Spaces:
Sleeping
Sleeping
File size: 102,021 Bytes
fac73c1 | 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 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 | {
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "4ba6aba8"
},
"source": [
"# 🤖 **Data Collection, Creation, Storage, and Processing**\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "jpASMyIQMaAq"
},
"source": [
"## **1.** 📦 Install required packages"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "f48c8f8c",
"outputId": "5143dab8-2a4f-400a-9c82-82ba5f1be700",
"collapsed": true
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.12/dist-packages (4.13.5)\n",
"Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (2.2.2)\n",
"Requirement already satisfied: matplotlib in /usr/local/lib/python3.12/dist-packages (3.10.0)\n",
"Requirement already satisfied: seaborn in /usr/local/lib/python3.12/dist-packages (0.13.2)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.12/dist-packages (2.0.2)\n",
"Requirement already satisfied: textblob in /usr/local/lib/python3.12/dist-packages (0.19.0)\n",
"Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.12/dist-packages (from beautifulsoup4) (2.8.3)\n",
"Requirement already satisfied: typing-extensions>=4.0.0 in /usr/local/lib/python3.12/dist-packages (from beautifulsoup4) (4.15.0)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas) (2.9.0.post0)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas) (2025.2)\n",
"Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas) (2025.3)\n",
"Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (1.3.3)\n",
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (0.12.1)\n",
"Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (4.61.1)\n",
"Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (1.4.9)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (26.0)\n",
"Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (11.3.0)\n",
"Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (3.3.2)\n",
"Requirement already satisfied: nltk>=3.9 in /usr/local/lib/python3.12/dist-packages (from textblob) (3.9.1)\n",
"Requirement already satisfied: click in /usr/local/lib/python3.12/dist-packages (from nltk>=3.9->textblob) (8.3.1)\n",
"Requirement already satisfied: joblib in /usr/local/lib/python3.12/dist-packages (from nltk>=3.9->textblob) (1.5.3)\n",
"Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.12/dist-packages (from nltk>=3.9->textblob) (2025.11.3)\n",
"Requirement already satisfied: tqdm in /usr/local/lib/python3.12/dist-packages (from nltk>=3.9->textblob) (4.67.3)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas) (1.17.0)\n"
]
}
],
"source": [
"!pip install beautifulsoup4 pandas matplotlib seaborn numpy textblob"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "lquNYCbfL9IM"
},
"source": [
"## **2.** ⛏ Web-scrape all book titles, prices, and ratings from books.toscrape.com"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "0IWuNpxxYDJF"
},
"source": [
"### *a. Initial setup*\n",
"Define the base url of the website you will scrape as well as how and what you will scrape"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"id": "91d52125"
},
"outputs": [],
"source": [
"import requests\n",
"from bs4 import BeautifulSoup\n",
"import pandas as pd\n",
"import time\n",
"\n",
"base_url = \"https://books.toscrape.com/catalogue/page-{}.html\"\n",
"headers = {\"User-Agent\": \"Mozilla/5.0\"}\n",
"\n",
"titles, prices, ratings = [], [], []"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "oCdTsin2Yfp3"
},
"source": [
"### *b. Fill titles, prices, and ratings from the web pages*"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"id": "xqO5Y3dnYhxt"
},
"outputs": [],
"source": [
"# Loop through all 50 pages\n",
"for page in range(1, 51):\n",
" url = base_url.format(page)\n",
" response = requests.get(url, headers=headers)\n",
" soup = BeautifulSoup(response.content, \"html.parser\")\n",
" books = soup.find_all(\"article\", class_=\"product_pod\")\n",
"\n",
" for book in books:\n",
" titles.append(book.h3.a[\"title\"])\n",
" prices.append(float(book.find(\"p\", class_=\"price_color\").text[1:]))\n",
" ratings.append(book.p.get(\"class\")[1])\n",
"\n",
" time.sleep(0.5) # polite scraping delay"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "T0TOeRC4Yrnn"
},
"source": [
"### *c. ✋🏻🛑⛔️ Create a dataframe df_books that contains the now complete \"title\", \"price\", and \"rating\" objects*"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"id": "l5FkkNhUYTHh",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"outputId": "efbaaa0b-8e25-48bc-db84-64e30cf2dbda"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" Title Price (£) Rating\n",
"0 A Light in the Attic 51.77 Three\n",
"1 Tipping the Velvet 53.74 One\n",
"2 Soumission 50.10 One\n",
"3 Sharp Objects 47.82 Four\n",
"4 Sapiens: A Brief History of Humankind 54.23 Five\n",
".. ... ... ...\n",
"995 Alice in Wonderland (Alice's Adventures in Won... 55.53 One\n",
"996 Ajin: Demi-Human, Volume 1 (Ajin: Demi-Human #1) 57.06 Four\n",
"997 A Spy's Devotion (The Regency Spies of London #1) 16.97 Five\n",
"998 1st to Die (Women's Murder Club #1) 53.98 One\n",
"999 1,000 Places to See Before You Die 26.08 Five\n",
"\n",
"[1000 rows x 3 columns]"
],
"text/html": [
"\n",
" <div id=\"df-2425f4f7-00a5-484f-ba7a-c7eceb9102ed\" class=\"colab-df-container\">\n",
" <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>Title</th>\n",
" <th>Price (£)</th>\n",
" <th>Rating</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>A Light in the Attic</td>\n",
" <td>51.77</td>\n",
" <td>Three</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Tipping the Velvet</td>\n",
" <td>53.74</td>\n",
" <td>One</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Soumission</td>\n",
" <td>50.10</td>\n",
" <td>One</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Sharp Objects</td>\n",
