File size: 99,996 Bytes
ee857e8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 | {
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
"_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
"execution": {
"iopub.execute_input": "2021-06-23T10:14:01.220679Z",
"iopub.status.busy": "2021-06-23T10:14:01.219714Z",
"iopub.status.idle": "2021-06-23T10:14:01.359474Z",
"shell.execute_reply": "2021-06-23T10:14:01.357018Z",
"shell.execute_reply.started": "2021-06-23T10:14:01.220489Z"
},
"trusted": true
},
"outputs": [],
"source": [
"# This Python 3 environment comes with many helpful analytics libraries installed\n",
"# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n",
"# For example, here's several helpful packages to load\n",
"\n",
"import numpy as np # linear algebra\n",
"import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
"\n",
"# Input data files are available in the read-only \"../input/\" directory\n",
"# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n",
"\n",
"import os\n",
"for dirname, _, filenames in os.walk('/kaggle/input'):\n",
" for filename in filenames:\n",
" \n",
" print(os.path.join(dirname, filename))\n",
"\n",
"# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n",
"ls # You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"execution": {
"iopub.status.busy": "2021-06-23T10:14:01.360753Z",
"iopub.status.idle": "2021-06-23T10:14:01.361256Z"
},
"trusted": true
},
"outputs": [],
"source": [
"import tensorflow as tf\n",
"import psutil\n",
"\n",
"print(\"TensorFlow version\",tf.__version__)\n",
"print(\"Num GPUs Available: \", len(tf.config.list_physical_devices('GPU')))\n",
"psutil.virtual_memory()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"execution": {
"iopub.status.busy": "2021-06-23T10:14:01.362996Z",
"iopub.status.idle": "2021-06-23T10:14:01.363698Z"
},
"trusted": true
},
"outputs": [],
"source": [
"print (spacy.util.is_package(\"en_core_web_lg\"))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# **Readability Scores + spaCy**"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"execution": {
"iopub.execute_input": "2021-06-25T19:37:17.991312Z",
"iopub.status.busy": "2021-06-25T19:37:17.990794Z",
"iopub.status.idle": "2021-06-25T19:41:20.773700Z",
"shell.execute_reply": "2021-06-25T19:41:20.772698Z",
"shell.execute_reply.started": "2021-06-25T19:37:17.991258Z"
},
"trusted": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"working directory /kaggle/working\n",
"\n",
"spaCy features\n",
"xtrain id url_legal license \\\n",
"0 c12129c31 NaN NaN \n",
"1 85aa80a4c NaN NaN \n",
"2 b69ac6792 NaN NaN \n",
"3 dd1000b26 NaN NaN \n",
"4 37c1b32fb NaN NaN \n",
"5 f9bf357fe NaN NaN \n",
"6 eaf8e7355 NaN NaN \n",
"\n",
" excerpt target standard_error \n",
"0 When the young people returned to the ballroom... -0.340259 0.464009 \n",
"1 All through dinner time, Mrs. Fayre was somewh... -0.315372 0.480805 \n",
"2 As Roger had predicted, the snow departed as q... -0.580118 0.476676 \n",
"3 And outside before the palace a great garden w... -1.054013 0.450007 \n",
"4 Once upon a time there were Three Bears who li... 0.247197 0.510845 \n",
"5 Hal and Chester found ample time to take an in... -0.861809 0.480936 \n",
"6 Hal Paine and Chester Crawford were typical Am... -1.759061 0.476507 \n",
"\n",
"xtrain target 0 -0.340259\n",
"1 -0.315372\n",
"2 -0.580118\n",
"3 -1.054013\n",
"4 0.247197\n",
"5 -0.861809\n",
"6 -1.759061\n",
"Name: target, dtype: float64\n",
"\n",
"calculating Flesch score\n",
"counting unique words\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 100 When the two friends had thus become reconciled, they examined the cub, and s target -0.811519925\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 200 Maggie soon thought she had been hours in the attic, and it must be tea time, target 0.277737321\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 300 In Computer science, cloud computing describes a type of outsourcing of compu target -1.413698838\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 400 A habitat is an ecological or environmental area that is inhabited by a parti target -0.616799879\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 500 Nanotechnology has provided the possibility of delivering drugs to specific c target -1.6251413\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 600 Animal tissues are grouped into four basic types: connective, muscle, nervous target -2.601398503\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 700 A local area network (LAN) is a computer network in a small area like a home, target -1.10578373\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 800 You guessed it–science! Fluorescent colors are very special. You might have s target -0.101779002\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 900 Our immune systems work to protect us from illness by recognizing foreign mol target -0.986988435\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 1000 Fog is an accumulation of tiny water droplets or ice crystals suspended above target -0.691647347\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 1100 Chameli's mother had a lot of beautiful jewelry. \n",
"One day, Chameli's mother s target -0.047198886\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 1200 December was an anxious month. Several German divisions were east of the Piav target -2.279783534\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 1300 The Government of the United States and the Imperial German Government are co target -1.532702197\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 1400 It was not, however, until the morning that we entered the harbor of Havre th target -0.841382898\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 1500 After a time the polished rocky sides of the shaft grew to be of a solemn sam target -1.826667527\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 1600 One morning, Grandma had two loaves of \"riz bread,\" and some election cakes, target -0.698302533\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 1700 This beautiful Agave is now in blossom in the garden here, and I am happy to target -2.162795917\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 1800 Quickly he opens the paper to its full extent, and places it on the floor car target -0.584273721\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 1900 There is a great park here, known as the Maidan, where dogs run with bones to target -0.583532619\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 2000 Mabel lives on a hill, quite near a beautiful lake, and is very fond of going target 0.902661245\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 2100 He fallow-deer — This is the domestic or park deer; and no two animals can ma target -2.57511146\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 2200 The sun is a star, just like the other millions of stars you see when you loo target -0.580630824\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 2300 This may be a useful lesson to you, dear Isabel,\" she said. \"It will teach yo target -0.223570721\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 2400 By looking at any map of Europe, it will be seen that England is separated fr target -1.188880582\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 2500 It was a beautiful place to play. There were trees for hide-and-seek, flat sp target -0.025405297\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 2600 When Doris got home she opened her paint-box. What do you think? Of course it target 0.198997768\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 2700 Forty years ago women were given no representation in conventions where polit target -1.291127806\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"text 2800 The American Civil War (1861–1865) was a civil war in the United States of Am target 0.223365705\n",
