Spaces:
Running
Running
File size: 97,429 Bytes
2ca7685 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"id": "0140b2b1-c1e5-48a5-a8e2-43808de9cd17",
"metadata": {},
"outputs": [],
"source": [
"from datasets import load_dataset"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "c57fe556-c2f2-466d-a880-111c750b949f",
"metadata": {},
"outputs": [],
"source": [
"dataset_name = \"OpenAssistant/oasst1\"\n",
"dataset = load_dataset(dataset_name, split=\"train\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "2d72c5f1-6e74-4913-843c-ca093aa9b7af",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(84437, 18)"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dataset.shape"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "5a0e9099-cebf-4c8d-9ef7-1d9992c7b17c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'message_id': 'be4d0752-afbe-473b-99f3-48f1b5880f90',\n",
" 'parent_id': 'ac94bfcf-7f25-4084-8755-dde345ac2323',\n",
" 'user_id': 'c212120c-0b79-4b32-a5b1-d96686ca92ca',\n",
" 'created_date': '2023-02-06T18:34:30.836581+00:00',\n",
" 'text': \"Yes, that's correct. Keeping the code for the TESR and the registration code in the same file can make it easier to manage and maintain the code. The ExampleMod class acts as a container for the TESR code, providing a convenient and logical grouping. The functionality of the code remains unchanged, and the TESR will still be properly registered and used to render the custom tile entities in the game.\",\n",
" 'role': 'assistant',\n",
" 'lang': 'en',\n",
" 'review_count': 3,\n",
" 'review_result': True,\n",
" 'deleted': False,\n",
" 'rank': 2,\n",
" 'synthetic': False,\n",
" 'model_name': None,\n",
" 'detoxify': {'toxicity': 0.00026471694582141936,\n",
" 'severe_toxicity': 3.753640703507699e-05,\n",
" 'obscene': 0.00018712480959948152,\n",
" 'identity_attack': 0.00012360737309791148,\n",
" 'insult': 0.000221485854126513,\n",
" 'threat': 4.4919768697582185e-05,\n",
" 'sexual_explicit': 3.185281457263045e-05},\n",
" 'message_tree_id': '6ab24d72-0181-4594-a9cd-deaf170242fb',\n",
" 'tree_state': 'ready_for_export',\n",
" 'emojis': {'name': ['_skip_labeling'], 'count': [4]},\n",
" 'labels': {'name': ['spam',\n",
" 'fails_task',\n",
" 'lang_mismatch',\n",
" 'pii',\n",
" 'not_appropriate',\n",
" 'hate_speech',\n",
" 'sexual_content',\n",
" 'quality',\n",
" 'toxicity',\n",
" 'humor',\n",
" 'helpfulness',\n",
" 'creativity',\n",
" 'violence'],\n",
" 'value': [0.3333333333333333,\n",
" 1.0,\n",
" 0.0,\n",
" 0.0,\n",
" 0.5,\n",
" 0.0,\n",
" 0.0,\n",
" 0.16666666666666666,\n",
" 0.0,\n",
" 0.125,\n",
" 0.0,\n",
" 0.25,\n",
" 0.0],\n",
" 'count': [3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2]}}"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dataset[9]"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "cdba1b26-5f8a-47a2-9097-84752978f11d",
"metadata": {},
"outputs": [],
"source": [
"df = dataset.to_pandas()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "8f87cf6d-ec9c-4433-8d24-5e1ee919da53",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['Can you write a short introduction about the relevance of the term \"monopsony\" in economics? Please use examples related to potential monopsonies in the labour market and cite relevant research.',\n",
" '\"Monopsony\" refers to a market structure where there is only one buyer for a particular good or service. In economics, this term is particularly relevant in the labor market, where a monopsony employer has significant power over the wages and working conditions of their employees. The presence of a monopsony can result in lower wages and reduced employment opportunities for workers, as the employer has little incentive to increase wages or provide better working conditions.\\n\\nRecent research has identified potential monopsonies in industries such as retail and fast food, where a few large companies control a significant portion of the market (Bivens & Mishel, 2013). In these industries, workers often face low wages, limited benefits, and reduced bargaining power, leading to a situation where they are dependent on the employer for their livelihood. This dependence can result in further suppression of wages and a decline in working conditions.\\n\\nOverall, the concept of monopsony is essential to understanding the dynamics of labor markets and the impact of market power on workers. Further research is needed to understand the extent and impact of monopsonies on the economy and to develop policies to address this issue.\\n\\nReferences:\\nBivens, J., & Mishel, L. (2013). The Pay of Corporate Executives and Financial Professionals as Evidence of Rents in Top 1 Percent Incomes. Journal of Economic Perspectives, 27(3), 57-78.',\n",
" 'Now explain it to a dog',\n",
" 'Monopsony is a market structure in which there is a single buyer in a market. In the context of labor markets, a monopsony occurs when there is only one employer in a particular industry or geographic area, giving that employer significant power over the wages and working conditions of workers. This results in a situation where the employer has the ability to suppress wages and reduce the bargaining power of workers.\\n\\nResearch has shown that the existence of monopsony power in labor markets can have negative effects on workers, such as lower wages, reduced benefits, and limited job opportunities. For example, a study by Autor, Dorn, and Hanson (2013) found evidence of monopsony power in certain U.S. labor markets, resulting in lower wages and reduced job opportunities for workers. Similarly, another study by Bharadwaj, Black, and Kolesnikova (2019) found that the presence of a single dominant employer in a local labor market was associated with lower wages for workers.',\n",
" 'How can one fight back when a monospony had been created?',\n",
" 'Monopsony refers to a market structure where there is only one buyer of a good or service. In the context of labor markets, a monopsony occurs when there is only one employer in a particular geographic area or industry, giving them significant power to set wages and working conditions. Research has shown that the existence of monopsonies can lead to lower wages and reduced job opportunities for workers. For example, a study by the National Bureau of Economic Research found that in industries with high levels of concentration, workers earn lower wages and are less likely to receive benefits such as health insurance.',\n",
" \"What can be done at a regulatory level to ensure, in a monopsony, that the power over the employees isn't abused? List a few options and focus on the organs that should act.\",\n",
" 'Here are some potential regulatory options to address monopsony power over employees:\\n\\n- Antitrust enforcement agencies like the FTC or DOJ could investigate and take action against dominant employers that are abusing their market power to suppress wages or worsen working conditions. They could force divestitures or other structural remedies.\\n- Labor standards agencies could set industry-specific minimum wage floors or other regulations around compensation and working conditions. This would reduce the ability of dominant employers to push wages/conditions below certain thresholds.\\n- Sector-specific regulators could impose requirements around how companies hire, compensate, and treat workers. For example, banking regulators could prohibit abusive practices by dominant banks with regard to their employees.\\n- Legislatures could pass laws',\n",