" <td>47.82</td>\n",
" <td>Four</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Sapiens: A Brief History of Humankind</td>\n",
" <td>54.23</td>\n",
" <td>Five</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>995</th>\n",
" <td>Alice in Wonderland (Alice's Adventures in Won...</td>\n",
" <td>55.53</td>\n",
" <td>One</td>\n",
" </tr>\n",
" <tr>\n",
" <th>996</th>\n",
" <td>Ajin: Demi-Human, Volume 1 (Ajin: Demi-Human #1)</td>\n",
" <td>57.06</td>\n",
" <td>Four</td>\n",
" </tr>\n",
" <tr>\n",
" <th>997</th>\n",
" <td>A Spy's Devotion (The Regency Spies of London #1)</td>\n",
" <td>16.97</td>\n",
" <td>Five</td>\n",
" </tr>\n",
" <tr>\n",
" <th>998</th>\n",
" <td>1st to Die (Women's Murder Club #1)</td>\n",
" <td>53.98</td>\n",
" <td>One</td>\n",
" </tr>\n",
" <tr>\n",
" <th>999</th>\n",
" <td>1,000 Places to See Before You Die</td>\n",
" <td>26.08</td>\n",
" <td>Five</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1000 rows × 3 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-2425f4f7-00a5-484f-ba7a-c7eceb9102ed')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-2425f4f7-00a5-484f-ba7a-c7eceb9102ed button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-2425f4f7-00a5-484f-ba7a-c7eceb9102ed');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
" <div id=\"id_2f22002d-32e1-49bd-8cbd-a9a39da1104e\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('df_books')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_2f22002d-32e1-49bd-8cbd-a9a39da1104e button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('df_books');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "df_books",
"summary": "{\n \"name\": \"df_books\",\n \"rows\": 1000,\n \"fields\": [\n {\n \"column\": \"Title\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 999,\n \"samples\": [\n \"The Grownup\",\n \"Persepolis: The Story of a Childhood (Persepolis #1-2)\",\n \"Ayumi's Violin\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Price (\\u00a3)\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14.446689669952772,\n \"min\": 10.0,\n \"max\": 59.99,\n \"num_unique_values\": 903,\n \"samples\": [\n 19.73,\n 55.65,\n 46.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Rating\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"One\",\n \"Two\",\n \"Four\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 6
}
],
"source": [
"import requests\n",
"from bs4 import BeautifulSoup\n",
"import pandas as pd\n",
"import time\n",
"\n",
"base_url = \"https://books.toscrape.com/catalogue/page-{}.html\"\n",
"headers = {\"User-Agent\": \"Mozilla/5.0\"}\n",
"\n",
"titles = []\n",
"prices = []\n",
"ratings = []\n",
"\n",
"# Loop through all 50 pages\n",
"for page in range(1, 51):\n",
" url = base_url.format(page)\n",
" response = requests.get(url, headers=headers)\n",
" soup = BeautifulSoup(response.content, \"html.parser\")\n",
" books = soup.find_all(\"article\", class_=\"product_pod\")\n",
"\n",
" for book in books:\n",
" titles.append(book.h3.a[\"title\"])\n",
" prices.append(float(book.find(\"p\", class_=\"price_color\").text[1:]))\n",
" ratings.append(book.p.get(\"class\")[1])\n",
"\n",
" time.sleep(0.5) # polite scraping delay\n",
"\n",
"# Create DataFrame\n",
"df_books = pd.DataFrame({\n",
" \"Title\": titles,\n",
" \"Price (£)\": prices,\n",
" \"Rating\": ratings\n",
"})\n",
"\n",
"# Display nicely (for Jupyter / Colab)\n",
"df_books"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "duI5dv3CZYvF"
},
"source": [
"### *d. Save web-scraped dataframe either as a CSV or Excel file*"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"id": "lC1U_YHtZifh"
},
"outputs": [],
"source": [
"# 💾 Save to CSV\n",
"df_books.to_csv(\"books_data.csv\", index=False)\n",
"\n",
"# 💾 Or save to Excel\n",
"# df_books.to_excel(\"books_data.xlsx\", index=False)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "qMjRKMBQZlJi"
},
"source": [
"### *e. ✋🏻🛑⛔️ View first fiew lines*"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"id": "O_wIvTxYZqCK",
"outputId": "a4b4b3c8-7a49-4878-c0fe-d6c7f0447705"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" Title Price (£) Rating\n",
"0 A Light in the Attic 51.77 Three\n",
"1 Tipping the Velvet 53.74 One\n",
"2 Soumission 50.10 One\n",
"3 Sharp Objects 47.82 Four\n",
"4 Sapiens: A Brief History of Humankind 54.23 Five"
],
"text/html": [
"\n",
" <div id=\"df-53e77369-d3ca-4caa-8718-76f2c714eb6e\" class=\"colab-df-container\">\n",
" <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>Title</th>\n",
" <th>Price (£)</th>\n",
" <th>Rating</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>A Light in the Attic</td>\n",
" <td>51.77</td>\n",
" <td>Three</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Tipping the Velvet</td>\n",
" <td>53.74</td>\n",
" <td>One</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Soumission</td>\n",
" <td>50.10</td>\n",
" <td>One</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Sharp Objects</td>\n",
" <td>47.82</td>\n",
" <td>Four</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Sapiens: A Brief History of Humankind</td>\n",
" <td>54.23</td>\n",
" <td>Five</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-53e77369-d3ca-4caa-8718-76f2c714eb6e')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-53e77369-d3ca-4caa-8718-76f2c714eb6e button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-53e77369-d3ca-4caa-8718-76f2c714eb6e');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "df_books",
"summary": "{\n \"name\": \"df_books\",\n \"rows\": 1000,\n \"fields\": [\n {\n \"column\": \"Title\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 999,\n \"samples\": [\n \"The Grownup\",\n \"Persepolis: The Story of a Childhood (Persepolis #1-2)\",\n \"Ayumi's Violin\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Price (\\u00a3)\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14.446689669952772,\n \"min\": 10.0,\n \"max\": 59.99,\n \"num_unique_values\": 903,\n \"samples\": [\n 19.73,\n 55.65,\n 46.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Rating\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"One\",\n \"Two\",\n \"Four\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 8