"\n",
"getting spaCy features\n",
"namelist ['f0', 'f1', 'f2', 'f3', 'f4', 'f5', 'f6', 'f7', 'f8', 'f9', 'f10', 'f11', 'f12', 'f13', 'f14', 'f15', 'f16', 'f17', 'f18', 'f19', 'f20', 'f21', 'f22', 'f23', 'f24', 'f25', 'f26', 'f27', 'f28', 'f29', 'f30', 'f31', 'f32', 'f33', 'f34', 'f35', 'f36', 'f37', 'f38', 'f39', 'f40', 'f41', 'f42', 'f43', 'f44', 'f45', 'f46', 'f47', 'f48', 'f49', 'f50', 'f51', 'f52', 'f53', 'f54', 'f55', 'f56', 'f57', 'f58', 'f59', 'f60', 'f61', 'f62', 'f63', 'f64', 'f65', 'f66', 'f67', 'f68', 'f69', 'f70', 'f71', 'f72', 'f73', 'f74', 'f75', 'f76', 'f77', 'f78', 'f79', 'f80', 'f81', 'f82', 'f83', 'f84', 'f85', 'f86', 'f87', 'f88', 'f89', 'f90', 'f91', 'f92', 'f93', 'f94', 'f95', 'f96', 'f97', 'f98', 'f99', 'f100', 'f101', 'f102', 'f103', 'f104', 'f105', 'f106', 'f107', 'f108', 'f109', 'f110', 'f111', 'f112', 'f113', 'f114', 'f115', 'f116', 'f117', 'f118', 'f119', 'f120', 'f121', 'f122', 'f123', 'f124', 'f125', 'f126', 'f127', 'f128', 'f129', 'f130', 'f131', 'f132', 'f133', 'f134', 'f135', 'f136', 'f137', 'f138', 'f139', 'f140', 'f141', 'f142', 'f143', 'f144', 'f145', 'f146', 'f147', 'f148', 'f149', 'f150', 'f151', 'f152', 'f153', 'f154', 'f155', 'f156', 'f157', 'f158', 'f159', 'f160', 'f161', 'f162', 'f163', 'f164', 'f165', 'f166', 'f167', 'f168', 'f169', 'f170', 'f171', 'f172', 'f173', 'f174', 'f175', 'f176', 'f177', 'f178', 'f179', 'f180', 'f181', 'f182', 'f183', 'f184', 'f185', 'f186', 'f187', 'f188', 'f189', 'f190', 'f191', 'f192', 'f193', 'f194', 'f195', 'f196', 'f197', 'f198', 'f199', 'f200', 'f201', 'f202', 'f203', 'f204', 'f205', 'f206', 'f207', 'f208', 'f209', 'f210', 'f211', 'f212', 'f213', 'f214', 'f215', 'f216', 'f217', 'f218', 'f219', 'f220', 'f221', 'f222', 'f223', 'f224', 'f225', 'f226', 'f227', 'f228', 'f229', 'f230', 'f231', 'f232', 'f233', 'f234', 'f235', 'f236', 'f237', 'f238', 'f239', 'f240', 'f241', 'f242', 'f243', 'f244', 'f245', 'f246', 'f247', 'f248', 'f249', 'f250', 'f251', 'f252', 'f253', 'f254', 'f255', 'f256', 'f257', 'f258', 'f259', 'f260', 'f261', 'f262', 'f263', 'f264', 'f265', 'f266', 'f267', 'f268', 'f269', 'f270', 'f271', 'f272', 'f273', 'f274', 'f275', 'f276', 'f277', 'f278', 'f279', 'f280', 'f281', 'f282', 'f283', 'f284', 'f285', 'f286', 'f287', 'f288', 'f289', 'f290', 'f291', 'f292', 'f293', 'f294', 'f295', 'f296', 'f297', 'f298', 'f299']\n",
"train_vectors f0 f1 f2 f3 f4 f5 f6 \\\n",
"0 0.054942 0.104693 -0.129839 -0.077362 0.066479 -0.007780 -0.010820 \n",
"1 -0.014731 0.213879 -0.183907 -0.048958 0.112992 0.026316 0.028143 \n",
"2 -0.006671 0.217069 -0.125178 -0.073087 0.106584 0.016715 0.011751 \n",
"3 0.040802 0.123908 -0.106365 -0.109637 0.090377 0.020302 -0.004274 \n",
"4 -0.018610 0.109863 -0.161603 -0.035534 0.143024 -0.053699 -0.026999 \n",
"\n",
" f7 f8 f9 ... f290 f291 f292 f293 \\\n",
"0 -0.054412 -0.069162 2.085747 ... -0.238603 0.031822 0.059434 -0.093304 \n",
"1 -0.137892 -0.094396 2.170374 ... -0.105756 0.051830 0.006578 -0.007093 \n",
"2 -0.115226 -0.071845 2.141033 ... -0.116192 0.020743 0.012045 -0.028818 \n",
"3 -0.007752 -0.103293 2.044155 ... -0.201305 0.014579 -0.002538 -0.046069 \n",
"4 -0.152680 -0.012829 2.205194 ... -0.284280 0.039023 0.082985 -0.052379 \n",
"\n",
" f294 f295 f296 f297 f298 f299 \n",
"0 -0.134071 0.053603 0.038264 -0.028437 -0.022459 0.068514 \n",
"1 0.065427 -0.029093 -0.000948 0.012834 0.015731 0.002224 \n",
"2 0.044761 -0.033804 0.015294 -0.019791 0.020420 0.016437 \n",
"3 -0.155320 0.064200 0.079673 -0.035276 0.001438 0.066118 \n",
"4 -0.135277 0.122106 0.057177 -0.104051 -0.100320 0.024026 \n",
"\n",
"[5 rows x 300 columns]\n",
"xtrain id url_legal license \\\n",
"0 c12129c31 NaN NaN \n",
"1 85aa80a4c NaN NaN \n",
"2 b69ac6792 NaN NaN \n",
"3 dd1000b26 NaN NaN \n",
"4 37c1b32fb NaN NaN \n",
"\n",
" excerpt target \\\n",
"0 When the young people returned to the ballroom... -0.340259 \n",
"1 All through dinner time, Mrs. Fayre was somewh... -0.315372 \n",
"2 As Roger had predicted, the snow departed as q... -0.580118 \n",
"3 And outside before the palace a great garden w... -1.054013 \n",
"4 Once upon a time there were Three Bears who li... 0.247197 \n",
"\n",
" standard_error nof_char nof_words w2c nof_sentences ... \\\n",
"0 0.464009 992 174 0.175403 11 ... \n",
"1 0.480805 937 164 0.175027 10 ... \n",
"2 0.476676 908 162 0.178414 11 ... \n",
"3 0.450007 909 163 0.179318 5 ... \n",
"4 0.510845 723 147 0.203320 5 ... \n",
"\n",
" f290 f291 f292 f293 f294 f295 f296 \\\n",
"0 -0.238603 0.031822 0.059434 -0.093304 -0.134071 0.053603 0.038264 \n",
"1 -0.105756 0.051830 0.006578 -0.007093 0.065427 -0.029093 -0.000948 \n",
"2 -0.116192 0.020743 0.012045 -0.028818 0.044761 -0.033804 0.015294 \n",
"3 -0.201305 0.014579 -0.002538 -0.046069 -0.155320 0.064200 0.079673 \n",
"4 -0.284280 0.039023 0.082985 -0.052379 -0.135277 0.122106 0.057177 \n",
"\n",
" f297 f298 f299 \n",
"0 -0.028437 -0.022459 0.068514 \n",
"1 0.012834 0.015731 0.002224 \n",
"2 -0.019791 0.020420 0.016437 \n",
"3 -0.035276 0.001438 0.066118 \n",
"4 -0.104051 -0.100320 0.024026 \n",
"\n",
"[5 rows x 318 columns]\n",
"\n",
"2267 566 2267 566\n",
"X nof_words nof_sentences nof_syllables flesch_score txt_diversity \\\n",
"981 165 12 235 72.387841 0.709091 \n",
"683 182 8 321 34.531662 0.631868 \n",
"195 172 9 249 64.963966 0.703488 \n",
"1158 151 5 264 28.272066 0.741722 \n",
"1553 173 9 281 49.910572 0.722543 \n",
"2273 169 9 273 51.114017 0.662722 \n",
"2056 188 14 241 84.755000 0.632979 \n",
"\n",
" nof_unique_words nof_char w2c flesch_score2 punctsPerSentence \\\n",
"981 117 896 0.184152 6.578561 1.812500 \n",
"683 115 1106 0.164557 14.094588 1.700000 \n",
"195 121 988 0.174089 8.945891 4.000000 \n",
"1158 112 927 0.162891 16.818464 4.833333 \n",
"1553 125 1018 0.169941 11.073141 3.000000 \n",
"2273 112 989 0.170880 10.794872 4.166667 \n",
"2056 119 938 0.200426 4.773739 1.588235 \n",
"\n",
" ... f290 f291 f292 f293 f294 f295 \\\n",
"981 ... -0.135388 0.006350 0.059477 -0.048736 0.037906 -0.004224 \n",
"683 ... -0.209450 0.023985 -0.054420 -0.117216 -0.131639 0.101565 \n",
"195 ... -0.155826 0.020981 0.004709 0.017356 0.054904 -0.006336 \n",
"1158 ... -0.246229 0.019796 -0.079219 -0.012937 -0.049782 0.086845 \n",
"1553 ... -0.115806 0.026836 0.069627 -0.061271 -0.058355 0.045644 \n",
"2273 ... -0.201175 0.044129 0.031399 -0.086733 -0.077939 0.026245 \n",
"2056 ... -0.159391 0.044991 0.042129 -0.041979 -0.002026 0.052522 \n",
"\n",
" f296 f297 f298 f299 \n",
"981 -0.000829 0.038497 0.012296 0.009338 \n",
"683 -0.080587 -0.070543 0.008028 0.024660 \n",
"195 -0.047379 -0.007128 -0.015000 0.042302 \n",
"1158 -0.022204 -0.057120 -0.018331 0.023094 \n",
"1553 0.062768 -0.013423 -0.016792 0.006240 \n",
"2273 -0.007248 -0.011341 -0.099948 0.014829 \n",
"2056 0.005720 0.018664 0.004293 0.039324 \n",
"\n",
"[7 rows x 310 columns]\n",
"\n",
"y 981 1.597870\n",
"683 -0.743435\n",
"195 -0.280994\n",
"1158 -1.464792\n",
"1553 -1.884352\n",
"2273 -0.578085\n",
"2056 0.666116\n",
"Name: target, dtype: float64\n",
"\n",
"Xtest nof_words nof_sentences nof_syllables flesch_score txt_diversity \\\n",
