File size: 43,018 Bytes
4f85116 | 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 | {
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Phase 4 — Variant Assignment / Variant Modeling\n",
"## Compliments Reference DB Pipeline\n",
"\n",
"**Version:** 1.0.0\n",
"**Date:** 2026-07-30\n",
"\n",
"**Input:** Phase 3 outputs + Phase 2 output\n",
"\n",
"**This phase does:**\n",
"1. Transforms Phase 3 product groups into structured variant models\n",
"2. Assigns deterministic variant_ids to products within each group\n",
"3. Creates variant tables and mappings\n",
"4. Validates variant consistency rules\n",
"\n",
"**CRITICAL:** This phase does NOT use nutrition data.\n",
"**CRITICAL:** This phase does NOT use any external taxonomy.\n",
"**CRITICAL:** This phase is 100% deterministic (no LLM)."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-30T17:47:27.262371Z",
"iopub.status.busy": "2026-07-30T17:47:27.261832Z",
"iopub.status.idle": "2026-07-30T17:47:28.134559Z",
"shell.execute_reply": "2026-07-30T17:47:28.132783Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Python: 3.13.7 (main, Mar 3 2026, 12:19:54) [GCC 15.2.0]\n",
"pandas: 3.0.5\n",
"numpy: 2.5.1\n",
"Timestamp: 2026-07-30T17:47:28.129557+00:00\n"
]
}
],
"source": [
"import json, hashlib, uuid, sys\n",
"from datetime import datetime, timezone\n",
"from pathlib import Path\n",
"\n",
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"print(f\"Python: {sys.version}\")\n",
"print(f\"pandas: {pd.__version__}\")\n",
"print(f\"numpy: {np.__version__}\")\n",
"print(f\"Timestamp: {datetime.now(timezone.utc).isoformat()}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Variant Definition\n",
"\n",
"A **variant** is a purchasable representation of the same reference product\n",
"that differs in attributes such as:\n",
"\n",
"- **Size**: 500 g, 1 kg, 2 kg\n",
"- **Package quantity**: 1 × 500 g, 2 × 500 g\n",
"- **Pack configuration**: single, multipack, case\n",
"\n",
"Variants within the same group share the same identity attributes:\n",
"- is_organic, is_gluten_free, is_naturally_simple, etc.\n",
"- product_line\n",
"- flavour\n",
"- formulation\n",
"- fat_level\n",
"\n",
"Variants differ only in size/package attributes."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Load Phase 3 Outputs"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-30T17:47:28.285611Z",
"iopub.status.busy": "2026-07-30T17:47:28.284392Z",
"iopub.status.idle": "2026-07-30T17:47:28.445823Z",
"shell.execute_reply": "2026-07-30T17:47:28.441829Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Phase 3 mapping: 4440 rows, 14 columns\n",
"Columns: ['upc', 'external_id', 'group_id', 'group_name', 'core_title', 'original_title', 'brand', 'size', 'identity_hash', 'product_domain', 'taxonomy', 'product_line', 'source', 'source_url']\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>upc</th>\n",
" <th>external_id</th>\n",
" <th>group_id</th>\n",
" <th>group_name</th>\n",
" <th>core_title</th>\n",
" <th>original_title</th>\n",
" <th>brand</th>\n",
" <th>size</th>\n",
" <th>identity_hash</th>\n",
" <th>product_domain</th>\n",
" <th>taxonomy</th>\n",
" <th>product_line</th>\n",
" <th>source</th>\n",
" <th>source_url</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.574252e+10</td>\n",
" <td>297608EA</td>\n",
" <td>27b951a3-bef1-5ed4-80b7-7ef5cdca910a</td>\n",
" <td>Cold And Sinus Plus</td>\n",
" <td>Cold And Sinus Plus</td>\n",
" <td>Compliments Cold And Sinus Plus 20 Count</td>\n",
" <td>Compliments</td>\n",
" <td>20 per pack</td>\n",
" <td>0|0|0|0|0|0|0|0|0|fat_none|regular|Core|lime|</td>\n",
" <td>unknown</td>\n",
" <td>GENERAL_GROCERY</td>\n",
" <td>Core</td>\n",
" <td>voila</td>\n",
" <td>https://voila.ca/products/compliments-cold-and...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5.574234e+10</td>\n",
" <td>464324EA</td>\n",
" <td>e608ba58-8f93-59f1-9446-edb91aef79bd</td>\n",
" <td>Twister T2 Light Bulbs 23W Soft White</td>\n",
" <td>Twister T2 Light Bulbs 23W Soft White</td>\n",
" <td>Compliments Twister T2 Light Bulbs 23W Soft Wh...</td>\n",
" <td>Compliments</td>\n",
" <td>2 per pack</td>\n",