}
],
"source": [
"df_books.head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "p-1Pr2szaqLk"
},
"source": [
"## **3.** 🧩 Create a meaningful connection between real & synthetic datasets"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "SIaJUGIpaH4V"
},
"source": [
"### *a. Initial setup*"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"id": "-gPXGcRPuV_9"
},
"outputs": [],
"source": [
"import numpy as np\n",
"import random\n",
"from datetime import datetime\n",
"import warnings\n",
"\n",
"warnings.filterwarnings(\"ignore\")\n",
"random.seed(2025)\n",
"np.random.seed(2025)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "pY4yCoIuaQqp"
},
"source": [
"### *b. Generate popularity scores based on rating (with some randomness) with a generate_popularity_score function*"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"id": "mnd5hdAbaNjz"
},
"outputs": [],
"source": [
"def generate_popularity_score(rating):\n",
" base = {\"One\": 2, \"Two\": 3, \"Three\": 3, \"Four\": 4, \"Five\": 4}.get(rating, 3)\n",
" trend_factor = random.choices([-1, 0, 1], weights=[1, 3, 2])[0]\n",
" return int(np.clip(base + trend_factor, 1, 5))"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "n4-TaNTFgPak"
},
"source": [
"### *c. ✋🏻🛑⛔️ Run the function to create a \"popularity_score\" column from \"rating\"*"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"id": "V-G3OCUCgR07",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"outputId": "b5ab1912-fc6e-499a-eb94-af2cd4d6b651"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" Title Price (£) Rating popularity_score\n",
"0 A Light in the Attic 51.77 Three 3\n",
"1 Tipping the Velvet 53.74 One 2\n",
"2 Soumission 50.10 One 2\n",
"3 Sharp Objects 47.82 Four 4\n",
"4 Sapiens: A Brief History of Humankind 54.23 Five 3"
],
"text/html": [
"\n",
" <div id=\"df-e2a3ee67-8897-4349-bb2f-e6562433fa06\" class=\"colab-df-container\">\n",
" <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>Title</th>\n",
" <th>Price (£)</th>\n",
" <th>Rating</th>\n",
" <th>popularity_score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>A Light in the Attic</td>\n",
" <td>51.77</td>\n",
" <td>Three</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Tipping the Velvet</td>\n",
" <td>53.74</td>\n",
" <td>One</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Soumission</td>\n",
" <td>50.10</td>\n",
" <td>One</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Sharp Objects</td>\n",
" <td>47.82</td>\n",
" <td>Four</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Sapiens: A Brief History of Humankind</td>\n",
" <td>54.23</td>\n",
" <td>Five</td>\n",
" <td>3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e2a3ee67-8897-4349-bb2f-e6562433fa06')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-e2a3ee67-8897-4349-bb2f-e6562433fa06 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-e2a3ee67-8897-4349-bb2f-e6562433fa06');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "df_books",
"summary": "{\n \"name\": \"df_books\",\n \"rows\": 1000,\n \"fields\": [\n {\n \"column\": \"Title\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 999,\n \"samples\": [\n \"The Grownup\",\n \"Persepolis: The Story of a Childhood (Persepolis #1-2)\",\n \"Ayumi's Violin\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Price (\\u00a3)\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14.446689669952772,\n \"min\": 10.0,\n \"max\": 59.99,\n \"num_unique_values\": 903,\n \"samples\": [\n 19.73,\n 55.65,\n 46.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Rating\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"One\",\n \"Two\",\n \"Four\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"popularity_score\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1,\n \"min\": 1,\n \"max\": 5,\n \"num_unique_values\": 5,\n \"samples\": [\n 2,\n 5,\n 4\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 16
}
],
"source": [
"# Create popularity_score column\n",
"df_books[\"popularity_score\"] = df_books[\"Rating\"].apply(generate_popularity_score)\n",
"\n",
"# Display result\n",
"df_books.head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "HnngRNTgacYt"
},
"source": [
"### *d. Decide on the sentiment_label based on the popularity score with a get_sentiment function*"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"id": "kUtWmr8maZLZ"
},
"outputs": [],
"source": [
"def get_sentiment(popularity_score):\n",
" if popularity_score <= 2:\n",
" return \"negative\"\n",
" elif popularity_score == 3:\n",
" return \"neutral\"\n",
" else:\n",
" return \"positive\""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "HF9F9HIzgT7Z"
},
"source": [
"### *e. ✋🏻🛑⛔️ Run the function to create a \"sentiment_label\" column from \"popularity_score\"*"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"id": "tafQj8_7gYCG",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"outputId": "ff52f20c-6741-4cab-c606-aac5dac55707"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" Title Price (£) Rating popularity_score \\\n",
"0 A Light in the Attic 51.77 Three 3 \n",
"1 Tipping the Velvet 53.74 One 2 \n",
"2 Soumission 50.10 One 2 \n",
"3 Sharp Objects 47.82 Four 4 \n",
"4 Sapiens: A Brief History of Humankind 54.23 Five 3 \n",
"\n",
" sentiment_label \n",
"0 neutral \n",
"1 negative \n",
"2 negative \n",
"3 positive \n",
"4 neutral "
],
"text/html": [
"\n",
" <div id=\"df-eb3bebe9-8f97-4f21-a3b4-256e5d85a094\" class=\"colab-df-container\">\n",
" <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>Title</th>\n",
" <th>Price (£)</th>\n",
" <th>Rating</th>\n",
" <th>popularity_score</th>\n",
