AttributesIds'].apply(has_SUGGESTIVE_attribute).sum()\n",
"both_matches = ((fashion_df['ClassId'].isin(SUGGESTIVE_category_ids)) & \n",
" (fashion_df['AttributesIds'].apply(has_SUGGESTIVE_attribute))).sum()\n",
"\n",
"print(f\"\\nBreakdown:\")\n",
"print(f\" - Matched by category only: {category_matches - both_matches}\")\n",
"print(f\" - Matched by attribute only: {attribute_matches - both_matches}\")\n",
"print(f\" - Matched by both: {both_matches}\")\n",
"\n",
"# Show sample of SUGGESTIVE images\n",
"print(\"\\n\" + \"=\"*60)\n",
"print(\"SAMPLE OF SUGGESTIVE IMAGES (first 10 rows):\")\n",
"print(\"=\"*60)\n",
"print(SUGGESTIVE_fashion_df[['ImageId', 'ClassId', 'AttributesIds']].head(10))\n"
]
},
{
"cell_type": "code",
"execution_count": 60,
"id": "0e1b67fa",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"============================================================\n",
"DIAGNOSTIC: BREAKDOWN OF MATCHES\n",
"============================================================\n",
"\n",
"1. Matches by Category (ClassId):\n",
" No category matches\n",
"\n",
"2. Matches by Attribute (AttributesIds):\n",
" - micro (length) (id: 148): 3190 matches\n",
" - bodycon (dress) (id: 106): 1144 matches\n",
" - plunging (neckline) (id: 192): 966 matches\n",
" - booty (shorts) (id: 51): 20 matches\n",
"\n",
"3. Sample rows with their matched attributes/categories:\n",
" (First 5 rows showing ImageId, ClassId, and matched attributes)\n",
"\n",
" ImageId: 000b3a87508b0fa185fbd53ecbe2e4c6\n",
" ClassId: 33 -> neckline\n",
" Matched Attributes: ['plunging (neckline)']\n",
"\n",
" ImageId: 001a66b16b12f12dc45e2bba40e04683\n",
" ClassId: 10 -> dress\n",
" Matched Attributes: ['bodycon (dress)']\n",
"\n",
" ImageId: 00211c06b1fe730097dde122cd4d3f8c\n",
" ClassId: 7 -> shorts\n",
" Matched Attributes: ['micro (length)']\n",
"\n",
" ImageId: 003ae3da258f7ba7267af5f159dd3502\n",
" ClassId: 10 -> dress\n",
" Matched Attributes: ['bodycon (dress)']\n",
"\n",
" ImageId: 0048f6c47de85cc4dc263912bd0ff6f5\n",
" ClassId: 33 -> neckline\n",
" Matched Attributes: ['plunging (neckline)']\n"
]
}
],
"source": [
"# DIAGNOSTIC: Show what's actually being matched\n",
"# This helps identify which attributes/categories are causing matches\n",
"\n",
"print(\"=\"*60)\n",
"print(\"DIAGNOSTIC: BREAKDOWN OF MATCHES\")\n",
"print(\"=\"*60)\n",
"\n",
"# Create a mapping of attribute IDs to names\n",
"attr_id_to_name = dict(zip(attributes_df['id'], attributes_df['name']))\n",
"cat_id_to_name = dict(zip(categories_df['id'], categories_df['name']))\n",
"\n",
"# Analyze what's matching in the SUGGESTIVE_fashion_df\n",
"print(\"\\n1. Matches by Category (ClassId):\")\n",
"category_matches = SUGGESTIVE_fashion_df[SUGGESTIVE_fashion_df['ClassId'].isin(SUGGESTIVE_category_ids)]\n",
"if len(category_matches) > 0:\n",
" cat_counts = category_matches['ClassId'].value_counts()\n",
" for cat_id, count in cat_counts.items():\n",
" cat_name = cat_id_to_name.get(cat_id, f\"Unknown (id: {cat_id})\")\n",
" print(f\" - {cat_name} (id: {cat_id}): {count} matches\")\n",