" \"Regulatory intervention can be used to address the negative consequences of monopsony power in the labor market. A few options include:\\n\\n1. Antitrust enforcement: Antitrust laws can be used to prevent firms from engaging in practices that limit competition and suppress wages. The antitrust division of the Department of Justice and the Federal Trade Commission (FTC) are responsible for enforcing these laws.\\n\\n2. Labor standards and protections: Governments can set minimum wage standards and other labor protections to ensure that workers are paid a fair wage, even in industries dominated by a single buyer. The U.S. Department of Labor is responsible for enforcing these standards.\\n\\n3. Occupational licensing reform: Occupational licensing requirements can restrict worker mobility and increase the bargaining power of employers. Reforms to licensing requirements can reduce these barriers and increase competition in the labor market. State governments typically regulate occupational licensing.\\n\\n4. Collective bargaining rights: Collective bargaining by workers can increase their bargaining power and lead to higher wages. Governments can protect and promote collective bargaining rights to counteract the effects of monopsony power. The National Labor Relations Board is responsible for enforcing workers' rights to engage in collective bargaining in the U.S.\\n\\nThese are just a few examples of regulatory options that can be used to address monopsony power in the labor market. The specific actions taken will depend on the particular circumstances and context of each case.\",\n",
" \"Yes, that's correct. Keeping the code for the TESR and the registration code in the same file can make it easier to manage and maintain the code. The ExampleMod class acts as a container for the TESR code, providing a convenient and logical grouping. The functionality of the code remains unchanged, and the TESR will still be properly registered and used to render the custom tile entities in the game.\",\n",
" 'I would imagine this is similar or even the same as a \"monopoly\" but I am not sure.\\n\\nAssuming that this some kind of \"final state\" of a particular industry or even an entire economy, give me some larger historical examples of this kind of structure consolidating over time, and describe what circumstances are common prerequisite.',\n",
" 'Bouguereau died in 1905, so it is unlikely that any of his direct descendants are still alive. However, his works continue to be popular and are sold at auction and through art dealers. It is possible that some indirect descendants may benefit from the sale of his works.']"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[df[\"message_tree_id\"] == \"6ab24d72-0181-4594-a9cd-deaf170242fb\"].text.tolist()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "89f1575f-5b97-4598-b4e3-81953061a76d",
"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>message_id</th>\n",
" <th>parent_id</th>\n",
" <th>user_id</th>\n",
" <th>created_date</th>\n",
" <th>text</th>\n",
" <th>role</th>\n",
" <th>lang</th>\n",
" <th>review_count</th>\n",
" <th>review_result</th>\n",
" <th>deleted</th>\n",
" <th>rank</th>\n",
" <th>synthetic</th>\n",
" <th>model_name</th>\n",
" <th>detoxify</th>\n",
" <th>message_tree_id</th>\n",
" <th>tree_state</th>\n",
" <th>emojis</th>\n",
" <th>labels</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>84433</th>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>None</td>\n",
" <td>ad5d3a46-2f52-4270-89a9-a6b1d180d809</td>\n",
" <td>2023-02-10T13:49:30.080447+00:00</td>\n",
" <td>Nork jarri zion ahotsa Dragoi Bolako Vegetari ...</td>\n",
" <td>prompter</td>\n",
" <td>eu</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1', '_skip_reply'], 'count': [5, 4]}</td>\n",
" <td>{'name': ['spam', 'lang_mismatch', 'pii', 'not...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" message_id parent_id \\\n",
"84433 d3946880-4402-42a8-8a9e-6dab5efa787f None \n",
"\n",
" user_id created_date \\\n",
"84433 ad5d3a46-2f52-4270-89a9-a6b1d180d809 2023-02-10T13:49:30.080447+00:00 \n",
"\n",
" text role lang \\\n",
"84433 Nork jarri zion ahotsa Dragoi Bolako Vegetari ... prompter eu \n",
"\n",
" review_count review_result deleted rank synthetic model_name \\\n",
"84433 3 True False NaN False None \n",
"\n",
" detoxify message_tree_id tree_state \\\n",
"84433 None d3946880-4402-42a8-8a9e-6dab5efa787f ready_for_export \n",
"\n",
" emojis \\\n",
"84433 {'name': ['+1', '_skip_reply'], 'count': [5, 4]} \n",
"\n",
" labels \n",
"84433 {'name': ['spam', 'lang_mismatch', 'pii', 'not... "
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[df[\"message_id\"] == \"d3946880-4402-42a8-8a9e-6dab5efa787f\"]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "b037c587-420b-4391-8479-4b95aaf79677",
"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>message_id</th>\n",
" <th>parent_id</th>\n",
" <th>user_id</th>\n",
" <th>created_date</th>\n",
" <th>text</th>\n",
" <th>role</th>\n",
" <th>lang</th>\n",
" <th>review_count</th>\n",
" <th>review_result</th>\n",
" <th>deleted</th>\n",
" <th>rank</th>\n",
" <th>synthetic</th>\n",
" <th>model_name</th>\n",
" <th>detoxify</th>\n",
" <th>message_tree_id</th>\n",
" <th>tree_state</th>\n",
" <th>emojis</th>\n",
" <th>labels</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>84432</th>\n",
" <td>47ba67f2-f711-4feb-91ff-0a0ffe556fe5</td>\n",
" <td>2e934881-260c-4a6c-8f09-66e0312f84ac</td>\n",
" <td>55e23953-c333-4b02-a459-c99d2c7172a3</td>\n",
" <td>2023-02-21T17:18:06.837900+00:00</td>\n",
" <td>James Potter eta Lily Potter ziren Harry Potte...</td>\n",
" <td>assistant</td>\n",
" <td>eu</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>2.0</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>2e934881-260c-4a6c-8f09-66e0312f84ac</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1'], 'count': [1]}</td>\n",
" <td>{'name': ['spam', 'fails_task', 'lang_mismatch...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84433</th>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>None</td>\n",
" <td>ad5d3a46-2f52-4270-89a9-a6b1d180d809</td>\n",
" <td>2023-02-10T13:49:30.080447+00:00</td>\n",
" <td>Nork jarri zion ahotsa Dragoi Bolako Vegetari ...</td>\n",
" <td>prompter</td>\n",
" <td>eu</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1', '_skip_reply'], 'count': [5, 4]}</td>\n",
" <td>{'name': ['spam', 'lang_mismatch', 'pii', 'not...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84434</th>\n",
" <td>4e8a349d-7781-42ae-8868-1ecf5df4c2cb</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>9f3e4da7-7d7a-4cf9-9d35-f59d00de240d</td>\n",
" <td>2023-02-11T15:26:37.799100+00:00</td>\n",
" <td>Dragoi bolaren aurreneko denboraldian ez da Ve...</td>\n",
" <td>assistant</td>\n",
" <td>eu</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>0.0</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1'], 'count': [1]}</td>\n",
" <td>{'name': ['spam', 'fails_task', 'lang_mismatch...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84435</th>\n",
" <td>ca45d4bd-2da7-4d56-beec-bf9f772e8426</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>055ac9a6-80e3-4ef5-b89a-edd88e261208</td>\n",
" <td>2023-02-12T19:23:29.730612+00:00</td>\n",