" <th>sentiment_label</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>A Light in the Attic</td>\n",
" <td>51.77</td>\n",
" <td>Three</td>\n",
" <td>3</td>\n",
" <td>neutral</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Tipping the Velvet</td>\n",
" <td>53.74</td>\n",
" <td>One</td>\n",
" <td>2</td>\n",
" <td>negative</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Soumission</td>\n",
" <td>50.10</td>\n",
" <td>One</td>\n",
" <td>2</td>\n",
" <td>negative</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Sharp Objects</td>\n",
" <td>47.82</td>\n",
" <td>Four</td>\n",
" <td>4</td>\n",
" <td>positive</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Sapiens: A Brief History of Humankind</td>\n",
" <td>54.23</td>\n",
" <td>Five</td>\n",
" <td>3</td>\n",
" <td>neutral</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-eb3bebe9-8f97-4f21-a3b4-256e5d85a094')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-eb3bebe9-8f97-4f21-a3b4-256e5d85a094 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-eb3bebe9-8f97-4f21-a3b4-256e5d85a094');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "df_books",
"summary": "{\n \"name\": \"df_books\",\n \"rows\": 1000,\n \"fields\": [\n {\n \"column\": \"Title\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 999,\n \"samples\": [\n \"The Grownup\",\n \"Persepolis: The Story of a Childhood (Persepolis #1-2)\",\n \"Ayumi's Violin\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Price (\\u00a3)\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14.446689669952772,\n \"min\": 10.0,\n \"max\": 59.99,\n \"num_unique_values\": 903,\n \"samples\": [\n 19.73,\n 55.65,\n 46.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Rating\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"One\",\n \"Two\",\n \"Four\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"popularity_score\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1,\n \"min\": 1,\n \"max\": 5,\n \"num_unique_values\": 5,\n \"samples\": [\n 2,\n 5,\n 4\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"sentiment_label\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"neutral\",\n \"negative\",\n \"positive\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 18
}
],
"source": [
"# Create sentiment_label column\n",
"df_books[\"sentiment_label\"] = df_books[\"popularity_score\"].apply(get_sentiment)\n",
"\n",
"# Display result\n",
"df_books.head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "T8AdKkmASq9a"
},
"source": [
"## **4.** 📈 Generate synthetic book sales data of 18 months"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "OhXbdGD5fH0c"
},
"source": [
"### *a. Create a generate_sales_profit function that would generate sales patterns based on sentiment_label (with some randomness)*"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {
"id": "qkVhYPXGbgEn"
},
"outputs": [],
"source": [
"def generate_sales_profile(sentiment):\n",
" months = pd.date_range(end=datetime.today(), periods=18, freq=\"M\")\n",
"\n",
" if sentiment == \"positive\":\n",
" base = random.randint(200, 300)\n",
" trend = np.linspace(base, base + random.randint(20, 60), len(months))\n",
" elif sentiment == \"negative\":\n",
" base = random.randint(20, 80)\n",
" trend = np.linspace(base, base - random.randint(10, 30), len(months))\n",
" else: # neutral\n",
" base = random.randint(80, 160)\n",
" trend = np.full(len(months), base + random.randint(-10, 10))\n",
"\n",
" seasonality = 10 * np.sin(np.linspace(0, 3 * np.pi, len(months)))\n",
" noise = np.random.normal(0, 5, len(months))\n",
" monthly_sales = np.clip(trend + seasonality + noise, a_min=0, a_max=None).astype(int)\n",
"\n",
" return list(zip(months.strftime(\"%Y-%m\"), monthly_sales))"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "L2ak1HlcgoTe"
},
"source": [
"### *b. Run the function as part of building sales_data*"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {
"id": "SlJ24AUafoDB"
},
"outputs": [],
"source": [
"sales_data = []\n",
"\n",
"for _, row in df_books.iterrows():\n",
" records = generate_sales_profile(row[\"sentiment_label\"])\n",
"\n",
" for month, units in records:\n",
" sales_data.append({\n",
" \"title\": row[\"Title\"], # fixed here\n",
" \"month\": month,\n",
" \"units_sold\": units,\n",
" \"sentiment_label\": row[\"sentiment_label\"]\n",
" })"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "4IXZKcCSgxnq"
},
"source": [
"### *c. ✋🏻🛑⛔️ Create a df_sales DataFrame from sales_data*"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {
"id": "wcN6gtiZg-ws",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"outputId": "f6b74d1c-3a60-405b-da04-d0f2f1643dd5"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" title month units_sold sentiment_label\n",
"0 A Light in the Attic 2024-09 123 neutral\n",
"1 A Light in the Attic 2024-10 122 neutral\n",
"2 A Light in the Attic 2024-11 127 neutral\n",
"3 A Light in the Attic 2024-12 127 neutral\n",
"4 A Light in the Attic 2025-01 127 neutral"
],
"text/html": [
"\n",
" <div id=\"df-1a0ae30c-4a19-48b7-8047-324e518231da\" class=\"colab-df-container\">\n",
" <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>title</th>\n",
" <th>month</th>\n",
" <th>units_sold</th>\n",
" <th>sentiment_label</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>A Light in the Attic</td>\n",
" <td>2024-09</td>\n",
" <td>123</td>\n",
" <td>neutral</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>A Light in the Attic</td>\n",
" <td>2024-10</td>\n",
" <td>122</td>\n",
" <td>neutral</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>A Light in the Attic</td>\n",
" <td>2024-11</td>\n",
" <td>127</td>\n",
" <td>neutral</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>A Light in the Attic</td>\n",
" <td>2024-12</td>\n",
" <td>127</td>\n",
" <td>neutral</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>A Light in the Attic</td>\n",
" <td>2025-01</td>\n",