"else:\n",
" print(\" No category matches\")\n",
"\n",
"print(\"\\n2. Matches by Attribute (AttributesIds):\")\n",
"# Find which attributes are matching\n",
"matching_attributes = {}\n",
"for idx, row in SUGGESTIVE_fashion_df.iterrows():\n",
" if pd.notna(row['AttributesIds']) and row['AttributesIds'] != '':\n",
" try:\n",
" attr_ids = [int(x.strip()) for x in str(row['AttributesIds']).split(',')]\n",
" matching_attr_ids = SUGGESTIVE_attribute_ids.intersection(set(attr_ids))\n",
" for attr_id in matching_attr_ids:\n",
" matching_attributes[attr_id] = matching_attributes.get(attr_id, 0) + 1\n",
" except:\n",
" pass\n",
"\n",
"if matching_attributes:\n",
" for attr_id, count in sorted(matching_attributes.items(), key=lambda x: x[1], reverse=True):\n",
" attr_name = attr_id_to_name.get(attr_id, f\"Unknown (id: {attr_id})\")\n",
" print(f\" - {attr_name} (id: {attr_id}): {count} matches\")\n",
"else:\n",
" print(\" No attribute matches\")\n",
"\n",
"print(\"\\n3. Sample rows with their matched attributes/categories:\")\n",
"print(\" (First 5 rows showing ImageId, ClassId, and matched attributes)\")\n",
"for idx, row in SUGGESTIVE_fashion_df.head(5).iterrows():\n",
" print(f\"\\n ImageId: {row['ImageId']}\")\n",
" print(f\" ClassId: {row['ClassId']} -> {cat_id_to_name.get(row['ClassId'], 'Unknown')}\")\n",
" if pd.notna(row['AttributesIds']) and row['AttributesIds'] != '':\n",
" try:\n",
" attr_ids = [int(x.strip()) for x in str(row['AttributesIds']).split(',')]\n",
" matching_attr_ids = SUGGESTIVE_attribute_ids.intersection(set(attr_ids))\n",
" if matching_attr_ids:\n",
" print(f\" Matched Attributes: {[attr_id_to_name.get(aid, f'id:{aid}') for aid in matching_attr_ids]}\")\n",
" except:\n",
" pass\n"
]
},
{
"cell_type": "code",
"execution_count": 61,
"id": "aaaf424a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"============================================================\n",
"UNIQUE IMAGE ANALYSIS:\n",
"============================================================\n",
"Total unique images in dataset: 45623\n",
"Unique images with SUGGESTIVE content: 5079\n",
"Percentage of unique images: 11.13%\n",
"\n",
"Average annotations per SUGGESTIVE image: 1.03\n",
"Max annotations for a single image: 4\n",
"Min annotations for a single image: 1\n",
"\n",
"============================================================\n",
"DISTRIBUTION OF SUGGESTIVE CATEGORIES IN FILTERED DATA:\n",
"============================================================\n",
"ClassId\n",
"10 1502\n",
"33 965\n",
"7 857\n",
"4 684\n",
"1 322\n",
"0 317\n",
"9 215\n",
"8 123\n",
"3 83\n",
"2 79\n",
"11 51\n",
"5 11\n",
"12 8\n",
"37 1\n",
"Name: count, dtype: int64\n",
"\n",
"Top SUGGESTIVE categories by count:\n",
" - dress (id: 10): 1502 annotations\n",
" - neckline (id: 33): 965 annotations\n",
" - shorts (id: 7): 857 annotations\n",
" - jacket (id: 4): 684 annotations\n",
" - top, t-shirt, sweatshirt (id: 1): 322 annotations\n",
" - shirt, blouse (id: 0): 317 annotations\n",
" - coat (id: 9): 215 annotations\n",
