File size: 78,706 Bytes
5d45e2d | 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 | {
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<h1> ----- PIPELINE NOTEBOOK ----- </h1>"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn.pipeline import Pipeline\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.preprocessing import OneHotEncoder\n",
"from xgboost import XGBRegressor\n",
"\n",
"from sklearn.compose import ColumnTransformer\n",
"\n",
"from sklearn import set_config"
]
},
{
"cell_type": "code",
"execution_count": 3,
"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>Unnamed: 0</th>\n",
" <th>Store</th>\n",
" <th>DayOfWeek</th>\n",
" <th>Date</th>\n",
" <th>Sales</th>\n",
" <th>Customers</th>\n",
" <th>Promo</th>\n",
" <th>StateHoliday</th>\n",
" <th>SchoolHoliday</th>\n",
" <th>StoreType</th>\n",
" <th>Assortment</th>\n",
" <th>CompetitionDistance</th>\n",
" <th>CompetitionOpenSinceMonth</th>\n",
" <th>CompetitionOpenSinceYear</th>\n",
" <th>Promo2</th>\n",
" <th>Promo2SinceWeek</th>\n",
" <th>Promo2SinceYear</th>\n",
" <th>PromoInterval</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>2015-07-31</td>\n",
" <td>5263</td>\n",
" <td>555</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>Large Store</td>\n",
" <td>basic</td>\n",
" <td>1270</td>\n",
" <td>9</td>\n",
" <td>2008</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" <td>2015-07-31</td>\n",
" <td>6064</td>\n",
" <td>625</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>Small Shop</td>\n",
" <td>basic</td>\n",
" <td>570</td>\n",
" <td>11</td>\n",
" <td>2007</td>\n",
" <td>1</td>\n",
" <td>13</td>\n",
" <td>2010</td>\n",
" <td>Jan,Apr,Jul,Oct</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" <td>5</td>\n",
" <td>2015-07-31</td>\n",
" <td>8314</td>\n",
" <td>821</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>Small Shop</td>\n",
" <td>basic</td>\n",
" <td>14130</td>\n",
" <td>12</td>\n",
" <td>2006</td>\n",
" <td>1</td>\n",
" <td>14</td>\n",
" <td>2011</td>\n",
" <td>Jan,Apr,Jul,Oct</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>2015-07-31</td>\n",
" <td>13995</td>\n",
" <td>1498</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>Large Store</td>\n",
" <td>extended</td>\n",
" <td>620</td>\n",
" <td>9</td>\n",
" <td>2009</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>2015-07-31</td>\n",
" <td>4822</td>\n",
" <td>559</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>Small Shop</td>\n",
" <td>basic</td>\n",
" <td>29910</td>\n",
" <td>4</td>\n",
" <td>2015</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 Store DayOfWeek Date Sales Customers Promo \\\n",
"0 0 1 5 2015-07-31 5263 555 1 \n",
"1 1 2 5 2015-07-31 6064 625 1 \n",
"2 2 3 5 2015-07-31 8314 821 1 \n",
"3 3 4 5 2015-07-31 13995 1498 1 \n",
"4 4 5 5 2015-07-31 4822 559 1 \n",
"\n",
" StateHoliday SchoolHoliday StoreType Assortment CompetitionDistance \\\n",
"0 0 1 Large Store basic 1270 \n",
"1 0 1 Small Shop basic 570 \n",
"2 0 1 Small Shop basic 14130 \n",
"3 0 1 Large Store extended 620 \n",
"4 0 1 Small Shop basic 29910 \n",
"\n",
" CompetitionOpenSinceMonth CompetitionOpenSinceYear Promo2 \\\n",
"0 9 2008 0 \n",
"1 11 2007 1 \n",
"2 12 2006 1 \n",
"3 9 2009 0 \n",
"4 4 2015 0 \n",
"\n",
" Promo2SinceWeek Promo2SinceYear PromoInterval \n",
"0 0 0 0 \n",