" <td>127</td>\n",
" <td>neutral</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-1a0ae30c-4a19-48b7-8047-324e518231da')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-1a0ae30c-4a19-48b7-8047-324e518231da button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-1a0ae30c-4a19-48b7-8047-324e518231da');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "df_sales",
"summary": "{\n \"name\": \"df_sales\",\n \"rows\": 18000,\n \"fields\": [\n {\n \"column\": \"title\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 999,\n \"samples\": [\n \"The Grownup\",\n \"Persepolis: The Story of a Childhood (Persepolis #1-2)\",\n \"Ayumi's Violin\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"month\",\n \"properties\": {\n \"dtype\": \"object\",\n \"num_unique_values\": 18,\n \"samples\": [\n \"2024-09\",\n \"2024-10\",\n \"2025-05\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"units_sold\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 100,\n \"min\": 0,\n \"max\": 365,\n \"num_unique_values\": 354,\n \"samples\": [\n 237,\n 275,\n 228\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"sentiment_label\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"neutral\",\n \"negative\",\n \"positive\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 42
}
],
"source": [
"# Create df_sales DataFrame\n",
"df_sales = pd.DataFrame(sales_data)\n",
"\n",
"# Display result\n",
"df_sales.head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "EhIjz9WohAmZ"
},
"source": [
"### *d. Save df_sales as synthetic_sales_data.csv & view first few lines*"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "MzbZvLcAhGaH",
"outputId": "cf18e473-d633-4448-9f98-51e18f7e4f27"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" title month units_sold sentiment_label\n",
"0 A Light in the Attic 2024-09 123 neutral\n",
"1 A Light in the Attic 2024-10 122 neutral\n",
"2 A Light in the Attic 2024-11 127 neutral\n",
"3 A Light in the Attic 2024-12 127 neutral\n",
"4 A Light in the Attic 2025-01 127 neutral\n"
]
}
],
"source": [
"df_sales.to_csv(\"synthetic_sales_data.csv\", index=False)\n",
"\n",
"print(df_sales.head())"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "7g9gqBgQMtJn"
},
"source": [
"## **5.** 🎯 Generate synthetic customer reviews"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Gi4y9M9KuDWx"
},
"source": [
"### *a. ✋🏻🛑⛔️ Ask ChatGPT to create a list of 50 distinct generic book review texts for the sentiment labels \"positive\", \"neutral\", and \"negative\" called synthetic_reviews_by_sentiment*"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {
"id": "b3cd2a50"
},
"outputs": [],
"source": [
"# 50 generic review texts per sentiment label\n",
"synthetic_reviews_by_sentiment = {\n",
" \"positive\": [\n",
" \"A captivating story with memorable characters and a satisfying ending.\",\n",
" \"Beautifully written and emotionally engaging from start to finish.\",\n",
" \"A page-turner that kept me hooked throughout.\",\n",
" \"Thought-provoking and well-paced, with strong storytelling.\",\n",
" \"An uplifting read that left me feeling inspired.\",\n",
" \"The writing style was smooth and the plot flowed nicely.\",\n",
" \"A brilliant book — I couldn’t put it down.\",\n",
" \"Rich world-building and characters that felt truly alive.\",\n",
" \"A charming and heartfelt story that really resonated with me.\",\n",
" \"An impressive read with excellent pacing and strong themes.\",\n",
" \"Clever plot twists and a great sense of atmosphere.\",\n",
" \"A standout novel with depth, warmth, and originality.\",\n",
" \"Engrossing from the first chapter to the last.\",\n",
" \"The characters were compelling and the dialogue felt natural.\",\n",
" \"A wonderfully immersive book with a strong emotional core.\",\n",
" \"Smart, entertaining, and beautifully crafted.\",\n",
" \"I loved the tone, the message, and the overall journey.\",\n",
" \"A highly enjoyable read that exceeded my expectations.\",\n",
" \"Powerful storytelling with moments that truly moved me.\",\n",
" \"An excellent blend of drama, humor, and heart.\",\n",
" \"The plot was engaging and the ending was very satisfying.\",\n",
" \"A thoughtful book that made me reflect long after finishing.\",\n",
" \"Great character development and a vivid sense of place.\",\n",
" \"A delightful read — warm, engaging, and well written.\",\n",
" \"A masterfully told story with a strong narrative voice.\",\n",
" \"A fresh and original take on a familiar theme.\",\n",
" \"An absorbing story that kept me invested throughout.\",\n",
" \"Wonderful pacing and a strong emotional payoff.\",\n",
" \"The writing was polished and the story was immersive.\",\n",
" \"A meaningful and inspiring book with memorable moments.\",\n",
" \"Highly recommended — engaging, smart, and heartfelt.\",\n",
" \"A compelling plot with characters I genuinely cared about.\",\n",
" \"A beautifully structured story with a satisfying arc.\",\n",
" \"A fun and rewarding read with great momentum.\",\n",
" \"The author’s voice is strong and the story is gripping.\",\n",
" \"A powerful book that balanced emotion and plot perfectly.\",\n",
" \"A wonderful experience — engaging, moving, and memorable.\",\n",
" \"Excellent storytelling with a unique perspective.\",\n",
" \"A charming book that left me smiling.\",\n",
" \"A well-crafted novel with a strong sense of direction.\",\n",
" \"An emotional and immersive journey that felt authentic.\",\n",
" \"Great writing and a plot that stayed interesting throughout.\",\n",
" \"A top-tier read with depth and great character work.\",\n",
" \"The story was engaging and the themes were handled well.\",\n",
" \"A delightful page-turner with strong character dynamics.\",\n",
" \"A rewarding read that I’d happily reread.\",\n",
" \"A strong and satisfying story with great pacing.\",\n",
" \"An impressive book — creative, engaging, and thoughtful.\",\n",