" - skirt (id: 8): 123 annotations\n",
" - cardigan (id: 3): 83 annotations\n",
" - sweater (id: 2): 79 annotations\n"
]
}
],
"source": [
"# Get unique image IDs (since same image can have multiple annotations)\n",
"unique_SUGGESTIVE_image_ids = SUGGESTIVE_fashion_df['ImageId'].unique()\n",
"unique_total_image_ids = fashion_df['ImageId'].unique()\n",
"\n",
"print(\"=\"*60)\n",
"print(\"UNIQUE IMAGE ANALYSIS:\")\n",
"print(\"=\"*60)\n",
"print(f\"Total unique images in dataset: {len(unique_total_image_ids)}\")\n",
"print(f\"Unique images with SUGGESTIVE content: {len(unique_SUGGESTIVE_image_ids)}\")\n",
"print(f\"Percentage of unique images: {len(unique_SUGGESTIVE_image_ids) / len(unique_total_image_ids) * 100:.2f}%\")\n",
"\n",
"# Count how many annotations per SUGGESTIVE image\n",
"annotations_per_image = SUGGESTIVE_fashion_df.groupby('ImageId').size().sort_values(ascending=False)\n",
"print(f\"\\nAverage annotations per SUGGESTIVE image: {annotations_per_image.mean():.2f}\")\n",
"print(f\"Max annotations for a single image: {annotations_per_image.max()}\")\n",
"print(f\"Min annotations for a single image: {annotations_per_image.min()}\")\n",
"\n",
"# Show distribution of SUGGESTIVE categories in the filtered data\n",
"print(\"\\n\" + \"=\"*60)\n",
"print(\"DISTRIBUTION OF SUGGESTIVE CATEGORIES IN FILTERED DATA:\")\n",
"print(\"=\"*60)\n",
"category_counts = SUGGESTIVE_fashion_df['ClassId'].value_counts()\n",
"print(category_counts)\n",
"\n",
"# Map category IDs to names for better readability\n",
"category_id_to_name = dict(zip(categories_df['id'], categories_df['name']))\n",
"print(\"\\nTop SUGGESTIVE categories by count:\")\n",
"for cat_id, count in category_counts.head(10).items():\n",
" cat_name = category_id_to_name.get(cat_id, f\"Unknown (id: {cat_id})\")\n",
" print(f\" - {cat_name} (id: {cat_id}): {count} annotations\")\n",
"\n",
"# Save the filtered DataFrame\n",
"# SUGGESTIVE_fashion_df.to_csv(DATA_PATH / \"SUGGESTIVE_train.csv\", index=False)\n",
"# pd.Series(unique_SUGGESTIVE_image_ids).to_csv(DATA_PATH / \"SUGGESTIVE_image_ids.csv\", index=False, header=['ImageId'])\n"
]
},
{
"cell_type": "code",
"execution_count": 62,
"id": "a4736cf0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"============================================================\n",
"CREATING NEW DATASET\n",
"============================================================\n",
"Total unique SUGGESTIVE image IDs: 5079\n",
"\n",
"Created folder: /Users/youniss/Documents/GitHub/haram-police/data/new_dataset\n",
"\n",
"Copying images from /Users/youniss/Documents/GitHub/haram-police/data/train and /Users/youniss/Documents/GitHub/haram-police/data/test...\n",
"\n",
"✓ Successfully copied: 5079 images\n",
"\n",
"✓ Saved DataFrame to: /Users/youniss/Documents/GitHub/haram-police/data/SUGGESTIVE_fashion.csv\n",
" Total rows: 5218\n",
"\n",
"============================================================\n",
"SUMMARY:\n",
"============================================================\n",
" - Images folder: /Users/youniss/Documents/GitHub/haram-police/data/new_dataset\n",
