File size: 162,505 Bytes
477b130 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "9e7940e4-1ba3-4192-a82c-5008dc5ed698",
"metadata": {},
"outputs": [],
"source": [
"import gradio as gr\n",
"from transformers import pipeline\n",
"from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "54c98c8e-a9d2-453c-933a-6a945143361f",
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn.model_selection import train_test_split\n",
"import sklearn"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "4be240ca-2fe4-4d02-9955-c54d414fc795",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import pandas as pd"
]
},
{
"cell_type": "markdown",
"id": "0e93873a-e119-4fb5-aa38-b8814098f758",
"metadata": {},
"source": [
"### first we need to import our libraries dataset and convert them into .csv"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "ad1e3444-0197-4a5f-945d-bee10e977ffe",
"metadata": {},
"outputs": [],
"source": [
"spam_folder = \"enron2/spam\"\n",
"ham_folder = \"enron2/ham\""
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "262cfd88-9c03-4131-8e62-94dc9e5cce7e",
"metadata": {},
"outputs": [],
"source": [
"def load_emails(folder, label):\n",
" emails = []\n",
" for filename in os.listdir(folder):\n",
" if filename.endswith(\".txt\"):\n",
" with open(os.path.join(folder, filename), \"r\", encoding=\"utf-8\", errors=\"ignore\") as file:\n",
" text = file.read()\n",
" emails.append((text, label))\n",
" return emails"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "f54a8a8a-9e31-46b4-82c1-6111e158594b",
"metadata": {},
"outputs": [],
"source": [
"spam_emails = load_emails(spam_folder, label=1) \n",
"ham_emails = load_emails(ham_folder, label=0) "
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "8229102b-ec10-47f3-9cc8-dc42f7c4d6e5",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CSV file created successfully!\n"
]
}
],
"source": [
"df = pd.DataFrame(all_emails, columns=[\"text\", \"label\"])\n",
"df.to_csv(\"dataset/emails.csv\", index=False, escapechar='\\\\', quotechar='\"')\n",
"print(\"CSV file created successfully!\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "a5484a4b-6a93-40ea-993a-36118c5a31b1",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(\"dataset/emails.csv\")"
]
},
{
"cell_type": "markdown",
"id": "643bbc72-bfaa-4e82-85f8-3f216bc9e843",
"metadata": {},
"source": [
"### now we need to clean our messy dataset"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "d778066a-5526-428c-a118-4e1178b206c1",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package punkt to\n",
"[nltk_data] C:\\Users\\raofb\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package punkt is already up-to-date!\n",
"[nltk_data] Downloading package stopwords to\n",
"[nltk_data] C:\\Users\\raofb\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package stopwords is already up-to-date!\n",
"[nltk_data] Downloading package wordnet to\n",
"[nltk_data] C:\\Users\\raofb\\AppData\\Roaming\\nltk_data...\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import re\n",
"import nltk\n",
"from bs4 import BeautifulSoup\n",
"from nltk.corpus import stopwords\n",
"from nltk.stem import WordNetLemmatizer\n",
"from nltk.tokenize import word_tokenize\n",
"nltk.download('punkt')\n",
"nltk.download('stopwords')\n",
"nltk.download('wordnet')"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "24c1784f-8262-487a-9868-44762dc976ea",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package punkt_tab to\n",
"[nltk_data] C:\\Users\\raofb\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Unzipping tokenizers\\punkt_tab.zip.\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"nltk.download('punkt_tab')"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "e043a0fb-f7e0-4727-8aee-b8ecce88b835",
"metadata": {},
"outputs": [],
"source": [
"stop_words = set(stopwords.words('english'))\n",
"def clean_text(text):\n",
" # Lowercase\n",
" text = text.lower()\n",
" \n",
" # Remove HTML\n",
" text = BeautifulSoup(text, \"html.parser\").get_text()\n",
" \n",
" # Replace URLs and emails\n",
" text = re.sub(r'http\\S+', '<URL>', text)\n",
" text = re.sub(r'\\S+@\\S+', '<EMAIL>', text)\n",
" \n",
" # Remove special characters (retain $ for monetary values)\n",
" text = re.sub(r'[^\\w\\s$]', '', text)\n",
" \n",
" # Replace numbers (except after $)\n",
" text = re.sub(r'\\b\\d+\\b', '<NUM>', text)\n",
" \n",
" # Normalize whitespace\n",
" text = re.sub(r'\\s+', ' ', text).strip()\n",
"\n",
" tokens = word_tokenize(text)\n",
" lemmatizer = WordNetLemmatizer()\n",
" tokens = [lemmatizer.lemmatize(word) for word in tokens if word not in stopwords.words('english')]\n",
"\n",
" return ' '.join(tokens)"
]
},
{
"cell_type": "markdown",
"id": "f60b360e-c425-47f2-ad9c-6caf1d04f8ba",
"metadata": {},
"source": [
"### now we apply our nltk function to dataset"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "90b9a80e-0937-46c0-8430-226fa0f4d0cf",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"df = pd.read_csv('Dataset/emails.csv')\n",
"df['cleaned_text'] = df['text'].apply(clean_text)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "a425c6e7-5628-4af2-9f0f-c2fe8b7d5eb2",
"metadata": {},
"outputs": [],
"source": [
"df.to_csv('cleaned_emails.csv', index=False)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "54941e16-8791-426e-ba66-d207b90d7876",
"metadata": {
"scrolled": true
},
"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>text</th>\n",
" <th>label</th>\n",
" <th>cleaned_text</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Subject: fw : this is the solution i mentioned...</td>\n",
" <td>1</td>\n",
" <td>subject fw solution mentioned lsc oo thank ema...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Subject: advs\\ngreetings ,\\ni am benedicta lin...</td>\n",
" <td>1</td>\n",
" <td>subject advs greeting benedicta lindiwe hendri...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Subject: whats new in summer ? bawled\\ncarolyn...</td>\n",
" <td>1</td>\n",
" <td>subject whats new summer bawled carolyn regret...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Subject: \\nh $ ello\\ndea 54 r home owner ,\\nwe...</td>\n",
" <td>1</td>\n",
" <td>subject h $ ello dea < NUM > r home owner beet...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Subject: : ) ) you can not save the world by q...</td>\n",
" <td>1</td>\n",
" <td>subject save world quitting smoking save self ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Subject: need software ? click here .\\ntop qua...</td>\n",
" <td>1</td>\n",
" <td>subject need software click top quality softwa...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Subject: spend too much on your phone bill ? 2...</td>\n",
" <td>1</td>\n",
" <td>subject spend much phone bill < NUM > crystal ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>Subject: slotting order confirmation may 18 , ...</td>\n",
" <td>1</td>\n",
" <td>subject slotting order confirmation may < NUM ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>Subject: we shiip to ur country for mircosoft ...</td>\n",
" <td>1</td>\n",
" <td>subject shiip ur country mircosoft adobe norto...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>Subject: urgent business proposal ,\\nmrs . reg...</td>\n",
" <td>1</td>\n",
" <td>subject urgent business proposal mr regina ros...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" text label \\\n",
"0 Subject: fw : this is the solution i mentioned... 1 \n",
"1 Subject: advs\\ngreetings ,\\ni am benedicta lin... 1 \n",
"2 Subject: whats new in summer ? bawled\\ncarolyn... 1 \n",
"3 Subject: \\nh $ ello\\ndea 54 r home owner ,\\nwe... 1 \n",
"4 Subject: : ) ) you can not save the world by q... 1 \n",
"5 Subject: need software ? click here .\\ntop qua... 1 \n",
"6 Subject: spend too much on your phone bill ? 2... 1 \n",
"7 Subject: slotting order confirmation may 18 , ... 1 \n",
"8 Subject: we shiip to ur country for mircosoft ... 1 \n",
"9 Subject: urgent business proposal ,\\nmrs . reg... 1 \n",
"\n",
" cleaned_text \n",
"0 subject fw solution mentioned lsc oo thank ema... \n",
"1 subject advs greeting benedicta lindiwe hendri... \n",
"2 subject whats new summer bawled carolyn regret... \n",
"3 subject h $ ello dea < NUM > r home owner beet... \n",
"4 subject save world quitting smoking save self ... \n",
"5 subject need software click top quality softwa... \n",
"6 subject spend much phone bill < NUM > crystal ... \n",
"7 subject slotting order confirmation may < NUM ... \n",
"8 subject shiip ur country mircosoft adobe norto... \n",
"9 subject urgent business proposal mr regina ros... "
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"read = pd.read_csv(\"cleaned_emails.csv\")\n",
"read.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "f4b111d3-d794-4aaa-ac45-ef86a398cddf",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv('cleaned_emails.csv')\n",
"\n",
"# Drop the 'text' column\n",
"df = df.drop(columns=['text'])\n",
"\n",
"# Rename 'cleaned_text' to 'text'\n",
"df = df.rename(columns={'cleaned_text': 'text'})\n",
"\n",
"# Save the updated DataFrame to a new CSV file (or overwrite the existing one)\n",
"df.to_csv('Cleaned_data.csv', index=False)"
]
},
{
"cell_type": "markdown",
"id": "04a92aca-fa9c-468b-84dd-b6bc404b2851",
"metadata": {},
"source": [
"### 2nd cleaning ---------------------------"
]
},
{
"cell_type": "code",
"execution_count": 38,
"id": "977a3274-d470-4bf1-9467-dd63a0774ee7",
"metadata": {},
"outputs": [],
"source": [
"from langdetect import detect, LangDetectException\n",
"from nltk.tokenize import word_tokenize, sent_tokenize"
]
},
{
"cell_type": "code",
"execution_count": 39,
"id": "e690b5d1-aa74-4146-9bda-9437790ae571",
"metadata": {},
"outputs": [],
"source": [
"stop_words = set(stopwords.words('english'))\n",
"lemmatizer = WordNetLemmatizer()\n",
"\n",
"def clean_text(text):\n",
" try:\n",
" # Detect and remove non-English text\n",
" if detect(text) != 'en':\n",
" return ''\n",
" except LangDetectException:\n",
" return ''\n",
" \n",
" # Lowercase\n",
" text = text.lower()\n",
" \n",
" # Remove HTML\n",
" text = BeautifulSoup(text, \"html.parser\").get_text()\n",
" \n",
" # Enhanced URL/email replacement\n",
" text = re.sub(r'\\b(?:https?://|www\\.)\\S+', '<URL>', text)\n",
" text = re.sub(r'\\b[\\w\\.-]+@[\\w\\.-]+\\.\\w{2,}\\b', '<EMAIL>', text)\n",
" \n",
" # Date pattern replacement (MM/DD/YYYY, DD-MM-YYYY, Month names, etc.)\n",
" text = re.sub(r'\\b(\\d{1,2}[/-]\\d{1,2}[/-]\\d{2,4}\\b|(?:jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)[a-z]*\\s+\\d{1,2},?\\s+\\d{4})', '<DATE>', text)\n",
" \n",
" # Time pattern replacement\n",
" text = re.sub(r'\\b\\d{1,2}:\\d{2}\\s*(?:am|pm)?\\b', '<TIME>', text)\n",
" \n",
" # Handle monetary values before general number replacement\n",
" money_values = re.findall(r'\\$\\d+[\\d,.]*', text)\n",
" text = re.sub(r'\\$\\d+[\\d,.]*', '<MONEY>', text)\n",
" \n",
" # Replace other numbers\n",
" text = re.sub(r'\\b\\d+\\b', '<NUM>', text)\n",
" \n",
" # Split and recombine long sentences\n",
" sentences = sent_tokenize(text)\n",
" processed_sentences = []\n",
" for sent in sentences:\n",
" # Limit sentence length to 15 words\n",
" tokens = word_tokenize(sent)[:15]\n",
" processed_sentences.append(' '.join(tokens))\n",
" text = ' '.join(processed_sentences)\n",
" \n",
" # Remove special characters (keep $ for money handling)\n",
" text = re.sub(r'[^\\w\\s<>]', '', text)\n",
" \n",
" # Tokenization and lemmatization\n",
" tokens = word_tokenize(text)\n",
" tokens = [lemmatizer.lemmatize(word) for word in tokens if word not in stop_words]\n",
" \n",
" return ' '.join(tokens)"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "64a46265-6d3e-4f80-bca9-5c6b418e0b55",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv('Cleaned_data.csv')\n",
"df['cleaned_text'] = df['text'].apply(clean_text)\n"
]
},
{
"cell_type": "code",
"execution_count": 41,
"id": "038cbb13-af40-4376-8721-d8a337aaf59e",
"metadata": {},
"outputs": [],
"source": [
"df.to_csv('cleaned_data1.csv', index=False)"
]
},
{
"cell_type": "markdown",
"id": "ecbb27b3-0a56-40c2-a3a9-79ccb0752c78",
"metadata": {},
"source": [
"#### we save our final data into our directories "
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "0a079539-bbb3-47b2-9488-71c429a13dd9",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv('Final_data.csv')\n",
"\n",
"# Drop the 'text' column\n",
"df = df.drop(columns=['text'])\n",
"\n",
"# Rename 'cleaned_text' to 'text'\n",
"df = df.rename(columns={'cleaned_text': 'text'})\n",
"\n",
"# Save the updated DataFrame to a new CSV file (or overwrite the existing one)\n",
"df.to_csv('test.csv', index=False)"
]
},
{
"cell_type": "markdown",
"id": "60e531d9-0caa-4fc7-a691-e30e91a6d515",
"metadata": {},
"source": [
"### now we split our data into training and testing"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "128b90d9-b454-4f88-970a-8f5257b17671",
"metadata": {},
"outputs": [],
"source": [
"from sklearn.model_selection import train_test_split"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "95b7cbf5-127d-4af1-bf25-1a7c9c9c859d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" category text\n",
"0 spam subject fw solution mentioned lsc oo thank ema...\n",
"1 spam subject advs greeting benedicta lindiwe hendri...\n",
"2 spam subject whats new summer bawled carolyn regret...\n",
"3 spam subject h $ ello dea < NUM > r home owner beet...\n",
"4 spam subject save world quitting smoking save self ...\n",
"category\n",
"spam 5996\n",
"ham 5861\n",
"Name: count, dtype: int64\n"
]
}
],
"source": [
"df = pd.read_csv(\"updated_dataset.csv\")\n",
"print(df.head()) # we check the first row\n",
"print(df[\"category\"].value_counts()) # Check classes"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "9aa78718-154e-498e-b792-b63c2410cc71",
"metadata": {},
"outputs": [],
"source": [
"X = df[\"text\"] # Input text\n",
"y = df[\"category\"] # Labels (0 or 1)\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(\n",
" X,\n",
" y,\n",
" test_size=0.2, ## 20% of data for testing\n",
" random_state=42, ## Seed for reproducibility\n",
" stratify=y ## Preserve spam/ham ratio in both splits\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "bbc78d97-0357-464b-b26b-b4e39b185f94",
"metadata": {},
"outputs": [],
"source": [
"import tensorflow as tf"
]
},
{
"cell_type": "markdown",
"id": "3f417943-a5f7-4db6-bef5-b046c5d874fd",
"metadata": {},
"source": [
"### SAVE OUR TRAIN AND TEST DATA"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "6bd3a326-0e59-4b53-94c1-7e54dcab6834",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Training samples: 9485\n",
"Testing samples: 2372\n"
]
}
],
"source": [
"train_df = pd.DataFrame({\"text\": X_train, \"category\": y_train})\n",
"test_df = pd.DataFrame({\"text\": X_test, \"category\": y_test})\n",
"\n",
"# Save to CSV files\n",
"train_df.to_csv(\"Train and Test/train.csv\", index=False)\n",
"test_df.to_csv(\"Train and Test/test.csv\", index=False)\n",
"\n",
"print(f\"Training samples: {len(train_df)}\")\n",
"print(f\"Testing samples: {len(test_df)}\")"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "e7dffbbc-765e-4093-9ec7-baac9f63f873",
"metadata": {
"jupyter": {
"source_hidden": true
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" category text\n",
