File size: 29,321 Bytes
3752cdf |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import os\n",
"from sklearn.model_selection import train_test_split"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"file2obj = pd.read_csv(\"../data/processed/OM_file_to_obj.csv\")\n",
"obj2info = pd.read_csv(\"../data/processed/OM_obj_to_info.csv\")\n",
"\n",
"\n",
"# Could eventually do something with these columns, but need cleaning first\n",
"obj2info.drop(\n",
" columns=[\"number_of_parts\", \"production.date.start\", \"production.date.end\", \"obj_num_old\"],\n",
" inplace=True,\n",
")\n",
"\n",
"file2obj[\"image\"] = file2obj.apply(lambda x: os.path.join(x[\"root\"], x[\"file\"]), axis=1)\n",
"# file2obj.rename(columns={\"obj_num\": \"label\"}, inplace=True)\n",
"\n",
"join_df = file2obj[[\"obj_num\", \"file\", \"image\", \"root\"]].merge(\n",
" obj2info, left_on=\"obj_num\", right_on=\"obj_num\", how=\"left\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 data/raw/images/fulling_mill/1985\n",
"1 data/raw/images/fulling_mill/1985\n",
"2 data/raw/images/fulling_mill/1985\n",
"3 data/raw/images/fulling_mill/1985\n",
"4 data/raw/images/fulling_mill/1985\n",
" ... \n",
"37300 data/raw/images/egyptian/2014\n",
"37301 data/raw/images/egyptian/2014\n",
"37302 data/raw/images/egyptian/2014\n",
"37303 data/raw/images/egyptian/1963\n",
"37304 data/raw/images/egyptian/1963\n",
"Name: root, Length: 37305, dtype: object"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"file2obj[\"root\"]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"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>obj_num</th>\n",
" <th>description</th>\n",
" <th>object_name</th>\n",
" <th>other_name</th>\n",
" <th>material</th>\n",
" <th>production.period</th>\n",
" <th>production.place</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>eg3</td>\n",
" <td>squat shouldered jar, no rim</td>\n",
" <td>bowls</td>\n",
" <td>bowl</td>\n",
" <td>limestone</td>\n",
" <td>1st Dynasty</td>\n",
" <td>Egypt</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>eg64</td>\n",
" <td>axe-head</td>\n",
" <td>axes: woodworking tools</td>\n",
" <td>axe-head</td>\n",
" <td>granite</td>\n",
" <td>NaN</td>\n",
" <td>Egypt</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>eg71</td>\n",
" <td>the working end of a fish tail knife with pres...</td>\n",
" <td>knives</td>\n",
" <td>knife</td>\n",
" <td>Flint/Chert</td>\n",
" <td>Naqada II</td>\n",
" <td>Egypt</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>eg75</td>\n",
" <td>seated figure of priest holding unrolled papyr...</td>\n",
" <td>Human Figurine</td>\n",
" <td>imhotep figurine</td>\n",
" <td>bronze</td>\n",
" <td>Late Period</td>\n",
" <td>Egypt</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>durom.1971.78</td>\n",
" <td>seated woman, inset eyes (lost), headdress had...</td>\n",
" <td>Human Figurine</td>\n",
" <td>Hathor figurine</td>\n",
" <td>bronze</td>\n",
" <td>Late Period</td>\n",
" <td>Egypt</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12349</th>\n",
" <td>durma.2020.3.2562</td>\n",
" <td>A silver Roman coin which is a part of the Pie...</td>\n",
" <td>coins</td>\n",
" <td>NaN</td>\n",
" <td>metal</td>\n",
" <td>Roman</td>\n",
" <td>Rome</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12350</th>\n",
" <td>durma.2020.3.2060</td>\n",
" <td>A silver Roman coin which is a part of the Pie...</td>\n",
" <td>coins</td>\n",
" <td>NaN</td>\n",
" <td>metal</td>\n",
" <td>Roman</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12351</th>\n",
" <td>durma.2020.3.1446</td>\n",
" <td>A silver Roman coin which is a part of the Pie...</td>\n",
" <td>coins</td>\n",