" - Images copied: 5079\n",
" - CSV file: /Users/youniss/Documents/GitHub/haram-police/data/SUGGESTIVE_fashion.csv\n",
" - CSV rows: 5218\n",
" - Unique images: 5079\n"
]
}
],
"source": [
"# Create new_dataset folder and copy all SUGGESTIVE images from train and test\n",
"import shutil\n",
"\n",
"# Get unique image IDs from SUGGESTIVE_fashion_df\n",
"unique_SUGGESTIVE_image_ids = set(SUGGESTIVE_fashion_df['ImageId'].unique())\n",
"\n",
"print(\"=\"*60)\n",
"print(\"CREATING NEW DATASET\")\n",
"print(\"=\"*60)\n",
"print(f\"Total unique SUGGESTIVE image IDs: {len(unique_SUGGESTIVE_image_ids)}\")\n",
"\n",
"# Create new_dataset folder\n",
"NEW_DATASET_PATH = DATA_PATH / \"new_dataset\"\n",
"NEW_DATASET_PATH.mkdir(exist_ok=True)\n",
"print(f\"\\nCreated folder: {NEW_DATASET_PATH}\")\n",
"\n",
"# Paths to source folders\n",
"TRAIN_IMAGE_PATH = DATA_PATH / \"train\"\n",
"TEST_IMAGE_PATH = DATA_PATH / \"test\"\n",
"\n",
"# Copy images from train and test folders\n",
"copied_count = 0\n",
"not_found_count = 0\n",
"not_found_ids = []\n",
"\n",
"print(f\"\\nCopying images from {TRAIN_IMAGE_PATH} and {TEST_IMAGE_PATH}...\")\n",
"\n",
"for image_id in unique_SUGGESTIVE_image_ids:\n",
" image_filename = f\"{image_id}.jpg\"\n",
" source_path = None\n",
" \n",
" # Try train folder first\n",
" train_path = TRAIN_IMAGE_PATH / image_filename\n",
" if train_path.exists():\n",
" source_path = train_path\n",
" else:\n",
" # Try test folder\n",
" test_path = TEST_IMAGE_PATH / image_filename\n",
" if test_path.exists():\n",
" source_path = test_path\n",
" \n",
" if source_path:\n",
" dest_path = NEW_DATASET_PATH / image_filename\n",
" shutil.copy2(source_path, dest_path)\n",
" copied_count += 1\n",
" else:\n",
" not_found_count += 1\n",
" not_found_ids.append(image_id)\n",
"\n",
"print(f\"\\n✓ Successfully copied: {copied_count} images\")\n",
"if not_found_count > 0:\n",
" print(f\"⚠ Not found: {not_found_count} images\")\n",
" print(f\" First 10 missing IDs: {not_found_ids[:10]}\")\n",
"\n",
"# Save the SUGGESTIVE_fashion_df to CSV\n",
"csv_path = DATA_PATH / \"SUGGESTIVE_fashion.csv\"\n",
"SUGGESTIVE_fashion_df.to_csv(csv_path, index=False)\n",
"print(f\"\\n✓ Saved DataFrame to: {csv_path}\")\n",
"print(f\" Total rows: {len(SUGGESTIVE_fashion_df)}\")\n",
"\n",
"print(\"\\n\" + \"=\"*60)\n",
"print(\"SUMMARY:\")\n",
"print(\"=\"*60)\n",
"print(f\" - Images folder: {NEW_DATASET_PATH}\")\n",
"print(f\" - Images copied: {copied_count}\")\n",
"print(f\" - CSV file: {csv_path}\")\n",
"print(f\" - CSV rows: {len(SUGGESTIVE_fashion_df)}\")\n",
"print(f\" - Unique images: {len(unique_SUGGESTIVE_image_ids)}\")\n"
]
},
{
"cell_type": "code",
"execution_count": 63,
"id": "a4bdc53c",
"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>ImageId</th>\n",
" <th>EncodedPixels</th>\n",
" <th>Height</th>\n",
" <th>Width</th>\n",
" <th>ClassId</th>\n",
" <th>AttributesIds</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>49</th>\n",
" <td>000b3a87508b0fa185fbd53ecbe2e4c6</td>\n",