"0 spam subject fw solution mentioned lsc oo thank ema...\n",
"1 spam subject advs greeting benedicta lindiwe hendri...\n",
"2 spam subject whats new summer bawled carolyn regret...\n",
"3 spam subject h $ ello dea < NUM > r home owner beet...\n",
"4 spam subject save world quitting smoking save self ...\n"
]
}
],
"source": [
"import pandas as pd\n",
"\n",
"# Load your CSV dataset\n",
"df = pd.read_csv('Final_data.csv')\n",
"\n",
"# Rename the 'label' column to 'category'\n",
"df.rename(columns={'label': 'category'}, inplace=True)\n",
"\n",
"# Replace 0 with 'ham' and 1 with 'spam' in the 'category' column\n",
"df['category'] = df['category'].replace({0: 'ham', 1: 'spam'})\n",
"\n",
"# Save the updated DataFrame back to a CSV (optional)\n",
"df.to_csv('updated_dataset.csv', index=False)\n",
"\n",
"# Display the updated DataFrame\n",
"print(df.head())"
]
},
{
"cell_type": "markdown",
"id": "97a86b3e-f6e2-4aba-a924-8af72ff049a1",
"metadata": {},
"source": [
"### Check our split data values"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "0efe481d-e9f2-44b4-91f8-e42aa7c9709a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Train class distribution:\n",
" category\n",
"spam 4796\n",
"ham 4689\n",
"Name: count, dtype: int64\n",
"Test class distribution:\n",
" category\n",
"spam 1200\n",
"ham 1172\n",
"Name: count, dtype: int64\n"
]
}
],
"source": [
"print(\"Train class distribution:\\n\", train_df[\"category\"].value_counts())\n",
"print(\"Test class distribution:\\n\", test_df[\"category\"].value_counts())"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "4272c7ef-3e31-4779-92b3-9385c1b9f3d6",
"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>text</th>\n",
" <th>category</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>subject need outstanding logo working company ...</td>\n",
" <td>spam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>subject weijun decided interview guess mean ba...</td>\n",
" <td>ham</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>subject investment partnership proposal dear s...</td>\n",
" <td>spam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>subject tage resume submittal need time extern...</td>\n",
" <td>ham</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>subject trading ag prod vince wanted let know ...</td>\n",
" <td>ham</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>subject utf < NUM > q best dvd collect utf < N...</td>\n",
" <td>spam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>subject portcalc methodology keith power emrs ...</td>\n",
" <td>ham</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>subject ibuyit approver ah wonderful new syste...</td>\n",
" <td>ham</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>subject osman sezgen steve kromer requesting o...</td>\n",
" <td>ham</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>subject read email change life dear homeowner ...</td>\n",
" <td>spam</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" text category\n",
"0 subject need outstanding logo working company ... spam\n",
"1 subject weijun decided interview guess mean ba... ham\n",
"2 subject investment partnership proposal dear s... spam\n",
"3 subject tage resume submittal need time extern... ham\n",
"4 subject trading ag prod vince wanted let know ... ham\n",
"5 subject utf < NUM > q best dvd collect utf < N... spam\n",
"6 subject portcalc methodology keith power emrs ... ham\n",
"7 subject ibuyit approver ah wonderful new syste... ham\n",
"8 subject osman sezgen steve kromer requesting o... ham\n",
"9 subject read email change life dear homeowner ... spam"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_train = pd.read_csv(\"Train and Test/train.csv\")\n",
"df_train.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "a75e71c9-468d-49e0-811d-2b416d1cbe5b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(4689, 2)"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_ham = df_train[df_train['category']=='ham']\n",
"df_ham.shape"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "1bc2aece-1656-4019-94dd-0b7fb4710b78",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(4796, 2)"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_spam = df_train[df_train['category']=='spam']\n",
"df_spam.shape"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "fc422e3e-df9d-4e06-b722-daee1659179a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(9485, 2)"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_balanced = pd.concat([df_ham, df_spam])\n",
"df_balanced.shape"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "81ce7ac6-619b-4d4e-ad41-769e2159a6d3",
"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>text</th>\n",
" <th>category</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>9456</th>\n",
" <td>subject get thru july newsletter get thru news...</td>\n",
" <td>spam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9458</th>\n",
" <td>subject cheap med nowrpmsqp every ph armaceuti...</td>\n",
" <td>spam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9459</th>\n",
" <td>subject trusted source prescription medication...</td>\n",
" <td>spam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9460</th>\n",
" <td>subject would hate reject chance reduce expend...</td>\n",
" <td>spam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9469</th>\n",
" <td>subject backplanes < NUM > vicodin whim cocked...</td>\n",
" <td>spam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9473</th>\n",
" <td>subject love girl idn wan na see girl naked pc...</td>\n",
" <td>spam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9476</th>\n",
" <td>subject clalis $ < NUM > < NUM > discount drug...</td>\n",
" <td>spam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9479</th>\n",
" <td>subject shoot spe rm drink increase cum volume...</td>\n",
" <td>spam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9483</th>\n",
" <td>subject george williams george williams abidja...</td>\n",
" <td>spam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9484</th>\n",
" <td>subject utf < NUM > q election result r utf < ...</td>\n",
" <td>spam</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" text category\n",
"9456 subject get thru july newsletter get thru news... spam\n",
"9458 subject cheap med nowrpmsqp every ph armaceuti... spam\n",
"9459 subject trusted source prescription medication... spam\n",
"9460 subject would hate reject chance reduce expend... spam\n",
"9469 subject backplanes < NUM > vicodin whim cocked... spam\n",
"9473 subject love girl idn wan na see girl naked pc... spam\n",
"9476 subject clalis $ < NUM > < NUM > discount drug... spam\n",
"9479 subject shoot spe rm drink increase cum volume... spam\n",
"9483 subject george williams george williams abidja... spam\n",
"9484 subject utf < NUM > q election result r utf < ... spam"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_balanced.tail(10)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "65f1fe2c-7a36-414c-8315-3647bd222686",
"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>text</th>\n",
" <th>category</th>\n",
" <th>spam</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2123</th>\n",
" <td>subject reminder cera executive roundtable hou...</td>\n",
" <td>ham</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3480</th>\n",
" <td>subject fw tw docket rp < NUM > < NUM > < NUM ...</td>\n",
" <td>ham</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1113</th>\n",
" <td>subject < NUM > sm unique logo business lack v...</td>\n",
" <td>spam</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>365</th>\n",
" <td>subject satellite dish click info stop getting...</td>\n",
" <td>spam</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1920</th>\n",
" <td>subject truly amazed hi new product offer c _ ...</td>\n",
" <td>spam</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2371</th>\n",
" <td>subject chess board widow living < NUM > hi</td>\n",
" <td>spam</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8423</th>\n",
" <td>subject enron stanford program stinson monday ...</td>\n",
" <td>ham</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7240</th>\n",
" <td>subject change lifestyle < NUM > k month bait ...</td>\n",
" <td>spam</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7885</th>\n",
" <td>subject cera monthly summary july < NUM > cera...</td>\n",
" <td>ham</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7869</th>\n",
" <td>subject save money buying ftware enough money ...</td>\n",
" <td>spam</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" text category spam\n",
"2123 subject reminder cera executive roundtable hou... ham 0\n",
"3480 subject fw tw docket rp < NUM > < NUM > < NUM ... ham 0\n",
"1113 subject < NUM > sm unique logo business lack v... spam 1\n",
"365 subject satellite dish click info stop getting... spam 1\n",
"1920 subject truly amazed hi new product offer c _ ... spam 1\n",
"2371 subject chess board widow living < NUM > hi spam 1\n",
"8423 subject enron stanford program stinson monday ... ham 0\n",
"7240 subject change lifestyle < NUM > k month bait ... spam 1\n",
"7885 subject cera monthly summary july < NUM > cera... ham 0\n",
"7869 subject save money buying ftware enough money ... spam 1"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_balanced['spam'] = df_balanced['category'].apply(lambda x: 1 if x==\"spam\" else 0)\n",
"df_balanced.sample(10)"
]
},
{
"cell_type": "markdown",
"id": "022e9214-90da-476c-b3ec-12bee25e80a4",
"metadata": {},
"source": [
"### -----------------------------------------------Part-2------------------------------------------------------------------------"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "047a7701-f782-4f80-aaf5-6bafc5301fbb",
"metadata": {},
"outputs": [],
"source": [
"import tensorflow as tf\n",
"import tensorflow_hub as hub\n",
"import tensorflow_text as text\n",
"import keras_nlp"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "645881bc-ecfc-461b-9a14-61c64c5f3764",
"metadata": {},
"outputs": [],
"source": [
"preprocess_path = \"/Users/techgarage/Projects/Data Engineering/Final Project/bert-tensorflow2-en-uncased-preprocess-v3\"\n",
"encoder_path = \"/Users/techgarage/Projects/Data Engineering/Final Project/bert-tensorflow2-en-uncased-l-12-h-768-a-12-v4\""
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "d5e2d09b-c72f-4693-89fb-7d86134b7acd",
"metadata": {},
"outputs": [],
"source": [
"bert_preprocess = hub.KerasLayer(preprocess_path)\n",
"bert_encoder = hub.KerasLayer(encoder_path, trainable=True) "
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "d7023825-23df-4ab1-85c3-ea261b3a1761",
"metadata": {
"collapsed": true,
"jupyter": {
"outputs_hidden": true,
"source_hidden": true
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'default': <tf.Tensor: shape=(2, 768), dtype=float32, numpy=\n",
"array([[-0.9430887 , -0.57238555, -0.8907942 , ..., -0.8635234 ,\n",
" -0.7363553 , 0.93383116],\n",
" [-0.8458787 , -0.3137438 , -0.5593949 , ..., -0.3633124 ,\n",
" -0.6121973 , 0.8722634 ]], dtype=float32)>, 'pooled_output': <tf.Tensor: shape=(2, 768), dtype=float32, numpy=\n",
"array([[-0.9430887 , -0.57238555, -0.8907942 , ..., -0.8635234 ,\n",
" -0.7363553 , 0.93383116],\n",
" [-0.8458787 , -0.3137438 , -0.5593949 , ..., -0.3633124 ,\n",
" -0.6121973 , 0.8722634 ]], dtype=float32)>, 'sequence_output': <tf.Tensor: shape=(2, 128, 768), dtype=float32, numpy=\n",
"array([[[-0.19839856, -0.20800582, -0.1962688 , ..., -0.47272685,\n",
" 0.0864562 , 0.7098722 ],\n",
" [-0.5383126 , -0.7158387 , -0.28930873, ..., -0.72038037,\n",
" 0.5794679 , 0.39614454],\n",
" [-0.14156267, -0.7373614 , 0.37026387, ..., -0.37185436,\n",
" 0.07691361, 0.9704544 ],\n",
" ...,\n",
" [ 0.06476687, -0.4518682 , 0.21092355, ..., 0.10411158,\n",
" -0.15344658, 0.15741925],\n",
" [ 0.00561799, -0.4243467 , 0.17027403, ..., 0.12554014,\n",
" -0.1677104 , 0.14828748],\n",
" [-0.06908819, -0.43356168, 0.25077093, ..., 0.12376285,\n",
" -0.21341398, 0.12534308]],\n",
"\n",
" [[-0.05573511, 0.17838944, -0.12837237, ..., -0.16575927,\n",
" 0.15549946, 0.21796423],\n",
" [ 0.27656567, -0.06027734, 0.24292594, ..., 0.05262224,\n",
" 0.5221071 , -0.07443378],\n",
" [ 0.05904233, 0.11985369, -0.04732013, ..., 0.05382551,\n",
" 0.24277204, 0.04877569],\n",
" ...,\n",
" [-0.06302132, 0.17733227, 0.40315932, ..., 0.11782701,\n",
" -0.20818709, -0.0962089 ],\n",
" [-0.0760133 , 0.21092619, 0.45218655, ..., 0.14849319,\n",
" -0.26165274, -0.06360148],\n",
" [ 0.1626576 , 0.12422754, 0.5222455 , ..., 0.24048476,\n",
" -0.24223803, -0.14883336]]], dtype=float32)>, 'encoder_outputs': [<tf.Tensor: shape=(2, 128, 768), dtype=float32, numpy=\n",
"array([[[ 0.04222755, -0.00565784, -0.15892257, ..., 0.24197707,\n",
" -0.0975021 , -0.04534519],\n",
" [-0.57877016, 0.4591414 , 0.17042653, ..., 0.17379816,\n",
" 0.3257624 , -0.1035484 ],\n",
" [-1.0044422 , -0.39177877, -0.36441994, ..., 0.4770085 ,\n",
" 0.24922882, 0.28879505],\n",
" ...,\n",
" [-0.02801086, -0.17419498, 0.6732487 , ..., 0.30962443,\n",
" -0.48121578, 0.01905968],\n",
" [-0.11255493, -0.16464029, 0.5454035 , ..., 0.33624443,\n",
" -0.38363996, -0.0586778 ],\n",
" [ 0.01631033, -0.09114645, 0.5857597 , ..., 0.65954405,\n",
" -0.7021383 , -0.12894379]],\n",
"\n",
" [[ 0.20487462, 0.04901898, 0.01649245, ..., 0.04353925,\n",
" 0.04925472, 0.02829387],\n",
" [ 1.4605433 , 0.41298807, 0.85494065, ..., 0.6134594 ,\n",
" 0.80718094, -0.2633693 ],\n",
" [-0.05972779, -0.18533123, -0.5527816 , ..., -0.10191233,\n",
" 0.65774244, 0.43938908],\n",
" ...,\n",
" [ 0.01185893, -0.2301354 , 0.6187198 , ..., 0.19465885,\n",
" -0.42088404, 0.1006694 ],\n",
" [-0.07991942, -0.24889088, 0.48138082, ..., 0.21367387,\n",
" -0.30915743, 0.01614393],\n",
" [ 0.04677403, -0.17776218, 0.5053538 , ..., 0.582287 ,\n",
" -0.6344621 , -0.06023622]]], dtype=float32)>, <tf.Tensor: shape=(2, 128, 768), dtype=float32, numpy=\n",
"array([[[-0.08198933, -0.24693474, -0.39003628, ..., 0.439112 ,\n",
" 0.05109447, -0.0044647 ],\n",
" [-0.9807272 , 0.6689387 , 0.48308071, ..., 0.1564306 ,\n",
" 0.09792089, -0.02700958],\n",
" [-1.1450135 , -0.21649039, 0.16978282, ..., 0.54555625,\n",
" -0.08833696, 0.4793641 ],\n",
" ...,\n",
" [-0.07667708, -0.46201542, 0.5964664 , ..., 0.88089323,\n",
" -0.61731744, -0.07153333],\n",
" [-0.22768137, -0.37603164, 0.567706 , ..., 0.7776769 ,\n",
" -0.6923214 , -0.16456038],\n",
" [-0.07292495, -0.47088498, 0.42633674, ..., 1.1841507 ,\n",
" -0.885921 , -0.15032959]],\n",
"\n",
" [[ 0.06639995, -0.14721206, -0.10672337, ..., 0.06945898,\n",
" 0.08428381, 0.07299946],\n",
" [ 1.2143568 , 0.48814198, 1.1617565 , ..., 0.427473 ,\n",
" 1.390525 , -0.6787748 ],\n",
" [-0.0177076 , -0.1816837 , -0.19067988, ..., -0.30094966,\n",
" 0.28298748, 0.4206936 ],\n",
" ...,\n",
" [-0.04438182, -0.12137772, 0.4709124 , ..., 0.74642366,\n",
" -0.4703179 , -0.0582533 ],\n",
" [-0.06758315, -0.02387481, 0.50011903, ..., 0.79208016,\n",
" -0.4944227 , -0.11274293],\n",
" [ 0.13245018, -0.14612037, 0.41312754, ..., 1.0047185 ,\n",
" -0.68071204, -0.25335985]]], dtype=float32)>, <tf.Tensor: shape=(2, 128, 768), dtype=float32, numpy=\n",
"array([[[ 1.88205242e-02, -4.19564575e-01, -9.72785205e-02, ...,\n",
" 4.34135646e-01, 2.40221262e-01, 2.04072416e-01],\n",