"4 147 5 183 71.675633 0.346939 \n",
"9 191 8 274 61.238524 0.675393 \n",
"14 181 11 259 69.076178 0.696133 \n",
"19 176 8 256 61.450455 0.693182 \n",
"24 169 6 273 41.584295 0.733728 \n",
"29 167 10 256 60.198272 0.694611 \n",
"34 146 5 230 43.923027 0.630137 \n",
"\n",
" nof_unique_words nof_char w2c flesch_score2 punctsPerSentence \\\n",
"4 51 723 0.203320 10.565796 6.400000 \n",
"9 129 1026 0.186160 10.648999 2.625000 \n",
"14 126 967 0.187177 7.712356 2.230769 \n",
"19 122 957 0.183908 10.153636 3.125000 \n",
"24 124 993 0.170191 14.456538 4.000000 \n",
"29 116 937 0.178228 9.011623 2.083333 \n",
"34 92 802 0.182045 14.387041 1.500000 \n",
"\n",
" ... f290 f291 f292 f293 f294 f295 f296 \\\n",
"4 ... -0.284280 0.039023 0.082985 -0.052379 -0.135277 0.122106 0.057177 \n",
"9 ... -0.187329 0.043337 0.025266 -0.083779 -0.068758 0.022553 0.040310 \n",
"14 ... -0.173686 0.034872 0.118947 -0.056733 -0.031695 0.045877 0.025237 \n",
"19 ... -0.191329 0.022130 0.035867 0.000256 0.020506 0.012822 0.054820 \n",
"24 ... -0.214793 0.006693 0.043532 -0.063686 -0.038540 0.034346 0.009910 \n",
"29 ... -0.135137 0.031284 0.025826 -0.051649 -0.006029 -0.006497 0.011574 \n",
"34 ... -0.135040 0.043721 0.088910 -0.033691 0.038809 0.023250 -0.022141 \n",
"\n",
" f297 f298 f299 \n",
"4 -0.104051 -0.100320 0.024026 \n",
"9 0.023220 -0.014123 0.073939 \n",
"14 0.017827 -0.013019 0.070423 \n",
"19 0.012178 0.026124 0.014872 \n",
"24 -0.043891 -0.028318 0.008500 \n",
"29 0.073487 0.016896 0.012550 \n",
"34 -0.017283 0.009402 0.041435 \n",
"\n",
"[7 rows x 310 columns]\n",
"\n",
"ytest 4 0.247197\n",
"9 -1.238432\n",
"14 0.245806\n",
"19 -1.009999\n",
"24 -1.483887\n",
"29 -1.413744\n",
"34 0.022598\n",
"Name: target, dtype: float64\n",
"\n",
"testTexts 4 Once upon a time there were Three Bears who li...\n",
"9 One day he had gone beyond any point which he ...\n",
"14 Aunt Abigail was gone, Eleanor was gone. The r...\n",
"19 Father had been away in the country for three ...\n",
"24 One beautiful misummer night in 18— a large, h...\n",
"29 Before Fred could complete the sentence his fo...\n",
"34 When Josie arrived at her destination she went...\n",
"Name: excerpt, dtype: object\n",
"\n",
"Coefficients: \n",
" [ 1.48112616e-02 -1.55412549e-02 -7.73959046e-03 -2.88993529e-02\n",
" 1.67597648e+00 -1.13562873e-02 -6.76790330e-04 2.31096998e-01\n",
" -9.55646587e-02 -4.19500101e-02 1.36526000e-01 -4.64126500e-01\n",
" -2.03473618e+00 9.43253633e-01 -2.02192115e-01 -1.34499713e+00\n",
" 3.64497640e-01 6.57803691e-01 4.88818959e-01 2.15804127e+00\n",
" 3.14023294e-01 1.67664341e+00 9.81973042e-01 -6.91690628e-01\n",
" -1.01460977e+00 -2.02116650e+00 1.71898026e+00 1.74817617e-01\n",
" -1.22450073e+00 -1.30771453e-01 2.11451440e+00 6.13313101e-01\n",
" 6.78876769e-01 -2.25069093e-01 7.07877084e-01 2.04801343e-01\n",
" 1.96560164e+00 -1.46212410e+00 1.31736764e+00 -1.05987346e+00\n",
" 7.89324172e-01 -1.33164448e+00 9.95217519e-01 -2.49868056e+00\n",
" 1.29056335e-01 1.49038129e+00 -5.42990407e-01 -8.39090134e-01\n",
" -1.41186945e+00 7.54193366e-02 2.57674731e-01 1.30808569e-01\n",
" -4.92950811e-01 -1.58826836e+00 5.96774858e-01 1.06580809e-01\n",
" -1.99887650e+00 3.42666469e-01 6.91031626e-01 -1.36461958e+00\n",
" -7.99921013e-01 1.06241437e+00 6.02372886e-01 1.34139155e-01\n",
" 5.87312458e-01 -8.89612395e-01 2.31979457e-01 -2.72189030e-01\n",
" 1.27046369e+00 -7.87424473e-01 -5.96105483e-01 1.24769951e+00\n",
" 1.40308240e+00 1.27394400e+00 4.91412901e-01 -7.72385024e-01\n",
" -5.05964685e-01 1.14412032e-01 8.54139656e-01 1.73251441e-01\n",
" 5.39661393e-01 -1.52359023e+00 8.30725440e-01 -2.26389149e+00\n",
" -4.30577198e-01 -2.44745684e-01 9.70829904e-01 9.66891873e-01\n",
" 5.73260492e-01 2.39438422e+00 6.31846069e-01 -9.79336578e-01\n",
" -7.77869900e-01 -8.86337073e-01 8.90635384e-01 1.50316880e+00\n",
" 2.77835843e-01 3.36868622e+00 -6.44468462e-01 8.65056836e-01\n",
" -7.77913999e-01 7.31843409e-01 -1.85950207e-01 -1.59319060e+00\n",
" 1.45043870e+00 -8.12437286e-02 -2.70250697e+00 1.04160621e-02\n",
" 6.05750580e-02 -6.64125045e-01 9.65134691e-01 1.08247921e+00\n",
" 1.55597965e+00 2.14804900e+00 -1.78798007e+00 5.47404008e-01\n",
" 5.62647384e-01 -7.78201603e-01 4.11461894e-02 -1.02381785e+00\n",
" 4.75500088e-02 1.78260419e+00 4.47533117e-02 1.22368838e+00\n",
" 7.79222434e-01 9.18839415e-01 -4.49509730e-01 -8.75912387e-01\n",
" -6.25593418e-01 -9.89823633e-01 -2.26460072e-01 4.07520063e-01\n",
" 1.01842585e+00 -1.75370348e+00 -1.88901046e+00 1.02996122e+00\n",
" 6.23973502e-01 1.05602333e+00 -1.00035180e+00 8.30154535e-01\n",
" -7.36426230e-01 -1.23791657e-01 -2.67737114e-01 4.15182059e-01\n",
" 1.83684335e+00 2.83771232e-02 -1.23688909e+00 1.10544755e+00\n",
" -1.28570229e+00 5.76877283e-02 -1.67473796e+00 5.93510889e-01\n",
" -5.22998133e-01 8.88995961e-01 -6.45399566e-01 7.12948999e-01\n",
" 1.14934601e+00 -8.13445538e-01 -5.62938695e-01 -3.20461496e-01\n",
" 1.40390815e+00 -8.46474289e-01 -1.10234188e+00 1.14106878e+00\n",
" 3.63046803e-01 -3.11109625e-01 4.11949925e-01 3.34908944e-02\n",
" -8.05188696e-01 1.68705750e-01 9.73377722e-02 1.02001860e+00\n",
" -3.23013411e-01 6.57740349e-01 8.48421459e-02 -8.48525076e-01\n",
" 1.13746190e+00 1.34074006e+00 1.01844132e+00 9.41773743e-01\n",
" 2.95959229e-01 3.40927881e-01 2.09716200e-01 1.03042481e+00\n",
" -4.80037659e-01 -1.53610920e+00 6.90516961e-01 2.50788383e+00\n",
" -1.13485462e+00 5.40351535e-01 1.53150011e+00 2.50065741e-01\n",
" -1.66960225e+00 -1.46658813e+00 1.25153767e+00 1.38410771e-01\n",
" 2.24230354e+00 1.77595626e+00 9.52513188e-01 3.93867629e-02\n",
" 5.24358446e-01 -2.91415353e+00 9.89378191e-01 -9.35222678e-01\n",
" 2.09256753e+00 5.85871842e-01 5.67877375e-01 -2.64329976e-01\n",
" 5.24332810e-01 4.07220229e-01 -9.98309823e-01 -1.77984935e+00\n",
" -3.05702491e-01 -5.94020140e-01 1.64474431e+00 -9.60539779e-01\n",
" 5.73586279e-01 -8.04563719e-01 2.85977044e-01 -7.12660606e-01\n",
" 1.16091398e+00 5.21863006e-01 6.36117494e-01 -1.54157975e+00\n",
" -2.48319258e-02 -7.80990052e-01 1.93422206e+00 -1.81617141e-01\n",
" 8.74368246e-01 -9.95851975e-01 1.20673851e+00 6.25174832e-01\n",
" -4.14509525e-01 3.47246439e-01 1.24975180e+00 -1.24743672e-01\n",
" 2.83320953e+00 -2.47267863e-01 -4.76491480e-01 -1.15920506e-01\n",
" -6.13646729e-01 -2.02507388e+00 -1.17955649e+00 -4.96551385e-01\n",
" 7.02227766e-01 -1.35640131e+00 1.49416852e-01 1.19430963e+00\n",
" -9.06887201e-02 -6.62766712e-01 -2.14906303e+00 -3.19839067e-01\n",
" -1.20248193e+00 -1.31185676e+00 -2.09510746e-01 -2.99065619e-01\n",
" -3.96931126e-01 -2.74447079e-01 -7.14053736e-01 -2.31750076e+00\n",
" -1.63908613e+00 -1.18412058e+00 -1.59452523e+00 2.56873125e-01\n",
" -1.75285642e+00 -1.52126210e-03 4.38063031e-01 5.63524168e-01\n",
" -1.86617995e+00 5.31489429e-02 -6.01337084e-01 1.37594875e-01\n",
" 2.94007258e-01 1.44702658e+00 -2.10128714e+00 -1.73651395e+00\n",
" -6.93153045e-01 1.19929792e+00 -1.30700577e+00 9.80201534e-01\n",
" 1.27176203e+00 -3.31401047e-01 -8.54530472e-01 -8.68841038e-01\n",
" 2.37037887e-01 -6.57746733e-01 1.09954468e-01 -1.09134992e-01\n",
" -9.02331545e-01 1.42930236e+00 -1.97150272e+00 -2.42991619e+00\n",
" 4.67394492e-01 6.05340704e-01 2.91821556e+00 7.67391194e-01\n",
" -1.13204002e+00 -9.21798068e-01 -5.39630783e-01 -4.09563689e-01\n",
" -1.44841898e+00 1.68235528e+00 -1.34297779e+00 9.36105670e-01\n",
" -1.86417473e-02 2.78968737e+00 -4.39593949e-01 1.35258287e+00\n",
" -7.39050533e-01 1.85308077e+00]\n",