" <td>457283 2 458562 6 459841 9 461120 13 462400 15...</td>\n",
" <td>1280</td>\n",
" <td>852</td>\n",
" <td>33</td>\n",
" <td>192</td>\n",
" </tr>\n",
" <tr>\n",
" <th>147</th>\n",
" <td>001a66b16b12f12dc45e2bba40e04683</td>\n",
" <td>64049 3 64548 10 65048 17 65548 23 65754 36 66...</td>\n",
" <td>500</td>\n",
" <td>375</td>\n",
" <td>10</td>\n",
" <td>106,115,127,142,149,229,295,316</td>\n",
" </tr>\n",
" <tr>\n",
" <th>180</th>\n",
" <td>00211c06b1fe730097dde122cd4d3f8c</td>\n",
" <td>296470 1 297469 3 298468 5 299467 8 300466 10 ...</td>\n",
" <td>1000</td>\n",
" <td>665</td>\n",
" <td>7</td>\n",
" <td>50,115,136,142,148,230,295,300,317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>304</th>\n",
" <td>003ae3da258f7ba7267af5f159dd3502</td>\n",
" <td>129565 3 130583 9 131602 14 132621 19 133641 2...</td>\n",
" <td>1024</td>\n",
" <td>683</td>\n",
" <td>10</td>\n",
" <td>106,127,141,150,295,316,317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>369</th>\n",
" <td>0048f6c47de85cc4dc263912bd0ff6f5</td>\n",
" <td>4777361 1 4781320 3 4785279 5 4789239 7 479319...</td>\n",
" <td>3960</td>\n",
" <td>2640</td>\n",
" <td>33</td>\n",
" <td>192</td>\n",
" </tr>\n",
" <tr>\n",
" <th>372</th>\n",
" <td>0048f6c47de85cc4dc263912bd0ff6f5</td>\n",
" <td>3982550 2 3986509 8 3990469 13 3994429 18 3998...</td>\n",
" <td>3960</td>\n",
" <td>2640</td>\n",
" <td>7</td>\n",
" <td>50,115,136,142,148,317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>445</th>\n",
" <td>005380bd939eb68085af3f804d387824</td>\n",
" <td>2317673 15 2320644 45 2323624 67 2326613 79 23...</td>\n",
" <td>3000</td>\n",
" <td>2001</td>\n",
" <td>10</td>\n",
" <td>106,114,127,142,150,229,295,311,317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>456</th>\n",
" <td>0054564ae183ad9a1b152eef0bc11e1d</td>\n",
" <td>195071 2 196093 5 197115 8 198134 13 199151 20...</td>\n",
" <td>1024</td>\n",
" <td>683</td>\n",
" <td>10</td>\n",
" <td>106,115,127,142,149,229,295,316,317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>465</th>\n",
" <td>0055347a114b215f8f469fec9e38c272</td>\n",
" <td>236337 20 237832 26 239327 33 240823 38 242320...</td>\n",
" <td>1500</td>\n",
" <td>1000</td>\n",
" <td>10</td>\n",
" <td>106,115,127,142,149,229,295,316,317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>526</th>\n",
" <td>005e9b75edcee7d655c390ea5416641d</td>\n",
" <td>480863 2 481943 3 483023 4 484102 6 485182 7 4...</td>\n",
" <td>1080</td>\n",
" <td>1080</td>\n",
" <td>33</td>\n",
" <td>192</td>\n",
" </tr>\n",
" <tr>\n",
" <th>593</th>\n",
" <td>006bb85ca0935680110f4ce67d88b4ee</td>\n",
" <td>2461619 6 2463717 17 2465814 24 2467912 23 247...</td>\n",
" <td>2096</td>\n",
" <td>3000</td>\n",
" <td>10</td>\n",
" <td>106,115,127,142,149,295,316,317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>802</th>\n",
" <td>009447b79fce7da1ee19a54401517cde</td>\n",
" <td>23802163 9 23807451 27 23812746 37 23818049 40...</td>\n",
" <td>5304</td>\n",
" <td>7952</td>\n",
" <td>7</td>\n",