"1 13 2010 Jan,Apr,Jul,Oct \n",
"2 14 2011 Jan,Apr,Jul,Oct \n",
"3 0 0 0 \n",
"4 0 0 0 "
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv(r\"../Dataset/Rossmann_Cleaned_data.csv\")\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"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>PromoInterval</th>\n",
" <th>StoreType</th>\n",
" <th>Assortment</th>\n",
" <th>StateHoliday</th>\n",
" <th>Store</th>\n",
" <th>Customers</th>\n",
" <th>Promo</th>\n",
" <th>SchoolHoliday</th>\n",
" <th>CompetitionDistance</th>\n",
" <th>CompetitionOpenSinceMonth</th>\n",
" <th>CompetitionOpenSinceYear</th>\n",
" <th>Sales</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>Large Store</td>\n",
" <td>basic</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>555</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1270</td>\n",
" <td>9</td>\n",
" <td>2008</td>\n",
" <td>5263</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Jan,Apr,Jul,Oct</td>\n",
" <td>Small Shop</td>\n",
" <td>basic</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>625</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>570</td>\n",
" <td>11</td>\n",
" <td>2007</td>\n",
" <td>6064</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Jan,Apr,Jul,Oct</td>\n",
" <td>Small Shop</td>\n",
" <td>basic</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>821</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>14130</td>\n",
" <td>12</td>\n",
" <td>2006</td>\n",
" <td>8314</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0</td>\n",
" <td>Large Store</td>\n",
" <td>extended</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>1498</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>620</td>\n",
" <td>9</td>\n",
" <td>2009</td>\n",
" <td>13995</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>Small Shop</td>\n",
" <td>basic</td>\n",
" <td>0</td>\n",
" <td>5</td>\n",
" <td>559</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>29910</td>\n",
" <td>4</td>\n",
" <td>2015</td>\n",
" <td>4822</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" PromoInterval StoreType Assortment StateHoliday Store Customers \\\n",
"0 0 Large Store basic 0 1 555 \n",
"1 Jan,Apr,Jul,Oct Small Shop basic 0 2 625 \n",
"2 Jan,Apr,Jul,Oct Small Shop basic 0 3 821 \n",
"3 0 Large Store extended 0 4 1498 \n",
"4 0 Small Shop basic 0 5 559 \n",
"\n",
" Promo SchoolHoliday CompetitionDistance CompetitionOpenSinceMonth \\\n",
"0 1 1 1270 9 \n",
"1 1 1 570 11 \n",
"2 1 1 14130 12 \n",
"3 1 1 620 9 \n",
"4 1 1 29910 4 \n",
"\n",
" CompetitionOpenSinceYear Sales \n",
"0 2008 5263 \n",
"1 2007 6064 \n",
"2 2006 8314 \n",
"3 2009 13995 \n",
"4 2015 4822 "
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = df[[\"PromoInterval\",\"StoreType\",\"Assortment\",\"StateHoliday\",\"Store\",\"Customers\",\"Promo\",\"SchoolHoliday\",\"CompetitionDistance\",\"CompetitionOpenSinceMonth\",\"CompetitionOpenSinceYear\",\"Sales\"]]\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"8\n",
"7388\n"
]
}
],
"source": [
"print(df[\"Customers\"].min())\n",
"print(df[\"Customers\"].max())"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 844338 entries, 0 to 844337\n",
"Data columns (total 12 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 PromoInterval 844338 non-null object\n",
" 1 StoreType 844338 non-null object\n",