" <td>NaN</td>\n",
" <td>metal</td>\n",
" <td>Roman</td>\n",
" <td>Rome</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12352</th>\n",
" <td>durma.2020.3.2042</td>\n",
" <td>A silver Roman coin which is a part of the Pie...</td>\n",
" <td>coins</td>\n",
" <td>NaN</td>\n",
" <td>metal</td>\n",
" <td>Roman</td>\n",
" <td>Rome</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12353</th>\n",
" <td>durma.2020.3.2072</td>\n",
" <td>A silver Roman coin which is a part of the Pie...</td>\n",
" <td>coins</td>\n",
" <td>NaN</td>\n",
" <td>metal</td>\n",
" <td>Roman</td>\n",
" <td>Rome</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>11673 rows Γ 7 columns</p>\n",
"</div>"
],
"text/plain": [
" obj_num description \\\n",
"0 eg3 squat shouldered jar, no rim \n",
"1 eg64 axe-head \n",
"2 eg71 the working end of a fish tail knife with pres... \n",
"3 eg75 seated figure of priest holding unrolled papyr... \n",
"4 durom.1971.78 seated woman, inset eyes (lost), headdress had... \n",
"... ... ... \n",
"12349 durma.2020.3.2562 A silver Roman coin which is a part of the Pie... \n",
"12350 durma.2020.3.2060 A silver Roman coin which is a part of the Pie... \n",
"12351 durma.2020.3.1446 A silver Roman coin which is a part of the Pie... \n",
"12352 durma.2020.3.2042 A silver Roman coin which is a part of the Pie... \n",
"12353 durma.2020.3.2072 A silver Roman coin which is a part of the Pie... \n",
"\n",
" object_name other_name material \\\n",
"0 bowls bowl limestone \n",
"1 axes: woodworking tools axe-head granite \n",
"2 knives knife Flint/Chert \n",
"3 Human Figurine imhotep figurine bronze \n",
"4 Human Figurine Hathor figurine bronze \n",
"... ... ... ... \n",
"12349 coins NaN metal \n",
"12350 coins NaN metal \n",
"12351 coins NaN metal \n",
"12352 coins NaN metal \n",
"12353 coins NaN metal \n",
"\n",
" production.period production.place \n",
"0 1st Dynasty Egypt \n",
"1 NaN Egypt \n",
"2 Naqada II Egypt \n",
"3 Late Period Egypt \n",
"4 Late Period Egypt \n",
"... ... ... \n",
"12349 Roman Rome \n",
"12350 Roman NaN \n",
"12351 Roman Rome \n",
"12352 Roman Rome \n",
"12353 Roman Rome \n",
"\n",
"[11673 rows x 7 columns]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"obj2info.dropna(subset=[\"material\", \"description\"], inplace=False)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"label_col = \"material\"\n",
"\n",
"o2i_lim = obj2info.dropna(subset=[label_col, \"description\"], inplace=False)\n",
"\n",
"num_counts = o2i_lim[label_col].value_counts()\n",
"for lower_lim in [3]:\n",
" o2i_lim = o2i_lim[o2i_lim[label_col].isin(num_counts[num_counts > lower_lim].index)]\n",
"train, val_test = train_test_split(\n",
" o2i_lim, stratify=o2i_lim[label_col], test_size=0.4, random_state=42\n",
")\n",
"val, test = train_test_split(\n",
" val_test, stratify=val_test[label_col], test_size=0.8, random_state=42\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"from datasets import Dataset, DatasetDict"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"ds = Dataset.from_pandas(join_df).to_pandas()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"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>obj_num</th>\n",
" <th>file</th>\n",
" <th>image</th>\n",
" <th>root</th>\n",
" <th>description</th>\n",
" <th>object_name</th>\n",
" <th>other_name</th>\n",
" <th>material</th>\n",
" <th>production.period</th>\n",
" <th>production.place</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>durma.1985.15.68</td>\n",
" <td>1985.15.68.jpg</td>\n",
" <td>data/raw/images/fulling_mill/1985/1985.15.68.jpg</td>\n",
" <td>data/raw/images/fulling_mill/1985</td>\n",
" <td>2 fragments of a bowl with open fret work at t...</td>\n",