"Mean squared error: 0.3317574750\n",
"Root Mean squared error: 0.5759839191\n",
"Coefficient of determination: 0.69\n",
"sklearn RMSE 0.5759839190527772\n",
"ytest is a <class 'pandas.core.series.Series'> y_pred is a <class 'numpy.ndarray'>\n",
"testTexts is a <class 'pandas.core.series.Series'> testResults is a <class 'pandas.core.frame.DataFrame'>\n",
" excerpt predregr target\n",
"4 Once upon a time there were Three Bears who li... 0.303138 0.247197\n",
"9 One day he had gone beyond any point which he ... -1.311287 -1.238432\n",
"14 Aunt Abigail was gone, Eleanor was gone. The r... 0.211536 0.245806\n",
"19 Father had been away in the country for three ... -1.139146 -1.009999\n",
"24 One beautiful misummer night in 18— a large, h... -1.115843 -1.483887\n",
"29 Before Fred could complete the sentence his fo... -1.260631 -1.413744\n",
"34 When Josie arrived at her destination she went... -0.316249 0.022598\n"
]
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"# -*- coding: utf-8 -*-\n",
"\"\"\"\n",
"Created on Sun May 16 08:05:43 2021\n",
"\n",
"@author: Jacob\n",
"\"\"\"\n",
"import matplotlib.pyplot as plt\n",
"import math\n",
"import os\n",
"\n",
"import numpy as np\n",
"import pandas as pd \n",
"from pandas import DataFrame\n",
"\n",
"from sklearn.feature_extraction.text import CountVectorizer\n",
"from sklearn.pipeline import make_pipeline\n",
"from sklearn.linear_model import LinearRegression, Ridge, ElasticNet\n",
"from sklearn.metrics import mean_squared_error as mse\n",
"from sklearn.model_selection import KFold\n",
"from sklearn.preprocessing import StandardScaler\n",
"\n",
"from sklearn import datasets, linear_model\n",
"from sklearn.metrics import mean_squared_error, r2_score\n",
"\n",
"import spacy\n",
"from transformers import XLNetTokenizer\n",
"\n",
"import sys\n",
"\n",
"\n",
"print(\"working directory\" , os.getcwd())\n",
"\n",
"useSpaCyParsing = True\n",
"\n",
"print()\n",
"\n",
"if useSpaCyParsing:\n",
" print(\"spaCy features\")\n",
" nlp = spacy.load('en_core_web_lg')\n",
"\n",
"\n",
"\n",
"nfolds = 10\n",
" \n",
" \n",
"# count syllables: https://stackoverflow.com/questions/46759492/syllable-count-in-python\n",
"def syllable_count(word):\n",
" \n",
" count = 0\n",
" vowels = \"aeiouy\"\n",
" \n",
" if word[0] in vowels:\n",
" count += 1\n",
" \n",
" for index in range(1, len(word)):\n",
" if word[index] in vowels and word[index - 1] not in vowels:\n",
" count += 1\n",
" if word.endswith(\"e\"):\n",
" count -= 1\n",
" \n",
" if count == 0:\n",
" count += 1\n",
" \n",
" return count\n",
"\n",
"\n",
"\n",
"def punctsPerSentence(text):\n",
" \n",
" doc = nlp(text)\n",
" \n",
" nPuncts = 0 \n",
" nSentences = 0\n",
" \n",
" for sent in doc.sents:\n",
" \n",
" sentence = sent.text.strip()\n",
" \n",
" nSentences += 1\n",
" \n",
" for i in range (0, len (sentence)): \n",
" #Checks whether given character is a punctuation mark \n",
" if sentence[i] in ('!', \",\" ,\"\\'\" ,\";\" ,\"\\\"\", \".\", \"-\" ,\"?\"): \n",
" nPuncts += 1 \n",
" \n",
"# print (\"Number of punctuation characters in text: \", nPuncts) \n",
" \n",
" punctsPerSentence = nPuncts / nSentences\n",
" \n",
" return punctsPerSentence\n",
" \n",
"\n",
" \n",
"xtrain = pd.read_csv('../input/commonlitreadabilityprize/train.csv')\n",
"xtest = pd.read_csv('../input/commonlitreadabilityprize/test.csv')\n",
"\n",
"\n",
"print(\"xtrain\", xtrain.head(7))\n",
"print()\n",
"\n",
"print(\"xtrain target\", xtrain.target.head(7))\n",
"print()\n",
"\n",
"\n",
"\n",
"print(\"calculating Flesch score\")\n",
"# Flesch score: https://blog.ung.edu/press/measure-readability/\n",
"\n",
"# count the characters\n",
"xtrain['nof_char'] = xtrain['excerpt'].apply(len)\n",
"xtest['nof_char'] = xtest['excerpt'].apply(len)\n",
"\n",
"# count the words\n",
"xtrain['nof_words'] = xtrain['excerpt'].apply(lambda s: len(s.split(' ')))\n",
"xtest['nof_words'] = xtest['excerpt'].apply(lambda s: len(s.split(' ')))\n",
"\n",
"# words to characters\n",
"xtrain['w2c'] = xtrain['nof_words'] / xtrain['nof_char']\n",
"xtest['w2c'] = xtest['nof_words'] / xtest['nof_char']\n",
"\n",
"# nof sentences\n",
"xtrain['nof_sentences'] = xtrain['excerpt'].apply(lambda s: s.count('.'))\n",
"xtest['nof_sentences'] = xtest['excerpt'].apply(lambda s: s.count('.'))\n",
"\n",
"# nof syllables\n",
"xtrain['nof_syllables'] = xtrain['excerpt'].apply(lambda s: syllable_count(s))\n",
"xtest['nof_syllables'] = xtest['excerpt'].apply(lambda s: syllable_count(s))\n",
"\n",
"# nof punctuation characters per sentence\n",
"xtrain['punctsPerSentence'] = xtrain['excerpt'].apply(lambda s: punctsPerSentence(s))\n",
"xtest['punctsPerSentence'] = xtest['excerpt'].apply(lambda s: punctsPerSentence(s))\n",
"\n",
"\n",
"# Flesch score\n",
"a = 206.835 - 1.015 * (xtrain['nof_words'] / xtrain['nof_sentences'])\n",
"b = -84.6 * (xtrain['nof_syllables'] / xtrain['nof_words'])\n",
"xtrain['flesch_score'] = a + b\n",
"\n",
"a = 206.835 - 1.015 * (xtest['nof_words'] / xtest['nof_sentences'])\n",
"b = -84.6 * (xtest['nof_syllables'] / xtest['nof_words'])\n",
"xtest['flesch_score'] = a + b\n",
"\n",
"# Flesch score 2\n",
"a = (xtrain['nof_words'] / xtrain['nof_sentences'])\n",
"b = (xtrain['nof_syllables'] / xtrain['nof_words'])\n",
"xtrain['flesch_score2'] = 0.39 * a + 11.8 * b - 15.59\n",
"\n",
"a = (xtest['nof_words'] / xtest['nof_sentences'])\n",
"b = (xtest['nof_syllables'] / xtest['nof_words'])\n",
"xtest['flesch_score2'] = 0.39 * a + 11.8 * b - 15.59\n",
" \n",
" \n",
"del a,b\n",
"\n",
"\n",
"print(\"counting unique words\")\n",
"# count the unique words\n",
"xtrain['nof_unique_words'] = xtrain['excerpt'].apply(lambda s: len(set( s.split(' ') )))\n",
"xtest['nof_unique_words'] = xtest['excerpt'].apply(lambda s: len(set( s.split(' ') )))\n",
"\n",
"# text diversity\n",
"xtrain['txt_diversity'] = xtrain['nof_unique_words'] / xtrain['nof_words']\n",
"xtest['txt_diversity'] = xtest['nof_unique_words'] / xtest['nof_words']\n",
"\n",
"# word lengths\n",
"words = xtrain['excerpt'].apply(lambda s: s.split(' '))\n",
"word_lengths = words.apply(lambda s: [len(f) for f in s ])\n",
"xtrain['longest_word'] = word_lengths.apply(max)\n",
"xtrain['avg_word'] = word_lengths.apply(np.mean)\n",
"\n",
"words = xtest['excerpt'].apply(lambda s: s.split(' '))\n",
"word_lengths = words.apply(lambda s: [len(f) for f in s ])\n",
"xtest['longest_word'] = word_lengths.apply(max)\n",
"xtest['avg_word'] = word_lengths.apply(np.mean)\n",
"\n",
"xtrain['txt_diversity'] = xtrain['nof_unique_words'] / xtrain['nof_words']\n",
"xtest['txt_diversity'] = xtest['nof_unique_words'] / xtest['nof_words']\n",
"\n",
"\n",
"\n",
"\n",
"nText = 0\n",
"\n",
"for text in xtrain.excerpt:\n",
" \n",
" target = xtrain.target.iloc[nText]\n",
"\n",
" nText += 1\n",
" \n",
" if nText % 100 == 0:\n",
" print()\n",
" print(\"--------------------------------------------------------------------------------\")\n",
" print(\"text\", nText , text[:77], \"target\", target)\n",
" print()\n",
" \n",
"\n",
"\n",
"\n",
" \n",
"useSpaCyFeatures = True\n",
"\n",
"if useSpaCyFeatures:\n",
" \n",
" print(\"getting spaCy features\")\n",
"\n",
" with nlp.disable_pipes():\n",
" train_vectors = np.array([nlp(text).vector for text in xtrain.excerpt])\n",
" test_vectors = np.array([nlp(text).vector for text in xtest.excerpt])\n",
" \n",
" namelist = ['f' + str(ii) for ii in range(train_vectors.shape[1])]\n",
" \n",
" print(\"namelist\" , namelist)\n",
" \n",
" train_vectors = pd.DataFrame(train_vectors)\n",
" test_vectors = pd.DataFrame(test_vectors)\n",