" [-4.48446095e-01, 1.81707352e-01, 4.33682859e-01, ...,\n",
" -5.54058142e-02, -4.61606085e-02, 1.36725694e-01],\n",
" [-1.06392920e+00, -2.69372582e-01, 6.61358237e-01, ...,\n",
" 3.99683654e-01, -2.06476793e-01, 2.66633153e-01],\n",
" ...,\n",
" [-1.29950047e-03, -5.26915431e-01, 8.76984775e-01, ...,\n",
" 1.12286353e+00, -8.32752362e-02, -8.66764039e-02],\n",
" [-5.30661419e-02, -4.99284506e-01, 7.59432733e-01, ...,\n",
" 1.04773223e+00, -1.10542774e-01, -2.57611960e-01],\n",
" [ 4.16158885e-03, -5.81846416e-01, 6.97214842e-01, ...,\n",
" 1.34556234e+00, -2.37027630e-01, -1.53350607e-01]],\n",
"\n",
" [[ 1.98504999e-02, -2.34437555e-01, 1.12557501e-01, ...,\n",
" 2.38051996e-01, 1.49298698e-01, 2.20182493e-01],\n",
" [ 1.29915905e+00, 3.28751534e-01, 1.23260486e+00, ...,\n",
" 3.10731322e-01, 7.98960507e-01, -5.44931173e-01],\n",
" [-5.44543229e-02, -6.17580451e-02, -6.97334185e-02, ...,\n",
" -2.71830112e-01, 2.33011786e-03, 4.77785051e-01],\n",
" ...,\n",
" [-8.16972479e-02, -1.25493705e-01, 7.47347534e-01, ...,\n",
" 9.28182423e-01, -6.34126663e-02, -1.33340880e-01],\n",
" [-1.30778015e-01, -3.14075388e-02, 6.66660905e-01, ...,\n",
" 9.91367698e-01, -1.05210334e-01, -1.73617572e-01],\n",
" [ 6.76381961e-02, -1.79536566e-01, 7.31914282e-01, ...,\n",
" 1.12215555e+00, -2.49684200e-01, -3.13854456e-01]]],\n",
" dtype=float32)>, <tf.Tensor: shape=(2, 128, 768), dtype=float32, numpy=\n",
"array([[[ 0.23253876, -0.5878328 , -0.5117078 , ..., 0.54637855,\n",
" 0.3729315 , 0.8276504 ],\n",
" [-0.4173653 , 0.10359846, 0.07069035, ..., 0.13642198,\n",
" -0.09496864, -0.17008804],\n",
" [-1.3769395 , -0.33059418, 0.7084929 , ..., 0.23613824,\n",
" -0.13318482, 0.6639668 ],\n",
" ...,\n",
" [-0.14409971, -0.95972544, 0.8196844 , ..., 1.029249 ,\n",
" -0.505237 , -0.0820753 ],\n",
" [-0.24914083, -0.8525534 , 0.71119857, ..., 0.9299053 ,\n",
" -0.5289181 , -0.19867681],\n",
" [-0.17688558, -1.0652891 , 0.8114191 , ..., 1.232535 ,\n",
" -0.5275141 , -0.18064196]],\n",
"\n",
" [[ 0.07835185, -0.16930445, -0.25908536, ..., 0.11454112,\n",
" 0.27769732, 0.53462124],\n",
" [ 1.1889614 , -0.39503306, 0.7059822 , ..., 0.3740296 ,\n",
" 0.11370531, -0.6435863 ],\n",
" [ 0.31502503, -0.49227 , -0.01700327, ..., -0.00761845,\n",
" 0.27753487, 0.73732984],\n",
" ...,\n",
" [-0.27396932, -0.601428 , 0.8877718 , ..., 0.7409698 ,\n",
" -0.56265104, 0.03451739],\n",
" [-0.3649508 , -0.45706168, 0.78661674, ..., 0.76761526,\n",
" -0.5909752 , -0.01154372],\n",
" [-0.01357281, -0.62979025, 0.93073106, ..., 0.9332208 ,\n",
" -0.68241715, -0.3531196 ]]], dtype=float32)>, <tf.Tensor: shape=(2, 128, 768), dtype=float32, numpy=\n",
"array([[[ 0.11884356, -0.5148154 , -0.32688135, ..., 0.101791 ,\n",
" 0.23662724, 0.88309544],\n",
" [-0.2888226 , 0.30233493, -0.06162377, ..., -0.19382872,\n",
" -0.0729757 , -0.23562919],\n",
" [-1.2452599 , -0.5015673 , 0.32685408, ..., 0.53150743,\n",
" -0.3750096 , 0.73725295],\n",
" ...,\n",
" [ 0.03977381, -0.8479642 , 0.7485787 , ..., 0.6571404 ,\n",
" -0.6224219 , -0.21472959],\n",
" [-0.0742109 , -0.7208384 , 0.60503834, ..., 0.6880955 ,\n",
" -0.6776467 , -0.3155314 ],\n",
" [-0.06136909, -0.9506144 , 0.76140445, ..., 0.8818397 ,\n",
" -0.8236465 , -0.3216293 ]],\n",
"\n",
" [[-0.04276581, 0.07925801, -0.28103375, ..., -0.33148646,\n",
" 0.41494718, 0.64737356],\n",
" [ 0.7152701 , -0.49672917, 1.1861763 , ..., -0.18042506,\n",
" 0.06279897, -0.78743297],\n",
" [ 0.49038363, -0.30374768, -0.25442252, ..., -0.3617459 ,\n",
" 0.42115545, 0.861674 ],\n",
" ...,\n",
" [-0.17577647, -0.24708512, 1.2082454 , ..., -0.04786705,\n",
" -0.13006926, -0.3941232 ],\n",
" [-0.17560306, -0.11561126, 1.0242093 , ..., 0.03608295,\n",
" -0.18673371, -0.4092454 ],\n",
" [ 0.18188742, -0.33772412, 1.145873 , ..., 0.23452786,\n",
" -0.31088895, -0.6601856 ]]], dtype=float32)>, <tf.Tensor: shape=(2, 128, 768), dtype=float32, numpy=\n",
"array([[[ 0.06071234, -0.7956739 , -0.4278758 , ..., 0.02831682,\n",
" 0.33086035, 0.78214604],\n",
" [-0.48937097, 0.10409439, -0.5440423 , ..., -0.6400165 ,\n",
" 0.06334624, -0.07265621],\n",
" [-0.8370529 , -0.43852547, 0.02520663, ..., 0.22630142,\n",
" -0.22112286, 0.7913871 ],\n",
" ...,\n",
" [-0.10923568, -0.8002732 , 1.0630294 , ..., 0.44094047,\n",
" -0.6448848 , -0.13665396],\n",
" [-0.2489643 , -0.7156884 , 0.97479945, ..., 0.57076055,\n",
" -0.72722065, -0.20035143],\n",
" [-0.17111725, -0.9605686 , 1.0823051 , ..., 0.782978 ,\n",
" -0.85319215, -0.20169927]],\n",
"\n",
" [[-0.03043595, -0.3351068 , -0.13165352, ..., -0.32476133,\n",
" 0.35392705, 0.56300366],\n",
" [ 0.58081585, -0.35410577, 1.2072893 , ..., -0.2792115 ,\n",
" 0.03580071, -0.7630123 ],\n",
" [ 0.5630262 , -0.4679435 , -0.38500452, ..., -0.45557278,\n",
" -0.00384355, 0.8763245 ],\n",
" ...,\n",
" [-0.23482245, -0.10766596, 1.4201454 , ..., 0.07200695,\n",
" -0.3376395 , -0.47948518],\n",
" [-0.25911236, 0.01417249, 1.3014742 , ..., 0.17332402,\n",
" -0.39001083, -0.49856895],\n",
" [ 0.21144739, -0.26251334, 1.3444276 , ..., 0.28540578,\n",
" -0.39566213, -0.74265194]]], dtype=float32)>, <tf.Tensor: shape=(2, 128, 768), dtype=float32, numpy=\n",
"array([[[-0.02161034, -0.9120089 , -0.2800715 , ..., -0.10675792,\n",
" 0.6008877 , 0.961232 ],\n",
" [-0.76047474, -0.03780157, -0.7370079 , ..., -0.39759997,\n",
" -0.07949114, 0.102171 ],\n",
" [-1.0510209 , -0.33599663, 0.21717477, ..., -0.04515497,\n",
" -0.0876311 , 1.1958765 ],\n",
" ...,\n",
" [ 0.24660665, -0.8857314 , 1.0813076 , ..., 0.4609538 ,\n",
" -0.3729293 , 0.05634779],\n",
" [ 0.11600631, -0.79443914, 0.9784327 , ..., 0.57947654,\n",
" -0.50094205, -0.02501383],\n",
" [ 0.06238839, -1.0905796 , 1.1894618 , ..., 0.7936153 ,\n",
" -0.64365435, -0.00459876]],\n",
"\n",
" [[-0.02165605, -0.00627999, -0.09550503, ..., -0.46217042,\n",
" 0.49604496, 0.5488441 ],\n",
" [ 0.82693785, -0.37880576, 1.3755609 , ..., 0.05833477,\n",
" 0.0601463 , -0.9805254 ],\n",
" [ 0.6558955 , -0.07985266, -0.06040744, ..., -0.0520392 ,\n",
" -0.07544921, 0.7840497 ],\n",
" ...,\n",
" [-0.12956248, -0.13533002, 1.4172117 , ..., 0.5473515 ,\n",
" -0.3337415 , -0.3622912 ],\n",
" [-0.12117871, -0.05489191, 1.328096 , ..., 0.51856905,\n",
" -0.3706308 , -0.34924036],\n",
" [ 0.34187743, -0.27316713, 1.5144311 , ..., 0.68457603,\n",
" -0.24899381, -0.59764874]]], dtype=float32)>, <tf.Tensor: shape=(2, 128, 768), dtype=float32, numpy=\n",
"array([[[ 0.267469 , -0.62187463, -0.20508286, ..., -0.06582171,\n",
" 0.3819914 , 0.92700386],\n",
" [-0.49007717, -0.19729286, -0.63019806, ..., -0.4946556 ,\n",
" 0.5848053 , 0.48207486],\n",
" [-0.7382609 , -0.42379066, 0.04920355, ..., 0.22922839,\n",
" 0.4823346 , 1.3403559 ],\n",
" ...,\n",
" [ 0.36012125, -0.72662765, 1.2360562 , ..., 0.4134717 ,\n",
" -0.7964586 , -0.0168159 ],\n",
" [ 0.19020146, -0.6944481 , 1.0574071 , ..., 0.40931013,\n",
" -0.8179945 , -0.10516895],\n",
" [ 0.08327669, -0.9118013 , 1.1854435 , ..., 0.6869288 ,\n",
" -0.96097374, -0.18211707]],\n",
"\n",
" [[-0.15515378, 0.24348043, -0.5878669 , ..., -0.8551526 ,\n",
" 0.37197673, 0.77416694],\n",
" [ 0.82778156, -0.5299998 , 1.1944404 , ..., -0.18086453,\n",
" 0.22024067, -0.62813413],\n",
" [ 0.743023 , -0.2938047 , -0.23586163, ..., -0.41389942,\n",
" -0.06697719, 0.97216934],\n",
" ...,\n",
" [-0.06196451, -0.00945033, 1.3805895 , ..., 0.41180745,\n",
" -0.6445146 , -0.17519078],\n",
" [-0.08102008, 0.17403589, 1.4231976 , ..., 0.429969 ,\n",
" -0.68531966, -0.1757994 ],\n",
" [ 0.65523195, -0.11694056, 1.641292 , ..., 0.7779677 ,\n",
" -0.36524218, -0.4030809 ]]], dtype=float32)>, <tf.Tensor: shape=(2, 128, 768), dtype=float32, numpy=\n",
"array([[[ 0.262105 , -0.49547008, -0.21239214, ..., -0.00404145,\n",
" 0.11047935, 1.0197922 ],\n",
" [-0.48511976, -0.2839242 , -0.02731339, ..., -0.695119 ,\n",
" 0.44140273, 0.6733612 ],\n",
" [-0.4911195 , -0.29700607, 0.18301496, ..., -0.37084612,\n",
" 0.44985855, 1.3507713 ],\n",
" ...,\n",
" [ 0.3708187 , -0.71213204, 0.8711745 , ..., 0.37050912,\n",
" -0.65640986, 0.17500949],\n",
" [ 0.24236405, -0.6819058 , 0.8009118 , ..., 0.3233849 ,\n",
" -0.6954117 , 0.0448739 ],\n",
" [ 0.06622784, -0.8053169 , 0.8632049 , ..., 0.46156222,\n",
" -0.81855065, -0.05946006]],\n",
"\n",
" [[-0.04873446, 0.4529825 , -0.92919904, ..., -0.8306872 ,\n",
" 0.24304585, 0.5967375 ],\n",
" [ 0.63002735, -0.47839594, 0.7894074 , ..., -0.39560497,\n",
" 0.16381933, -0.5277528 ],\n",
" [ 0.4487518 , -0.16525362, -0.53505677, ..., -0.24357045,\n",
" 0.38862032, 0.5095053 ],\n",
" ...,\n",
" [ 0.04551447, 0.29526532, 0.99386215, ..., 0.27326238,\n",
" -0.3456278 , -0.23659004],\n",
" [-0.01135593, 0.43595943, 1.0248154 , ..., 0.3244376 ,\n",
" -0.46688926, -0.21477409],\n",
" [ 0.83194435, 0.27556145, 1.482031 , ..., 0.6464286 ,\n",
" -0.01236844, -0.57039464]]], dtype=float32)>, <tf.Tensor: shape=(2, 128, 768), dtype=float32, numpy=\n",
"array([[[-0.287879 , -0.80240715, -0.20276153, ..., -0.19355206,\n",
" -0.6109808 , 1.0038904 ],\n",
" [-0.8657336 , -0.31282604, -0.22360814, ..., -0.6522808 ,\n",
" 0.48126665, 0.6094352 ],\n",
" [-0.76809317, -0.24397063, 0.23806915, ..., -0.6669281 ,\n",
" 0.12250681, 1.3389902 ],\n",
" ...,\n",
" [-0.24871868, -0.92885894, 0.6644963 , ..., 0.44990155,\n",
" -0.61868006, 0.21143207],\n",
" [-0.33172315, -0.86779344, 0.68440217, ..., 0.48378584,\n",
" -0.6701277 , 0.1242202 ],\n",
" [-0.47390074, -0.971211 , 0.7892387 , ..., 0.5549451 ,\n",
" -0.82587767, -0.04555673]],\n",
"\n",
" [[-0.1323342 , 0.56171477, -0.44893602, ..., -0.71494114,\n",
" -0.39547947, 0.38463563],\n",
" [ 0.5482401 , -0.60376394, 0.7847973 , ..., -0.3984929 ,\n",
" 0.06032612, -0.7970418 ],\n",
" [ 0.25018427, -0.15513963, -0.18558574, ..., -0.08695153,\n",
" 0.0445721 , -0.04240235],\n",
" ...,\n",
" [-0.24507912, 0.46590155, 0.5433186 , ..., 0.13668773,\n",
" -0.598839 , -0.45822692],\n",
" [-0.27610523, 0.70140356, 0.6461801 , ..., 0.17265077,\n",
" -0.7190671 , -0.4098673 ],\n",
" [ 0.6226735 , 0.5686493 , 1.1515373 , ..., 0.5658265 ,\n",
" -0.32691854, -0.5872827 ]]], dtype=float32)>, <tf.Tensor: shape=(2, 128, 768), dtype=float32, numpy=\n",
"array([[[-0.26158482, -0.6000199 , -0.14985457, ..., -0.3541886 ,\n",
" -0.0744052 , 0.8018481 ],\n",
" [-0.5006118 , -0.8921 , -0.40147567, ..., -1.1037706 ,\n",
" 0.4858664 , 0.48425287],\n",
" [-0.53629315, -0.6906576 , 0.29962227, ..., -0.62254155,\n",
" 0.23217814, 1.3942658 ],\n",
" ...,\n",
" [ 0.16818719, -1.0856829 , 0.5047239 , ..., 0.0128454 ,\n",
" -0.3836278 , -0.03140625],\n",
" [ 0.0023242 , -0.9831716 , 0.5245629 , ..., 0.05957055,\n",
" -0.4703085 , -0.05248631],\n",
" [-0.21012276, -1.0518107 , 0.6366271 , ..., 0.0917865 ,\n",
" -0.6165241 , -0.13285404]],\n",
"\n",
" [[-0.11200634, 0.32884985, -0.1780588 , ..., -0.31254804,\n",
" 0.03413404, -0.0067618 ],\n",
" [ 0.730604 , -0.37129667, 0.45334762, ..., -0.27244237,\n",
" -0.08073802, -0.4595476 ],\n",
" [ 0.26112485, -0.16279833, -0.12435186, ..., 0.01330798,\n",
" 0.23121914, 0.2716457 ],\n",
" ...,\n",
" [-0.17112523, 0.3180147 , 0.5765437 , ..., 0.03357287,\n",
" -0.97571343, -0.28733844],\n",
" [-0.22259393, 0.5266339 , 0.7034917 , ..., 0.11205668,\n",
" -1.0813433 , -0.23581836],\n",
" [ 0.43861124, 0.44458354, 1.0901142 , ..., 0.34537375,\n",
" -0.9213069 , -0.32855487]]], dtype=float32)>, <tf.Tensor: shape=(2, 128, 768), dtype=float32, numpy=\n",
"array([[[-0.19839856, -0.20800582, -0.1962688 , ..., -0.47272685,\n",
" 0.0864562 , 0.7098722 ],\n",
" [-0.5383126 , -0.7158387 , -0.28930873, ..., -0.72038037,\n",
" 0.5794679 , 0.39614454],\n",
" [-0.14156267, -0.7373614 , 0.37026387, ..., -0.37185436,\n",
" 0.07691361, 0.9704544 ],\n",
" ...,\n",
" [ 0.06476687, -0.4518682 , 0.21092355, ..., 0.10411158,\n",
" -0.15344658, 0.15741925],\n",
" [ 0.00561799, -0.4243467 , 0.17027403, ..., 0.12554014,\n",
" -0.1677104 , 0.14828748],\n",
" [-0.06908819, -0.43356168, 0.25077093, ..., 0.12376285,\n",
" -0.21341398, 0.12534308]],\n",
"\n",
" [[-0.05573511, 0.17838944, -0.12837237, ..., -0.16575927,\n",
" 0.15549946, 0.21796423],\n",
" [ 0.27656567, -0.06027734, 0.24292594, ..., 0.05262224,\n",
" 0.5221071 , -0.07443378],\n",
" [ 0.05904233, 0.11985369, -0.04732013, ..., 0.05382551,\n",
" 0.24277204, 0.04877569],\n",
" ...,\n",
" [-0.06302132, 0.17733227, 0.40315932, ..., 0.11782701,\n",
" -0.20818709, -0.0962089 ],\n",
" [-0.0760133 , 0.21092619, 0.45218655, ..., 0.14849319,\n",
" -0.26165274, -0.06360148],\n",
" [ 0.1626576 , 0.12422754, 0.5222455 , ..., 0.24048476,\n",
" -0.24223803, -0.14883336]]], dtype=float32)>]}\n"
]
}
],
"source": [
"# Example input text\n",
"text = [\"This is a sample sentence.\", \"BERT is powerful!\"]\n",
"\n",
"# Preprocess the text\n",
"preprocessed_text = bert_preprocess(text)\n",
"\n",
"# Encode the text\n",
"bert_output = bert_encoder(preprocessed_text)\n",
"\n",
"# bert_output contains the contextualized embeddings\n",
"print(bert_output)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "cd44a41e-b6cc-4f8c-8452-c9294a50b4ce",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<tf.Tensor: shape=(2, 768), dtype=float32, numpy=\n",
"array([[-0.8435169 , -0.51327276, -0.8884573 , ..., -0.7474886 ,\n",
" -0.75314736, 0.91964495],\n",
" [-0.87208366, -0.5054398 , -0.9444669 , ..., -0.85847515,\n",
" -0.71745366, 0.88082975]], dtype=float32)>"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def get_sentence_embeding(sentences):\n",
" preprocessed_text = bert_preprocess(sentences)\n",
" return bert_encoder(preprocessed_text)['pooled_output']\n",
"\n",
"get_sentence_embeding([\n",
" \"500$ discount. hurry up\", \n",
" \"Bhavin, are you up for a volleybal game tomorrow?\"]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "335a2120-1cbb-41b0-824b-e70a3193160c",
"metadata": {},
"outputs": [],
"source": [
"from sklearn.metrics.pairwise import cosine_similarity"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "8d7b58eb-e09f-4043-bce7-003ea7e7f22b",
"metadata": {},
"outputs": [],
"source": [
"sl=get_sentence_embeding([\n",
" \"apple\",\n",
" \"mango\",\n",
" \"orange\",\n",
" \"Bill gates\",\n",
" \"tim cook\",\n",
" \"jeff bezos\"\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "cd167304-6e8d-4300-bc6a-7265dfe941bf",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[0.9614038]], dtype=float32)"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cosine_similarity([sl[0]],[sl[1]])"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "e882510f-afad-400d-bfb8-714a27503ac4",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[0.9564287]], dtype=float32)"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cosine_similarity([sl[2]],[sl[3]])"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "a002b3e9-85e9-4a38-9a71-a184664cd29c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[0.987975]], dtype=float32)"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cosine_similarity([sl[0]],[sl[4]])\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "1574cef7-1543-4393-b3be-da7eae69f029",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"functional_1\"</span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1mModel: \"functional_1\"\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃<span style=\"font-weight: bold\"> Layer (type) </span>┃<span style=\"font-weight: bold\"> Output Shape </span>┃<span style=\"font-weight: bold\"> Param # </span>┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ text (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ bert_preprocess_encode │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">768</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BertPreprocessEncode</span>) │ │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">768</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ output (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">769</span> │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