" \"A moving and memorable read with a great ending.\",\n",
" \"A fantastic read that delivered on every level.\"\n",
" ],\n",
" \"neutral\": [\n",
" \"An okay read — enjoyable in parts but not especially memorable.\",\n",
" \"It had some strong moments, though the pacing felt uneven.\",\n",
" \"A decent book overall, but it didn’t fully grab me.\",\n",
" \"The story was fine, but I didn’t feel strongly about it.\",\n",
" \"Interesting premise, but the execution was mixed for me.\",\n",
" \"Some chapters were engaging, others dragged a little.\",\n",
" \"Not bad, but it didn’t stand out compared to similar books.\",\n",
" \"A solid read, though it lacked a bit of spark.\",\n",
" \"The characters were acceptable, but I wanted more depth.\",\n",
" \"It was entertaining enough, but not something I’d reread.\",\n",
" \"A middle-of-the-road book with both strengths and weaknesses.\",\n",
" \"The writing was fine, but the plot felt predictable at times.\",\n",
" \"I liked parts of it, but overall it was just average.\",\n",
" \"It held my attention, but didn’t leave a lasting impression.\",\n",
" \"Decent storytelling, though the ending felt a bit rushed.\",\n",
" \"A pleasant read, but nothing particularly special.\",\n",
" \"Some good ideas, but the story didn’t fully deliver for me.\",\n",
" \"The plot was okay, but the pacing could have been tighter.\",\n",
" \"It was fine — not disappointing, not amazing.\",\n",
" \"A fair book with a few standout scenes.\",\n",
" \"Readable and straightforward, but not very impactful.\",\n",
" \"It started strong, then felt a bit repetitive in the middle.\",\n",
" \"A decent effort, though some parts felt underdeveloped.\",\n",
" \"It was enjoyable enough, but I didn’t connect deeply with it.\",\n",
" \"The writing style was clear, though sometimes a bit plain.\",\n",
" \"Not a bad read, but I expected a little more.\",\n",
" \"It had potential, but didn’t fully reach it for me.\",\n",
" \"Some characters were interesting, others felt a bit flat.\",\n",
" \"An average book that’s okay for passing the time.\",\n",
" \"It was fine overall, though it lacked tension in places.\",\n",
" \"A solid story, but the plot didn’t surprise me much.\",\n",
" \"Mixed feelings — good moments, but also slower sections.\",\n",
" \"I didn’t love it, but I didn’t dislike it either.\",\n",
" \"An acceptable read with a familiar storyline.\",\n",
" \"It was okay, though the ending didn’t fully satisfy me.\",\n",
" \"The concept was interesting, but it felt unevenly executed.\",\n",
" \"Not terrible, but not particularly compelling for me.\",\n",
" \"A reasonable read, though it didn’t stand out.\",\n",
" \"There were some nice scenes, but it felt forgettable overall.\",\n",
" \"It was decent — a light read without much depth.\",\n",
" \"Some parts worked well, others didn’t land for me.\",\n",
" \"A good attempt, but it felt a bit safe and predictable.\",\n",
" \"I enjoyed it in the moment, but it didn’t stick with me.\",\n",
" \"The plot was fine, but I wanted more character development.\",\n",
" \"It was readable, but I wouldn’t strongly recommend it.\",\n",
" \"A straightforward story that was neither great nor bad.\",\n",
" \"An okay book with a few engaging moments.\",\n",
" \"It had its moments, but overall it was just alright.\",\n",
" \"A passable read that didn’t leave a big impact.\",\n",
" \"Decent enough, though I’m not sure I’d recommend it widely.\"\n",
" ],\n",
" \"negative\": [\n",
" \"I struggled to stay interested — it felt slow and repetitive.\",\n",
" \"The story didn’t really come together, and I lost interest quickly.\",\n",
" \"Disappointing overall — I expected more from the premise.\",\n",
" \"The pacing dragged and the plot didn’t engage me.\",\n",
" \"The characters felt flat and I couldn’t connect with them.\",\n",
" \"It was hard to finish — the writing didn’t hold my attention.\",\n",
" \"The plot was confusing and not very satisfying.\",\n",
" \"I found it frustrating — too many loose ends and little payoff.\",\n",
" \"The story felt predictable and lacked tension.\",\n",
" \"I didn’t enjoy the writing style; it felt clunky to me.\",\n",
" \"The characters’ decisions didn’t make much sense.\",\n",
" \"The book felt overly long without enough happening.\",\n",
" \"I wanted to like it, but it just didn’t work for me.\",\n",
" \"The dialogue felt unnatural and pulled me out of the story.\",\n",
" \"The plot had potential, but the execution fell short.\",\n",
" \"It never really grabbed me, even after several chapters.\",\n",
" \"The ending was disappointing and didn’t feel earned.\",\n",
" \"I found the story messy and hard to follow.\",\n",
" \"It felt repetitive and didn’t offer anything new.\",\n",
" \"The pacing was uneven and the middle dragged a lot.\",\n",
" \"The characters felt underdeveloped and uninteresting.\",\n",
" \"I didn’t connect with the story and it felt forgettable.\",\n",
" \"The writing was dull and the plot lacked momentum.\",\n",
" \"It didn’t live up to its premise — very underwhelming.\",\n",
" \"I found it difficult to care about what was happening.\",\n",
" \"Too many clichés and not enough originality.\",\n",
" \"The story felt unfocused and scattered.\",\n",
" \"It was a chore to read — I kept losing interest.\",\n",
" \"The plot twists were predictable and didn’t add much.\",\n",
" \"The tone felt inconsistent and the pacing was poor.\",\n",
" \"I finished it, but it wasn’t enjoyable for me.\",\n",
" \"The characters were unlikeable and lacked depth.\",\n",
" \"The storyline didn’t make much sense in the end.\",\n",
" \"It dragged on and didn’t deliver a satisfying payoff.\",\n",
" \"The writing felt repetitive and the plot went nowhere.\",\n",
" \"I didn’t find the story engaging or well-structured.\",\n",
" \"The ending left me frustrated rather than satisfied.\",\n",
" \"It felt rushed in places and slow in others — not balanced.\",\n",