" <td>Dragoi Bolako Vegetari euskarazko ahotsa jarri...</td>\n",
" <td>assistant</td>\n",
" <td>eu</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1'], 'count': [1]}</td>\n",
" <td>{'name': ['spam', 'lang_mismatch', 'quality'],...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84436</th>\n",
" <td>6ea871e7-7582-4607-8b0a-84e4d0169868</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>9aec2d31-b3db-463e-a2f7-5e22ee03d2b0</td>\n",
" <td>2023-02-11T11:12:41.558670+00:00</td>\n",
" <td>Vegetari euskarazko ahotsa Felix Arkarazo akto...</td>\n",
" <td>assistant</td>\n",
" <td>eu</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>2.0</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1', '_skip_labeling'], 'count': [1...</td>\n",
" <td>{'name': ['spam', 'fails_task', 'lang_mismatch...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" message_id \\\n",
"84432 47ba67f2-f711-4feb-91ff-0a0ffe556fe5 \n",
"84433 d3946880-4402-42a8-8a9e-6dab5efa787f \n",
"84434 4e8a349d-7781-42ae-8868-1ecf5df4c2cb \n",
"84435 ca45d4bd-2da7-4d56-beec-bf9f772e8426 \n",
"84436 6ea871e7-7582-4607-8b0a-84e4d0169868 \n",
"\n",
" parent_id \\\n",
"84432 2e934881-260c-4a6c-8f09-66e0312f84ac \n",
"84433 None \n",
"84434 d3946880-4402-42a8-8a9e-6dab5efa787f \n",
"84435 d3946880-4402-42a8-8a9e-6dab5efa787f \n",
"84436 d3946880-4402-42a8-8a9e-6dab5efa787f \n",
"\n",
" user_id created_date \\\n",
"84432 55e23953-c333-4b02-a459-c99d2c7172a3 2023-02-21T17:18:06.837900+00:00 \n",
"84433 ad5d3a46-2f52-4270-89a9-a6b1d180d809 2023-02-10T13:49:30.080447+00:00 \n",
"84434 9f3e4da7-7d7a-4cf9-9d35-f59d00de240d 2023-02-11T15:26:37.799100+00:00 \n",
"84435 055ac9a6-80e3-4ef5-b89a-edd88e261208 2023-02-12T19:23:29.730612+00:00 \n",
"84436 9aec2d31-b3db-463e-a2f7-5e22ee03d2b0 2023-02-11T11:12:41.558670+00:00 \n",
"\n",
" text role lang \\\n",
"84432 James Potter eta Lily Potter ziren Harry Potte... assistant eu \n",
"84433 Nork jarri zion ahotsa Dragoi Bolako Vegetari ... prompter eu \n",
"84434 Dragoi bolaren aurreneko denboraldian ez da Ve... assistant eu \n",
"84435 Dragoi Bolako Vegetari euskarazko ahotsa jarri... assistant eu \n",
"84436 Vegetari euskarazko ahotsa Felix Arkarazo akto... assistant eu \n",
"\n",
" review_count review_result deleted rank synthetic model_name \\\n",
"84432 3 True False 2.0 False None \n",
"84433 3 True False NaN False None \n",
"84434 3 True False 0.0 False None \n",
"84435 3 True False 1.0 False None \n",
"84436 3 True False 2.0 False None \n",
"\n",
" detoxify message_tree_id tree_state \\\n",
"84432 None 2e934881-260c-4a6c-8f09-66e0312f84ac ready_for_export \n",
"84433 None d3946880-4402-42a8-8a9e-6dab5efa787f ready_for_export \n",
"84434 None d3946880-4402-42a8-8a9e-6dab5efa787f ready_for_export \n",
"84435 None d3946880-4402-42a8-8a9e-6dab5efa787f ready_for_export \n",
"84436 None d3946880-4402-42a8-8a9e-6dab5efa787f ready_for_export \n",
"\n",
" emojis \\\n",
"84432 {'name': ['+1'], 'count': [1]} \n",
"84433 {'name': ['+1', '_skip_reply'], 'count': [5, 4]} \n",
"84434 {'name': ['+1'], 'count': [1]} \n",
"84435 {'name': ['+1'], 'count': [1]} \n",
"84436 {'name': ['+1', '_skip_labeling'], 'count': [1... \n",
"\n",
" labels \n",
"84432 {'name': ['spam', 'fails_task', 'lang_mismatch... \n",
"84433 {'name': ['spam', 'lang_mismatch', 'pii', 'not... \n",
"84434 {'name': ['spam', 'fails_task', 'lang_mismatch... \n",
"84435 {'name': ['spam', 'lang_mismatch', 'quality'],... \n",
"84436 {'name': ['spam', 'fails_task', 'lang_mismatch... "
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.tail()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "5117c4c4-4cbb-40aa-ab61-ef08b3c8bb93",
"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>message_id</th>\n",
" <th>parent_id</th>\n",
" <th>user_id</th>\n",
" <th>created_date</th>\n",
" <th>text</th>\n",
" <th>role</th>\n",
" <th>lang</th>\n",
" <th>review_count</th>\n",
" <th>review_result</th>\n",
" <th>deleted</th>\n",
" <th>rank</th>\n",
" <th>synthetic</th>\n",
" <th>model_name</th>\n",
" <th>detoxify</th>\n",
" <th>message_tree_id</th>\n",
" <th>tree_state</th>\n",
" <th>emojis</th>\n",
" <th>labels</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>6ab24d72-0181-4594-a9cd-deaf170242fb</td>\n",
" <td>None</td>\n",
" <td>c3fe8c76-fc30-4fa7-b7f8-c492f5967d18</td>\n",
" <td>2023-02-05T14:23:50.983374+00:00</td>\n",
" <td>Can you write a short introduction about the r...</td>\n",
" <td>prompter</td>\n",
" <td>en</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>{'toxicity': 0.00044308538781479, 'severe_toxi...</td>\n",
" <td>6ab24d72-0181-4594-a9cd-deaf170242fb</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1', '_skip_reply', '_skip_ranking'...</td>\n",
" <td>{'name': ['spam', 'lang_mismatch', 'pii', 'not...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>c8e83833-ecbc-44fe-b6db-735228c25a1c</td>\n",
" <td>6ab24d72-0181-4594-a9cd-deaf170242fb</td>\n",
" <td>2c96e467-66f0-4be7-9693-bda51356a424</td>\n",
" <td>2023-02-06T13:50:44.657083+00:00</td>\n",
" <td>\"Monopsony\" refers to a market structure where...</td>\n",
" <td>assistant</td>\n",
" <td>en</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>0.0</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>{'toxicity': 0.00026396565954200923, 'severe_t...</td>\n",
" <td>6ab24d72-0181-4594-a9cd-deaf170242fb</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1', '_skip_labeling'], 'count': [3...</td>\n",
" <td>{'name': ['spam', 'fails_task', 'lang_mismatch...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6708c47f-05c9-4346-b3d2-40b2bd24fde4</td>\n",
" <td>c8e83833-ecbc-44fe-b6db-735228c25a1c</td>\n",
" <td>2c96e467-66f0-4be7-9693-bda51356a424</td>\n",
" <td>2023-02-06T18:48:49.391686+00:00</td>\n",
" <td>Now explain it to a dog</td>\n",
" <td>prompter</td>\n",
" <td>en</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>{'toxicity': 0.03648477792739868, 'severe_toxi...</td>\n",
" <td>6ab24d72-0181-4594-a9cd-deaf170242fb</td>\n",
" <td>ready_for_export</td>\n",
" <td>None</td>\n",
" <td>{'name': ['spam', 'lang_mismatch', 'pii', 'not...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>343ee2d4-87ae-41fd-a768-bdd65959dc4a</td>\n",
" <td>6ab24d72-0181-4594-a9cd-deaf170242fb</td>\n",
" <td>49ddcb0d-6588-43bd-858d-19c577f12e7b</td>\n",
" <td>2023-02-06T13:37:56.044680+00:00</td>\n",
" <td>Monopsony is a market structure in which there...</td>\n",
" <td>assistant</td>\n",
" <td>en</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>{'toxicity': 0.0008866374846547842, 'severe_to...</td>\n",
" <td>6ab24d72-0181-4594-a9cd-deaf170242fb</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1', '_skip_reply', '_skip_labeling...</td>\n",
" <td>{'name': ['spam', 'fails_task', 'lang_mismatch...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>18145bf4-37fd-4ac0-80f5-6108b5f2b365</td>\n",
" <td>343ee2d4-87ae-41fd-a768-bdd65959dc4a</td>\n",
" <td>e10e99a0-38ac-4b07-bf5d-4427696e4e0d</td>\n",
" <td>2023-02-06T18:52:51.428543+00:00</td>\n",
" <td>How can one fight back when a monospony had be...</td>\n",
" <td>prompter</td>\n",
" <td>en</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>{'toxicity': 0.0009362137061543763, 'severe_to...</td>\n",
" <td>6ab24d72-0181-4594-a9cd-deaf170242fb</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1'], 'count': [1]}</td>\n",
" <td>{'name': ['spam', 'lang_mismatch', 'pii', 'not...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84432</th>\n",