"</pre>\n"
],
"text/plain": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ text (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ bert_preprocess_encode │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m768\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"│ (\u001b[38;5;33mBertPreprocessEncode\u001b[0m) │ │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dropout (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m768\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ output (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m769\u001b[0m │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">769</span> (3.00 KB)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m769\u001b[0m (3.00 KB)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">769</span> (3.00 KB)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m769\u001b[0m (3.00 KB)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"class BertPreprocessEncode(tf.keras.layers.Layer):\n",
" def __init__(self, preprocess_path, encoder_path, **kwargs):\n",
" super(BertPreprocessEncode, self).__init__(**kwargs)\n",
" self.preprocess = hub.KerasLayer(preprocess_path)\n",
" self.encoder = hub.KerasLayer(encoder_path)\n",
"\n",
" def call(self, inputs):\n",
" preprocessed = self.preprocess(inputs)\n",
" encoded = self.encoder(preprocessed)\n",
" return encoded['pooled_output']\n",
"\n",
"# Define the input layer\n",
"text_input = tf.keras.layers.Input(shape=(), dtype=tf.string, name='text')\n",
"\n",
"# Use the custom preprocessing and encoding layer\n",
"bert_output = BertPreprocessEncode(preprocess_path, encoder_path)(text_input)\n",
"\n",
"# Add a dropout layer and a dense layer for classification\n",
"dropout = tf.keras.layers.Dropout(0.1, name=\"dropout\")(bert_output)\n",
"output = tf.keras.layers.Dense(1, activation='sigmoid', name=\"output\")(dropout)\n",
"\n",
"# Build the model\n",
"model = tf.keras.Model(inputs=[text_input], outputs=[output])\n",
"\n",
"# Compile the model\n",
"model.compile(\n",
" optimizer='adam',\n",
" loss='binary_crossentropy',\n",
" metrics=['accuracy']\n",
")\n",
"\n",
"# Print the model summary\n",
"model.summary()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "36f5f101-c490-487e-981e-2599ffa25d42",
"metadata": {
"collapsed": true,
"jupyter": {
"outputs_hidden": true,
"source_hidden": true
}
},
"outputs": [
{
"ename": "ConnectionError",
"evalue": "('Connection aborted.', ConnectionResetError(54, 'Connection reset by peer'))",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mConnectionResetError\u001b[0m Traceback (most recent call last)",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/connectionpool.py:715\u001b[0m, in \u001b[0;36mHTTPConnectionPool.urlopen\u001b[0;34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)\u001b[0m\n\u001b[1;32m 714\u001b[0m \u001b[38;5;66;03m# Make the request on the httplib connection object.\u001b[39;00m\n\u001b[0;32m--> 715\u001b[0m httplib_response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 716\u001b[0m \u001b[43m \u001b[49m\u001b[43mconn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 717\u001b[0m \u001b[43m \u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 718\u001b[0m \u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 719\u001b[0m \u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout_obj\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 720\u001b[0m \u001b[43m \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mbody\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 721\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 722\u001b[0m \u001b[43m \u001b[49m\u001b[43mchunked\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mchunked\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 723\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 725\u001b[0m \u001b[38;5;66;03m# If we're going to release the connection in ``finally:``, then\u001b[39;00m\n\u001b[1;32m 726\u001b[0m \u001b[38;5;66;03m# the response doesn't need to know about the connection. Otherwise\u001b[39;00m\n\u001b[1;32m 727\u001b[0m \u001b[38;5;66;03m# it will also try to release it and we'll have a double-release\u001b[39;00m\n\u001b[1;32m 728\u001b[0m \u001b[38;5;66;03m# mess.\u001b[39;00m\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/connectionpool.py:404\u001b[0m, in \u001b[0;36mHTTPConnectionPool._make_request\u001b[0;34m(self, conn, method, url, timeout, chunked, **httplib_request_kw)\u001b[0m\n\u001b[1;32m 403\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 404\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_validate_conn\u001b[49m\u001b[43m(\u001b[49m\u001b[43mconn\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 405\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (SocketTimeout, BaseSSLError) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 406\u001b[0m \u001b[38;5;66;03m# Py2 raises this as a BaseSSLError, Py3 raises it as socket timeout.\u001b[39;00m\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/connectionpool.py:1060\u001b[0m, in \u001b[0;36mHTTPSConnectionPool._validate_conn\u001b[0;34m(self, conn)\u001b[0m\n\u001b[1;32m 1059\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mgetattr\u001b[39m(conn, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msock\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m): \u001b[38;5;66;03m# AppEngine might not have `.sock`\u001b[39;00m\n\u001b[0;32m-> 1060\u001b[0m \u001b[43mconn\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconnect\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1062\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m conn\u001b[38;5;241m.\u001b[39mis_verified:\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/connection.py:419\u001b[0m, in \u001b[0;36mHTTPSConnection.connect\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 417\u001b[0m context\u001b[38;5;241m.\u001b[39mload_default_certs()\n\u001b[0;32m--> 419\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msock \u001b[38;5;241m=\u001b[39m \u001b[43mssl_wrap_socket\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 420\u001b[0m \u001b[43m \u001b[49m\u001b[43msock\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 421\u001b[0m \u001b[43m \u001b[49m\u001b[43mkeyfile\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mkey_file\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 422\u001b[0m \u001b[43m \u001b[49m\u001b[43mcertfile\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcert_file\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 423\u001b[0m \u001b[43m \u001b[49m\u001b[43mkey_password\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mkey_password\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 424\u001b[0m \u001b[43m \u001b[49m\u001b[43mca_certs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mca_certs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 425\u001b[0m \u001b[43m \u001b[49m\u001b[43mca_cert_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mca_cert_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 426\u001b[0m \u001b[43m \u001b[49m\u001b[43mca_cert_data\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mca_cert_data\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 427\u001b[0m \u001b[43m \u001b[49m\u001b[43mserver_hostname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mserver_hostname\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 428\u001b[0m \u001b[43m \u001b[49m\u001b[43mssl_context\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcontext\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 429\u001b[0m \u001b[43m \u001b[49m\u001b[43mtls_in_tls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtls_in_tls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 430\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 432\u001b[0m \u001b[38;5;66;03m# If we're using all defaults and the connection\u001b[39;00m\n\u001b[1;32m 433\u001b[0m \u001b[38;5;66;03m# is TLSv1 or TLSv1.1 we throw a DeprecationWarning\u001b[39;00m\n\u001b[1;32m 434\u001b[0m \u001b[38;5;66;03m# for the host.\u001b[39;00m\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/util/ssl_.py:449\u001b[0m, in \u001b[0;36mssl_wrap_socket\u001b[0;34m(sock, keyfile, certfile, cert_reqs, ca_certs, server_hostname, ssl_version, ciphers, ssl_context, ca_cert_dir, key_password, ca_cert_data, tls_in_tls)\u001b[0m\n\u001b[1;32m 448\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m send_sni:\n\u001b[0;32m--> 449\u001b[0m ssl_sock \u001b[38;5;241m=\u001b[39m \u001b[43m_ssl_wrap_socket_impl\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 450\u001b[0m \u001b[43m \u001b[49m\u001b[43msock\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcontext\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtls_in_tls\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mserver_hostname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mserver_hostname\u001b[49m\n\u001b[1;32m 451\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 452\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/util/ssl_.py:493\u001b[0m, in \u001b[0;36m_ssl_wrap_socket_impl\u001b[0;34m(sock, ssl_context, tls_in_tls, server_hostname)\u001b[0m\n\u001b[1;32m 492\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m server_hostname:\n\u001b[0;32m--> 493\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mssl_context\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mwrap_socket\u001b[49m\u001b[43m(\u001b[49m\u001b[43msock\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mserver_hostname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mserver_hostname\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 494\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/ssl.py:500\u001b[0m, in \u001b[0;36mSSLContext.wrap_socket\u001b[0;34m(self, sock, server_side, do_handshake_on_connect, suppress_ragged_eofs, server_hostname, session)\u001b[0m\n\u001b[1;32m 494\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mwrap_socket\u001b[39m(\u001b[38;5;28mself\u001b[39m, sock, server_side\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[1;32m 495\u001b[0m do_handshake_on_connect\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m 496\u001b[0m suppress_ragged_eofs\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m 497\u001b[0m server_hostname\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, session\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[1;32m 498\u001b[0m \u001b[38;5;66;03m# SSLSocket class handles server_hostname encoding before it calls\u001b[39;00m\n\u001b[1;32m 499\u001b[0m \u001b[38;5;66;03m# ctx._wrap_socket()\u001b[39;00m\n\u001b[0;32m--> 500\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msslsocket_class\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_create\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 501\u001b[0m \u001b[43m \u001b[49m\u001b[43msock\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msock\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 502\u001b[0m \u001b[43m \u001b[49m\u001b[43mserver_side\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mserver_side\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 503\u001b[0m \u001b[43m \u001b[49m\u001b[43mdo_handshake_on_connect\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdo_handshake_on_connect\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 504\u001b[0m \u001b[43m \u001b[49m\u001b[43msuppress_ragged_eofs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msuppress_ragged_eofs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 505\u001b[0m \u001b[43m \u001b[49m\u001b[43mserver_hostname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mserver_hostname\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 506\u001b[0m \u001b[43m \u001b[49m\u001b[43mcontext\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 507\u001b[0m \u001b[43m \u001b[49m\u001b[43msession\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msession\u001b[49m\n\u001b[1;32m 508\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/ssl.py:1040\u001b[0m, in \u001b[0;36mSSLSocket._create\u001b[0;34m(cls, sock, server_side, do_handshake_on_connect, suppress_ragged_eofs, server_hostname, context, session)\u001b[0m\n\u001b[1;32m 1039\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdo_handshake_on_connect should not be specified for non-blocking sockets\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m-> 1040\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdo_handshake\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1041\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mOSError\u001b[39;00m, \u001b[38;5;167;01mValueError\u001b[39;00m):\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/ssl.py:1309\u001b[0m, in \u001b[0;36mSSLSocket.do_handshake\u001b[0;34m(self, block)\u001b[0m\n\u001b[1;32m 1308\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msettimeout(\u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[0;32m-> 1309\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sslobj\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdo_handshake\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1310\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n",
"\u001b[0;31mConnectionResetError\u001b[0m: [Errno 54] Connection reset by peer",
"\nDuring handling of the above exception, another exception occurred:\n",