" 2 Assortment 844338 non-null object\n",
" 3 StateHoliday 844338 non-null int64 \n",
" 4 Store 844338 non-null int64 \n",
" 5 Customers 844338 non-null int64 \n",
" 6 Promo 844338 non-null int64 \n",
" 7 SchoolHoliday 844338 non-null int64 \n",
" 8 CompetitionDistance 844338 non-null int64 \n",
" 9 CompetitionOpenSinceMonth 844338 non-null int64 \n",
" 10 CompetitionOpenSinceYear 844338 non-null int64 \n",
" 11 Sales 844338 non-null int64 \n",
"dtypes: int64(9), object(3)\n",
"memory usage: 77.3+ MB\n"
]
}
],
"source": [
"df.info()"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(844338, 12)"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Unique values in PromoInterval: ['0' 'Jan,Apr,Jul,Oct' 'Feb,May,Aug,Nov' 'Mar,Jun,Sept,Dec']\n",
"Unique values in StoreType: ['Large Store' 'Small Shop' 'Hypermarket' 'Medium Store']\n",
"Unique values in Assortment: ['basic' 'extended' 'extra']\n",
"Unique values in StateHoliday: [0 1]\n",
"Unique values in Store: [ 1 2 3 ... 1115 876 292]\n",
"Unique values in Customers: [ 555 625 821 ... 3900 36 4065]\n",
"Unique values in Promo: [1 0]\n",
"Unique values in SchoolHoliday: [1 0]\n",
"Unique values in CompetitionDistance: [ 1270 570 14130 620 29910 310 24000 7520 2030 3160 960 1070\n",
" 1300 4110 3270 50 13840 3240 2340 550 1040 4060 4590 430\n",
" 2300 60 1200 2170 40 9800 2910 1320 2240 7660 540 4230\n",
" 1090 260 180 1180 290 4880 9710 270 1060 18010 6260 10570\n",
" 450 30360 7170 720 6620 420 7340 2840 5540 350 2050 3700\n",
" 22560 410 250 1130 4840 17500 2200 1650 330 22440 19960 3510\n",
" 3320 7910 2370 22390 2710 11810 1870 480 560 10690 2380 2410\n",
" 240 16690 14620 1890 8780 8980 15140 17930 2440 150 5210 390\n",
" 6190 1390 1930 2190 3300 46590 7890 1630 20930 4510 5740 680\n",
" 3450 3580 2100 2290 3570 58260 16760 1410 760 3370 1350 2000\n",
" 2460 900 920 5190 1730 25360 1700 1540 2930 16570 280 8050\n",
" 8540 2090 2610 31830 4360 1780 16240 16420 3050 2020 2950 11840\n",
" 8530 17110 2970 5340 1480 1160 3720 100 140 12540 980 2640\n",
" 110 13090 4130 3770 1250 1710 5800 12610 9670 3560 1860 19360\n",
" 850 5760 1470 1100 2770 520 16970 220 3850 4210 6360 20260\n",
" 5140 490 5630 380 6870 300 11680 970 15050 4030 8650 190\n",
" 3150 640 1640 1000 13530 2920 7930 10180 10800 17410 6680 3840\n",
" 13570 4370 5710 1420 320 610 1110 780 6880 710 1310 4660\n",
" 70 340 3520 22330 4630 80 27190 210 15340 1140 4580 360\n",
" 4520 1450 16180 8480 3640 2960 7840 9260 2320 18640 6970 1220\n",
" 2260 1290 1460 2740 800 6540 4150 2325 9580 19840 38630 120\n",
" 15430 1950 2470 5100 18660 8740 11300 14160 38710 9000 3140 32330\n",
" 8140 8400 13140 10070 3130 370 670 1840 4040 90 10600 1590\n",
" 2280 8080 15770 18650 8090 9360 16490 1490 8880 5290 1500 9720\n",
" 8970 2060 2890 2040 4490 13620 6470 5870 8250 1970 11120 1150\n",
" 15710 160 2140 6630 1800 26130 130 6690 1600 460 2120 4820\n",
" 10850 3620 23130 5360 9200 5830 4970 1080 8240 5890 1560 840\n",
" 8460 4460 6210 6910 4650 1620 3530 2880 16350 12870 810 30030\n",
" 13020 910 3900 2530 500 11400 1510 3970 5780 1850 75860 26450\n",
" 3390 34050 1790 44320 4160 10890 3110 20390 5260 5300 5030 14810\n",
" 8300 770 1940 7470 2550 2310 14300 2180 14960 660 4680 1740\n",
" 1260 5470 2780 1610 990 13080 820 9070 1280 4740 8260 590\n",