" <td>47ba67f2-f711-4feb-91ff-0a0ffe556fe5</td>\n",
" <td>2e934881-260c-4a6c-8f09-66e0312f84ac</td>\n",
" <td>55e23953-c333-4b02-a459-c99d2c7172a3</td>\n",
" <td>2023-02-21T17:18:06.837900+00:00</td>\n",
" <td>James Potter eta Lily Potter ziren Harry Potte...</td>\n",
" <td>assistant</td>\n",
" <td>eu</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>2.0</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>2e934881-260c-4a6c-8f09-66e0312f84ac</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1'], 'count': [1]}</td>\n",
" <td>{'name': ['spam', 'fails_task', 'lang_mismatch...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84433</th>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>None</td>\n",
" <td>ad5d3a46-2f52-4270-89a9-a6b1d180d809</td>\n",
" <td>2023-02-10T13:49:30.080447+00:00</td>\n",
" <td>Nork jarri zion ahotsa Dragoi Bolako Vegetari ...</td>\n",
" <td>prompter</td>\n",
" <td>eu</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1', '_skip_reply'], 'count': [5, 4]}</td>\n",
" <td>{'name': ['spam', 'lang_mismatch', 'pii', 'not...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84434</th>\n",
" <td>4e8a349d-7781-42ae-8868-1ecf5df4c2cb</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>9f3e4da7-7d7a-4cf9-9d35-f59d00de240d</td>\n",
" <td>2023-02-11T15:26:37.799100+00:00</td>\n",
" <td>Dragoi bolaren aurreneko denboraldian ez da Ve...</td>\n",
" <td>assistant</td>\n",
" <td>eu</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>0.0</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1'], 'count': [1]}</td>\n",
" <td>{'name': ['spam', 'fails_task', 'lang_mismatch...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84435</th>\n",
" <td>ca45d4bd-2da7-4d56-beec-bf9f772e8426</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>055ac9a6-80e3-4ef5-b89a-edd88e261208</td>\n",
" <td>2023-02-12T19:23:29.730612+00:00</td>\n",
" <td>Dragoi Bolako Vegetari euskarazko ahotsa jarri...</td>\n",
" <td>assistant</td>\n",
" <td>eu</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1'], 'count': [1]}</td>\n",
" <td>{'name': ['spam', 'lang_mismatch', 'quality'],...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84436</th>\n",
" <td>6ea871e7-7582-4607-8b0a-84e4d0169868</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>9aec2d31-b3db-463e-a2f7-5e22ee03d2b0</td>\n",
" <td>2023-02-11T11:12:41.558670+00:00</td>\n",
" <td>Vegetari euskarazko ahotsa Felix Arkarazo akto...</td>\n",
" <td>assistant</td>\n",
" <td>eu</td>\n",
" <td>3</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>2.0</td>\n",
" <td>False</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>d3946880-4402-42a8-8a9e-6dab5efa787f</td>\n",
" <td>ready_for_export</td>\n",
" <td>{'name': ['+1', '_skip_labeling'], 'count': [1...</td>\n",
" <td>{'name': ['spam', 'fails_task', 'lang_mismatch...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>84437 rows 脳 18 columns</p>\n",
"</div>"
],
"text/plain": [
" message_id \\\n",
"0 6ab24d72-0181-4594-a9cd-deaf170242fb \n",
"1 c8e83833-ecbc-44fe-b6db-735228c25a1c \n",
"2 6708c47f-05c9-4346-b3d2-40b2bd24fde4 \n",
"3 343ee2d4-87ae-41fd-a768-bdd65959dc4a \n",
"4 18145bf4-37fd-4ac0-80f5-6108b5f2b365 \n",
"... ... \n",
"84432 47ba67f2-f711-4feb-91ff-0a0ffe556fe5 \n",
"84433 d3946880-4402-42a8-8a9e-6dab5efa787f \n",
"84434 4e8a349d-7781-42ae-8868-1ecf5df4c2cb \n",
"84435 ca45d4bd-2da7-4d56-beec-bf9f772e8426 \n",
"84436 6ea871e7-7582-4607-8b0a-84e4d0169868 \n",
"\n",
" parent_id \\\n",
"0 None \n",
"1 6ab24d72-0181-4594-a9cd-deaf170242fb \n",
"2 c8e83833-ecbc-44fe-b6db-735228c25a1c \n",
"3 6ab24d72-0181-4594-a9cd-deaf170242fb \n",
"4 343ee2d4-87ae-41fd-a768-bdd65959dc4a \n",
"... ... \n",
"84432 2e934881-260c-4a6c-8f09-66e0312f84ac \n",
"84433 None \n",
"84434 d3946880-4402-42a8-8a9e-6dab5efa787f \n",
"84435 d3946880-4402-42a8-8a9e-6dab5efa787f \n",
"84436 d3946880-4402-42a8-8a9e-6dab5efa787f \n",
"\n",
" user_id created_date \\\n",
"0 c3fe8c76-fc30-4fa7-b7f8-c492f5967d18 2023-02-05T14:23:50.983374+00:00 \n",
"1 2c96e467-66f0-4be7-9693-bda51356a424 2023-02-06T13:50:44.657083+00:00 \n",
"2 2c96e467-66f0-4be7-9693-bda51356a424 2023-02-06T18:48:49.391686+00:00 \n",
"3 49ddcb0d-6588-43bd-858d-19c577f12e7b 2023-02-06T13:37:56.044680+00:00 \n",
"4 e10e99a0-38ac-4b07-bf5d-4427696e4e0d 2023-02-06T18:52:51.428543+00:00 \n",
"... ... ... \n",
"84432 55e23953-c333-4b02-a459-c99d2c7172a3 2023-02-21T17:18:06.837900+00:00 \n",
"84433 ad5d3a46-2f52-4270-89a9-a6b1d180d809 2023-02-10T13:49:30.080447+00:00 \n",
"84434 9f3e4da7-7d7a-4cf9-9d35-f59d00de240d 2023-02-11T15:26:37.799100+00:00 \n",
"84435 055ac9a6-80e3-4ef5-b89a-edd88e261208 2023-02-12T19:23:29.730612+00:00 \n",
"84436 9aec2d31-b3db-463e-a2f7-5e22ee03d2b0 2023-02-11T11:12:41.558670+00:00 \n",
"\n",
" text role lang \\\n",
"0 Can you write a short introduction about the r... prompter en \n",
"1 \"Monopsony\" refers to a market structure where... assistant en \n",
"2 Now explain it to a dog prompter en \n",
"3 Monopsony is a market structure in which there... assistant en \n",
"4 How can one fight back when a monospony had be... prompter en \n",
"... ... ... ... \n",
"84432 James Potter eta Lily Potter ziren Harry Potte... assistant eu \n",
"84433 Nork jarri zion ahotsa Dragoi Bolako Vegetari ... prompter eu \n",
"84434 Dragoi bolaren aurreneko denboraldian ez da Ve... assistant eu \n",
"84435 Dragoi Bolako Vegetari euskarazko ahotsa jarri... assistant eu \n",
"84436 Vegetari euskarazko ahotsa Felix Arkarazo akto... assistant eu \n",
"\n",
" review_count review_result deleted rank synthetic model_name \\\n",
"0 3 True False NaN False None \n",
"1 3 True False 0.0 False None \n",
"2 3 True False NaN False None \n",
"3 3 True False 1.0 False None \n",
"4 3 True False NaN False None \n",
"... ... ... ... ... ... ... \n",
"84432 3 True False 2.0 False None \n",
"84433 3 True False NaN False None \n",
"84434 3 True False 0.0 False None \n",
"84435 3 True False 1.0 False None \n",
"84436 3 True False 2.0 False None \n",
"\n",
" detoxify \\\n",
"0 {'toxicity': 0.00044308538781479, 'severe_toxi... \n",
"1 {'toxicity': 0.00026396565954200923, 'severe_t... \n",
"2 {'toxicity': 0.03648477792739868, 'severe_toxi... \n",
"3 {'toxicity': 0.0008866374846547842, 'severe_to... \n",
"4 {'toxicity': 0.0009362137061543763, 'severe_to... \n",
"... ... \n",
"84432 None \n",
"84433 None \n",
"84434 None \n",
"84435 None \n",
"84436 None \n",
"\n",
" message_tree_id tree_state \\\n",
"0 6ab24d72-0181-4594-a9cd-deaf170242fb ready_for_export \n",
"1 6ab24d72-0181-4594-a9cd-deaf170242fb ready_for_export \n",
"2 6ab24d72-0181-4594-a9cd-deaf170242fb ready_for_export \n",
"3 6ab24d72-0181-4594-a9cd-deaf170242fb ready_for_export \n",
"4 6ab24d72-0181-4594-a9cd-deaf170242fb ready_for_export \n",
"... ... ... \n",
"84432 2e934881-260c-4a6c-8f09-66e0312f84ac ready_for_export \n",
"84433 d3946880-4402-42a8-8a9e-6dab5efa787f ready_for_export \n",
"84434 d3946880-4402-42a8-8a9e-6dab5efa787f ready_for_export \n",
"84435 d3946880-4402-42a8-8a9e-6dab5efa787f ready_for_export \n",
"84436 d3946880-4402-42a8-8a9e-6dab5efa787f ready_for_export \n",
"\n",
" emojis \\\n",
"0 {'name': ['+1', '_skip_reply', '_skip_ranking'... \n",
"1 {'name': ['+1', '_skip_labeling'], 'count': [3... \n",
"2 None \n",
"3 {'name': ['+1', '_skip_reply', '_skip_labeling... \n",
"4 {'name': ['+1'], 'count': [1]} \n",
"... ... \n",