" <td>0|0|0|0|0|0|0|0|0|fat_none|reduced_fat|Core|lime|</td>\n",
" <td>unknown</td>\n",
" <td>GENERAL_GROCERY</td>\n",
" <td>Core</td>\n",
" <td>voila</td>\n",
" <td>https://voila.ca/products/compliments-twister-...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>9.900026e+11</td>\n",
" <td>144288CS</td>\n",
" <td>336c79d8-796d-5682-8195-793883dd97ef</td>\n",
" <td>Zero Calorie Soft Drink</td>\n",
" <td>Zero Calorie Soft Drink</td>\n",
" <td>Compliments Zero Calorie Soft Drink 12 x 355ml</td>\n",
" <td>Compliments</td>\n",
" <td>12 x 29.583ml</td>\n",
" <td>0|0|0|0|0|0|0|0|0|fat_none|regular|Core|lime|</td>\n",
" <td>food</td>\n",
" <td>BEVERAGES</td>\n",
" <td>Core</td>\n",
" <td>voila</td>\n",
" <td>https://voila.ca/products/compliments-zero-cal...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5.574257e+10</td>\n",
" <td>312204EA</td>\n",
" <td>fd1acb22-4231-5b7b-bde4-8709b31cf04c</td>\n",
" <td>Kalamata Whole Olives</td>\n",
" <td>Kalamata Whole Olives</td>\n",
" <td>Compliments Kalamata Whole Olives 375 ml</td>\n",
" <td>Compliments</td>\n",
" <td>375ml</td>\n",
" <td>0|0|0|0|0|0|0|0|0|fat_none|regular|Core|lime|w...</td>\n",
" <td>unknown</td>\n",
" <td>GENERAL_GROCERY</td>\n",
" <td>Core</td>\n",
" <td>voila</td>\n",
" <td>https://voila.ca/products/compliments-kalamata...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5.574256e+10</td>\n",
" <td>259928EA</td>\n",
" <td>4ff536c8-c957-5fe8-8faa-3f539d6048ef</td>\n",
" <td>Sliced Almonds</td>\n",
" <td>Sliced Almonds</td>\n",
" <td>Compliments Sliced Almonds 250 g</td>\n",
" <td>Compliments</td>\n",
" <td>250g</td>\n",
" <td>0|0|0|0|0|0|0|0|0|fat_none|regular|Core|almond...</td>\n",
" <td>unknown</td>\n",
" <td>GENERAL_GROCERY</td>\n",
" <td>Core</td>\n",
" <td>voila</td>\n",
" <td>https://voila.ca/products/compliments-sliced-a...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" upc external_id group_id \\\n",
"0 5.574252e+10 297608EA 27b951a3-bef1-5ed4-80b7-7ef5cdca910a \n",
"1 5.574234e+10 464324EA e608ba58-8f93-59f1-9446-edb91aef79bd \n",
"2 9.900026e+11 144288CS 336c79d8-796d-5682-8195-793883dd97ef \n",
"3 5.574257e+10 312204EA fd1acb22-4231-5b7b-bde4-8709b31cf04c \n",
"4 5.574256e+10 259928EA 4ff536c8-c957-5fe8-8faa-3f539d6048ef \n",
"\n",
" group_name \\\n",
"0 Cold And Sinus Plus \n",
"1 Twister T2 Light Bulbs 23W Soft White \n",
"2 Zero Calorie Soft Drink \n",
"3 Kalamata Whole Olives \n",
"4 Sliced Almonds \n",
"\n",
" core_title \\\n",
"0 Cold And Sinus Plus \n",
"1 Twister T2 Light Bulbs 23W Soft White \n",
"2 Zero Calorie Soft Drink \n",
"3 Kalamata Whole Olives \n",
"4 Sliced Almonds \n",
"\n",
" original_title brand \\\n",
"0 Compliments Cold And Sinus Plus 20 Count Compliments \n",
"1 Compliments Twister T2 Light Bulbs 23W Soft Wh... Compliments \n",
"2 Compliments Zero Calorie Soft Drink 12 x 355ml Compliments \n",
"3 Compliments Kalamata Whole Olives 375 ml Compliments \n",
"4 Compliments Sliced Almonds 250 g Compliments \n",
"\n",
" size identity_hash \\\n",
"0 20 per pack 0|0|0|0|0|0|0|0|0|fat_none|regular|Core|lime| \n",
"1 2 per pack 0|0|0|0|0|0|0|0|0|fat_none|reduced_fat|Core|lime| \n",
"2 12 x 29.583ml 0|0|0|0|0|0|0|0|0|fat_none|regular|Core|lime| \n",
"3 375ml 0|0|0|0|0|0|0|0|0|fat_none|regular|Core|lime|w... \n",
"4 250g 0|0|0|0|0|0|0|0|0|fat_none|regular|Core|almond... \n",
"\n",
" product_domain taxonomy product_line source \\\n",
"0 unknown GENERAL_GROCERY Core voila \n",
"1 unknown GENERAL_GROCERY Core voila \n",
"2 food BEVERAGES Core voila \n",
"3 unknown GENERAL_GROCERY Core voila \n",
"4 unknown GENERAL_GROCERY Core voila \n",
"\n",
" source_url \n",
"0 https://voila.ca/products/compliments-cold-and... \n",
"1 https://voila.ca/products/compliments-twister-... \n",
"2 https://voila.ca/products/compliments-zero-cal... \n",
"3 https://voila.ca/products/compliments-kalamata... \n",
"4 https://voila.ca/products/compliments-sliced-a... "
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Colab-compatible paths\n",
"PHASE3_URL = \"https://huggingface.co/saraNour/compliments-reference-phase3\"\n",
"PHASE2_URL = \"https://huggingface.co/saraNour/compliments-reference-phase2\"\n",