"\u001b[0;31mProtocolError\u001b[0m Traceback (most recent call last)",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/requests/adapters.py:667\u001b[0m, in \u001b[0;36mHTTPAdapter.send\u001b[0;34m(self, request, stream, timeout, verify, cert, proxies)\u001b[0m\n\u001b[1;32m 666\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 667\u001b[0m resp \u001b[38;5;241m=\u001b[39m \u001b[43mconn\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43murlopen\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 668\u001b[0m \u001b[43m \u001b[49m\u001b[43mmethod\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 669\u001b[0m \u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 670\u001b[0m \u001b[43m \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbody\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 671\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 672\u001b[0m \u001b[43m \u001b[49m\u001b[43mredirect\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 673\u001b[0m \u001b[43m \u001b[49m\u001b[43massert_same_host\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 674\u001b[0m \u001b[43m \u001b[49m\u001b[43mpreload_content\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 675\u001b[0m \u001b[43m \u001b[49m\u001b[43mdecode_content\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 676\u001b[0m \u001b[43m \u001b[49m\u001b[43mretries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmax_retries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 677\u001b[0m \u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 678\u001b[0m \u001b[43m \u001b[49m\u001b[43mchunked\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mchunked\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 679\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 681\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (ProtocolError, \u001b[38;5;167;01mOSError\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m err:\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/connectionpool.py:801\u001b[0m, in \u001b[0;36mHTTPConnectionPool.urlopen\u001b[0;34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)\u001b[0m\n\u001b[1;32m 799\u001b[0m e \u001b[38;5;241m=\u001b[39m ProtocolError(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mConnection aborted.\u001b[39m\u001b[38;5;124m\"\u001b[39m, e)\n\u001b[0;32m--> 801\u001b[0m retries \u001b[38;5;241m=\u001b[39m \u001b[43mretries\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mincrement\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 802\u001b[0m \u001b[43m \u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43merror\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43me\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m_pool\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m_stacktrace\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msys\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mexc_info\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m2\u001b[39;49m\u001b[43m]\u001b[49m\n\u001b[1;32m 803\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 804\u001b[0m retries\u001b[38;5;241m.\u001b[39msleep()\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/util/retry.py:552\u001b[0m, in \u001b[0;36mRetry.increment\u001b[0;34m(self, method, url, response, error, _pool, _stacktrace)\u001b[0m\n\u001b[1;32m 551\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m read \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mFalse\u001b[39;00m \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_is_method_retryable(method):\n\u001b[0;32m--> 552\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[43msix\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mreraise\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mtype\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43merror\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43merror\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m_stacktrace\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 553\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m read \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/packages/six.py:769\u001b[0m, in \u001b[0;36mreraise\u001b[0;34m(tp, value, tb)\u001b[0m\n\u001b[1;32m 768\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m value\u001b[38;5;241m.\u001b[39m__traceback__ \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m tb:\n\u001b[0;32m--> 769\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m value\u001b[38;5;241m.\u001b[39mwith_traceback(tb)\n\u001b[1;32m 770\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m value\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/connectionpool.py:715\u001b[0m, in \u001b[0;36mHTTPConnectionPool.urlopen\u001b[0;34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)\u001b[0m\n\u001b[1;32m 714\u001b[0m \u001b[38;5;66;03m# Make the request on the httplib connection object.\u001b[39;00m\n\u001b[0;32m--> 715\u001b[0m httplib_response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 716\u001b[0m \u001b[43m \u001b[49m\u001b[43mconn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 717\u001b[0m \u001b[43m \u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 718\u001b[0m \u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 719\u001b[0m \u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout_obj\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 720\u001b[0m \u001b[43m \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mbody\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 721\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 722\u001b[0m \u001b[43m \u001b[49m\u001b[43mchunked\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mchunked\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 723\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 725\u001b[0m \u001b[38;5;66;03m# If we're going to release the connection in ``finally:``, then\u001b[39;00m\n\u001b[1;32m 726\u001b[0m \u001b[38;5;66;03m# the response doesn't need to know about the connection. Otherwise\u001b[39;00m\n\u001b[1;32m 727\u001b[0m \u001b[38;5;66;03m# it will also try to release it and we'll have a double-release\u001b[39;00m\n\u001b[1;32m 728\u001b[0m \u001b[38;5;66;03m# mess.\u001b[39;00m\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/connectionpool.py:404\u001b[0m, in \u001b[0;36mHTTPConnectionPool._make_request\u001b[0;34m(self, conn, method, url, timeout, chunked, **httplib_request_kw)\u001b[0m\n\u001b[1;32m 403\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 404\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_validate_conn\u001b[49m\u001b[43m(\u001b[49m\u001b[43mconn\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 405\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (SocketTimeout, BaseSSLError) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 406\u001b[0m \u001b[38;5;66;03m# Py2 raises this as a BaseSSLError, Py3 raises it as socket timeout.\u001b[39;00m\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/connectionpool.py:1060\u001b[0m, in \u001b[0;36mHTTPSConnectionPool._validate_conn\u001b[0;34m(self, conn)\u001b[0m\n\u001b[1;32m 1059\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mgetattr\u001b[39m(conn, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msock\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m): \u001b[38;5;66;03m# AppEngine might not have `.sock`\u001b[39;00m\n\u001b[0;32m-> 1060\u001b[0m \u001b[43mconn\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconnect\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1062\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m conn\u001b[38;5;241m.\u001b[39mis_verified:\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/connection.py:419\u001b[0m, in \u001b[0;36mHTTPSConnection.connect\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 417\u001b[0m context\u001b[38;5;241m.\u001b[39mload_default_certs()\n\u001b[0;32m--> 419\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msock \u001b[38;5;241m=\u001b[39m \u001b[43mssl_wrap_socket\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 420\u001b[0m \u001b[43m \u001b[49m\u001b[43msock\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 421\u001b[0m \u001b[43m \u001b[49m\u001b[43mkeyfile\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mkey_file\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 422\u001b[0m \u001b[43m \u001b[49m\u001b[43mcertfile\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcert_file\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 423\u001b[0m \u001b[43m \u001b[49m\u001b[43mkey_password\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mkey_password\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 424\u001b[0m \u001b[43m \u001b[49m\u001b[43mca_certs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mca_certs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 425\u001b[0m \u001b[43m \u001b[49m\u001b[43mca_cert_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mca_cert_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 426\u001b[0m \u001b[43m \u001b[49m\u001b[43mca_cert_data\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mca_cert_data\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 427\u001b[0m \u001b[43m \u001b[49m\u001b[43mserver_hostname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mserver_hostname\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 428\u001b[0m \u001b[43m \u001b[49m\u001b[43mssl_context\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcontext\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 429\u001b[0m \u001b[43m \u001b[49m\u001b[43mtls_in_tls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtls_in_tls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 430\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 432\u001b[0m \u001b[38;5;66;03m# If we're using all defaults and the connection\u001b[39;00m\n\u001b[1;32m 433\u001b[0m \u001b[38;5;66;03m# is TLSv1 or TLSv1.1 we throw a DeprecationWarning\u001b[39;00m\n\u001b[1;32m 434\u001b[0m \u001b[38;5;66;03m# for the host.\u001b[39;00m\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/util/ssl_.py:449\u001b[0m, in \u001b[0;36mssl_wrap_socket\u001b[0;34m(sock, keyfile, certfile, cert_reqs, ca_certs, server_hostname, ssl_version, ciphers, ssl_context, ca_cert_dir, key_password, ca_cert_data, tls_in_tls)\u001b[0m\n\u001b[1;32m 448\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m send_sni:\n\u001b[0;32m--> 449\u001b[0m ssl_sock \u001b[38;5;241m=\u001b[39m \u001b[43m_ssl_wrap_socket_impl\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 450\u001b[0m \u001b[43m \u001b[49m\u001b[43msock\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcontext\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtls_in_tls\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mserver_hostname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mserver_hostname\u001b[49m\n\u001b[1;32m 451\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 452\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/urllib3/util/ssl_.py:493\u001b[0m, in \u001b[0;36m_ssl_wrap_socket_impl\u001b[0;34m(sock, ssl_context, tls_in_tls, server_hostname)\u001b[0m\n\u001b[1;32m 492\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m server_hostname:\n\u001b[0;32m--> 493\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mssl_context\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mwrap_socket\u001b[49m\u001b[43m(\u001b[49m\u001b[43msock\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mserver_hostname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mserver_hostname\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 494\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/ssl.py:500\u001b[0m, in \u001b[0;36mSSLContext.wrap_socket\u001b[0;34m(self, sock, server_side, do_handshake_on_connect, suppress_ragged_eofs, server_hostname, session)\u001b[0m\n\u001b[1;32m 494\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mwrap_socket\u001b[39m(\u001b[38;5;28mself\u001b[39m, sock, server_side\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[1;32m 495\u001b[0m do_handshake_on_connect\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m 496\u001b[0m suppress_ragged_eofs\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m 497\u001b[0m server_hostname\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, session\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[1;32m 498\u001b[0m \u001b[38;5;66;03m# SSLSocket class handles server_hostname encoding before it calls\u001b[39;00m\n\u001b[1;32m 499\u001b[0m \u001b[38;5;66;03m# ctx._wrap_socket()\u001b[39;00m\n\u001b[0;32m--> 500\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msslsocket_class\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_create\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 501\u001b[0m \u001b[43m \u001b[49m\u001b[43msock\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msock\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 502\u001b[0m \u001b[43m \u001b[49m\u001b[43mserver_side\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mserver_side\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 503\u001b[0m \u001b[43m \u001b[49m\u001b[43mdo_handshake_on_connect\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdo_handshake_on_connect\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 504\u001b[0m \u001b[43m \u001b[49m\u001b[43msuppress_ragged_eofs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msuppress_ragged_eofs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 505\u001b[0m \u001b[43m \u001b[49m\u001b[43mserver_hostname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mserver_hostname\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 506\u001b[0m \u001b[43m \u001b[49m\u001b[43mcontext\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 507\u001b[0m \u001b[43m \u001b[49m\u001b[43msession\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msession\u001b[49m\n\u001b[1;32m 508\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/ssl.py:1040\u001b[0m, in \u001b[0;36mSSLSocket._create\u001b[0;34m(cls, sock, server_side, do_handshake_on_connect, suppress_ragged_eofs, server_hostname, context, session)\u001b[0m\n\u001b[1;32m 1039\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdo_handshake_on_connect should not be specified for non-blocking sockets\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m-> 1040\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdo_handshake\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1041\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mOSError\u001b[39;00m, \u001b[38;5;167;01mValueError\u001b[39;00m):\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/ssl.py:1309\u001b[0m, in \u001b[0;36mSSLSocket.do_handshake\u001b[0;34m(self, block)\u001b[0m\n\u001b[1;32m 1308\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msettimeout(\u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[0;32m-> 1309\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sslobj\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdo_handshake\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1310\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n",
"\u001b[0;31mProtocolError\u001b[0m: ('Connection aborted.', ConnectionResetError(54, 'Connection reset by peer'))",
"\nDuring handling of the above exception, another exception occurred:\n",