"84432 {'name': ['+1'], 'count': [1]} \n",
"84433 {'name': ['+1', '_skip_reply'], 'count': [5, 4]} \n",
"84434 {'name': ['+1'], 'count': [1]} \n",
"84435 {'name': ['+1'], 'count': [1]} \n",
"84436 {'name': ['+1', '_skip_labeling'], 'count': [1... \n",
"\n",
" labels \n",
"0 {'name': ['spam', 'lang_mismatch', 'pii', 'not... \n",
"1 {'name': ['spam', 'fails_task', 'lang_mismatch... \n",
"2 {'name': ['spam', 'lang_mismatch', 'pii', 'not... \n",
"3 {'name': ['spam', 'fails_task', 'lang_mismatch... \n",
"4 {'name': ['spam', 'lang_mismatch', 'pii', 'not... \n",
"... ... \n",
"84432 {'name': ['spam', 'fails_task', 'lang_mismatch... \n",
"84433 {'name': ['spam', 'lang_mismatch', 'pii', 'not... \n",
"84434 {'name': ['spam', 'fails_task', 'lang_mismatch... \n",
"84435 {'name': ['spam', 'lang_mismatch', 'quality'],... \n",
"84436 {'name': ['spam', 'fails_task', 'lang_mismatch... \n",
"\n",
"[84437 rows x 18 columns]"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "7da865e2-28c3-4b5f-b519-e414e047e802",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(40396,)"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.parent_id.unique().shape"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "3d9f97ac-cc85-48a5-86ac-0220c1cd8749",
"metadata": {},
"outputs": [],
"source": [
"root_ids = df[df.parent_id.astype(str) == \"None\"][\"message_id\"].to_list()"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "25c0819a-04f1-4ddb-ab53-03b63e144a37",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"9846"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"root_ids.__len__()"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "12fc1dc2-4509-4bbe-b51f-2cc0d5b4c656",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(9846,)"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[\"message_tree_id\"].unique().shape"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "f05079a1-07da-445e-b879-b7c6eda27948",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count\n",
"4 3991\n",
"12 2777\n",
"13 1026\n",
"9 828\n",
"5 330\n",
"14 323\n",
"10 136\n",
"15 121\n",
"16 59\n",
"6 51\n",
"11 48\n",
"17 44\n",
"18 22\n",
"19 13\n",
"20 12\n",
"7 10\n",
"26 7\n",
"25 5\n",
"24 5\n",
"21 5\n",
"8 3\n",
"28 3\n",
"27 3\n",
"34 2\n",
"40 2\n",
"22 2\n",
"23 2\n",
"3 1\n",
"56 1\n",
"55 1\n",
"29 1\n",
"30 1\n",
"31 1\n",
"32 1\n",
"35 1\n",
"36 1\n",
"37 1\n",
"41 1\n",
"42 1\n",
"46 1\n",
"47 1\n",
"52 1\n",
"2 1\n",
"Name: count, dtype: int64"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[\"message_tree_id\"].value_counts().value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "2423d4da-939a-4ffe-b0b8-cb004df106d5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Axes: >"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"df[\"message_tree_id\"].value_counts().hist(bins=20)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "7730a5d8-0d49-4672-8e12-cd07d4b5c968",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_1954595/2136755740.py:3: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" df_message_tree[\"role\"] = df_message_tree[\"role\"].map({\"prompter\":\"user\", \"assistant\": \"assistant\"})\n"
]
}
],
"source": [
"for message_tree_id in df[\"message_tree_id\"].unique().tolist():\n",
" df_message_tree = df.query(f\"message_tree_id == '{message_tree_id}'\")#.sort_values(\"created_date\")\n",
" df_message_tree[\"role\"] = df_message_tree[\"role\"].map({\"prompter\":\"user\", \"assistant\": \"assistant\"})\n",
" break"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "3c71c483-abc9-4b92-9aeb-9a9513abcd78",
"metadata": {
"collapsed": true,
"jupyter": {
"outputs_hidden": true
},
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<|im_start|>user\n",
"Can you write a short introduction about the relevance of the term \"monopsony\" in economics? Please use examples related to potential monopsonies in the labour market and cite relevant research.<|im_end|>\n",
"***********************************************************\n",
"<|im_start|>assistant\n",
"\"Monopsony\" refers to a market structure where there is only one buyer for a particular good or service. In economics, this term is particularly relevant in the labor market, where a monopsony employer has significant power over the wages and working conditions of their employees. The presence of a monopsony can result in lower wages and reduced employment opportunities for workers, as the employer has little incentive to increase wages or provide better working conditions.\n",
"\n",
"Recent research has identified potential monopsonies in industries such as retail and fast food, where a few large companies control a significant portion of the market (Bivens & Mishel, 2013). In these industries, workers often face low wages, limited benefits, and reduced bargaining power, leading to a situation where they are dependent on the employer for their livelihood. This dependence can result in further suppression of wages and a decline in working conditions.\n",
"\n",
"Overall, the concept of monopsony is essential to understanding the dynamics of labor markets and the impact of market power on workers. Further research is needed to understand the extent and impact of monopsonies on the economy and to develop policies to address this issue.\n",
"\n",
"References:\n",
"Bivens, J., & Mishel, L. (2013). The Pay of Corporate Executives and Financial Professionals as Evidence of Rents in Top 1 Percent Incomes. Journal of Economic Perspectives, 27(3), 57-78.<|im_end|>\n",
"***********************************************************\n",
"<|im_start|>user\n",
"Now explain it to a dog<|im_end|>\n",
"***********************************************************\n",
"<|im_start|>assistant\n",
"Monopsony is a market structure in which there is a single buyer in a market. In the context of labor markets, a monopsony occurs when there is only one employer in a particular industry or geographic area, giving that employer significant power over the wages and working conditions of workers. This results in a situation where the employer has the ability to suppress wages and reduce the bargaining power of workers.\n",
"\n",
"Research has shown that the existence of monopsony power in labor markets can have negative effects on workers, such as lower wages, reduced benefits, and limited job opportunities. For example, a study by Autor, Dorn, and Hanson (2013) found evidence of monopsony power in certain U.S. labor markets, resulting in lower wages and reduced job opportunities for workers. Similarly, another study by Bharadwaj, Black, and Kolesnikova (2019) found that the presence of a single dominant employer in a local labor market was associated with lower wages for workers.<|im_end|>\n",
"***********************************************************\n",
"<|im_start|>user\n",
"How can one fight back when a monospony had been created?<|im_end|>\n",
"***********************************************************\n",
"<|im_start|>assistant\n",
"Monopsony refers to a market structure where there is only one buyer of a good or service. In the context of labor markets, a monopsony occurs when there is only one employer in a particular geographic area or industry, giving them significant power to set wages and working conditions. Research has shown that the existence of monopsonies can lead to lower wages and reduced job opportunities for workers. For example, a study by the National Bureau of Economic Research found that in industries with high levels of concentration, workers earn lower wages and are less likely to receive benefits such as health insurance.<|im_end|>\n",