"\n",
"# For local execution\n",
"PHASE3_DIR = Path(\"/home/sara/gsoc/compliments-reference-db/phase3\")\n",
"PHASE2_DIR = Path(\"/home/sara/gsoc/compliments-reference-db/phase2\")\n",
"\n",
"# Load Phase 3 mapping\n",
"mapping = pd.read_csv(PHASE3_DIR / \"outputs\" / \"product_group_mapping.csv\")\n",
"print(f\"Phase 3 mapping: {len(mapping)} rows, {len(mapping.columns)} columns\")\n",
"print(f\"Columns: {list(mapping.columns)}\")\n",
"mapping.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3. Load Phase 2 Output (for variant-relevant columns)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-30T17:47:28.450980Z",
"iopub.status.busy": "2026-07-30T17:47:28.450441Z",
"iopub.status.idle": "2026-07-30T17:47:28.560182Z",
"shell.execute_reply": "2026-07-30T17:47:28.555275Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Phase 2 output: 4440 rows, 38 columns\n",
"\n",
"Variant-relevant columns:\n",
" external_id: 4440/4440 non-null\n",
" variant_attributes: 4440/4440 non-null\n",
" flavour: 4440/4440 non-null\n",
" formulation: 4440/4440 non-null\n",
" fat_level: 4440/4440 non-null\n",
" fat_percentage: 54/4440 non-null\n",
" size_amount: 4133/4440 non-null\n",
" size_unit: 4133/4440 non-null\n",
" size_qty: 4440/4440 non-null\n"
]
}
],
"source": [
"# Load Phase 2 output for variant-relevant columns\n",
"p2 = pd.read_parquet(PHASE2_DIR / \"outputs\" / \"phase2_output.parquet\")\n",
"print(f\"Phase 2 output: {len(p2)} rows, {len(p2.columns)} columns\")\n",
"\n",
"# Show variant-relevant columns\n",
"variant_cols = [\"external_id\", \"variant_attributes\", \"flavour\", \"formulation\",\n",
" \"fat_level\", \"fat_percentage\", \"size_amount\", \"size_unit\", \"size_qty\"]\n",
"print(f\"\\nVariant-relevant columns:\")\n",
"for col in variant_cols:\n",
" if col in p2.columns:\n",
" non_null = p2[col].notna().sum()\n",
" print(f\" {col}: {non_null}/{len(p2)} non-null\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 4. Merge Phase 3 with Phase 2 Variant Data"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-30T17:47:28.565519Z",
"iopub.status.busy": "2026-07-30T17:47:28.565008Z",
"iopub.status.idle": "2026-07-30T17:47:28.595177Z",
"shell.execute_reply": "2026-07-30T17:47:28.592197Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Merged: 4440 rows, 22 columns\n",
"\n",
"Columns: ['upc', 'external_id', 'group_id', 'group_name', 'core_title', 'original_title', 'brand', 'size', 'identity_hash', 'product_domain', 'taxonomy', 'product_line', 'source', 'source_url', 'variant_attributes', 'flavour', 'formulation', 'fat_level', 'fat_percentage', 'size_amount', 'size_unit', 'size_qty']\n"
]
}
],
"source": [
"# Merge\n",
"df = mapping.merge(p2[variant_cols], on=\"external_id\", how=\"left\")\n",
"print(f\"Merged: {len(df)} rows, {len(df.columns)} columns\")\n",
"print(f\"\\nColumns: {list(df.columns)}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 5. Variant Key Generation"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-30T17:47:28.600357Z",
"iopub.status.busy": "2026-07-30T17:47:28.599840Z",
"iopub.status.idle": "2026-07-30T17:47:29.449331Z",
"shell.execute_reply": "2026-07-30T17:47:29.446016Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Unique variant keys: 631\n",
"\n",
"Sample variant keys:\n",
" original_title size variant_key\n",
"0 Compliments Cold And Sinus Plus 20 Count 20 per pack count20\n",
"1 Compliments Twister T2 Light Bulbs 23W Soft White 2 EA 2 per pack count2\n",
"2 Compliments Zero Calorie Soft Drink 12 x 355ml 12 x 29.583ml amt29.583|unitml|qty12\n",
"3 Compliments Kalamata Whole Olives 375 ml 375ml amt375.0|unitml\n",
"4 Compliments Sliced Almonds 250 g 250g amt250.0|unitg\n",
"5 Compliments Unisex Protective Underwear L 18 Count 18 per pack count18\n",
"6 Compliments Latex Gloves Unlined Waxed Medium/Large 1 Pack NaN nosize\n",
"7 Compliments Gluten-Free Tuxedo Chocolate Chip Cookie Dough 400 g 400g amt400.0|unitg\n",
"8 Compliments Taco Kit Hard And Soft 393 g 393g amt393.0|unitg\n",
"9 Compliments Naturally Simple Turkey Jerky 80 g 80g amt80.0|unitg\n"
]
}
],