" <td>None</td>\n",
" <td>Rim Sherds</td>\n",
" <td>pottery</td>\n",
" <td>Post-Medieval</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>durma.1985.52.37</td>\n",
" <td>1985.52.37.ff2.jpg</td>\n",
" <td>data/raw/images/fulling_mill/1985/1985.52.37.f...</td>\n",
" <td>data/raw/images/fulling_mill/1985</td>\n",
" <td>Reconstructed small vessel (many pieces with s...</td>\n",
" <td>pottery</td>\n",
" <td>Pottery</td>\n",
" <td>pottery</td>\n",
" <td>Roman</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>durma.1985.81.4496</td>\n",
" <td>1985.81.4496 d2.jpg</td>\n",
" <td>data/raw/images/fulling_mill/1985/1985.81.4496...</td>\n",
" <td>data/raw/images/fulling_mill/1985</td>\n",
" <td>Fragment of a Samian beaker. Panell decoration...</td>\n",
" <td>vessels</td>\n",
" <td>pottery</td>\n",
" <td>pottery</td>\n",
" <td>Roman</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>durma.1985.9.1</td>\n",
" <td>1985.9.1.1-d4.jpg</td>\n",
" <td>data/raw/images/fulling_mill/1985/1985.9.1.1-d...</td>\n",
" <td>data/raw/images/fulling_mill/1985</td>\n",
" <td>2 Fragmentary Saxon Cinerary Urns + 1 relative...</td>\n",
" <td>None</td>\n",
" <td>Cinerary Urns</td>\n",
" <td>pottery</td>\n",
" <td>Saxon</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>durma.1985.52.37</td>\n",
" <td>1985.52.37.sf2.jpg</td>\n",
" <td>data/raw/images/fulling_mill/1985/1985.52.37.s...</td>\n",
" <td>data/raw/images/fulling_mill/1985</td>\n",
" <td>Reconstructed small vessel (many pieces with s...</td>\n",
" <td>pottery</td>\n",
" <td>Pottery</td>\n",
" <td>pottery</td>\n",
" <td>Roman</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37300</th>\n",
" <td>durom.2014.1.2</td>\n",
" <td>2014.1.2 bb.jpg</td>\n",
" <td>data/raw/images/egyptian/2014/2014.1.2 bb.jpg</td>\n",
" <td>data/raw/images/egyptian/2014</td>\n",
" <td>One of a collection of 162 flint tools. Brown,...</td>\n",
" <td>blades</td>\n",
" <td>None</td>\n",
" <td>Flint/Chert</td>\n",
" <td>Neolithic Period</td>\n",
" <td>Egypt</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37301</th>\n",
" <td>durom.2014.1.71</td>\n",
" <td>2014.1.71 ll.jpg</td>\n",
" <td>data/raw/images/egyptian/2014/2014.1.71 ll.jpg</td>\n",
" <td>data/raw/images/egyptian/2014</td>\n",
" <td>One of a collection of 162 flint tools. Large,...</td>\n",
" <td>axes: woodworking tools</td>\n",
" <td>None</td>\n",
" <td>Flint/Chert</td>\n",
" <td>Neolithic Period</td>\n",
" <td>Egypt</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37302</th>\n",
" <td>durom.2014.1.2</td>\n",
" <td>2014.1.2 rr.jpg</td>\n",
" <td>data/raw/images/egyptian/2014/2014.1.2 rr.jpg</td>\n",
" <td>data/raw/images/egyptian/2014</td>\n",
" <td>One of a collection of 162 flint tools. Brown,...</td>\n",
" <td>blades</td>\n",
" <td>None</td>\n",
" <td>Flint/Chert</td>\n",
" <td>Neolithic Period</td>\n",
" <td>Egypt</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37303</th>\n",
" <td>durom.1963.4</td>\n",
" <td>1963.4.jpg</td>\n",
" <td>data/raw/images/egyptian/1963/1963.4.jpg</td>\n",
" <td>data/raw/images/egyptian/1963</td>\n",
" <td>The woman is dressed in Qing dynasty style and...</td>\n",
" <td>figures</td>\n",
" <td>ηιζ―ε©΄ε</td>\n",
" <td>ivory</td>\n",
" <td>late Qing dynasty</td>\n",
" <td>China</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37304</th>\n",
" <td>durom.1963.4</td>\n",
" <td>1963.4.2.jpg</td>\n",
" <td>data/raw/images/egyptian/1963/1963.4.2.jpg</td>\n",
" <td>data/raw/images/egyptian/1963</td>\n",
" <td>The woman is dressed in Qing dynasty style and...</td>\n",
" <td>figures</td>\n",
" <td>ηιζ―ε©΄ε</td>\n",
" <td>ivory</td>\n",
" <td>late Qing dynasty</td>\n",