"***********************************************************\n",
"<|im_start|>user\n",
"What can be done at a regulatory level to ensure, in a monopsony, that the power over the employees isn't abused? List a few options and focus on the organs that should act.<|im_end|>\n",
"***********************************************************\n",
"<|im_start|>assistant\n",
"Here are some potential regulatory options to address monopsony power over employees:\n",
"\n",
"- Antitrust enforcement agencies like the FTC or DOJ could investigate and take action against dominant employers that are abusing their market power to suppress wages or worsen working conditions. They could force divestitures or other structural remedies.\n",
"- Labor standards agencies could set industry-specific minimum wage floors or other regulations around compensation and working conditions. This would reduce the ability of dominant employers to push wages/conditions below certain thresholds.\n",
"- Sector-specific regulators could impose requirements around how companies hire, compensate, and treat workers. For example, banking regulators could prohibit abusive practices by dominant banks with regard to their employees.\n",
"- Legislatures could pass laws<|im_end|>\n",
"***********************************************************\n",
"<|im_start|>assistant\n",
"Regulatory intervention can be used to address the negative consequences of monopsony power in the labor market. A few options include:\n",
"\n",
"1. Antitrust enforcement: Antitrust laws can be used to prevent firms from engaging in practices that limit competition and suppress wages. The antitrust division of the Department of Justice and the Federal Trade Commission (FTC) are responsible for enforcing these laws.\n",
"\n",
"2. Labor standards and protections: Governments can set minimum wage standards and other labor protections to ensure that workers are paid a fair wage, even in industries dominated by a single buyer. The U.S. Department of Labor is responsible for enforcing these standards.\n",
"\n",
"3. Occupational licensing reform: Occupational licensing requirements can restrict worker mobility and increase the bargaining power of employers. Reforms to licensing requirements can reduce these barriers and increase competition in the labor market. State governments typically regulate occupational licensing.\n",
"\n",
"4. Collective bargaining rights: Collective bargaining by workers can increase their bargaining power and lead to higher wages. Governments can protect and promote collective bargaining rights to counteract the effects of monopsony power. The National Labor Relations Board is responsible for enforcing workers' rights to engage in collective bargaining in the U.S.\n",
"\n",
"These are just a few examples of regulatory options that can be used to address monopsony power in the labor market. The specific actions taken will depend on the particular circumstances and context of each case.<|im_end|>\n",
"***********************************************************\n",
"<|im_start|>assistant\n",
"Yes, that's correct. Keeping the code for the TESR and the registration code in the same file can make it easier to manage and maintain the code. The ExampleMod class acts as a container for the TESR code, providing a convenient and logical grouping. The functionality of the code remains unchanged, and the TESR will still be properly registered and used to render the custom tile entities in the game.<|im_end|>\n",
"***********************************************************\n",
"<|im_start|>user\n",
"I would imagine this is similar or even the same as a \"monopoly\" but I am not sure.\n",
"\n",
"Assuming that this some kind of \"final state\" of a particular industry or even an entire economy, give me some larger historical examples of this kind of structure consolidating over time, and describe what circumstances are common prerequisite.<|im_end|>\n",
"***********************************************************\n",
"<|im_start|>assistant\n",
"Bouguereau died in 1905, so it is unlikely that any of his direct descendants are still alive. However, his works continue to be popular and are sold at auction and through art dealers. It is possible that some indirect descendants may benefit from the sale of his works.<|im_end|>\n",
"***********************************************************\n"
]
}
],
"source": [
"# ChatML format\n",
"templates = {\n",
" \"assistant\": \"<|im_start|>assistant\\n{msg}<|im_end|>\", # message by assistant\n",
" \"user\": \"<|im_start|>user\\n{msg}<|im_end|>\" # message by user\n",
"}\n",
"\n",
"for _, (text, role) in df_message_tree[[\"text\", \"role\"]].iterrows():\n",
" text = templates[role].format(msg=text)\n",
" print(text)\n",
" print(\"***********************************************************\")\n",
" # print(f\"Text: {text}\")\n",
" # print(f\"Role: {role}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f3df6e39",
"metadata": {},
"outputs": [],
"source": [
"messages = []\n",
"for message_tree_id in df[\"message_tree_id\"].unique().tolist():\n",
" df_message_tree = df.query(f\"message_tree_id == '{message_tree_id}'\")#.sort_values(\"created_date\")\n",
" df_message_tree[\"role\"] = df_message_tree[\"role\"].map({\"prompter\":\"user\", \"assistant\": \"assistant\"})\n",
" \n",
" new_message = \"\"\n",
" for _, (text, role) in df_message_tree[[\"text\", \"role\"]].iterrows():\n",
" text = templates[role].format(msg=text)\n",
" new_message += f\"{text}\\n\"\n",
" messages.append({\"text\": new_message})"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "f0721e8b-e19e-46d1-83d8-d45f0a2d8f31",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"87"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(new_message.split())"
]
},
{
"cell_type": "code",
"execution_count": 41,
"id": "1d10160f-780e-4a57-86f5-cc435ee65660",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"9846"
]
},
"execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(messages)"
]
},
{
"cell_type": "code",
"execution_count": 42,