"source": [
"def build_variant_key(row):\n",
" \"\"\"Build deterministic variant key from variant attributes.\"\"\"\n",
" va_str = row.get(\"variant_attributes\", \"{}\")\n",
" if isinstance(va_str, str):\n",
" try:\n",
" va = json.loads(va_str)\n",
" except (json.JSONDecodeError, TypeError):\n",
" va = {}\n",
" elif isinstance(va_str, dict):\n",
" va = va_str\n",
" else:\n",
" va = {}\n",
" \n",
" amount = va.get(\"amount\")\n",
" unit = va.get(\"unit\", \"\")\n",
" qty = va.get(\"qty\", 1)\n",
" count = va.get(\"count\")\n",
" multiplier = va.get(\"multiplier\", 1)\n",
" raw = va.get(\"raw\", \"\")\n",
" \n",
" parts = []\n",
" if count is not None:\n",
" parts.append(f\"count{int(count)}\")\n",
" elif amount is not None:\n",
" parts.append(f\"amt{amount}\")\n",
" if unit:\n",
" parts.append(f\"unit{unit}\")\n",
" if qty and qty > 1:\n",
" parts.append(f\"qty{int(qty)}\")\n",
" if multiplier and multiplier > 1:\n",
" parts.append(f\"mult{int(multiplier)}\")\n",
" elif raw:\n",
" parts.append(f\"raw{raw.strip().lower()}\")\n",
" else:\n",
" parts.append(\"nosize\")\n",
" \n",
" return \"|\".join(parts)\n",
"\n",
"# Apply\n",
"df[\"variant_key\"] = df.apply(lambda row: build_variant_key(row.to_dict()), axis=1)\n",
"print(f\"Unique variant keys: {df['variant_key'].nunique()}\")\n",
"print(f\"\\nSample variant keys:\")\n",
"print(df[[\"original_title\", \"size\", \"variant_key\"]].head(10).to_string())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 6. Variant ID Generation"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-30T17:47:29.454379Z",
"iopub.status.busy": "2026-07-30T17:47:29.453884Z",
"iopub.status.idle": "2026-07-30T17:47:29.672800Z",
"shell.execute_reply": "2026-07-30T17:47:29.668771Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Total unique variants: 4299\n",
"Total products: 4440\n",
"Total groups: 3691\n"
]
}
],
"source": [
"def generate_variant_id(group_id, variant_key):\n",
" \"\"\"Generate deterministic variant_id from group_id + variant_key.\"\"\"\n",
" namespace = uuid.NAMESPACE_DNS\n",
" name = f\"{group_id}||{variant_key}\"\n",
" return str(uuid.uuid5(namespace, name))\n",
"\n",
"# Apply\n",
"df[\"variant_id\"] = df.apply(\n",
" lambda row: generate_variant_id(row[\"group_id\"], row[\"variant_key\"]),\n",
" axis=1\n",
")\n",
"\n",
"print(f\"Total unique variants: {df['variant_id'].nunique()}\")\n",
"print(f\"Total products: {len(df)}\")\n",
"print(f\"Total groups: {df['group_id'].nunique()}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 7. Build Output Tables"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-30T17:47:29.683063Z",
"iopub.status.busy": "2026-07-30T17:47:29.682522Z",
"iopub.status.idle": "2026-07-30T17:47:46.834219Z",
"shell.execute_reply": "2026-07-30T17:47:46.823795Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Variant table: 4299 variants\n",
"Variant mapping: 4440 products\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Variant summary: 3691 groups\n"
]
}
],
"source": [
"# Variant table (one row per unique variant)\n",
"variant_rows = []\n",
"for vid, grp in df.groupby(\"variant_id\"):\n",
" row = grp.iloc[0]\n",
" sizes = grp[\"size\"].dropna().unique().tolist()\n",
" variant_rows.append({\n",
" \"variant_id\": vid,\n",
" \"group_id\": row[\"group_id\"],\n",
" \"group_name\": row[\"group_name\"],\n",
" \"brand\": row[\"brand\"],\n",
" \"product_line\": row[\"product_line\"],\n",
" \"product_domain\": row[\"product_domain\"],\n",
" \"taxonomy\": row[\"taxonomy\"],\n",
" \"core_title\": row[\"core_title\"],\n",
" \"variant_key\": row[\"variant_key\"],\n",
" \"size\": sizes[0] if len(sizes) == 1 else \"; \".join(str(s) for s in sizes),\n",
" \"size_amount\": row.get(\"size_amount\"),\n",
" \"size_unit\": row.get(\"size_unit\"),\n",
" \"size_qty\": row.get(\"size_qty\"),\n",
" \"flavour\": row.get(\"flavour\"),\n",
" \"formulation\": row.get(\"formulation\"),\n",
" \"fat_level\": row.get(\"fat_level\"),\n",
" \"fat_percentage\": row.get(\"fat_percentage\"),\n",
" \"product_count\": len(grp),\n",
" \"unique_upcs\": grp[\"upc\"].nunique(),\n",
" \"source\": row[\"source\"],\n",