"\u001b[0;31mConnectionError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[6], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m text_input \u001b[38;5;241m=\u001b[39m tf\u001b[38;5;241m.\u001b[39mkeras\u001b[38;5;241m.\u001b[39mlayers\u001b[38;5;241m.\u001b[39mInput(shape\u001b[38;5;241m=\u001b[39m(), dtype\u001b[38;5;241m=\u001b[39mtf\u001b[38;5;241m.\u001b[39mstring)\n\u001b[0;32m----> 2\u001b[0m preprocessor \u001b[38;5;241m=\u001b[39m \u001b[43mkeras_nlp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodels\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mBertPreprocessor\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_preset\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mbert_base_en_uncased\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43mtrainable\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[1;32m 3\u001b[0m encoder_inputs \u001b[38;5;241m=\u001b[39m preprocessor(text_input)\n\u001b[1;32m 4\u001b[0m encoder \u001b[38;5;241m=\u001b[39m keras_nlp\u001b[38;5;241m.\u001b[39mmodels\u001b[38;5;241m.\u001b[39mBertBackbone\u001b[38;5;241m.\u001b[39mfrom_preset(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbert_base_en_uncased\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/keras_hub/src/models/preprocessor.py:186\u001b[0m, in \u001b[0;36mPreprocessor.from_preset\u001b[0;34m(cls, preset, config_file, **kwargs)\u001b[0m\n\u001b[1;32m 184\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39mbackbone_cls \u001b[38;5;241m!=\u001b[39m backbone_cls:\n\u001b[1;32m 185\u001b[0m \u001b[38;5;28mcls\u001b[39m \u001b[38;5;241m=\u001b[39m find_subclass(preset, \u001b[38;5;28mcls\u001b[39m, backbone_cls)\n\u001b[0;32m--> 186\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mloader\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload_preprocessor\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig_file\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/keras_hub/src/utils/preset_utils.py:690\u001b[0m, in \u001b[0;36mKerasPresetLoader.load_preprocessor\u001b[0;34m(self, cls, config_file, **kwargs)\u001b[0m\n\u001b[1;32m 684\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mload_preprocessor\u001b[39m(\n\u001b[1;32m 685\u001b[0m \u001b[38;5;28mself\u001b[39m, \u001b[38;5;28mcls\u001b[39m, config_file\u001b[38;5;241m=\u001b[39mPREPROCESSOR_CONFIG_FILE, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs\n\u001b[1;32m 686\u001b[0m ):\n\u001b[1;32m 687\u001b[0m \u001b[38;5;66;03m# If there is no `preprocessing.json` or it's for the wrong class,\u001b[39;00m\n\u001b[1;32m 688\u001b[0m \u001b[38;5;66;03m# delegate to the super class loader.\u001b[39;00m\n\u001b[1;32m 689\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m check_file_exists(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpreset, config_file):\n\u001b[0;32m--> 690\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload_preprocessor\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 691\u001b[0m preprocessor_json \u001b[38;5;241m=\u001b[39m load_json(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpreset, config_file)\n\u001b[1;32m 692\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28missubclass\u001b[39m(check_config_class(preprocessor_json), \u001b[38;5;28mcls\u001b[39m):\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/keras_hub/src/utils/preset_utils.py:618\u001b[0m, in \u001b[0;36mPresetLoader.load_preprocessor\u001b[0;34m(self, cls, config_file, **kwargs)\u001b[0m\n\u001b[1;32m 609\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mload_preprocessor\u001b[39m(\n\u001b[1;32m 610\u001b[0m \u001b[38;5;28mself\u001b[39m, \u001b[38;5;28mcls\u001b[39m, config_file\u001b[38;5;241m=\u001b[39mPREPROCESSOR_CONFIG_FILE, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs\n\u001b[1;32m 611\u001b[0m ):\n\u001b[1;32m 612\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Load a prepocessor layer from the preset.\u001b[39;00m\n\u001b[1;32m 613\u001b[0m \n\u001b[1;32m 614\u001b[0m \u001b[38;5;124;03m By default, we create a preprocessor from a tokenizer with default\u001b[39;00m\n\u001b[1;32m 615\u001b[0m \u001b[38;5;124;03m arguments. This allow us to support transformers checkpoints by\u001b[39;00m\n\u001b[1;32m 616\u001b[0m \u001b[38;5;124;03m only converting the backbone and tokenizer.\u001b[39;00m\n\u001b[1;32m 617\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 618\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_add_missing_kwargs\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 619\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mcls\u001b[39m(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/keras_hub/src/models/preprocessor.py:201\u001b[0m, in \u001b[0;36mPreprocessor._add_missing_kwargs\u001b[0;34m(cls, loader, kwargs)\u001b[0m\n\u001b[1;32m 190\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Fill in required kwargs when loading from preset.\u001b[39;00m\n\u001b[1;32m 191\u001b[0m \n\u001b[1;32m 192\u001b[0m \u001b[38;5;124;03mThis is a private method hit when loading a preprocessing layer that\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 198\u001b[0m \u001b[38;5;124;03mencoders.\u001b[39;00m\n\u001b[1;32m 199\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 200\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtokenizer\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m kwargs \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39mtokenizer_cls:\n\u001b[0;32m--> 201\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtokenizer\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[43mloader\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload_tokenizer\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtokenizer_cls\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 202\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124maudio_converter\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m kwargs \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39maudio_converter_cls:\n\u001b[1;32m 203\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124maudio_converter\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m loader\u001b[38;5;241m.\u001b[39mload_audio_converter(\n\u001b[1;32m 204\u001b[0m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39maudio_converter_cls\n\u001b[1;32m 205\u001b[0m )\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/keras_hub/src/utils/preset_utils.py:634\u001b[0m, in \u001b[0;36mKerasPresetLoader.load_tokenizer\u001b[0;34m(self, cls, config_file, **kwargs)\u001b[0m\n\u001b[1;32m 633\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mload_tokenizer\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28mcls\u001b[39m, config_file\u001b[38;5;241m=\u001b[39mTOKENIZER_CONFIG_FILE, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[0;32m--> 634\u001b[0m tokenizer_config \u001b[38;5;241m=\u001b[39m \u001b[43mload_json\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpreset\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig_file\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 635\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m load_serialized_object(tokenizer_config, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 636\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(tokenizer, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mload_preset_assets\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/keras_hub/src/utils/preset_utils.py:444\u001b[0m, in \u001b[0;36mload_json\u001b[0;34m(preset, config_file)\u001b[0m\n\u001b[1;32m 443\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mload_json\u001b[39m(preset, config_file\u001b[38;5;241m=\u001b[39mCONFIG_FILE):\n\u001b[0;32m--> 444\u001b[0m config_path \u001b[38;5;241m=\u001b[39m \u001b[43mget_file\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpreset\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig_file\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 445\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mopen\u001b[39m(config_path, encoding\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mutf-8\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mas\u001b[39;00m config_file:\n\u001b[1;32m 446\u001b[0m config \u001b[38;5;241m=\u001b[39m json\u001b[38;5;241m.\u001b[39mload(config_file)\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/keras_hub/src/utils/preset_utils.py:158\u001b[0m, in \u001b[0;36mget_file\u001b[0;34m(preset, path)\u001b[0m\n\u001b[1;32m 150\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 151\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUnexpected Kaggle preset. Kaggle model handles should have \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 152\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mthe form kaggle://\u001b[39m\u001b[38;5;132;01m{org}\u001b[39;00m\u001b[38;5;124m/\u001b[39m\u001b[38;5;132;01m{model}\u001b[39;00m\u001b[38;5;124m/keras/\u001b[39m\u001b[38;5;132;01m{variant}\u001b[39;00m\u001b[38;5;124m[/\u001b[39m\u001b[38;5;132;01m{version}\u001b[39;00m\u001b[38;5;124m]. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 155\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mversion). Received: preset=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpreset\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 156\u001b[0m )\n\u001b[1;32m 157\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 158\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mkagglehub\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel_download\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkaggle_handle\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpath\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 159\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m KaggleApiHTTPError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 160\u001b[0m message \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mstr\u001b[39m(e)\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/kagglehub/models.py:35\u001b[0m, in \u001b[0;36mmodel_download\u001b[0;34m(handle, path, force_download)\u001b[0m\n\u001b[1;32m 33\u001b[0m h \u001b[38;5;241m=\u001b[39m parse_model_handle(handle)\n\u001b[1;32m 34\u001b[0m logger\u001b[38;5;241m.\u001b[39minfo(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDownloading Model: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mh\u001b[38;5;241m.\u001b[39mto_url()\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m ...\u001b[39m\u001b[38;5;124m\"\u001b[39m, extra\u001b[38;5;241m=\u001b[39m{\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mEXTRA_CONSOLE_BLOCK})\n\u001b[0;32m---> 35\u001b[0m path, _ \u001b[38;5;241m=\u001b[39m \u001b[43mregistry\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel_resolver\u001b[49m\u001b[43m(\u001b[49m\u001b[43mh\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 36\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m path\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/kagglehub/registry.py:28\u001b[0m, in \u001b[0;36mMultiImplRegistry.__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 26\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m impl \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mreversed\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_impls):\n\u001b[1;32m 27\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m impl\u001b[38;5;241m.\u001b[39mis_supported(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[0;32m---> 28\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mimpl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 29\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 30\u001b[0m fails\u001b[38;5;241m.\u001b[39mappend(\u001b[38;5;28mtype\u001b[39m(impl)\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m)\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/kagglehub/resolver.py:29\u001b[0m, in \u001b[0;36mResolver.__call__\u001b[0;34m(self, handle, path, force_download)\u001b[0m\n\u001b[1;32m 15\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\n\u001b[1;32m 16\u001b[0m \u001b[38;5;28mself\u001b[39m, handle: T, path: Optional[\u001b[38;5;28mstr\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m*\u001b[39m, force_download: Optional[\u001b[38;5;28mbool\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[1;32m 17\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28mtuple\u001b[39m[\u001b[38;5;28mstr\u001b[39m, Optional[\u001b[38;5;28mint\u001b[39m]]:\n\u001b[1;32m 18\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Resolves a handle into a path with the requested file(s) and the resource's version number.\u001b[39;00m\n\u001b[1;32m 19\u001b[0m \n\u001b[1;32m 20\u001b[0m \u001b[38;5;124;03m Args:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 27\u001b[0m \u001b[38;5;124;03m Some cases where version number might be missing: Competition datasource, API-based models.\u001b[39;00m\n\u001b[1;32m 28\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m---> 29\u001b[0m path, version \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_resolve\u001b[49m\u001b[43m(\u001b[49m\u001b[43mhandle\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 31\u001b[0m \u001b[38;5;66;03m# Note handles are immutable, so _resolve() could not have altered our reference\u001b[39;00m\n\u001b[1;32m 32\u001b[0m register_datasource_access(handle, version)\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/kagglehub/http_resolver.py:167\u001b[0m, in \u001b[0;36mModelHttpResolver._resolve\u001b[0;34m(self, h, path, force_download)\u001b[0m\n\u001b[1;32m 164\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m path:\n\u001b[1;32m 165\u001b[0m \u001b[38;5;66;03m# Downloading a single file.\u001b[39;00m\n\u001b[1;32m 166\u001b[0m os\u001b[38;5;241m.\u001b[39mmakedirs(os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mdirname(out_path), exist_ok\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m--> 167\u001b[0m \u001b[43mapi_client\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdownload_file\u001b[49m\u001b[43m(\u001b[49m\u001b[43murl_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mout_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mh\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextract_auto_compressed_file\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[1;32m 168\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 169\u001b[0m \u001b[38;5;66;03m# List the files and decide how to download them:\u001b[39;00m\n\u001b[1;32m 170\u001b[0m \u001b[38;5;66;03m# - <= 25 files: Download files in parallel\u001b[39;00m\n\u001b[1;32m 171\u001b[0m \u001b[38;5;66;03m# > 25 files: Download the archive and uncompress\u001b[39;00m\n\u001b[1;32m 172\u001b[0m (files, has_more) \u001b[38;5;241m=\u001b[39m _list_files(api_client, h)\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/kagglehub/clients.py:175\u001b[0m, in \u001b[0;36mKaggleApiV1Client.download_file\u001b[0;34m(self, path, out_file, resource_handle, cached_path, extract_auto_compressed_file)\u001b[0m\n\u001b[1;32m 167\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 168\u001b[0m \u001b[38;5;124;03mIssues a call to kaggle api and downloads files. For competition downloads,\u001b[39;00m\n\u001b[1;32m 169\u001b[0m \u001b[38;5;124;03mcall may return early if local cache is newer than the last time the file was modified.\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 172\u001b[0m \u001b[38;5;124;03mbool: If downloading remote was necessary\u001b[39;00m\n\u001b[1;32m 173\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 174\u001b[0m url \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_build_url(path)\n\u001b[0;32m--> 175\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[43mrequests\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 176\u001b[0m \u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 177\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m{\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mUser-Agent\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mget_user_agent\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 178\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 179\u001b[0m \u001b[43m \u001b[49m\u001b[43mauth\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_auth\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 180\u001b[0m \u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mDEFAULT_CONNECT_TIMEOUT\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mDEFAULT_READ_TIMEOUT\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 181\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mas\u001b[39;00m response:\n\u001b[1;32m 182\u001b[0m kaggle_api_raise_for_status(response, resource_handle)\n\u001b[1;32m 184\u001b[0m total_size \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mint\u001b[39m(response\u001b[38;5;241m.