"id": "f50d9397-8bc8-4663-9204-9543aae1344b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'text': '<|im_start|>user\\nM茅todo del Perceptr贸n bicl谩sico: definici贸n y variantes del m茅todo. 驴c贸mo se aplicar铆a\\nal caso multicl谩sico?, 驴se podr铆a utilizar con patrones que s贸lo son cuadr谩ticamente\\nseparables?<|im_end|>\\n<|im_start|>assistant\\nEl m茅todo del Perceptr贸n bicl谩sico es un algoritmo de aprendizaje autom谩tico que se utiliza para clasificar patrones en dos categor铆as. El objetivo del Perceptr贸n es encontrar un hiperplano que separe las dos clases en el espacio de caracter铆sticas.\\n\\nEn el Perceptr贸n bicl谩sico, se utilizan los siguientes pasos para entrenar el modelo:\\n\\n1. Inicializar los pesos con valores aleatorios.\\n2. Seleccionar un patr贸n aleatorio del conjunto de entrenamiento y calcular la salida del Perceptr贸n.\\n3. Actualizar los pesos si la salida del Perceptr贸n es incorrecta.\\n4. Repetir los pasos 2 y 3 hasta que se alcance un criterio de parada.\\n\\nHay varias variantes del m茅todo del Perceptr贸n bicl谩sico, incluyendo el Perceptr贸n con margen, el Perceptr贸n promedio, el Perceptr贸n relajado y el Perceptr贸n de m煤ltiples capas.\\n\\nEn el caso multiclase, se puede utilizar una variante del Perceptr贸n bicl谩sico conocida como Perceptr贸n multicapa, que utiliza varias capas de neuronas para clasificar patrones en m煤ltiples categor铆as. Cada capa se encarga de realizar una transformaci贸n no lineal de los datos de entrada y de propagar la informaci贸n a la siguiente capa hasta llegar a la capa de salida, donde se realiza la clasificaci贸n.\\n\\nEn cuanto a si se puede utilizar el Perceptr贸n bicl谩sico con patrones que s贸lo son cuadr谩ticamente separables, la respuesta es que no. El Perceptr贸n bicl谩sico s贸lo puede separar patrones linealmente separables. Para patrones cuadr谩ticamente separables se pueden utilizar otros algoritmos de clasificaci贸n como SVM, regresi贸n log铆stica, 谩rboles de decisi贸n, entre otros.<|im_end|>\\n<|im_start|>assistant\\nEl m茅todo del Perceptr贸n bicl谩sico es un algoritmo de aprendizaje supervisado utilizado para la clasificaci贸n de patrones. Este m茅todo es una variante del Perceptr贸n original, que fue propuesto por Frank Rosenblatt en 1957.\\n\\nEn el caso del Perceptr贸n bicl谩sico, se considera una funci贸n de activaci贸n binaria que clasifica los patrones en dos clases diferentes. El objetivo del algoritmo es encontrar un hiperplano que pueda separar los patrones de las dos clases en el espacio de caracter铆sticas.\\n\\nExisten diferentes variantes del m茅todo del Perceptr贸n bicl谩sico, como por ejemplo:\\n\\n Perceptr贸n de Rosenblatt: es la versi贸n original del algoritmo, que utiliza una regla de aprendizaje basada en el descenso de gradiente estoc谩stico.\\n\\n Perceptr贸n de Widrow-Hoff: esta variante del Perceptr贸n utiliza una regla de aprendizaje basada en la correcci贸n del error, que se aplica a cada patr贸n individualmente.\\n\\n Perceptr贸n de margen m谩ximo: esta variante del Perceptr贸n intenta encontrar el hiperplano que separa las dos clases con el margen m谩ximo posible.\\n\\nEn el caso multicl谩sico, el m茅todo del Perceptr贸n bicl谩sico se puede utilizar utilizando una estrategia conocida como \"uno contra todos\" o \"uno contra el resto\". En esta estrategia, se entrena un clasificador Perceptr贸n bicl谩sico para cada una de las clases, y luego se selecciona la clase que tenga la mayor puntuaci贸n.\\n\\nEn cuanto a si se podr铆a utilizar con patrones que s贸lo son cuadr谩ticamente separables, el m茅todo del Perceptr贸n bicl谩sico no es adecuado para estos casos, ya que s贸lo puede separar patrones linealmente. Para patrones cuadr谩ticamente separables se utilizan otros algoritmos de clasificaci贸n, como el SVM (M谩quinas de Vectores de Soporte) que pueden separar patrones no lineales.<|im_end|>\\n<|im_start|>assistant\\nEl m茅todo del perceptr贸n binario es un algoritmo de aprendizaje supervisado para clasificadores binarios, es decir, pueden distinguir entre dos clases de muestras. Un perceptr贸n consta de una neurona artificial que toma un conjunto de entradas, suma sus pesos y aplica una funci贸n de umbral para producir la salida. La regla de aprendizaje del perceptr贸n es un proceso de ajuste de los pesos de entrada para minimizar el error de clasificaci贸n.\\nPara aplicar el m茅todo del perceptr贸n al caso multiclase, es decir, cuando hay m谩s de dos clases muestrales, se pueden utilizar diferentes estrategias, como por ejemplo:\\n\\nUtilice un perceptr贸n por clase y asigne la muestra a la clase con el perceptr贸n de puntuaci贸n m谩s alta. Utilice un conjunto de perceptrones que generen un binario para cada clase y asigne la plantilla a la clase cuyo c贸digo coincida con la salida del perceptr贸n. Usando un perceptr贸n multicapa, que consiste en una red neuronal artificial organizada en capas, donde la salida de una capa act煤a como entrada a la siguiente capa. El m茅todo del perceptr贸n de dos capas solo puede clasificar im谩genes que son linealmente separables, es decir, im谩genes que pueden separarse por una l铆nea recta. Si las muestras solo pueden descomponerse perpendicularmente, es decir, pueden descomponerse mediante una curva, entonces un perceptr贸n multicapa con una funci贸n de activaci贸n no lineal, como una tangente sigmoidea o una hip茅rbola. Esto permite que la red neuronal aprenda funciones no lineales y clasifique patrones m谩s complejos.<|im_end|>\\n'}"
]
},
"execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"messages[4]"
]
},
{
"cell_type": "code",
"execution_count": 43,
"id": "459d23c4-6bad-444e-a025-767f6cba848e",
"metadata": {},
"outputs": [],
"source": [
"import datasets"
]
},
{
"cell_type": "code",
"execution_count": 45,
"id": "a13e606b-d34d-473f-beba-e096b24e9824",
"metadata": {},
"outputs": [],
"source": [
"new_dataset = datasets.Dataset.from_list(messages)"
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "5bc9fa85-74b4-4db3-b675-281bdd13e238",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Dataset({\n",
" features: ['text'],\n",
" num_rows: 9846\n",
"})"
]
},
"execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"new_dataset"
]
},
{
"cell_type": "code",
"execution_count": 48,
"id": "002313f6-299f-4790-a803-a05c91872a5a",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "18a4f79af7094e8681d24a66d15ca687",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Pushing dataset shards to the dataset hub: 0%| | 0/1 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "0d8d2985a0af4786a10711a10b8e7fb0",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Creating parquet from Arrow format: 0%| | 0/10 [00:00<?, ?ba/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"new_dataset.push_to_hub(\"RaviNaik/oasst1-chatml\", token=\"\")"
]
},
{
"cell_type": "code",
"execution_count": 49,
"id": "7cb91c43-da77-4388-b8a1-7b00fb838fc4",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "66004e71272545a69f1cbd514d6b37d6",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Downloading readme: 0%| | 0.00/745 [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "64d5edf8986e47589f4910add8635d11",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Downloading data files: 0%| | 0/1 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "3a5bdc910f9749318448261652be48b8",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Downloading data: 0%| | 0.00/25.0M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "73b105b4daad4df18bc2effc1a30a39b",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Extracting data files: 0%| | 0/1 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "1bdd3ebca4fb4b0db8940e1a814e6ba0",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Generating train split: 0%| | 0/9846 [00:00<?, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"my_dataset = load_dataset(\"RaviNaik/oasst1-chatml\", split=\"train\")"
]
},
{
"cell_type": "code",
"execution_count": 50,
"id": "eed20b68-9cd4-4b02-a483-a8fcd036bcfb",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Dataset({\n",
" features: ['text'],\n",
" num_rows: 9846\n",
"})"
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"my_dataset"
]
},
{
"cell_type": "code",
"execution_count": 51,