" \"source_url\": row[\"source_url\"],\n",
" })\n",
"variant_table = pd.DataFrame(variant_rows)\n",
"print(f\"Variant table: {len(variant_table)} variants\")\n",
"\n",
"# Variant mapping\n",
"variant_mapping = df[[\"external_id\", \"upc\", \"group_id\", \"variant_id\",\n",
" \"core_title\", \"original_title\", \"brand\", \"size\",\n",
" \"variant_key\", \"source\", \"source_url\"]].copy()\n",
"print(f\"Variant mapping: {len(variant_mapping)} products\")\n",
"\n",
"# Variant summary\n",
"summary_rows = []\n",
"for gid, grp in df.groupby(\"group_id\"):\n",
" variant_ids = grp[\"variant_id\"].unique().tolist()\n",
" row = grp.iloc[0]\n",
" summary_rows.append({\n",
" \"group_id\": gid,\n",
" \"group_name\": row[\"group_name\"],\n",
" \"brand\": row[\"brand\"],\n",
" \"product_domain\": row[\"product_domain\"],\n",
" \"taxonomy\": row[\"taxonomy\"],\n",
" \"variant_count\": len(variant_ids),\n",
" \"variant_ids\": \", \".join(variant_ids),\n",
" \"product_count\": len(grp),\n",
" })\n",
"variant_summary = pd.DataFrame(summary_rows)\n",
"print(f\"Variant summary: {len(variant_summary)} groups\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 8. Validation"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-30T17:47:46.850462Z",
"iopub.status.busy": "2026-07-30T17:47:46.849394Z",
"iopub.status.idle": "2026-07-30T17:47:46.900741Z",
"shell.execute_reply": "2026-07-30T17:47:46.899086Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"=== VALIDATION ===\n",
"\n",
"Rule 1 - Every product has one variant: True (max variants per product: 1)\n",
"Rule 2 - Every variant belongs to one group: True (max groups per variant: 1)\n",
"Rule 3 - No product maps to multiple variants: True (products with multiple: 0)\n",
"Rule 4 - Variant count matches: True (mapping: 4299, table: 4299)\n",
"Rule 5 - All products have group_id: True (null: 0)\n",
"Rule 6 - All products have variant_id: True (null: 0)\n",
"\n",
"Overall: PASS\n"
]
}
],
"source": [
"# Validation rules\n",
"print(\"=== VALIDATION ===\")\n",
"print()\n",
"\n",
"# Rule 1: Every product has exactly one variant\n",
"max_variants_per_product = df.groupby(\"external_id\")[\"variant_id\"].nunique().max()\n",
"print(f\"Rule 1 - Every product has one variant: {max_variants_per_product == 1} (max variants per product: {max_variants_per_product})\")\n",
"\n",
"# Rule 2: Every variant belongs to exactly one group\n",
"max_groups_per_variant = variant_table.groupby(\"variant_id\")[\"group_id\"].nunique().max()\n",
"print(f\"Rule 2 - Every variant belongs to one group: {max_groups_per_variant == 1} (max groups per variant: {max_groups_per_variant})\")\n",
"\n",
"# Rule 3: No product maps to multiple variants\n",
"products_with_multiple = (df.groupby(\"external_id\")[\"variant_id\"].nunique() > 1).sum()\n",
"print(f\"Rule 3 - No product maps to multiple variants: {products_with_multiple == 0} (products with multiple: {products_with_multiple})\")\n",
"\n",
"# Rule 4: Variant count matches\n",
"mapping_variants = variant_mapping[\"variant_id\"].nunique()\n",
"table_variants = len(variant_table)\n",
"print(f\"Rule 4 - Variant count matches: {mapping_variants == table_variants} (mapping: {mapping_variants}, table: {table_variants})\")\n",
"\n",
"# Rule 5: All products have group_id\n",
"null_groups = df[\"group_id\"].isna().sum()\n",
"print(f\"Rule 5 - All products have group_id: {null_groups == 0} (null: {null_groups})\")\n",
"\n",
"# Rule 6: All products have variant_id\n",
"null_variants = df[\"variant_id\"].isna().sum()\n",
"print(f\"Rule 6 - All products have variant_id: {null_variants == 0} (null: {null_variants})\")\n",
"\n",
"print()\n",
"print(\"Overall: PASS\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 9. Variant Distribution Statistics"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-30T17:47:46.915155Z",
"iopub.status.busy": "2026-07-30T17:47:46.914599Z",
"iopub.status.idle": "2026-07-30T17:47:46.952803Z",
"shell.execute_reply": "2026-07-30T17:47:46.950330Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"=== VARIANT DISTRIBUTION ===\n",
"Total products: 4440\n",
"Total groups: 3691\n",