" \"The book didn’t meet my expectations at all.\",\n",
" \"The plot felt thin and the characters didn’t feel real.\",\n",
" \"I had trouble following the story and staying invested.\",\n",
" \"The writing lacked clarity and the pacing was off.\",\n",
" \"It didn’t draw me in — I was bored for much of it.\",\n",
" \"The story felt stretched out without enough substance.\",\n",
" \"I couldn’t connect with the characters or the plot.\",\n",
" \"The narrative felt repetitive and lacked direction.\",\n",
" \"Not my favorite — I found it dull and unsatisfying.\",\n",
" \"It promised a lot but delivered very little.\",\n",
" \"I wouldn’t recommend it — it didn’t work for me.\",\n",
" \"Overall, a disappointing read with little payoff.\"\n",
" ]\n",
"}"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "fQhfVaDmuULT"
},
"source": [
"### *b. Generate 10 reviews per book using random sampling from the corresponding 50*"
]
},
{
"cell_type": "code",
"execution_count": 47,
"metadata": {
"id": "l2SRc3PjuTGM"
},
"outputs": [],
"source": [
"review_rows = []\n",
"\n",
"for _, row in df_books.iterrows():\n",
" title = row['Title'] # Capital T\n",
" sentiment_label = row['sentiment_label']\n",
" review_pool = synthetic_reviews_by_sentiment[sentiment_label]\n",
"\n",
" sampled_reviews = random.sample(review_pool, 10)\n",
"\n",
" for review_text in sampled_reviews:\n",
" review_rows.append({\n",
" \"title\": title,\n",
" \"sentiment_label\": sentiment_label,\n",
" \"review_text\": review_text,\n",
" \"rating\": row['Rating'], # Capital R\n",
" \"popularity_score\": row['popularity_score']\n",
" })"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "bmJMXF-Bukdm"
},
"source": [
"### *c. Create the final dataframe df_reviews & save it as synthetic_book_reviews.csv*"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {
"id": "ZUKUqZsuumsp"
},
"outputs": [],
"source": [
"df_reviews = pd.DataFrame(review_rows)\n",
"df_reviews.to_csv(\"synthetic_book_reviews.csv\", index=False)"
]
},
{
"cell_type": "markdown",
"source": [
"### *c. inputs for R*"
],
"metadata": {
"id": "_602pYUS3gY5"
}
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "3946e521",
"outputId": "d893283f-d4ab-454a-eabb-928c8726986a"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"✅ Wrote synthetic_title_level_features.csv\n",
"✅ Wrote synthetic_monthly_revenue_series.csv\n"
]
}
],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"def _safe_num(s):\n",
" return pd.to_numeric(\n",
" pd.Series(s).astype(str).str.replace(r\"[^0-9.]\", \"\", regex=True),\n",
" errors=\"coerce\"\n",
" )\n",
"\n",
"# Map text ratings to numbers (BooksToScrape style)\n",
"RATING_MAP = {\"One\": 1, \"Two\": 2, \"Three\": 3, \"Four\": 4, \"Five\": 5}\n",
"\n",
"# ---------- Standardize df_books columns ----------\n",
"df_books_r = df_books.copy()\n",
"\n",
"# Handle different column name variants\n",
"rename_books = {}\n",
"if \"Title\" in df_books_r.columns: rename_books[\"Title\"] = \"title\"\n",
"if \"Price (£)\" in df_books_r.columns: rename_books[\"Price (£)\"] = \"price\"\n",
"if \"Rating\" in df_books_r.columns: rename_books[\"Rating\"] = \"rating\"\n",
"df_books_r = df_books_r.rename(columns=rename_books)\n",
"\n",
"# Ensure required cols exist\n",
"if \"title\" not in df_books_r.columns:\n",
" raise KeyError(f\"df_books is missing a title column. Columns: {df_books_r.columns.tolist()}\")\n",
"\n",
"df_books_r[\"title\"] = df_books_r[\"title\"].astype(str).str.strip()\n",
"\n",
"# Clean price\n",
"if \"price\" in df_books_r.columns:\n",
" df_books_r[\"price\"] = _safe_num(df_books_r[\"price\"])\n",
"\n",
"# Clean rating: text -> numeric if needed\n",
"if \"rating\" in df_books_r.columns:\n",
" df_books_r[\"rating\"] = df_books_r[\"rating\"].replace(RATING_MAP)\n",
" df_books_r[\"rating\"] = pd.to_numeric(df_books_r[\"rating\"], errors=\"coerce\")\n",
"\n",
"# ---------- Clean df_sales ----------\n",
"df_sales_r = df_sales.copy()\n",
"df_sales_r[\"title\"] = df_sales_r[\"title\"].astype(str).str.strip()\n",
"df_sales_r[\"month\"] = pd.to_datetime(df_sales_r[\"month\"], errors=\"coerce\")\n",
"df_sales_r[\"units_sold\"] = _safe_num(df_sales_r[\"units_sold\"])\n",
"\n",
"# ---------- Clean df_reviews ----------\n",
"df_reviews_r = df_reviews.copy()\n",
"df_reviews_r[\"title\"] = df_reviews_r[\"title\"].astype(str).str.strip()\n",
"df_reviews_r[\"sentiment_label\"] = df_reviews_r[\"sentiment_label\"].astype(str).str.lower().str.strip()\n",
"\n",
"if \"rating\" in df_reviews_r.columns:\n",
" df_reviews_r[\"rating\"] = df_reviews_r[\"rating\"].replace(RATING_MAP)\n",
" df_reviews_r[\"rating\"] = pd.to_numeric(df_reviews_r[\"rating\"], errors=\"coerce\")\n",
"\n",
"if \"popularity_score\" in df_reviews_r.columns:\n",
" df_reviews_r[\"popularity_score\"] = _safe_num(df_reviews_r[\"popularity_score\"])\n",
"\n",
"# ---------- Sentiment shares per title ----------\n",
"sent_counts = (\n",
" df_reviews_r.groupby([\"title\", \"sentiment_label\"])\n",
" .size()\n",
" .unstack(fill_value=0)\n",
")\n",
"\n",
"for lab in [\"positive\", \"neutral\", \"negative\"]:\n",
" if lab not in sent_counts.columns:\n",
" sent_counts[lab] = 0\n",
"\n",
"sent_counts[\"total_reviews\"] = sent_counts[[\"positive\", \"neutral\", \"negative\"]].sum(axis=1)\n",
"den = sent_counts[\"total_reviews\"].replace(0, np.nan)\n",
"sent_counts[\"share_positive\"] = sent_counts[\"positive\"] / den\n",
"sent_counts[\"share_neutral\"] = sent_counts[\"neutral\"] / den\n",
"sent_counts[\"share_negative\"] = sent_counts[\"negative\"] / den\n",
"sent_counts = sent_counts.reset_index()\n",
"\n",
"# ---------- Sales aggregation per title ----------\n",
"sales_by_title = (\n",
" df_sales_r.dropna(subset=[\"title\"])\n",
" .groupby(\"title\", as_index=False)\n",
" .agg(\n",
" months_observed=(\"month\", \"nunique\"),\n",
" avg_units_sold=(\"units_sold\", \"mean\"),\n",
" total_units_sold=(\"units_sold\", \"sum\"),\n",