" <td>50,115,136,142,148,230,295,298,317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>884</th>\n",
" <td>00af8f65bb93f4131499dc9807129a24</td>\n",
" <td>1313044 41 1315994 123 1318943 207 1321893 289...</td>\n",
" <td>3000</td>\n",
" <td>2000</td>\n",
" <td>4</td>\n",
" <td>17,115,135,145,148,225,281,311,317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1201</th>\n",
" <td>00f7d06a8db722b86961d911fb9f1d96</td>\n",
" <td>54821 5 55316 16 55811 27 56307 37 56802 48 57...</td>\n",
" <td>500</td>\n",
" <td>375</td>\n",
" <td>10</td>\n",
" <td>106,115,127,142,151,229,283,311</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1217</th>\n",
" <td>00f843a44365248e179ad2a489734913</td>\n",
" <td>1690956 5 1693572 11 1696188 15 1698804 18 170...</td>\n",
" <td>2617</td>\n",
" <td>1500</td>\n",
" <td>33</td>\n",
" <td>192</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1260</th>\n",
" <td>01098396b79639e29db8de146c2d0064</td>\n",
" <td>959078 8 962065 22 965051 38 968037 54 971024 ...</td>\n",
" <td>3000</td>\n",
" <td>2000</td>\n",
" <td>7</td>\n",
" <td>50,148,234,295,316,317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1274</th>\n",
" <td>010db49ecc226102e63815fcf5627319</td>\n",
" <td>1205717 31 1208132 69 1210571 82 1213011 94 12...</td>\n",
" <td>2448</td>\n",
" <td>2448</td>\n",
" <td>10</td>\n",
" <td>112,115,119,145,148,229,295,306,323,325</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1311</th>\n",
" <td>0116a12304c7f94686978f86100076f3</td>\n",
" <td>32646 31 33110 78 33587 109 34065 136 34542 15...</td>\n",
" <td>492</td>\n",
" <td>354</td>\n",
" <td>10</td>\n",
" <td>106,115,127,142,150,229,295,316,317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1356</th>\n",
" <td>011afec5e443599a79261ece1a662043</td>\n",
" <td>629287 14 631022 16 632757 18 634492 21 636227...</td>\n",
" <td>1737</td>\n",
" <td>1157</td>\n",
" <td>4</td>\n",
" <td>17,148,225,281,311,317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1371</th>\n",
" <td>011c59f7c25d18027f4f9b2b1cffd44a</td>\n",
" <td>168345 3 169142 7 169938 12 170735 17 171531 2...</td>\n",
" <td>800</td>\n",
" <td>800</td>\n",
" <td>10</td>\n",
" <td>101,115,129,145,148,289,301,317</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" ImageId \\\n",
"49 000b3a87508b0fa185fbd53ecbe2e4c6 \n",
"147 001a66b16b12f12dc45e2bba40e04683 \n",
"180 00211c06b1fe730097dde122cd4d3f8c \n",
"304 003ae3da258f7ba7267af5f159dd3502 \n",
"369 0048f6c47de85cc4dc263912bd0ff6f5 \n",
"372 0048f6c47de85cc4dc263912bd0ff6f5 \n",
"445 005380bd939eb68085af3f804d387824 \n",
"456 0054564ae183ad9a1b152eef0bc11e1d \n",
"465 0055347a114b215f8f469fec9e38c272 \n",
"526 005e9b75edcee7d655c390ea5416641d \n",
"593 006bb85ca0935680110f4ce67d88b4ee \n",
"802 009447b79fce7da1ee19a54401517cde \n",
"884 00af8f65bb93f4131499dc9807129a24 \n",
"1201 00f7d06a8db722b86961d911fb9f1d96 \n",
"1217 00f843a44365248e179ad2a489734913 \n",
"1260 01098396b79639e29db8de146c2d0064 \n",
"1274 010db49ecc226102e63815fcf5627319 \n",
"1311 0116a12304c7f94686978f86100076f3 \n",
"1356 011afec5e443599a79261ece1a662043 \n",