" train_vectors.columns = namelist\n",
" test_vectors.columns = namelist\n",
" \n",
" print(\"train_vectors\" , train_vectors.head())\n",
" \n",
" # combined\n",
" xtrain = pd.concat([xtrain, train_vectors], axis = 1)\n",
" xtest = pd.concat([xtest, test_vectors], axis = 1)\n",
"\n",
"#features = namelist\n",
"\n",
" features = ['nof_words', 'nof_sentences', 'nof_syllables', 'flesch_score',\n",
" 'txt_diversity', 'nof_unique_words', 'nof_char', 'w2c', \n",
" 'flesch_score2', 'punctsPerSentence'] + namelist\n",
"\n",
"else:\n",
"\n",
" features = ['nof_words', 'nof_sentences', 'nof_syllables', 'flesch_score',\n",
" 'txt_diversity', 'nof_unique_words', 'nof_char', 'w2c', \n",
" 'flesch_score2', 'punctsPerSentence'] \n",
"\n",
"print(\"xtrain\", xtrain.head())\n",
"print()\n",
"\n",
"X = xtrain[features].sample(frac=0.8, random_state=0)\n",
"# Xtest = xtrain[features].drop(X.index)\n",
"\n",
"y = xtrain['target'].sample(frac=0.8, random_state=0)\n",
"# ytest = xtrain['target'].drop(y.index)\n",
"\n",
"Xtest = xtrain[features].iloc[4::5]\n",
"ytest = xtrain['target'].iloc[4::5]\n",
"\n",
"testTexts = xtrain['excerpt'].iloc[4::5]\n",
" \n",
"print(len(X), len(Xtest), len(y), len(ytest))\n",
"\n",
"print(\"X\", X.head(7))\n",
"print()\n",
"print(\"y\", y.head(7))\n",
"print()\n",
"print(\"Xtest\", Xtest.head(7))\n",
"print()\n",
"print(\"ytest\", ytest.head(7))\n",
"print()\n",
"print(\"testTexts\", testTexts.head(7))\n",
"print()\n",
"\n",
" \n",
"# Create linear regression object\n",
"regr = linear_model.LinearRegression()\n",
"\n",
"# Train the model using the training sets\n",
"regr.fit(X, y)\n",
"\n",
"# Make predictions using the testing set\n",
"y_pred = regr.predict(Xtest)\n",
"\n",
"# The coefficients\n",
"print('Coefficients: \\n', regr.coef_)\n",
"# The mean squared error\n",
"print('Mean squared error: %.10f' % mean_squared_error(ytest, y_pred))\n",
"print('Root Mean squared error: %.10f' % math.sqrt(mean_squared_error(ytest, y_pred)))\n",
"# The coefficient of determination: 1 is perfect prediction\n",
"print('Coefficient of determination: %.2f'\n",
" % r2_score(ytest, y_pred))\n",
"print(\"sklearn RMSE\" , np.sqrt(mse(y_pred, ytest)))\n",
"\n",
"def plot_prediction(x, y):\n",
" plt.scatter(x, y, label='Predictions')\n",
"# plt.plot(x, y, color='k', label='Predictions')\n",
" plt.xlabel('Actual')\n",
" plt.ylabel('Linear Regression Prediction')\n",
" plt.legend()\n",
" \n",
"plot_prediction(ytest, y_pred)\n",
"\n",
"\n",
"print(\"ytest is a\",type(ytest), \" y_pred is a\",type(y_pred))\n",
"\n",
"\n",
"testResults = DataFrame()\n",
"testResults['excerpt'] = testTexts \n",
"testResults['predregr'] = y_pred \n",
"testResults['target'] = ytest\n",
"#testResults.loc[:,'target'] = ytest\n",
"\n",
"print(\"testTexts is a\",type(testTexts), \" testResults is a\",type(testResults))\n",
"\n",
"print(testResults.head(7))\n",
"\n",
"# testResults.to_csv('regression.csv', index = False)\n",
"\n",
"#continuousNN.doMultipleRegression(X , y, Xtest , ytest)\n",
"\n",
"#continuousNN.doMultipleNN(X , y , Xtest , ytest)\n",
"\n",
"Xtest = xtest[features]\n",
"\n",
"y_pred = regr.predict(Xtest)\n",
"\n",
"xsub = xtest[[\"id\"]].copy()\n",
"xsub[\"target\"] = y_pred\n",
"xsub.to_csv('regression.csv', index = False)\n",
"\n",
"\n",
"\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Transformers XLNet"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"execution": {
"iopub.execute_input": "2021-06-25T20:29:57.316067Z",
"iopub.status.busy": "2021-06-25T20:29:57.315669Z",
"iopub.status.idle": "2021-06-25T20:37:56.431985Z",
"shell.execute_reply": "2021-06-25T20:37:56.430279Z",
"shell.execute_reply.started": "2021-06-25T20:29:57.316036Z"
},
"trusted": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Truncation was not explicitly activated but `max_length` is provided a specific value, please use `truncation=True` to explicitly truncate examples to max length. Defaulting to 'longest_first' truncation strategy. If you encode pairs of sequences (GLUE-style) with the tokenizer you can select this strategy more precisely by providing a specific strategy to `truncation`.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"All model checkpoint layers were used when initializing TFXLNetForSequenceClassification.\n",
"\n",
"All the layers of TFXLNetForSequenceClassification were initialized from the model checkpoint at ./savedmodel/5.\n",
"If your task is similar to the task the model of the checkpoint was trained on, you can already use TFXLNetForSequenceClassification for predictions without further training.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"nr of testData 566\n",
"\n",
"Once upon a time there were Three Bears who lived\n",
"One day he had gone beyond any point which he had\n",
"Aunt Abigail was gone, Eleanor was gone. The room\n",
"Father had been away in the country for three or \n",
"One beautiful misummer night in 18— a large, heav\n",
"Before Fred could complete the sentence his foot \n",
"When Josie arrived at her destination she went to\n",
"n 10 predictedScore -0.6352807\n",
"n 20 predictedScore -0.57780975\n",
"n 30 predictedScore -2.1973433\n",
"n 40 predictedScore 0.3600465\n",
"n 50 predictedScore -1.5519806\n",
"n 60 predictedScore -0.85689175\n",
"n 70 predictedScore -0.09774914\n",
"n 80 predictedScore -0.66253567\n",
"n 90 predictedScore 0.100836724\n",
"n 100 predictedScore -1.6850315\n",
"n 110 predictedScore -2.3307252\n",
"n 120 predictedScore -1.9078956\n",
"n 130 predictedScore -0.14376666\n",
"n 140 predictedScore -0.5901213\n",
"n 150 predictedScore -1.5638647\n",
"n 160 predictedScore -0.7154779\n",
"n 170 predictedScore -0.65485036\n",
"n 180 predictedScore -0.527873\n",
"n 190 predictedScore -2.7968028\n",
"n 200 predictedScore -0.9472739\n",
"n 210 predictedScore 0.5601345\n",
"n 220 predictedScore 0.58908087\n",
"n 230 predictedScore 0.029123785\n",
"n 240 predictedScore -1.9193069\n",
"n 250 predictedScore -1.1744077\n",
"n 260 predictedScore -2.4476063\n",
"n 270 predictedScore -2.6000533\n",
"n 280 predictedScore -0.71867293\n",
"n 290 predictedScore -2.2777648\n",
"n 300 predictedScore -0.74542314\n",
"n 310 predictedScore -0.2118968\n",
"n 320 predictedScore -0.7084438\n",
"n 330 predictedScore -3.1341808\n",
"n 340 predictedScore -1.6591183\n",
"n 350 predictedScore -2.861485\n",
"n 360 predictedScore -0.39417243\n",
"n 370 predictedScore -3.2452447\n",
"n 380 predictedScore 0.39630795\n",
"n 390 predictedScore 0.33230662\n",
"n 400 predictedScore 0.089797206\n",
"n 410 predictedScore -0.9605478\n",
"n 420 predictedScore -2.0486407\n",
"n 430 predictedScore -2.3067622\n",
"n 440 predictedScore -0.46318254\n",
"n 450 predictedScore -1.3052845\n",
"n 460 predictedScore -1.2545989\n",
"n 470 predictedScore -0.4134524\n",
"n 480 predictedScore -1.9913256\n",
"n 490 predictedScore -1.0554487\n",
"n 500 predictedScore 0.115702085\n",
"n 510 predictedScore -0.66827846\n",
"n 520 predictedScore 0.11224969\n",
"n 530 predictedScore -2.9705956\n",
"n 540 predictedScore -1.5697746\n",
"n 550 predictedScore -3.2411354\n",
"n 560 predictedScore -0.817201\n",
"prediction done\n"
]
},
{
"ename": "ValueError",