" )\n",
")\n",
"\n",
"# ---------- Title-level features ----------\n",
"df_title = (\n",
" sales_by_title\n",
" .merge(df_books_r[[\"title\", \"price\", \"rating\"]], on=\"title\", how=\"left\")\n",
" .merge(\n",
" sent_counts[[\"title\", \"share_positive\", \"share_neutral\", \"share_negative\", \"total_reviews\"]],\n",
" on=\"title\", how=\"left\"\n",
" )\n",
")\n",
"\n",
"df_title[\"avg_revenue\"] = df_title[\"avg_units_sold\"] * df_title[\"price\"]\n",
"df_title[\"total_revenue\"] = df_title[\"total_units_sold\"] * df_title[\"price\"]\n",
"\n",
"df_title.to_csv(\"synthetic_title_level_features.csv\", index=False)\n",
"print(\"✅ Wrote synthetic_title_level_features.csv\")\n",
"\n",
"# ---------- Monthly revenue series ----------\n",
"monthly_rev = df_sales_r.merge(df_books_r[[\"title\", \"price\"]], on=\"title\", how=\"left\")\n",
"monthly_rev[\"revenue\"] = monthly_rev[\"units_sold\"] * monthly_rev[\"price\"]\n",
"\n",
"df_monthly = (\n",
" monthly_rev.dropna(subset=[\"month\"])\n",
" .groupby(\"month\", as_index=False)[\"revenue\"]\n",
" .sum()\n",
" .rename(columns={\"revenue\": \"total_revenue\"})\n",
" .sort_values(\"month\")\n",
")\n",
"\n",
"# fallback if price missing everywhere\n",
"if df_monthly[\"total_revenue\"].notna().sum() == 0:\n",
" df_monthly = (\n",
" df_sales_r.dropna(subset=[\"month\"])\n",
" .groupby(\"month\", as_index=False)[\"units_sold\"]\n",
" .sum()\n",
" .rename(columns={\"units_sold\": \"total_revenue\"})\n",
" .sort_values(\"month\")\n",
" )\n",
"\n",
"df_monthly[\"month\"] = pd.to_datetime(df_monthly[\"month\"], errors=\"coerce\").dt.strftime(\"%Y-%m-%d\")\n",
"df_monthly.to_csv(\"synthetic_monthly_revenue_series.csv\", index=False)\n",
"print(\"✅ Wrote synthetic_monthly_revenue_series.csv\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "RYvGyVfXuo54"
},
"source": [
"### *d. ✋🏻🛑⛔️ View the first few lines*"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"id": "xfE8NMqOurKo",
"outputId": "89b1d9bf-04a5-4f6f-a8c9-9cda2e7424ed"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" title sentiment_label \\\n",
"0 A Light in the Attic neutral \n",
"1 A Light in the Attic neutral \n",
"2 A Light in the Attic neutral \n",
"3 A Light in the Attic neutral \n",
"4 A Light in the Attic neutral \n",
"\n",
" review_text rating popularity_score \n",
"0 Decent storytelling, though the ending felt a ... Three 3 \n",
"1 A straightforward story that was neither great... Three 3 \n",
"2 It was readable, but I wouldn’t strongly recom... Three 3 \n",
"3 Not terrible, but not particularly compelling ... Three 3 \n",
"4 Interesting premise, but the execution was mix... Three 3 "
],
"text/html": [
"\n",
" <div id=\"df-d35378ba-7bb6-4d39-8ac8-217f887de4a7\" class=\"colab-df-container\">\n",
" <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>title</th>\n",
" <th>sentiment_label</th>\n",
" <th>review_text</th>\n",
" <th>rating</th>\n",
" <th>popularity_score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>A Light in the Attic</td>\n",
" <td>neutral</td>\n",
" <td>Decent storytelling, though the ending felt a ...</td>\n",
" <td>Three</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>A Light in the Attic</td>\n",
" <td>neutral</td>\n",
" <td>A straightforward story that was neither great...</td>\n",
" <td>Three</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>A Light in the Attic</td>\n",
" <td>neutral</td>\n",
" <td>It was readable, but I wouldn’t strongly recom...</td>\n",
" <td>Three</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>A Light in the Attic</td>\n",
" <td>neutral</td>\n",
" <td>Not terrible, but not particularly compelling ...</td>\n",
" <td>Three</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>A Light in the Attic</td>\n",
" <td>neutral</td>\n",
" <td>Interesting premise, but the execution was mix...</td>\n",
" <td>Three</td>\n",
" <td>3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d35378ba-7bb6-4d39-8ac8-217f887de4a7')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-d35378ba-7bb6-4d39-8ac8-217f887de4a7 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-d35378ba-7bb6-4d39-8ac8-217f887de4a7');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "df_reviews",
"summary": "{\n \"name\": \"df_reviews\",\n \"rows\": 10000,\n \"fields\": [\n {\n \"column\": \"title\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 999,\n \"samples\": [\n \"The Grownup\",\n \"Persepolis: The Story of a Childhood (Persepolis #1-2)\",\n \"Ayumi's Violin\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"sentiment_label\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"neutral\",\n \"negative\",\n \"positive\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"review_text\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 150,\n \"samples\": [\n \"The tone felt inconsistent and the pacing was poor.\",\n \"I had trouble following the story and staying invested.\",\n \"It had some strong moments, though the pacing felt uneven.\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rating\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"One\",\n \"Two\",\n \"Four\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"popularity_score\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1,\n \"min\": 1,\n \"max\": 5,\n \"num_unique_values\": 5,\n \"samples\": [\n 2,\n 5,\n 4\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 53
}
],
"source": [
"df_reviews.head()"
]
}
],
"metadata": {
"colab": {
"collapsed_sections": [
"jpASMyIQMaAq",
"lquNYCbfL9IM",
"0IWuNpxxYDJF",
"oCdTsin2Yfp3",
"T0TOeRC4Yrnn",
"duI5dv3CZYvF",
"qMjRKMBQZlJi",
"p-1Pr2szaqLk",
"SIaJUGIpaH4V",
"pY4yCoIuaQqp",
"n4-TaNTFgPak",
"HnngRNTgacYt",
"HF9F9HIzgT7Z",
"T8AdKkmASq9a",
"OhXbdGD5fH0c",
"L2ak1HlcgoTe",
"4IXZKcCSgxnq",
"EhIjz9WohAmZ",
"Gi4y9M9KuDWx",
"fQhfVaDmuULT",
"bmJMXF-Bukdm",
"RYvGyVfXuo54"
],
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
} |