" <td>China</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>37305 rows Γ 10 columns</p>\n",
"</div>"
],
"text/plain": [
" obj_num file \\\n",
"0 durma.1985.15.68 1985.15.68.jpg \n",
"1 durma.1985.52.37 1985.52.37.ff2.jpg \n",
"2 durma.1985.81.4496 1985.81.4496 d2.jpg \n",
"3 durma.1985.9.1 1985.9.1.1-d4.jpg \n",
"4 durma.1985.52.37 1985.52.37.sf2.jpg \n",
"... ... ... \n",
"37300 durom.2014.1.2 2014.1.2 bb.jpg \n",
"37301 durom.2014.1.71 2014.1.71 ll.jpg \n",
"37302 durom.2014.1.2 2014.1.2 rr.jpg \n",
"37303 durom.1963.4 1963.4.jpg \n",
"37304 durom.1963.4 1963.4.2.jpg \n",
"\n",
" image \\\n",
"0 data/raw/images/fulling_mill/1985/1985.15.68.jpg \n",
"1 data/raw/images/fulling_mill/1985/1985.52.37.f... \n",
"2 data/raw/images/fulling_mill/1985/1985.81.4496... \n",
"3 data/raw/images/fulling_mill/1985/1985.9.1.1-d... \n",
"4 data/raw/images/fulling_mill/1985/1985.52.37.s... \n",
"... ... \n",
"37300 data/raw/images/egyptian/2014/2014.1.2 bb.jpg \n",
"37301 data/raw/images/egyptian/2014/2014.1.71 ll.jpg \n",
"37302 data/raw/images/egyptian/2014/2014.1.2 rr.jpg \n",
"37303 data/raw/images/egyptian/1963/1963.4.jpg \n",
"37304 data/raw/images/egyptian/1963/1963.4.2.jpg \n",
"\n",
" root \\\n",
"0 data/raw/images/fulling_mill/1985 \n",
"1 data/raw/images/fulling_mill/1985 \n",
"2 data/raw/images/fulling_mill/1985 \n",
"3 data/raw/images/fulling_mill/1985 \n",
"4 data/raw/images/fulling_mill/1985 \n",
"... ... \n",
"37300 data/raw/images/egyptian/2014 \n",
"37301 data/raw/images/egyptian/2014 \n",
"37302 data/raw/images/egyptian/2014 \n",
"37303 data/raw/images/egyptian/1963 \n",
"37304 data/raw/images/egyptian/1963 \n",
"\n",
" description \\\n",
"0 2 fragments of a bowl with open fret work at t... \n",
"1 Reconstructed small vessel (many pieces with s... \n",
"2 Fragment of a Samian beaker. Panell decoration... \n",
"3 2 Fragmentary Saxon Cinerary Urns + 1 relative... \n",
"4 Reconstructed small vessel (many pieces with s... \n",
"... ... \n",
"37300 One of a collection of 162 flint tools. Brown,... \n",
"37301 One of a collection of 162 flint tools. Large,... \n",
"37302 One of a collection of 162 flint tools. Brown,... \n",
"37303 The woman is dressed in Qing dynasty style and... \n",
"37304 The woman is dressed in Qing dynasty style and... \n",
"\n",
" object_name other_name material production.period \\\n",
"0 None Rim Sherds pottery Post-Medieval \n",
"1 pottery Pottery pottery Roman \n",
"2 vessels pottery pottery Roman \n",
"3 None Cinerary Urns pottery Saxon \n",
"4 pottery Pottery pottery Roman \n",
"... ... ... ... ... \n",
"37300 blades None Flint/Chert Neolithic Period \n",
"37301 axes: woodworking tools None Flint/Chert Neolithic Period \n",
"37302 blades None Flint/Chert Neolithic Period \n",
"37303 figures ηιζ―ε©΄ε ivory late Qing dynasty \n",
"37304 figures ηιζ―ε©΄ε ivory late Qing dynasty \n",
"\n",
" production.place \n",
"0 None \n",
"1 None \n",
"2 None \n",
"3 None \n",
"4 None \n",
"... ... \n",
"37300 Egypt \n",
"37301 Egypt \n",
"37302 Egypt \n",
"37303 China \n",
"37304 China \n",
"\n",
"[37305 rows x 10 columns]"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ds"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(6819, 7) (2370, 7) (2370, 7) (11559, 7)\n",
"(19246, 10) (6743, 10) (7078, 10) (37305, 10)\n"
]
}
],
"source": [
"index_col = \"obj_num\"\n",
"text_col = \"obj_num\"\n",
"label_col = \"material\"\n",
"lower_lim = 3\n",
"problem_type = \"image\"\n",
"\n",
"\n",
"o2i_lim = (\n",
" ds.drop_duplicates(subset=[index_col, label_col], inplace=False)\n",
" .dropna(subset=[text_col, label_col], inplace=False)\n",
" .drop(columns=[\"root\", \"file\", \"image\"], inplace=False)\n",