"evalue": "Length of values (566) does not match length of index (7)",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-14-c07b27597ea6>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 506\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 507\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 508\u001b[0;31m \u001b[0mpredict_testdata\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtestData\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 509\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 510\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m<ipython-input-14-c07b27597ea6>\u001b[0m in \u001b[0;36mpredict_testdata\u001b[0;34m(texts)\u001b[0m\n\u001b[1;32m 420\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"prediction done\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 421\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 422\u001b[0;31m \u001b[0mtestResults\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'target'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpredictedScores\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 423\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 424\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/conda/lib/python3.7/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m__setitem__\u001b[0;34m(self, key, value)\u001b[0m\n\u001b[1;32m 3161\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3162\u001b[0m \u001b[0;31m# set column\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3163\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_set_item\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3164\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3165\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_setitem_slice\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mslice\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/conda/lib/python3.7/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m_set_item\u001b[0;34m(self, key, value)\u001b[0m\n\u001b[1;32m 3240\u001b[0m \"\"\"\n\u001b[1;32m 3241\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_ensure_valid_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3242\u001b[0;31m \u001b[0mvalue\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_sanitize_column\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3243\u001b[0m \u001b[0mNDFrame\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_set_item\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3244\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/conda/lib/python3.7/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m_sanitize_column\u001b[0;34m(self, key, value, broadcast)\u001b[0m\n\u001b[1;32m 3897\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3898\u001b[0m \u001b[0;31m# turn me into an ndarray\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3899\u001b[0;31m \u001b[0mvalue\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msanitize_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3900\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mndarray\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mIndex\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3901\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/conda/lib/python3.7/site-packages/pandas/core/internals/construction.py\u001b[0m in \u001b[0;36msanitize_index\u001b[0;34m(data, index)\u001b[0m\n\u001b[1;32m 750\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mindex\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 751\u001b[0m raise ValueError(\n\u001b[0;32m--> 752\u001b[0;31m \u001b[0;34m\"Length of values \"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 753\u001b[0m \u001b[0;34mf\"({len(data)}) \"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 754\u001b[0m \u001b[0;34m\"does not match length of index \"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mValueError\u001b[0m: Length of values (566) does not match length of index (7)"
]
}
],
"source": [
"# -*- coding: utf-8 -*-\n",
"\"\"\"\n",
"Created on Fri May 28 14:00:29 2021\n",
"\n",
"@author: Jacob\n",
"\"\"\"\n",
"\n",
"from transformers import BertTokenizer\n",
"from transformers import TFBertForSequenceClassification\n",
"\n",
"from transformers import XLNetTokenizer\n",
"from transformers import TFXLNetForSequenceClassification\n",
"\n",
"# from transformers import AutoModelForSequenceClassification\n",
"# from transformers import TrainingArguments\n",
"# from transformers import Trainer\n",
"\n",
"import tensorflow_datasets as tfds\n",
"import tensorflow as tf\n",
"\n",
"import csv\n",
"import os\n",
"import sys\n",
"import gc\n",
"\n",
"import matplotlib.pyplot as plt\n",
"\n",
"import numpy as np\n",
"import pandas as pd\n",
"from pandas import DataFrame\n",
"\n",
"import codecs\n",
"import math\n",
"from sklearn.metrics import mean_squared_error \n",
"\n",
"\n",
"# max_length_text = 7\n",
"# batch_size = 100\n",
"# number_of_epochs = 1\n",
"\n",
"# max_length_text = 100\n",
"# batch_size = 50\n",
"# number_of_epochs = 3\n",
"\n",
"max_length_text = 150\n",
"batch_size = 10\n",
"number_of_epochs = 1\n",
"\n",
"#max_length_text = 300\n",
"#batch_size = 1\n",
"#number_of_epochs = 1\n",
"\n",
"\n",
"testScores = []\n",
"testData = []\n",
"\n",
"def load_train_validate_lit_data(data_dir):\n",
" \"\"\"Loads the CommonLit train/validate datasets \n",
" Input:\n",
" data_dir: path to the \"aclImdb\" folder.\n",
" \n",
" Returns:\n",
" train/test datasets as pandas dataframes.\n",
" \"\"\"\n",
"\n",
" # CommonLit data\n",
" # --------------\n",
" cldata = {} \n",
" \n",
"# datadir = 'data/CommonLit/'-\n",
" \n",
" text_corpus = []\n",
" targetvals = []\n",
" \n",
" \n",
" with open('../input/commonlitreadabilityprize/train.csv', newline='', encoding='utf8') as trainfile:\n",
"# with open(data_dir + 'train+grades.csv', newline='', encoding='utf8') as trainfile:\n",
" \n",
" corpus = csv.reader(trainfile, delimiter=',', quotechar='\"')\n",
" \n",
" for split in [\"train\", \"validate\"]:\n",
" \n",
" cldata[split] = []\n",
" \n",
" \n",
" n = 0\n",
" ntest = 0\n",
" \n",
" for row in corpus:\n",
" # print()\n",
" # print(n, row[0])\n",
" # print(row[3])\n",
" if n > 0:\n",
" \n",
" text = row[3]\n",
" score = float(row[4])\n",
" \n",
" # if score <= 6:\n",
" # score = 0\n",
" # elif score >= 9:\n",
" # score = 1\n",
" # else:\n",
" # continue\n",
" \n",
" # if n % 50 == 0:\n",
" # cldata[\"test\"].append([text, score])\n",
" # elif n % 10 == 0:\n",
" # cldata[\"train\"].append([text, score]) \n",
"\n",
" if n % 5 == 0:\n",
" cldata[\"validate\"].append([text, score])\n",
" \n",
" if True: \n",
" # ntest < 1.4 * 37:\n",
" testData.append(text)\n",
" testScores.append(score)\n",
" ntest += 1\n",
" else:\n",
" \n",
" if score < -3.1 :\n",
" for dup in range(0,10):\n",
" cldata[\"train\"].append([text, score]) \n",
" elif score < -2.6:\n",
" for dup in range(0,4):\n",
" cldata[\"train\"].append([text, score]) \n",
" elif score < -2.1:\n",
" for dup in range(0,2):\n",
" cldata[\"train\"].append([text, score]) \n",
" elif score < 0.1:\n",
" cldata[\"train\"].append([text, score]) \n",
" elif score < 0.6:\n",
" for dup in range(0,2):\n",
" cldata[\"train\"].append([text, score]) \n",
" elif score < 1.2:\n",
" for dup in range(0,5):\n",
" cldata[\"train\"].append([text, score]) \n",
" else:\n",
" for dup in range(0,10):\n",
" cldata[\"train\"].append([text, score]) \n",
"\n",
" n += 1\n",
" \n",
"\n",
" np.random.shuffle(cldata[\"train\"]) \n",
" cldata[\"train\"] = pd.DataFrame(cldata[\"train\"], columns=['text', 'score'])\n",
" #print()\n",
" #print(\"training data\")\n",
" #print(cldata[\"train\"])\n",
" \n",
" np.random.shuffle(cldata[\"validate\"])\n",
" cldata[\"validate\"] = pd.DataFrame(cldata[\"validate\"], columns=['text', 'score'])\n",
" #print()\n",