"id": "acb3bbeb-612a-45d0-8f31-85604b438884",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'text': '<|im_start|>user\\nCan you write a short introduction about the relevance of the term \"monopsony\" in economics? Please use examples related to potential monopsonies in the labour market and cite relevant research.<|im_end|>\\n<|im_start|>assistant\\n\"Monopsony\" refers to a market structure where there is only one buyer for a particular good or service. In economics, this term is particularly relevant in the labor market, where a monopsony employer has significant power over the wages and working conditions of their employees. The presence of a monopsony can result in lower wages and reduced employment opportunities for workers, as the employer has little incentive to increase wages or provide better working conditions.\\n\\nRecent research has identified potential monopsonies in industries such as retail and fast food, where a few large companies control a significant portion of the market (Bivens & Mishel, 2013). In these industries, workers often face low wages, limited benefits, and reduced bargaining power, leading to a situation where they are dependent on the employer for their livelihood. This dependence can result in further suppression of wages and a decline in working conditions.\\n\\nOverall, the concept of monopsony is essential to understanding the dynamics of labor markets and the impact of market power on workers. Further research is needed to understand the extent and impact of monopsonies on the economy and to develop policies to address this issue.\\n\\nReferences:\\nBivens, J., & Mishel, L. (2013). The Pay of Corporate Executives and Financial Professionals as Evidence of Rents in Top 1 Percent Incomes. Journal of Economic Perspectives, 27(3), 57-78.<|im_end|>\\n<|im_start|>user\\nNow explain it to a dog<|im_end|>\\n<|im_start|>assistant\\nMonopsony is a market structure in which there is a single buyer in a market. In the context of labor markets, a monopsony occurs when there is only one employer in a particular industry or geographic area, giving that employer significant power over the wages and working conditions of workers. This results in a situation where the employer has the ability to suppress wages and reduce the bargaining power of workers.\\n\\nResearch has shown that the existence of monopsony power in labor markets can have negative effects on workers, such as lower wages, reduced benefits, and limited job opportunities. For example, a study by Autor, Dorn, and Hanson (2013) found evidence of monopsony power in certain U.S. labor markets, resulting in lower wages and reduced job opportunities for workers. Similarly, another study by Bharadwaj, Black, and Kolesnikova (2019) found that the presence of a single dominant employer in a local labor market was associated with lower wages for workers.<|im_end|>\\n<|im_start|>user\\nHow can one fight back when a monospony had been created?<|im_end|>\\n<|im_start|>assistant\\nMonopsony refers to a market structure where there is only one buyer of a good or service. In the context of labor markets, a monopsony occurs when there is only one employer in a particular geographic area or industry, giving them significant power to set wages and working conditions. Research has shown that the existence of monopsonies can lead to lower wages and reduced job opportunities for workers. For example, a study by the National Bureau of Economic Research found that in industries with high levels of concentration, workers earn lower wages and are less likely to receive benefits such as health insurance.<|im_end|>\\n<|im_start|>user\\nWhat can be done at a regulatory level to ensure, in a monopsony, that the power over the employees isn\\'t abused? List a few options and focus on the organs that should act.<|im_end|>\\n<|im_start|>assistant\\nHere are some potential regulatory options to address monopsony power over employees:\\n\\n- Antitrust enforcement agencies like the FTC or DOJ could investigate and take action against dominant employers that are abusing their market power to suppress wages or worsen working conditions. They could force divestitures or other structural remedies.\\n- Labor standards agencies could set industry-specific minimum wage floors or other regulations around compensation and working conditions. This would reduce the ability of dominant employers to push wages/conditions below certain thresholds.\\n- Sector-specific regulators could impose requirements around how companies hire, compensate, and treat workers. For example, banking regulators could prohibit abusive practices by dominant banks with regard to their employees.\\n- Legislatures could pass laws<|im_end|>\\n<|im_start|>assistant\\nRegulatory intervention can be used to address the negative consequences of monopsony power in the labor market. A few options include:\\n\\n1. Antitrust enforcement: Antitrust laws can be used to prevent firms from engaging in practices that limit competition and suppress wages. The antitrust division of the Department of Justice and the Federal Trade Commission (FTC) are responsible for enforcing these laws.\\n\\n2. Labor standards and protections: Governments can set minimum wage standards and other labor protections to ensure that workers are paid a fair wage, even in industries dominated by a single buyer. The U.S. Department of Labor is responsible for enforcing these standards.\\n\\n3. Occupational licensing reform: Occupational licensing requirements can restrict worker mobility and increase the bargaining power of employers. Reforms to licensing requirements can reduce these barriers and increase competition in the labor market. State governments typically regulate occupational licensing.\\n\\n4. Collective bargaining rights: Collective bargaining by workers can increase their bargaining power and lead to higher wages. Governments can protect and promote collective bargaining rights to counteract the effects of monopsony power. The National Labor Relations Board is responsible for enforcing workers\\' rights to engage in collective bargaining in the U.S.\\n\\nThese are just a few examples of regulatory options that can be used to address monopsony power in the labor market. The specific actions taken will depend on the particular circumstances and context of each case.<|im_end|>\\n<|im_start|>assistant\\nYes, that\\'s correct. Keeping the code for the TESR and the registration code in the same file can make it easier to manage and maintain the code. The ExampleMod class acts as a container for the TESR code, providing a convenient and logical grouping. The functionality of the code remains unchanged, and the TESR will still be properly registered and used to render the custom tile entities in the game.<|im_end|>\\n<|im_start|>user\\nI would imagine this is similar or even the same as a \"monopoly\" but I am not sure.\\n\\nAssuming that this some kind of \"final state\" of a particular industry or even an entire economy, give me some larger historical examples of this kind of structure consolidating over time, and describe what circumstances are common prerequisite.<|im_end|>\\n<|im_start|>assistant\\nBouguereau died in 1905, so it is unlikely that any of his direct descendants are still alive. However, his works continue to be popular and are sold at auction and through art dealers. It is possible that some indirect descendants may benefit from the sale of his works.<|im_end|>\\n'}"
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"my_dataset[0]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1ae08369-7a2c-4aca-b14d-c3adcd47fbc6",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": 5
}
|