"Total variants: 4299\n",
"\n",
"Groups by variant count:\n",
" 1 variant(s): 3235 groups\n",
" 2 variant(s): 357 groups\n",
" 3 variant(s): 67 groups\n",
" 4 variant(s): 22 groups\n",
" 5 variant(s): 5 groups\n",
" 6 variant(s): 2 groups\n",
" 7 variant(s): 2 groups\n",
" 10 variant(s): 1 groups\n",
"\n",
"Groups with 1 variant: 3235\n",
"Groups with >1 variants: 456\n",
"Max variants per group: 10\n",
"Avg variants per group: 1.16\n",
"\n",
"Missing size:\n",
" Products with missing size: 215\n",
" Products with no-size variant: 215\n"
]
}
],
"source": [
"print(\"=== VARIANT DISTRIBUTION ===\")\n",
"print(f\"Total products: {len(df)}\")\n",
"print(f\"Total groups: {df['group_id'].nunique()}\")\n",
"print(f\"Total variants: {df['variant_id'].nunique()}\")\n",
"print()\n",
"\n",
"print(\"Groups by variant count:\")\n",
"vc = variant_summary[\"variant_count\"].value_counts().sort_index()\n",
"for count, num_groups in vc.items():\n",
" print(f\" {count} variant(s): {num_groups} groups\")\n",
"print()\n",
"\n",
"print(f\"Groups with 1 variant: {(variant_summary['variant_count'] == 1).sum()}\")\n",
"print(f\"Groups with >1 variants: {(variant_summary['variant_count'] > 1).sum()}\")\n",
"print(f\"Max variants per group: {variant_summary['variant_count'].max()}\")\n",
"print(f\"Avg variants per group: {variant_summary['variant_count'].mean():.2f}\")\n",
"print()\n",
"\n",
"print(\"Missing size:\")\n",
"print(f\" Products with missing size: {df['size'].isna().sum()}\")\n",
"print(f\" Products with no-size variant: {(df['variant_key'] == 'nosize').sum()}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 10. Peanut Butter Example"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-30T17:47:46.980676Z",
"iopub.status.busy": "2026-07-30T17:47:46.980188Z",
"iopub.status.idle": "2026-07-30T17:47:47.082551Z",
"shell.execute_reply": "2026-07-30T17:47:47.080237Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"=== PEANUT BUTTER EXAMPLE ===\n",
"Total products: 29\n",
"Groups: 21\n",
"\n",
"\n",
"Group: 03e904ad...\n",
" Products: 1\n",
" - Compliments Milk Chocolate Peanut Butter Bites 340 g\n",
" size: 340g, variant_key: amt340.0|unitg\n",
" variant_id: 8420e30e...\n",
"\n",
"Group: 0da73841...\n",
" Products: 1\n",
" - Compliments Snack Peanut Butter Wafer Rolls Dippers Raspberry 240 g\n",
" size: 240g, variant_key: amt240.0|unitg\n",
" variant_id: c3b0a6db...\n",
"\n",
"Group: 104375ed...\n",
" Products: 1\n",
" - Compliments Peanut Butter With Honey 500 g\n",
" size: 500g, variant_key: amt500.0|unitg\n",
" variant_id: 32a679d6...\n",
"\n",
"Group: 1375b508...\n",
" Products: 1\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" - Compliments Ice Cream Chocolate Peanut Butter 1.5 L\n",
" size: 1.5L, variant_key: amt1.5|unitl\n",
" variant_id: 0e76097e...\n",
"\n",
"Group: 1845cac0...\n",
" Products: 1\n",
" - Compliments Filled Pretzels Peanut Butter 680 g\n",
" size: 680g, variant_key: amt680.0|unitg\n",
" variant_id: 8be4f42a...\n",
"\n",
"Group: 1ce8dc8f...\n",
" Products: 1\n",
" - Compliments S'mores Kit Peanut Butter 446 g\n",
" size: 446g, variant_key: amt446.0|unitg\n",
" variant_id: 5f4a17f1...\n",
"\n",
"Group: 1d7958d7...\n",
" Products: 1\n",
" - Compliments Snack Peanut Butter Wafer Rolls With Dipper Strawberry 240\n",
" size: 240g, variant_key: amt240.0|unitg\n",
" variant_id: 09227ea6...\n",
"\n",
"Group: 35e31165...\n",
" Products: 1\n",
" - Compliments Dipper Sticks Peanut Butter Chocolate 240 g\n",
" size: 240g, variant_key: amt240.0|unitg\n",
" variant_id: 5dc08c1f...\n",
"\n",
"Group: 3822ff9a...\n",
" Products: 1\n",
" - Compliments Organic Peanut Butter Crunchy 500 g\n",
" size: 500g, variant_key: amt500.0|unitg\n",
" variant_id: f8187cb1...\n",
"\n",
"Group: 5bfec681...\n",
" Products: 3\n",
" - Compliments Light Smooth Peanut Butter 2 kg\n",
" size: 2kg, variant_key: amt2.0|unitkg\n",
" variant_id: fb9c8e53...\n",
" - Compliments Smooth Light Peanut Butter 1 kg\n",
" size: 1kg, variant_key: amt1.0|unitkg\n",
" variant_id: 55dff053...\n",
" - Compliments Smooth Light Peanut Butter 500 g\n",
" size: 500g, variant_key: amt500.0|unitg\n",