\u001b[39mheaders[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mContent-Length\u001b[39m\u001b[38;5;124m\"\u001b[39m]) \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mContent-Length\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m response\u001b[38;5;241m.\u001b[39mheaders \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/requests/api.py:73\u001b[0m, in \u001b[0;36mget\u001b[0;34m(url, params, **kwargs)\u001b[0m\n\u001b[1;32m 62\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mget\u001b[39m(url, params\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 63\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124mr\u001b[39m\u001b[38;5;124;03m\"\"\"Sends a GET request.\u001b[39;00m\n\u001b[1;32m 64\u001b[0m \n\u001b[1;32m 65\u001b[0m \u001b[38;5;124;03m :param url: URL for the new :class:`Request` object.\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 70\u001b[0m \u001b[38;5;124;03m :rtype: requests.Response\u001b[39;00m\n\u001b[1;32m 71\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m---> 73\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mget\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mparams\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparams\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/requests/api.py:59\u001b[0m, in \u001b[0;36mrequest\u001b[0;34m(method, url, **kwargs)\u001b[0m\n\u001b[1;32m 55\u001b[0m \u001b[38;5;66;03m# By using the 'with' statement we are sure the session is closed, thus we\u001b[39;00m\n\u001b[1;32m 56\u001b[0m \u001b[38;5;66;03m# avoid leaving sockets open which can trigger a ResourceWarning in some\u001b[39;00m\n\u001b[1;32m 57\u001b[0m \u001b[38;5;66;03m# cases, and look like a memory leak in others.\u001b[39;00m\n\u001b[1;32m 58\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m sessions\u001b[38;5;241m.\u001b[39mSession() \u001b[38;5;28;01mas\u001b[39;00m session:\n\u001b[0;32m---> 59\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43msession\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmethod\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/requests/sessions.py:589\u001b[0m, in \u001b[0;36mSession.request\u001b[0;34m(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)\u001b[0m\n\u001b[1;32m 584\u001b[0m send_kwargs \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m 585\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtimeout\u001b[39m\u001b[38;5;124m\"\u001b[39m: timeout,\n\u001b[1;32m 586\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mallow_redirects\u001b[39m\u001b[38;5;124m\"\u001b[39m: allow_redirects,\n\u001b[1;32m 587\u001b[0m }\n\u001b[1;32m 588\u001b[0m send_kwargs\u001b[38;5;241m.\u001b[39mupdate(settings)\n\u001b[0;32m--> 589\u001b[0m resp \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msend\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprep\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43msend_kwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 591\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m resp\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/requests/sessions.py:703\u001b[0m, in \u001b[0;36mSession.send\u001b[0;34m(self, request, **kwargs)\u001b[0m\n\u001b[1;32m 700\u001b[0m start \u001b[38;5;241m=\u001b[39m preferred_clock()\n\u001b[1;32m 702\u001b[0m \u001b[38;5;66;03m# Send the request\u001b[39;00m\n\u001b[0;32m--> 703\u001b[0m r \u001b[38;5;241m=\u001b[39m \u001b[43madapter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msend\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 705\u001b[0m \u001b[38;5;66;03m# Total elapsed time of the request (approximately)\u001b[39;00m\n\u001b[1;32m 706\u001b[0m elapsed \u001b[38;5;241m=\u001b[39m preferred_clock() \u001b[38;5;241m-\u001b[39m start\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/requests/adapters.py:682\u001b[0m, in \u001b[0;36mHTTPAdapter.send\u001b[0;34m(self, request, stream, timeout, verify, cert, proxies)\u001b[0m\n\u001b[1;32m 667\u001b[0m resp \u001b[38;5;241m=\u001b[39m conn\u001b[38;5;241m.\u001b[39murlopen(\n\u001b[1;32m 668\u001b[0m method\u001b[38;5;241m=\u001b[39mrequest\u001b[38;5;241m.\u001b[39mmethod,\n\u001b[1;32m 669\u001b[0m url\u001b[38;5;241m=\u001b[39murl,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 678\u001b[0m chunked\u001b[38;5;241m=\u001b[39mchunked,\n\u001b[1;32m 679\u001b[0m )\n\u001b[1;32m 681\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (ProtocolError, \u001b[38;5;167;01mOSError\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m err:\n\u001b[0;32m--> 682\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mConnectionError\u001b[39;00m(err, request\u001b[38;5;241m=\u001b[39mrequest)\n\u001b[1;32m 684\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m MaxRetryError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 685\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(e\u001b[38;5;241m.\u001b[39mreason, ConnectTimeoutError):\n\u001b[1;32m 686\u001b[0m \u001b[38;5;66;03m# TODO: Remove this in 3.0.0: see #2811\u001b[39;00m\n",
"\u001b[0;31mConnectionError\u001b[0m: ('Connection aborted.', ConnectionResetError(54, 'Connection reset by peer'))"
]
}
],
"source": [
"text_input = tf.keras.layers.Input(shape=(), dtype=tf.string)\n",
"preprocessor = keras_nlp.models.BertPreprocessor.from_preset(\"bert_base_en_uncased\",trainable=True)\n",
"encoder_inputs = preprocessor(text_input)\n",
"encoder = keras_nlp.models.BertBackbone.from_preset(\"bert_base_en_uncased\")\n",
"outputs = encoder(encoder_inputs)\n",
"pooled_output = outputs[\"pooled_output\"] # [batch_size, 768].\n",
"sequence_output = outputs[\"sequence_output\"] # [batch_size, seq_length, 768]."
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "ca5f1364-47d2-4dde-afa2-51f75ce9850c",
"metadata": {},
"outputs": [
{
"ename": "ValueError",
"evalue": "Exception encountered when calling layer 'keras_layer' (type KerasLayer).\n\nA KerasTensor is symbolic: it's a placeholder for a shape an a dtype. It doesn't have any actual numerical value. You cannot convert it to a NumPy array.\n\nCall arguments received by layer 'keras_layer' (type KerasLayer):\n • inputs=<KerasTensor shape=(None,), dtype=string, sparse=None, name=test>\n • training=None",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[11], line 3\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# Bert layers\u001b[39;00m\n\u001b[1;32m 2\u001b[0m text_input \u001b[38;5;241m=\u001b[39m tf\u001b[38;5;241m.\u001b[39mkeras\u001b[38;5;241m.\u001b[39mlayers\u001b[38;5;241m.\u001b[39mInput(shape\u001b[38;5;241m=\u001b[39m(), dtype\u001b[38;5;241m=\u001b[39mtf\u001b[38;5;241m.\u001b[39mstring, name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtest\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m----> 3\u001b[0m preprocessed_text \u001b[38;5;241m=\u001b[39m \u001b[43mbert_preprocess\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext_input\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 4\u001b[0m outputs \u001b[38;5;241m=\u001b[39m bert_encoder(preprocessed_text)\n\u001b[1;32m 6\u001b[0m \u001b[38;5;66;03m# Neural network layers\u001b[39;00m\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/tf_keras/src/utils/traceback_utils.py:70\u001b[0m, in \u001b[0;36mfilter_traceback.<locals>.error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 67\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n\u001b[1;32m 68\u001b[0m \u001b[38;5;66;03m# To get the full stack trace, call:\u001b[39;00m\n\u001b[1;32m 69\u001b[0m \u001b[38;5;66;03m# `tf.debugging.disable_traceback_filtering()`\u001b[39;00m\n\u001b[0;32m---> 70\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\u001b[38;5;241m.\u001b[39mwith_traceback(filtered_tb) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 71\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[1;32m 72\u001b[0m \u001b[38;5;28;01mdel\u001b[39;00m filtered_tb\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/tensorflow_hub/keras_layer.py:250\u001b[0m, in \u001b[0;36mKerasLayer.call\u001b[0;34m(self, inputs, training)\u001b[0m\n\u001b[1;32m 247\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 248\u001b[0m \u001b[38;5;66;03m# Behave like BatchNormalization. (Dropout is different, b/181839368.)\u001b[39;00m\n\u001b[1;32m 249\u001b[0m training \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[0;32m--> 250\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[43msmart_cond\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msmart_cond\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtraining\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 251\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01mlambda\u001b[39;49;00m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtraining\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 252\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01mlambda\u001b[39;49;00m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtraining\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 254\u001b[0m \u001b[38;5;66;03m# Unwrap dicts returned by signatures.\u001b[39;00m\n\u001b[1;32m 255\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_output_key:\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/tensorflow_hub/keras_layer.py:252\u001b[0m, in \u001b[0;36mKerasLayer.call.<locals>.<lambda>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 247\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 248\u001b[0m \u001b[38;5;66;03m# Behave like BatchNormalization. (Dropout is different, b/181839368.)\u001b[39;00m\n\u001b[1;32m 249\u001b[0m training \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[1;32m 250\u001b[0m result \u001b[38;5;241m=\u001b[39m smart_cond\u001b[38;5;241m.\u001b[39msmart_cond(training,\n\u001b[1;32m 251\u001b[0m \u001b[38;5;28;01mlambda\u001b[39;00m: f(training\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m),\n\u001b[0;32m--> 252\u001b[0m \u001b[38;5;28;01mlambda\u001b[39;00m: \u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtraining\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m)\n\u001b[1;32m 254\u001b[0m \u001b[38;5;66;03m# Unwrap dicts returned by signatures.\u001b[39;00m\n\u001b[1;32m 255\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_output_key:\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/tensorflow/core/function/polymorphism/function_type.py:583\u001b[0m, in \u001b[0;36mcanonicalize_to_monomorphic\u001b[0;34m(args, kwargs, default_values, capture_types, polymorphic_type)\u001b[0m\n\u001b[1;32m 577\u001b[0m parameters\u001b[38;5;241m.\u001b[39mappend(\n\u001b[1;32m 578\u001b[0m _make_validated_mono_param(kwarg_name, arg[kwarg_name],\n\u001b[1;32m 579\u001b[0m Parameter\u001b[38;5;241m.\u001b[39mKEYWORD_ONLY, type_context,\n\u001b[1;32m 580\u001b[0m poly_parameter\u001b[38;5;241m.\u001b[39mtype_constraint))\n\u001b[1;32m 581\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 582\u001b[0m parameters\u001b[38;5;241m.\u001b[39mappend(\n\u001b[0;32m--> 583\u001b[0m \u001b[43m_make_validated_mono_param\u001b[49m\u001b[43m(\u001b[49m\u001b[43mname\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43marg\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpoly_parameter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mkind\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 584\u001b[0m \u001b[43m \u001b[49m\u001b[43mtype_context\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 585\u001b[0m \u001b[43m \u001b[49m\u001b[43mpoly_parameter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtype_constraint\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[1;32m 587\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m FunctionType(parameters, capture_types), type_context\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/tensorflow/core/function/polymorphism/function_type.py:522\u001b[0m, in \u001b[0;36m_make_validated_mono_param\u001b[0;34m(name, value, kind, type_context, poly_type)\u001b[0m\n\u001b[1;32m 518\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_make_validated_mono_param\u001b[39m(\n\u001b[1;32m 519\u001b[0m name, value, kind, type_context, poly_type\n\u001b[1;32m 520\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Parameter:\n\u001b[1;32m 521\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Generates and validates a parameter for Monomorphic FunctionType.\"\"\"\u001b[39;00m\n\u001b[0;32m--> 522\u001b[0m mono_type \u001b[38;5;241m=\u001b[39m \u001b[43mtrace_type\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_value\u001b[49m\u001b[43m(\u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtype_context\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m poly_type \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m mono_type\u001b[38;5;241m.\u001b[39mis_subtype_of(poly_type):\n\u001b[1;32m 525\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mParameter `\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m` was expected to be of type \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 526\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpoly_type\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m but is \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mmono_type\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/tensorflow/core/function/trace_type/trace_type_builder.py:185\u001b[0m, in \u001b[0;36mfrom_value\u001b[0;34m(value, context)\u001b[0m\n\u001b[1;32m 178\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m default_types\u001b[38;5;241m.\u001b[39mAttrs\u001b[38;5;241m.\u001b[39mfrom_type_and_attributes(\n\u001b[1;32m 179\u001b[0m \u001b[38;5;28mtype\u001b[39m(value),\n\u001b[1;32m 180\u001b[0m \u001b[38;5;28mtuple\u001b[39m(\n\u001b[1;32m 181\u001b[0m from_value(\u001b[38;5;28mgetattr\u001b[39m(value, a\u001b[38;5;241m.\u001b[39mname), context)\n\u001b[1;32m 182\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m value\u001b[38;5;241m.\u001b[39m__attrs_attrs__))\n\u001b[1;32m 184\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m util\u001b[38;5;241m.\u001b[39mis_np_ndarray(value):\n\u001b[0;32m--> 185\u001b[0m ndarray \u001b[38;5;241m=\u001b[39m \u001b[43mvalue\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m__array__\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 186\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m default_types\u001b[38;5;241m.\u001b[39mTENSOR(ndarray\u001b[38;5;241m.\u001b[39mshape, ndarray\u001b[38;5;241m.\u001b[39mdtype)\n\u001b[1;32m 188\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(value, custom_nest_protocol\u001b[38;5;241m.\u001b[39mCustomNestProtocol):\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/keras/src/backend/common/keras_tensor.py:61\u001b[0m, in \u001b[0;36mKerasTensor.__array__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 60\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__array__\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[0;32m---> 61\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 62\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mA KerasTensor is symbolic: it\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124ms a placeholder for a shape \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 63\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124man a dtype. It doesn\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt have any actual numerical value. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 64\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mYou cannot convert it to a NumPy array.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 65\u001b[0m )\n",