" #print(\"validation data\")\n",
" #print(cldata[\"validate\"])\n",
" \n",
" return cldata[\"train\"], cldata[\"validate\"]\n",
"\n",
"\n",
"\n",
"def load_train_test_imdb_data(data_dir):\n",
" \"\"\"Loads the IMDB train/test datasets from a folder path.\n",
" Input:\n",
" data_dir: path to the \"aclImdb\" folder.\n",
" \n",
" Returns:\n",
" train/test datasets as pandas dataframes.\n",
" \"\"\"\n",
"\n",
" data = {}\n",
" for split in [\"train\", \"test\"]:\n",
" \n",
" data[split] = []\n",
" \n",
" for sentiment in [\"neg\", \"pos\"]:\n",
" \n",
" score = 1 if sentiment == \"pos\" else 0\n",
"\n",
" path = os.path.join(data_dir, split, sentiment)\n",
" file_names = os.listdir(path)\n",
" \n",
" nData = 0\n",
" \n",
" for f_name in file_names:\n",
" \n",
" if nData % 20 == 0:\n",
" with open(os.path.join(path, f_name), \"r\", encoding=\"utf8\") as f:\n",
" review = f.read()\n",
" data[split].append([review, score])\n",
" \n",
" nData += 1 \n",
" \n",
"\n",
" np.random.shuffle(data[\"train\"]) \n",
" data[\"train\"] = pd.DataFrame(data[\"train\"], columns=['text', 'sentiment'])\n",
" print(\"training data\")\n",
" print(data[\"train\"])\n",
" np.random.shuffle(data[\"test\"])\n",
" data[\"test\"] = pd.DataFrame(data[\"test\"], columns=['text', 'sentiment'])\n",
" print(\"test data\")\n",
" print(data[\"test\"])\n",
" \n",
" return data[\"train\"], data[\"test\"]\n",
"\n",
"\n",
"\n",
"def convert_example_to_feature(text):\n",
"# # add special tokens\n",
"# # print(\"text\", text)\n",
"# text_with_special_tokens = '[CLS]' + text + '[SEP]'\n",
"# tokenized = tokenizer.tokenize(text_with_special_tokens)\n",
"# # print('tokenized', tokenized)\n",
" \n",
"# # convert tokens to ids in WordPiece\n",
"# input_ids = tokenizer.convert_tokens_to_ids(tokenized)\n",
" \n",
"# # precalculation of pad length, so that we can reuse it later on\n",
"# padding_length = max_length_text - len(input_ids)\n",
" \n",
"# # map tokens to WordPiece dictionary and add pad token for those text shorter than our max length\n",
"# input_ids = input_ids + ([0] * padding_length)\n",
" \n",
"# # attention should focus just on sequence with non padded tokens\n",
"# attention_mask = [1] * len(input_ids)\n",
" \n",
"# # do not focus attention on padded tokens\n",
"# attention_mask = attention_mask + ([0] * padding_length)\n",
" \n",
"# # token types, needed for example for question answering, for our purpose we will just set 0 as we have just one sequence\n",
"# token_type_ids = [0] * max_length_text\n",
"# bert_input = {\n",
"# \"input_ids\": input_ids,\n",
"# \"token_type_ids\": token_type_ids,\n",
"# \"attention_mask\": attention_mask\n",
"# }\n",
" \n",
"# return bert_input\n",
"\n",
" features = tokenizer.encode_plus(\n",
" text, \n",
" add_special_tokens = True, # add [CLS], [SEP]\n",
" max_length = max_length_text, # max length of the text that can go to XLNet\n",
" pad_to_max_length = True, # add [PAD] tokens\n",
" return_attention_mask = True, # add attention mask to not focus on pad tokens\n",
" )\n",
" # print('encoded', bert_input)\n",
" \n",
" return features\n",
"\n",
"try:\n",
" tokenizer = XLNetTokenizer.from_pretrained('../input/xlnet01/hf_xlnet-base-cased', do_lower_case=True)\n",
"except Exception as e: # catch *all* exceptions\n",
" print( \"Error: \" , e)\n",
"#tokenizer = BertTokenizer.from_pretrained('uncased_L-12_H-768_A-12', do_lower_case=True)\n",
"#tokenizer = BertTokenizer.from_pretrained('bert-base-uncased', do_lower_case=True)\n",
"\n",
"#max_length_text = 100\n",
"test_sentence = 'Test tokenization sentence. Followed by another sentence'\n",
"\n",
"transformer_input = convert_example_to_feature(test_sentence) \n",
"\n",
"#print(\"input\")\n",
"#print(transformer_input)\n",
"\n",
"# bert_input = tokenizer.encode_plus(\n",
"# test_sentence, \n",
"# add_special_tokens = True, # add [CLS], [SEP]\n",
"# max_length = max_length_text, # max length of the text that can go to BERT\n",
"# pad_to_max_length = True, # add [PAD] tokens\n",
"# return_attention_mask = True, # add attention mask to not focus on pad tokens\n",
"# )\n",
"# print('encoded', bert_input)\n",
"\n",
"\n",
"train_data, validate_data = load_train_validate_lit_data(data_dir=\"data/CommonLit/\")\n",
"\n",
"test_data = validate_data.head(7)\n",
"\n",
"#train_data, test_data = load_train_test_imdb_data(data_dir=\"data/aclImdb/\")\n",
"\n",
"#print(\"train_data\", train_data)\n",
"\n",
"target = train_data.pop('score')\n",
"ds_train = tf.data.Dataset.from_tensor_slices((train_data.values, target.values))\n",
"\n",
"target = validate_data.pop('score')\n",
"ds_validate = tf.data.Dataset.from_tensor_slices((validate_data.values, target.values))\n",
"\n",
"\n",
"# for review, label in tfds.as_numpy(ds_train.take(5)):\n",
"# print('review', review[0:50], label)\n",
"\n",
"# (ds_train, ds_test), ds_info = tfds.load('imdb_reviews', \n",
"# split = (tfds.Split.TRAIN, tfds.Split.TEST),\n",
"# as_supervised=True,\n",
"# with_info=True)\n",
"\n",
"# print('info', ds_info)\n",
"\n",
"# map to the expected input to TFBertForSequenceClassification, see here \n",
"def map_example_to_dict(input_ids, attention_masks, token_type_ids, label):\n",
" \n",
" return {\n",
" \"input_ids\": input_ids,\n",
" \"token_type_ids\": token_type_ids,\n",
" \"attention_mask\": attention_masks,\n",
" }, label\n",
"\n",
"\n",
"\n",
"def encode_examples(ds, limit=-1):\n",
" # prepare list, so that we can build up final TensorFlow dataset from slices.\n",
" input_ids_list = []\n",
" token_type_ids_list = []\n",
" attention_mask_list = []\n",
" label_list = []\n",
" \n",
" if (limit > 0):\n",
" ds = ds.take(limit)\n",
" \n",
" n = 0\n",
" maxNids = 0\n",
" minNids = 1000000\n",
" sumNids = 0\n",
" \n",
" for text, label in tfds.as_numpy(ds):\n",
"\n",
" transformer_input = convert_example_to_feature(text[0].decode())\n",
" \n",
" nids = len(transformer_input['input_ids'])\n",
" \n",
" sumNids += nids\n",
" \n",
" if nids < minNids:\n",
" minNids = nids\n",
" \n",
" if nids > maxNids:\n",
" maxNids = nids\n",
"\n",
" # bert_input = convert_example_to_feature(codecs.decode(review,'ascii'))\n",
" if n % 300 == 0:\n",
" \n",
" print()\n",
" print(\"******* text\",text[0])\n",
" print()\n",
" \n",
" # print(\" *** transformer_input\",transformer_input)\n",
" print()\n",
" print(\"nr input ids\", len(transformer_input['input_ids']))\n",
"# print(len(transformer_input['input_ids']),\" *** input_ids\",transformer_input['input_ids'])\n",
" print()\n",
"\n",
" \n",
" # if n > 1:\n",
" # break\n",
" n += 1\n",
" \n",
" input_ids_list.append(transformer_input['input_ids'])\n",
" token_type_ids_list.append(transformer_input['token_type_ids'])\n",
" attention_mask_list.append(transformer_input['attention_mask'])\n",
" label_list.append([label])\n",
" \n",
" meanNids = sumNids / n\n",
" print(\"minNids\", minNids, \"meanNids\", meanNids, \"maxNids\", maxNids) \n",
" \n",
" return tf.data.Dataset.from_tensor_slices((input_ids_list, attention_mask_list, token_type_ids_list, label_list)).map(map_example_to_dict)\n",
"\n",
"\n",
"\n",
"def predict_testdata():\n",
" \n",
" xtest = pd.read_csv('../input/commonlitreadabilityprize/test.csv')\n",
" \n",
" texts = xtest['excerpt']\n",
" \n",
" print(\"test texts\",texts.head)\n",
" \n",
" testResults = DataFrame()\n",
" testResults = xtest[[\"id\"]].copy()\n",
" \n",
" token_type_ids_list = []\n",
" attention_mask_list = []\n",
" label_list = []\n",
" \n",
" predictedScores = []\n",
" \n",
" n = 0\n",
" \n",
" for text in texts:\n",