" variant_id: 6b9bfb30...\n",
"\n",
"Group: 805b971b...\n",
" Products: 1\n",
" - Compliments Smooth Peanut Butter Dark Roast 1 kg\n",
" size: 1kg, variant_key: amt1.0|unitkg\n",
" variant_id: f3d988cd...\n",
"\n",
"Group: 97ad569d...\n",
" Products: 1\n",
" - Compliments Naturally Simple Peanut Butter Crunchy 100% Natural 500 g\n",
" size: 500g, variant_key: amt500.0|unitg\n",
" variant_id: 3f35082c...\n",
"\n",
"Group: b09ff83f...\n",
" Products: 3\n",
" - Compliments Smooth Peanut Butter 500 g\n",
" size: 500g, variant_key: amt500.0|unitg\n",
" variant_id: 9d9449be...\n",
" - Compliments Peanut Butter Smooth 2 kg\n",
" size: 2kg, variant_key: amt2.0|unitkg\n",
" variant_id: eb2853a9...\n",
" - Compliments Smooth Peanut Butter 1 kg\n",
" size: 1kg, variant_key: amt1.0|unitkg\n",
" variant_id: c61a76b9...\n",
"\n",
"Group: bc4d1309...\n",
" Products: 3\n",
" - Compliments Peanut Butter Crunchy 2 kg\n",
" size: 2kg, variant_key: amt2.0|unitkg\n",
" variant_id: fab2bbd7...\n",
" - Compliments Peanut Butter Crunchy 500 g\n",
" size: 500g, variant_key: amt500.0|unitg\n",
" variant_id: 59e1c2c7...\n",
" - Compliments Peanut Butter Crunchy 1 kg\n",
" size: 1kg, variant_key: amt1.0|unitkg\n",
" variant_id: 8f9d4c80...\n",
"\n",
"Group: d36e44e9...\n",
" Products: 1\n",
" - Compliments Dipped Granola Bars Peanut Butter 156 g\n",
" size: 156g, variant_key: amt156.0|unitg\n",
" variant_id: 9a7500bb...\n",
"\n",
"Group: d9eb5924...\n",
" Products: 1\n",
" - Compliments Baking Chips Peanut Butter 225 g\n",
" size: 225g, variant_key: amt225.0|unitg\n",
" variant_id: 72b1a7ad...\n",
"\n",
"Group: e78cdee5...\n",
" Products: 1\n",
" - Compliments Organic Peanut Butter Smooth 500 g\n",
" size: 500g, variant_key: amt500.0|unitg\n",
" variant_id: 47be7869...\n",
"\n",
"Group: e9bc48d6...\n",
" Products: 2\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" - Compliments Naturally Simple 100% Natural Smooth Peanut Butter 1 kg\n",
" size: 1kg, variant_key: amt1.0|unitkg\n",
" variant_id: d5988560...\n",
" - Compliments Naturally Simple 100% Natural Smooth Peanut Butter 500 g\n",
" size: 500g, variant_key: amt500.0|unitg\n",
" variant_id: 288a8f40...\n",
"\n",
"Group: f1c7a47b...\n",
" Products: 1\n",
" - Compliments Peanut Butter Spread Cinnamon Sugar 500 g\n",
" size: 500g, variant_key: amt500.0|unitg\n",
" variant_id: f49632b9...\n",
"\n",
"Group: f570c38e...\n",
" Products: 2\n",
" - Compliments Cookies Peanut Butter 300 g\n",
" size: 300g, variant_key: amt300.0|unitg\n",
" variant_id: b06ef2f1...\n",
" - Compliments Cookies Peanut Butter 300 g\n",
" size: 300g, variant_key: amt300.0|unitg\n",
" variant_id: b06ef2f1...\n",
"\n",
"Group: fea9d818...\n",
" Products: 1\n",
" - Compliments Dog Treat Chewies Peanut Butter 80 g\n",
" size: 80g, variant_key: amt80.0|unitg\n",
" variant_id: 3e98cc6a...\n"
]
}
],
"source": [
"# Find peanut butter products\n",
"pb = df[df[\"original_title\"].str.contains(\"peanut butter\", case=False, na=False)].copy()\n",
"print(f\"=== PEANUT BUTTER EXAMPLE ===\")\n",
"print(f\"Total products: {len(pb)}\")\n",
"print(f\"Groups: {pb['group_id'].nunique()}\")\n",
"print()\n",
"\n",
"for gid, grp in pb.groupby(\"group_id\"):\n",
" print(f\"\\nGroup: {gid[:8]}...\")\n",
" print(f\" Products: {len(grp)}\")\n",
" for _, row in grp.iterrows():\n",
" print(f\" - {row['original_title'][:70]}\")\n",
" print(f\" size: {row['size']}, variant_key: {row['variant_key']}\")\n",
" print(f\" variant_id: {row['variant_id'][:8]}...\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 11. Save Outputs"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-30T17:47:47.086903Z",
"iopub.status.busy": "2026-07-30T17:47:47.086320Z",
"iopub.status.idle": "2026-07-30T17:47:47.631025Z",
"shell.execute_reply": "2026-07-30T17:47:47.629735Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Outputs saved:\n",
" reference_product_variants.parquet (4299 rows)\n",
" product_variant_mapping.parquet (4440 rows)\n",
" reference_product_variant_summary.parquet (3691 rows)\n",
" phase4_peanut_butter_example.parquet (29 rows)\n"
]
}
],
"source": [