"\u001b[0;31mValueError\u001b[0m: Exception encountered when calling layer 'keras_layer' (type KerasLayer).\n\nA KerasTensor is symbolic: it's a placeholder for a shape an a dtype. It doesn't have any actual numerical value. You cannot convert it to a NumPy array.\n\nCall arguments received by layer 'keras_layer' (type KerasLayer):\n • inputs=<KerasTensor shape=(None,), dtype=string, sparse=None, name=test>\n • training=None"
]
}
],
"source": [
"# Bert layers\n",
"text_input = tf.keras.layers.Input(shape=(), dtype=tf.string, name='test')\n",
"preprocessed_text = bert_preprocess(text_input)\n",
"outputs = bert_encoder(preprocessed_text)\n",
"\n",
"# Neural network layers\n",
"l = tf.keras.layers.Dropout(0.1, name=\"dropout\")(outputs['pooled_output'])\n",
"l = tf.keras.layers.Dense(1, activation='sigmoid', name=\"output\")(l)\n",
"\n",
"# Use inputs and outputs to construct a final model\n",
"model = tf.keras.Model(inputs=[text_input], outputs = [l])"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "04f8b330-e5a6-4509-8bd0-5cfa2f50c541",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/3\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/techgarage/anaconda3/envs/DE/lib/python3.9/site-packages/keras/src/models/functional.py:237: UserWarning: The structure of `inputs` doesn't match the expected structure.\n",
"Expected: ['text']\n",
"Received: inputs=Tensor(shape=(None,))\n",
" warnings.warn(msg)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 3s/step - accuracy: 0.5000 - loss: 1.0744\n",
"Epoch 2/3\n",
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 209ms/step - accuracy: 0.5000 - loss: 0.7670\n",
"Epoch 3/3\n",
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 207ms/step - accuracy: 0.5000 - loss: 0.7240\n"
]
},
{
"data": {
"text/plain": [
"<keras.src.callbacks.history.History at 0x2d69dca00>"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import numpy as np\n",
"\n",
"# Example training data (spam detection)\n",
"train_texts = [\n",
" \"Win a free iPhone now!!!\", # Spam (1)\n",
" \"Meeting at 3 PM tomorrow\" # Ham (0)\n",
"]\n",
"train_labels = np.array([1, 0]) # Use numpy arrays for labels\n",
"\n",
"# Convert to a TensorFlow Dataset\n",
"train_dataset = tf.data.Dataset.from_tensor_slices((train_texts, train_labels))\n",
"train_dataset = train_dataset.batch(32) # Adjust batch size as needed\n",
"\n",
"# Train the model\n",
"model.fit(train_dataset, epochs=3)"
]
},
{
"cell_type": "code",
"execution_count": 39,
"id": "05be4db7-be33-49be-ac6e-441650cece64",
"metadata": {
"collapsed": true,
"jupyter": {
"outputs_hidden": true
}
},
"outputs": [
{
"ename": "ValueError",
"evalue": "Exception encountered when calling layer 'keras_layer_4' (type KerasLayer).\n\nA KerasTensor is symbolic: it's a placeholder for a shape an a dtype. It doesn't have any actual numerical value. You cannot convert it to a NumPy array.\n\nCall arguments received by layer 'keras_layer_4' (type KerasLayer):\n • inputs=<KerasTensor shape=(None,), dtype=string, sparse=False, name=text>\n • training=None",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[39], line 14\u001b[0m\n\u001b[1;32m 12\u001b[0m \u001b[38;5;66;03m# Define the model architecture\u001b[39;00m\n\u001b[1;32m 13\u001b[0m text_input \u001b[38;5;241m=\u001b[39m tf\u001b[38;5;241m.\u001b[39mkeras\u001b[38;5;241m.\u001b[39mlayers\u001b[38;5;241m.\u001b[39mInput(shape\u001b[38;5;241m=\u001b[39m(), dtype\u001b[38;5;241m=\u001b[39mtf\u001b[38;5;241m.\u001b[39mstring, name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtext\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m---> 14\u001b[0m preprocessed_text \u001b[38;5;241m=\u001b[39m \u001b[43mbert_preprocess\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext_input\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 15\u001b[0m encoded_output \u001b[38;5;241m=\u001b[39m bert_encoder(preprocessed_text)\n\u001b[1;32m 16\u001b[0m pooled_output \u001b[38;5;241m=\u001b[39m encoded_output[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mpooled_output\u001b[39m\u001b[38;5;124m'\u001b[39m]\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/tf_keras/src/utils/traceback_utils.py:70\u001b[0m, in \u001b[0;36mfilter_traceback.<locals>.error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 67\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n\u001b[1;32m 68\u001b[0m \u001b[38;5;66;03m# To get the full stack trace, call:\u001b[39;00m\n\u001b[1;32m 69\u001b[0m \u001b[38;5;66;03m# `tf.debugging.disable_traceback_filtering()`\u001b[39;00m\n\u001b[0;32m---> 70\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\u001b[38;5;241m.\u001b[39mwith_traceback(filtered_tb) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 71\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[1;32m 72\u001b[0m \u001b[38;5;28;01mdel\u001b[39;00m filtered_tb\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/tensorflow_hub/keras_layer.py:250\u001b[0m, in \u001b[0;36mKerasLayer.call\u001b[0;34m(self, inputs, training)\u001b[0m\n\u001b[1;32m 247\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 248\u001b[0m \u001b[38;5;66;03m# Behave like BatchNormalization. (Dropout is different, b/181839368.)\u001b[39;00m\n\u001b[1;32m 249\u001b[0m training \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[0;32m--> 250\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[43msmart_cond\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msmart_cond\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtraining\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 251\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01mlambda\u001b[39;49;00m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtraining\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 252\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01mlambda\u001b[39;49;00m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtraining\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 254\u001b[0m \u001b[38;5;66;03m# Unwrap dicts returned by signatures.\u001b[39;00m\n\u001b[1;32m 255\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_output_key:\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/tensorflow_hub/keras_layer.py:252\u001b[0m, in \u001b[0;36mKerasLayer.call.<locals>.<lambda>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 247\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 248\u001b[0m \u001b[38;5;66;03m# Behave like BatchNormalization. (Dropout is different, b/181839368.)\u001b[39;00m\n\u001b[1;32m 249\u001b[0m training \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[1;32m 250\u001b[0m result \u001b[38;5;241m=\u001b[39m smart_cond\u001b[38;5;241m.\u001b[39msmart_cond(training,\n\u001b[1;32m 251\u001b[0m \u001b[38;5;28;01mlambda\u001b[39;00m: f(training\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m),\n\u001b[0;32m--> 252\u001b[0m \u001b[38;5;28;01mlambda\u001b[39;00m: \u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtraining\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m)\n\u001b[1;32m 254\u001b[0m \u001b[38;5;66;03m# Unwrap dicts returned by signatures.\u001b[39;00m\n\u001b[1;32m 255\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_output_key:\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/tensorflow/core/function/polymorphism/function_type.py:583\u001b[0m, in \u001b[0;36mcanonicalize_to_monomorphic\u001b[0;34m(args, kwargs, default_values, capture_types, polymorphic_type)\u001b[0m\n\u001b[1;32m 577\u001b[0m parameters\u001b[38;5;241m.\u001b[39mappend(\n\u001b[1;32m 578\u001b[0m _make_validated_mono_param(kwarg_name, arg[kwarg_name],\n\u001b[1;32m 579\u001b[0m Parameter\u001b[38;5;241m.\u001b[39mKEYWORD_ONLY, type_context,\n\u001b[1;32m 580\u001b[0m poly_parameter\u001b[38;5;241m.\u001b[39mtype_constraint))\n\u001b[1;32m 581\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 582\u001b[0m parameters\u001b[38;5;241m.\u001b[39mappend(\n\u001b[0;32m--> 583\u001b[0m \u001b[43m_make_validated_mono_param\u001b[49m\u001b[43m(\u001b[49m\u001b[43mname\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43marg\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpoly_parameter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mkind\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 584\u001b[0m \u001b[43m \u001b[49m\u001b[43mtype_context\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 585\u001b[0m \u001b[43m \u001b[49m\u001b[43mpoly_parameter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtype_constraint\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[1;32m 587\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m FunctionType(parameters, capture_types), type_context\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/tensorflow/core/function/polymorphism/function_type.py:522\u001b[0m, in \u001b[0;36m_make_validated_mono_param\u001b[0;34m(name, value, kind, type_context, poly_type)\u001b[0m\n\u001b[1;32m 518\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_make_validated_mono_param\u001b[39m(\n\u001b[1;32m 519\u001b[0m name, value, kind, type_context, poly_type\n\u001b[1;32m 520\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Parameter:\n\u001b[1;32m 521\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Generates and validates a parameter for Monomorphic FunctionType.\"\"\"\u001b[39;00m\n\u001b[0;32m--> 522\u001b[0m mono_type \u001b[38;5;241m=\u001b[39m \u001b[43mtrace_type\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_value\u001b[49m\u001b[43m(\u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtype_context\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m poly_type \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m mono_type\u001b[38;5;241m.\u001b[39mis_subtype_of(poly_type):\n\u001b[1;32m 525\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mParameter `\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m` was expected to be of type \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 526\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpoly_type\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m but is \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mmono_type\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/tensorflow/core/function/trace_type/trace_type_builder.py:185\u001b[0m, in \u001b[0;36mfrom_value\u001b[0;34m(value, context)\u001b[0m\n\u001b[1;32m 178\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m default_types\u001b[38;5;241m.\u001b[39mAttrs\u001b[38;5;241m.\u001b[39mfrom_type_and_attributes(\n\u001b[1;32m 179\u001b[0m \u001b[38;5;28mtype\u001b[39m(value),\n\u001b[1;32m 180\u001b[0m \u001b[38;5;28mtuple\u001b[39m(\n\u001b[1;32m 181\u001b[0m from_value(\u001b[38;5;28mgetattr\u001b[39m(value, a\u001b[38;5;241m.\u001b[39mname), context)\n\u001b[1;32m 182\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m value\u001b[38;5;241m.\u001b[39m__attrs_attrs__))\n\u001b[1;32m 184\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m util\u001b[38;5;241m.\u001b[39mis_np_ndarray(value):\n\u001b[0;32m--> 185\u001b[0m ndarray \u001b[38;5;241m=\u001b[39m \u001b[43mvalue\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m__array__\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 186\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m default_types\u001b[38;5;241m.\u001b[39mTENSOR(ndarray\u001b[38;5;241m.\u001b[39mshape, ndarray\u001b[38;5;241m.\u001b[39mdtype)\n\u001b[1;32m 188\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(value, custom_nest_protocol\u001b[38;5;241m.\u001b[39mCustomNestProtocol):\n",
"File \u001b[0;32m~/anaconda3/envs/DE/lib/python3.9/site-packages/keras/src/backend/common/keras_tensor.py:108\u001b[0m, in \u001b[0;36mKerasTensor.__array__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 107\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__array__\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[0;32m--> 108\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 109\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mA KerasTensor is symbolic: it\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124ms a placeholder for a shape \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 110\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124man a dtype. It doesn\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt have any actual numerical value. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 111\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mYou cannot convert it to a NumPy array.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 112\u001b[0m )\n",
"\u001b[0;31mValueError\u001b[0m: Exception encountered when calling layer 'keras_layer_4' (type KerasLayer).\n\nA KerasTensor is symbolic: it's a placeholder for a shape an a dtype. It doesn't have any actual numerical value. You cannot convert it to a NumPy array.\n\nCall arguments received by layer 'keras_layer_4' (type KerasLayer):\n • inputs=<KerasTensor shape=(None,), dtype=string, sparse=False, name=text>\n • training=None"
]
}
],
"source": [
"import tensorflow as tf\n",
"import tensorflow_hub as hub\n",
"\n",
"# Load the preprocessing and encoder layers from local directories\n",
"preprocess_path = \"/Users/techgarage/Projects/Data Engineering/Final Project/bert-tensorflow2-en-uncased-preprocess-v3\"\n",
"encoder_path = \"/Users/techgarage/Projects/Data Engineering/Final Project/bert-tensorflow2-en-uncased-l-12-h-768-a-12-v4\"\n",
"\n",
"# Load the BERT layers\n",
"bert_preprocess = hub.KerasLayer(preprocess_path)\n",
"bert_encoder = hub.KerasLayer(encoder_path)\n",
"\n",
"# Define the model architecture\n",
"text_input = tf.keras.layers.Input(shape=(), dtype=tf.string, name='text')\n",
"preprocessed_text = bert_preprocess(text_input)\n",
"encoded_output = bert_encoder(preprocessed_text)\n",
"pooled_output = encoded_output['pooled_output']\n",
"\n",
"# Add classification head\n",
"dropout = tf.keras.layers.Dropout(0.1, name=\"dropout\")(pooled_output)\n",
"output = tf.keras.layers.Dense(1, activation='sigmoid', name=\"output\")(dropout)\n",
"\n",
"# Build the model\n",
"model = tf.keras.Model(inputs=[text_input], outputs=[output])\n",
"\n",
"# Compile the model\n",
"model.compile(\n",
" optimizer='adam',\n",
" loss='binary_crossentropy',\n",
" metrics=['accuracy']\n",
")\n",
"\n",
"model.summary()"
]
},
{
"cell_type": "code",
"execution_count": 53,
"id": "7233ee9f-f86e-46cb-91d6-c248bfa81ede",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"os.environ['TF_USE_LEGACY_KERAS']='1'"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "57d3f18e-5cc2-463c-a17b-012712d63f32",
"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": "3.9.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|