" \n",
" n += 1\n",
" \n",
" input_ids_list = []\n",
"\n",
" transformer_input = convert_example_to_feature(text)\n",
"\n",
" # if n % 500 == 0:\n",
" \n",
" # print()\n",
" # print(\"******* text \", text)\n",
" # print(\" *** transformer_input\",transformer_input)\n",
" # print(len(transformer_input['input_ids']),\" *** input_ids\",transformer_input['input_ids'])\n",
" # print()\n",
"\n",
" \n",
" # if n > 1:\n",
" # break\n",
" \n",
" input_ids_list.append(transformer_input['input_ids'])\n",
" # token_type_ids_list.append(transformer_input['token_type_ids'])\n",
" # attention_mask_list.append(transformer_input['attention_mask'])\n",
" \n",
" inp_tok = np.array([inputid for inputid in input_ids_list])\n",
" \n",
" preds = model.predict(inp_tok, batch_size=1, verbose=False)\n",
" \n",
" predictedScore = preds.logits[0][0]\n",
" \n",
" if n % 10 == 0:\n",
" print(\"n\", n, \"predictedScore\", predictedScore)\n",
" \n",
" predictedScores.append(predictedScore)\n",
"# preds = model.predict(inp_tok, batch_size=batch_size, verbose=True)\n",
" gc.collect()\n",
" \n",
"# print(\"texts\", texts)\n",
"# print(\"predictions\", preds.logits)\n",
"\n",
"# predictedScores = []\n",
" \n",
" n = 0\n",
" \n",
" print(\"prediction done\")\n",
" \n",
" testResults['target'] = predictedScores\n",
" \n",
" \n",
"\n",
" testResults.to_csv('xlnet.csv', index = False)\n",
" \n",
"\n",
"#batch_size = 50\n",
"\n",
"\n",
"# train dataset\n",
"print()\n",
"\n",
"training = True\n",
"\n",
"if training:\n",
" \n",
" print(\"training dataset\")\n",
" ds_train_encoded = encode_examples(ds_train)\n",
" ds_train_encoded_batched = ds_train_encoded.batch(batch_size)\n",
" #ds_train_encoded = encode_examples(ds_train).batch(batch_size)\n",
" #ds_train_encoded = encode_examples(ds_train).shuffle(10000).batch(batch_size)\n",
" # test dataset\n",
" print(\"validation dataset\")\n",
" ds_validate_encoded = encode_examples(ds_validate)\n",
" ds_validate_encoded_batched = ds_validate_encoded.batch(batch_size)\n",
" \n",
"# sys.exit()\n",
"\n",
" # recommended learning rate for Adam 5e-5, 3e-5, 2e-5\n",
" learning_rate = 2e-5\n",
" # we will do just 1 epoch for illustration, though multiple epochs might be better as long as we will not overfit the model\n",
"# number_of_epochs = 3\n",
" \n",
" # model initialization\n",
"# model = AutoModelForSequenceClassification.from_pretrained('./hf_xlnet-base-cased/', from_tf=True, num_labels=1)\n",
"# model = TFXLNetForSequenceClassification.from_pretrained('./hf_xlnet-base-cased/', num_labels=1)\n",
"\n",
" optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate, epsilon=1e-08)\n",
" loss = tf.keras.losses.MeanSquaredError()\n",
"\n",
"\n",
" step = 0\n",
" \n",
" while step <= 7:\n",
" # Place tensors on the CPU\n",
" with tf.device('/CPU:0'):\n",
" \n",
" newDir = './savedmodel/' + str(step + 1) \n",
" \n",
" if not os.path.exists(newDir):\n",
" os.makedirs(newDir)\n",
" \n",
" if step == 0:\n",
" # model = TFXLNetForSequenceClassification.from_pretrained('../input/xlnet01/savedmodel150_2best/', num_labels=1)\n",
" model = TFXLNetForSequenceClassification.from_pretrained('../input/xlnet01/hf_xlnet-base-cased/', num_labels=1)\n",
" else:\n",
" model = TFXLNetForSequenceClassification.from_pretrained('./savedmodel/' + str(step) + '/', num_labels=1)\n",
" \n",
" model.compile(optimizer=optimizer, loss=loss, metrics=[])\n",
" \n",
" print(\"start training with max_length_text\", max_length_text, \"batch_size\", batch_size, \"step\", step)\n",
" \n",
" history = model.fit(ds_train_encoded_batched, epochs=number_of_epochs, steps_per_epoch=10, validation_data=ds_validate_encoded_batched)\n",
" \n",
" print(\"training done step \" + str(step))\n",
" \n",
" step += 1\n",
" \n",
" model.save_pretrained('./savedmodel/' + str(step) + '/', saved_model=False)\n",
" \n",
" gc.collect()\n",
"\n",
"else:\n",
" # use saved model for prediction\n",
" with tf.device('/CPU:0'):\n",
"\n",
" model = TFXLNetForSequenceClassification.from_pretrained('../input/xlnet01/savedmodel150_2best', num_labels=1)\n",
" \n",
" print()\n",
" print(\"nr of testData\", len(testData))\n",
" print()\n",
" for testText in testData[:7]:\n",
" print(testText[:49])\n",
" \n",
"\n",
" predict_testdata()\n",
"\n",
" print()\n",
"\n",
"\n",
"\n",
"\n",
"sys.exit()\n",
"\n",
"predictions = model.predict(ds_validate_encoded, verbose = False)\n",
"print(\"type predictions\", type(predictions))\n",
"print(\"type predictions.logits\", type(predictions.logits))\n",
"print(\"predictions.logits\", predictions.logits)\n",
"print(\"len predictions\", len(predictions.logits))\n",
"#print(\"tf.argmax(predictions)\", tf.argmax(predictions).numpy())\n",
"#print(\"tf.nn.softmax(predictions, axis=-1)\", tf.nn.softmax(predictions.logits, axis=-1))\n",
"\n",
"print()\n",
"\n",
"print(\"test_data\", test_data)\n",
"\n",
"# result = model(ds, training=False)\n",
"# result = tf.argmax(result).numpy()\n",
"# print(result)\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<a href=\"./savedmodel/5/tf_model.h5\"> Download Model </a>\n",
"<a href=\"./savedmodel/5/config.json\"> Download Config </a>"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Ensemble"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"execution": {
"iopub.execute_input": "2021-06-25T19:42:17.207547Z",
"iopub.status.busy": "2021-06-25T19:42:17.207093Z",
"iopub.status.idle": "2021-06-25T19:42:17.236517Z",
"shell.execute_reply": "2021-06-25T19:42:17.235368Z",
"shell.execute_reply.started": "2021-06-25T19:42:17.207503Z"
},
"trusted": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"predictions\n",
" id target predtrsf avgred\n",
"0 c0f722661 -0.786303 -0.877908 -0.832105\n",
"1 f0953f0a5 -0.121382 0.276648 0.077633\n",
"2 0df072751 -0.838939 -0.771869 -0.805404\n",
"3 04caf4e0c -2.342430 -1.925204 -2.133817\n",
"4 0e63f8bea -1.534724 -1.855052 -1.694888\n",
"5 12537fe78 -0.725721 -0.330248 -0.527985\n",
"6 965e592c0 0.418392 0.393256 0.405824\n"
]
}
],
"source": [
"# -*- coding: utf-8 -*-\n",
"\"\"\"\n",
"Created on Thu Jun 17 14:37:27 2021\n",
"\n",
"@author: Jacob\n",
"\"\"\"\n",
"import pandas as pd \n",
"from pandas import DataFrame\n",
"\n",
"from sklearn.preprocessing import PolynomialFeatures\n",
"from sklearn.pipeline import make_pipeline\n",
"from sklearn.linear_model import LinearRegression\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn import datasets\n",
"from sklearn.metrics import mean_squared_error \n",
"\n",
"import numpy as np\n",
"from scipy.optimize import curve_fit\n",
"\n",
"import matplotlib.pyplot as plt\n",
"import math\n",
"import sys\n",
"\n",
"\n",
"\n",
"def sigmoid(x, L , theta, gamma, b):\n",
" \n",
" \n",
" y = L / (1 + np.exp(-gamma * (x - theta))) + b\n",
" \n",
" return (y)\n",
"\n",
"\n",
"predictionData = pd.read_csv('regression.csv')\n",
"\n",
"\n",
"resultsXLNet = pd.read_csv('xlnet.csv')\n",
"\n",
"predictionData['predtrsf'] = resultsXLNet['target']\n",
"\n",
"predictionData['avgred'] = (predictionData['target'] + predictionData['predtrsf']) / 2\n",
"\n",
"#y_pred = predictionData['predtrsf']\n",
"\n",
"\n",
"print(\"predictions\")\n",
"\n",
"print(predictionData)\n",
"\n",
"\n",
"# submissiion\n",
"xsub = xtest[[\"id\"]].copy()\n",
"xsub[\"target\"] = predictionData['avgred']\n",
"xsub.to_csv('submission.csv', index = False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
}
],
"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": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|