")\n",
"\n",
"\n",
"num_counts = o2i_lim[label_col].value_counts()\n",
"o2i_lim = o2i_lim[o2i_lim[label_col].isin(num_counts[num_counts > lower_lim].index)]\n",
"\n",
"train, val_test = train_test_split(\n",
" o2i_lim, stratify=o2i_lim[label_col], test_size=0.41, random_state=42\n",
")\n",
"val, test = train_test_split(\n",
" val_test, stratify=val_test[label_col], test_size=0.5, random_state=42\n",
")\n",
"print(train.shape, val.shape, test.shape, o2i_lim.shape)\n",
"\n",
"if problem_type == \"image\":\n",
" train = train.merge(\n",
" ds[[\"obj_num\", \"root\", \"file\", \"image\"]], left_on=\"obj_num\", right_on=\"obj_num\", how=\"left\"\n",
" )\n",
" val = val.merge(\n",
" ds[[\"obj_num\", \"root\", \"file\", \"image\"]], left_on=\"obj_num\", right_on=\"obj_num\", how=\"left\"\n",
" )\n",
" test = test.merge(\n",
" ds[[\"obj_num\", \"root\", \"file\", \"image\"]], left_on=\"obj_num\", right_on=\"obj_num\", how=\"left\"\n",
" )\n",
" print(train.shape, val.shape, test.shape, ds.shape)\n",
"\n",
"# ds_dict = DatasetDict({\"train\": Dataset.from_pandas(train), \"val\": Dataset.from_pandas(val), \"test\": Dataset.from_pandas(test)})\n",
"# ds_dict\n",
"\n",
"# if problem_type == \"image\":\n",
"\n",
"# o2i_lim_ds = o2i_lim_ds.train_test_split(test_size=0.3, stratify_by_column=label_col, seed=42)\n",
"# o2i_lim_ds_valtest = o2i_lim_ds[\"test\"].train_test_split(test_size=0.5, stratify_by_column=label_col, seed=42)\n",
"# o2i_lim_ds = DatasetDict({\"train\": o2i_lim_ds[\"train\"], \"val\": o2i_lim_ds_valtest[\"train\"], \"test\": o2i_lim_ds_valtest[\"test\"]})\n",
"\n",
"# if problem_type == \"image\":\n",
"# file2obj = ds[[\"obj_num\", \"file\", \"image\", \"root\"]].drop_duplicates(subset=[\"obj_num\"], inplace=False)\n",
"# train = o2i_lim_ds[\"train\"].merge(file2obj, left_on=\"obj_num\", right_on=\"obj_num\", how=\"left\")\n",
"# val = o2i_lim_ds[\"val\"].merge(file2obj, left_on=\"obj_num\", right_on=\"obj_num\", how=\"left\")\n",
"# test = o2i_lim_ds[\"test\"].merge(file2obj, left_on=\"obj_num\", right_on=\"obj_num\", how=\"left\")\n",
"# o2i_lim_ds = DatasetDict({\"train\": train, \"val\": val, \"test\": test})\n",
"# o2i_lim_ds"
]
},
{
"cell_type": "code",
"execution_count": null,
"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>obj_num</th>\n",
" <th>description</th>\n",
" <th>object_name</th>\n",
" <th>other_name</th>\n",
" <th>material</th>\n",
" <th>production.period</th>\n",
" <th>production.place</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"Empty DataFrame\n",
"Columns: [obj_num, description, object_name, other_name, material, production.period, production.place]\n",
"Index: []"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"o2i_lim"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"cols_to_drop = [\"col1\", \"col2\", \"col3\"]\n",
"ds = ds.drop(cols_to_drop, axis=1, errors=\"ignore\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ds_lim = ds_all.dropna(subset=[\"image\", args.label_col], inplace=False)\n",
"if \"3D\" in args.dataset:\n",
" ds_lim = ds_all[ds_all[\"original\"]]\n",
"\n",
"num_counts = ds_lim[args.label_col].value_counts()\n",
"ds_lim = ds_lim[ds_lim[args.label_col].isin(num_counts[num_counts > args.lower_lim].index)]\n",
"\n",
"train, val_test = train_test_split(\n",
" ds_lim,\n",
" stratify=ds_lim[args.label_col],\n",
" test_size=2 * args.testset_size,\n",
" random_state=42,\n",
")\n",
"val, test = train_test_split(\n",
" val_test, stratify=val_test[args.label_col], test_size=0.5, random_state=42\n",
")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "ArtifactClassification",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|