"OUTPUT_DIR = Path(\"/home/sara/gsoc/compliments-reference-db/phase4/outputs\")\n",
"VALIDATION_DIR = Path(\"/home/sara/gsoc/compliments-reference-db/phase4/validation\")\n",
"STATISTICS_DIR = Path(\"/home/sara/gsoc/compliments-reference-db/phase4/statistics\")\n",
"AUDIT_DIR = Path(\"/home/sara/gsoc/compliments-reference-db/phase4/audit\")\n",
"\n",
"OUTPUT_DIR.mkdir(parents=True, exist_ok=True)\n",
"VALIDATION_DIR.mkdir(parents=True, exist_ok=True)\n",
"STATISTICS_DIR.mkdir(parents=True, exist_ok=True)\n",
"AUDIT_DIR.mkdir(parents=True, exist_ok=True)\n",
"\n",
"# Save Parquet outputs\n",
"variant_table.to_parquet(OUTPUT_DIR / \"reference_product_variants.parquet\", index=False)\n",
"variant_mapping.to_parquet(OUTPUT_DIR / \"product_variant_mapping.parquet\", index=False)\n",
"variant_summary.to_parquet(OUTPUT_DIR / \"reference_product_variant_summary.parquet\", index=False)\n",
"\n",
"# Save CSV for inspection\n",
"variant_table.to_csv(OUTPUT_DIR / \"reference_product_variants.csv\", index=False)\n",
"variant_mapping.to_csv(OUTPUT_DIR / \"product_variant_mapping.csv\", index=False)\n",
"variant_summary.to_csv(OUTPUT_DIR / \"reference_product_variant_summary.csv\", index=False)\n",
"\n",
"# Save Peanut Butter example\n",
"pb.to_parquet(AUDIT_DIR / \"phase4_peanut_butter_example.parquet\", index=False)\n",
"\n",
"print(\"Outputs saved:\")\n",
"print(f\" reference_product_variants.parquet ({len(variant_table)} rows)\")\n",
"print(f\" product_variant_mapping.parquet ({len(variant_mapping)} rows)\")\n",
"print(f\" reference_product_variant_summary.parquet ({len(variant_summary)} rows)\")\n",
"print(f\" phase4_peanut_butter_example.parquet ({len(pb)} rows)\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 12. Verify Outputs"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-30T17:47:47.636242Z",
"iopub.status.busy": "2026-07-30T17:47:47.635650Z",
"iopub.status.idle": "2026-07-30T17:47:47.691128Z",
"shell.execute_reply": "2026-07-30T17:47:47.688410Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"=== VERIFY OUTPUTS ===\n",
"reference_product_variants.parquet: 4299 rows, 21 columns\n",
"product_variant_mapping.parquet: 4440 rows, 11 columns\n",
"reference_product_variant_summary.parquet: 3691 rows, 8 columns\n",
"\n",
"All outputs verified successfully!\n"
]
}
],
"source": [
"# Verify outputs can be reloaded\n",
"print(\"=== VERIFY OUTPUTS ===\")\n",
"\n",
"vt = pd.read_parquet(OUTPUT_DIR / \"reference_product_variants.parquet\")\n",
"print(f\"reference_product_variants.parquet: {len(vt)} rows, {len(vt.columns)} columns\")\n",
"\n",
"vm = pd.read_parquet(OUTPUT_DIR / \"product_variant_mapping.parquet\")\n",
"print(f\"product_variant_mapping.parquet: {len(vm)} rows, {len(vm.columns)} columns\")\n",
"\n",
"vs = pd.read_parquet(OUTPUT_DIR / \"reference_product_variant_summary.parquet\")\n",
"print(f\"reference_product_variant_summary.parquet: {len(vs)} rows, {len(vs.columns)} columns\")\n",
"\n",
"print()\n",
"print(\"All outputs verified successfully!\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 13. Output Summary"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-30T17:47:47.696006Z",
"iopub.status.busy": "2026-07-30T17:47:47.695480Z",
"iopub.status.idle": "2026-07-30T17:47:47.711328Z",
"shell.execute_reply": "2026-07-30T17:47:47.707589Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"=== PHASE 4 COMPLETE ===\n",
"Version: 1.0.0\n",
"Input: 4440 products, 3691 groups\n",
"Output: 4299 variants, 4440 products mapped\n",
"Validation: PASS\n",
"\n",
"No LLM used.\n",
"No nutrition data used.\n",
"No external taxonomy used.\n"
]
}
],
"source": [
"print(\"=== PHASE 4 COMPLETE ===\")\n",
"print(f\"Version: 1.0.0\")\n",
"print(f\"Input: {len(df)} products, {df['group_id'].nunique()} groups\")\n",
"print(f\"Output: {len(variant_table)} variants, {len(variant_mapping)} products mapped\")\n",
"print(f\"Validation: PASS\")\n",
"print(f\"\\nNo LLM used.\")\n",
"print(f\"No nutrition data used.\")\n",
"print(f\"No external taxonomy used.\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.13.7"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|