" 400 11260 20 22490 3330 2510 6900 18610 7160 40860 20620 12920\n",
" 18160 5950 4700 600 650 7280 5020 580 8990 3760 2330 4260\n",
" 3040 3000 3910 1910 1210 700 1010 4270 1340 2110 9230 1190\n",
" 4400 2270 12700 20970 170 7250 1360 440 15720 3340 2540 33060\n",
" 17340 8220 10950 10310 18370 2070 2490 730 8940 9910 5440 30\n",
" 4080 6920 1170 10740 510 1690 2870 3350 11640 27530 9790 10170\n",
" 7780 8040 530 230 7420 2130 14570 200 6930 7860 1680 2700\n",
" 17080 15170 3250 4140 2850 20050 18760 15040 3030 3780 830 8550\n",
" 7830 2900 11470 4870 12070 3200 8190 15320 3590 5650 5900 17540\n",
" 40540 13990 15270 35280 860 1920 5980 6400 11900 4380 6710 1370\n",
" 17650 4330 45740 3410 8670 13130 19780 2390 32240 26490 25430 9820\n",
" 2630 20640 16990 630 5390 15490 3210 1530 9770 17280 5090 7180\n",
" 9560 48330 1760 24770 3870 18620 12770 9640 2590 24530 16210 17570\n",
" 7980 3290 6320 5070 3470 2720 14600 6890 27650 8860 5000 1120\n",
" 940 14040 4770 3440 3020 6270 21770 740 21370 1020 9680 21810\n",
" 10620 3860 29190 4570 7550 12430 19700 4450 18670 19370 18540 3920\n",
" 3170 7290 1980 12480 3100 7240 18710 2620 6420 470 5150 15700\n",
" 5460 22350 2810 2820 6860 18020 1670 2220 1430 870 6300 19830\n",
" 9430 23620 9630 4180 3890 4420 21930 2480 3460 6560 5840 2230\n",
" 19640 6480 4610 6330 1520 3740 1990 36410 7680 13750 27150 17290\n",
" 26990 29070 3750 13170 5080 13190 5350 3230 3380 3430 8110 6250\n",
" 12020 5010 18050 5380 16680 11540 2210 4300 5220 9990 10450 690\n",
" 1830 5330 1400 3490 1900 1880 21790]\n",
"Unique values in CompetitionOpenSinceMonth: [ 9 11 12 4 10 8 3 6 5 1 2 7]\n",
"Unique values in CompetitionOpenSinceYear: [2008 2007 2006 2009 2015 2013 2014 2000 2011 2010 2005 1999 2003 2012\n",
" 2004 2002 1961 1995 2001 1990 1994 1900 1998]\n",
"Unique values in Sales: [ 5263 6064 8314 ... 660 17815 23303]\n"
]
}
],
"source": [
"def print_unique_values(dataframe):\n",
" for column in dataframe.columns:\n",
" unique_values = dataframe[column].unique()\n",
" print(f\"Unique values in {column}: {unique_values}\")\n",
"\n",
"# Example usage:\n",
"print_unique_values(df)\n"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"X = df.drop(columns = [\"Sales\"])\n",
"y = df[\"Sales\"]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train Test Split"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"((633253, 11), (211085, 11), (633253,), (211085,))"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from sklearn.model_selection import train_test_split\n",
"X_train, X_test, y_train, y_test = train_test_split(X,y, test_size=0.25, random_state=42)\n",
"\n",
"# Checking the shape after spliting\n",
"X_train.shape, X_test.shape, y_train.shape, y_test.shape"
]
},
{
"cell_type": "code",
"execution_count": 18,
"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>PromoInterval</th>\n",
" <th>StoreType</th>\n",
" <th>Assortment</th>\n",
" <th>StateHoliday</th>\n",
" <th>Store</th>\n",
" <th>Customers</th>\n",
" <th>Promo</th>\n",
" <th>SchoolHoliday</th>\n",
" <th>CompetitionDistance</th>\n",
" <th>CompetitionOpenSinceMonth</th>\n",
" <th>CompetitionOpenSinceYear</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>795018</th>\n",
" <td>Jan,Apr,Jul,Oct</td>\n",
" <td>Small Shop</td>\n",
" <td>basic</td>\n",
" <td>0</td>\n",
" <td>650</td>\n",