"1371 011c59f7c25d18027f4f9b2b1cffd44a \n",
"\n",
" EncodedPixels Height Width \\\n",
"49 457283 2 458562 6 459841 9 461120 13 462400 15... 1280 852 \n",
"147 64049 3 64548 10 65048 17 65548 23 65754 36 66... 500 375 \n",
"180 296470 1 297469 3 298468 5 299467 8 300466 10 ... 1000 665 \n",
"304 129565 3 130583 9 131602 14 132621 19 133641 2... 1024 683 \n",
"369 4777361 1 4781320 3 4785279 5 4789239 7 479319... 3960 2640 \n",
"372 3982550 2 3986509 8 3990469 13 3994429 18 3998... 3960 2640 \n",
"445 2317673 15 2320644 45 2323624 67 2326613 79 23... 3000 2001 \n",
"456 195071 2 196093 5 197115 8 198134 13 199151 20... 1024 683 \n",
"465 236337 20 237832 26 239327 33 240823 38 242320... 1500 1000 \n",
"526 480863 2 481943 3 483023 4 484102 6 485182 7 4... 1080 1080 \n",
"593 2461619 6 2463717 17 2465814 24 2467912 23 247... 2096 3000 \n",
"802 23802163 9 23807451 27 23812746 37 23818049 40... 5304 7952 \n",
"884 1313044 41 1315994 123 1318943 207 1321893 289... 3000 2000 \n",
"1201 54821 5 55316 16 55811 27 56307 37 56802 48 57... 500 375 \n",
"1217 1690956 5 1693572 11 1696188 15 1698804 18 170... 2617 1500 \n",
"1260 959078 8 962065 22 965051 38 968037 54 971024 ... 3000 2000 \n",
"1274 1205717 31 1208132 69 1210571 82 1213011 94 12... 2448 2448 \n",
"1311 32646 31 33110 78 33587 109 34065 136 34542 15... 492 354 \n",
"1356 629287 14 631022 16 632757 18 634492 21 636227... 1737 1157 \n",
"1371 168345 3 169142 7 169938 12 170735 17 171531 2... 800 800 \n",
"\n",
" ClassId AttributesIds \n",
"49 33 192 \n",
"147 10 106,115,127,142,149,229,295,316 \n",
"180 7 50,115,136,142,148,230,295,300,317 \n",
"304 10 106,127,141,150,295,316,317 \n",
"369 33 192 \n",
"372 7 50,115,136,142,148,317 \n",
"445 10 106,114,127,142,150,229,295,311,317 \n",
"456 10 106,115,127,142,149,229,295,316,317 \n",
"465 10 106,115,127,142,149,229,295,316,317 \n",
"526 33 192 \n",
"593 10 106,115,127,142,149,295,316,317 \n",
"802 7 50,115,136,142,148,230,295,298,317 \n",
"884 4 17,115,135,145,148,225,281,311,317 \n",
"1201 10 106,115,127,142,151,229,283,311 \n",
"1217 33 192 \n",
"1260 7 50,148,234,295,316,317 \n",
"1274 10 112,115,119,145,148,229,295,306,323,325 \n",
"1311 10 106,115,127,142,150,229,295,316,317 \n",
"1356 4 17,148,225,281,311,317 \n",
"1371 10 101,115,129,145,148,289,301,317 "
]
},
"execution_count": 63,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"SUGGESTIVE_fashion_df.head(20)"
]
},
{
"cell_type": "code",
"execution_count": 64,
"id": "a9e2133d",
"metadata": {},
"outputs": [],
"source": [
"# Show the \"EncodedPixels\" feature of the first SUGGESTIVE_fashion_df \n",
"from PIL import Image\n",
"\n",
"# Get the first image ID from the SUGGESTIVE_fashion_df\n",
"first_image_id = SUGGESTIVE_fashion_df.iloc[0]['ImageId']\n",
"\n",
"# Load the image\n",
"image = Image.open((DATA_PATH / \"train\" / f\"{first_image_id}.jpg\"))\n",
"image.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2d6351ab",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.5"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|