" <td>636</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1420</td>\n",
" <td>10</td>\n",
" <td>2012</td>\n",
" </tr>\n",
" <tr>\n",
" <th>463276</th>\n",
" <td>Jan,Apr,Jul,Oct</td>\n",
" <td>Small Shop</td>\n",
" <td>basic</td>\n",
" <td>0</td>\n",
" <td>72</td>\n",
" <td>261</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>2200</td>\n",
" <td>12</td>\n",
" <td>2009</td>\n",
" </tr>\n",
" <tr>\n",
" <th>268352</th>\n",
" <td>0</td>\n",
" <td>Medium Store</td>\n",
" <td>extra</td>\n",
" <td>0</td>\n",
" <td>733</td>\n",
" <td>3567</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>860</td>\n",
" <td>10</td>\n",
" <td>1999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>67308</th>\n",
" <td>0</td>\n",
" <td>Small Shop</td>\n",
" <td>extended</td>\n",
" <td>0</td>\n",
" <td>796</td>\n",
" <td>791</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>7180</td>\n",
" <td>11</td>\n",
" <td>2012</td>\n",
" </tr>\n",
" <tr>\n",
" <th>482458</th>\n",
" <td>0</td>\n",
" <td>Small Shop</td>\n",
" <td>extended</td>\n",
" <td>0</td>\n",
" <td>301</td>\n",
" <td>480</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4510</td>\n",
" <td>3</td>\n",
" <td>2015</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>259178</th>\n",
" <td>Feb,May,Aug,Nov</td>\n",
" <td>Small Shop</td>\n",
" <td>basic</td>\n",
" <td>0</td>\n",
" <td>1013</td>\n",
" <td>217</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>630</td>\n",
" <td>2</td>\n",
" <td>2015</td>\n",
" </tr>\n",
" <tr>\n",
" <th>365838</th>\n",
" <td>Jan,Apr,Jul,Oct</td>\n",
" <td>Small Shop</td>\n",
" <td>extended</td>\n",
" <td>0</td>\n",
" <td>11</td>\n",
" <td>1394</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>960</td>\n",
" <td>11</td>\n",
" <td>2011</td>\n",
" </tr>\n",
" <tr>\n",
" <th>131932</th>\n",
" <td>0</td>\n",
" <td>Small Shop</td>\n",
" <td>basic</td>\n",
" <td>0</td>\n",
" <td>376</td>\n",
" <td>796</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>160</td>\n",
" <td>8</td>\n",
" <td>2012</td>\n",
" </tr>\n",
" <tr>\n",
" <th>671155</th>\n",
" <td>0</td>\n",
" <td>Hypermarket</td>\n",
" <td>extended</td>\n",
" <td>0</td>\n",
" <td>76</td>\n",
" <td>885</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>19960</td>\n",
" <td>3</td>\n",
" <td>2006</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121958</th>\n",
" <td>Feb,May,Aug,Nov</td>\n",
" <td>Small Shop</td>\n",
" <td>basic</td>\n",
" <td>0</td>\n",
" <td>446</td>\n",
" <td>684</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>340</td>\n",
" <td>10</td>\n",
" <td>2000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>633253 rows × 11 columns</p>\n",
"</div>"
],
"text/plain": [
" PromoInterval StoreType Assortment StateHoliday Store \\\n",
"795018 Jan,Apr,Jul,Oct Small Shop basic 0 650 \n",
"463276 Jan,Apr,Jul,Oct Small Shop basic 0 72 \n",
"268352 0 Medium Store extra 0 733 \n",
"67308 0 Small Shop extended 0 796 \n",
"482458 0 Small Shop extended 0 301 \n",
"... ... ... ... ... ... \n",
"259178 Feb,May,Aug,Nov Small Shop basic 0 1013 \n",
"365838 Jan,Apr,Jul,Oct Small Shop extended 0 11 \n",
"131932 0 Small Shop basic 0 376 \n",
"671155 0 Hypermarket extended 0 76 \n",
"121958 Feb,May,Aug,Nov Small Shop basic 0 446 \n",
"\n",
" Customers Promo SchoolHoliday CompetitionDistance \\\n",
"795018 636 1 0 1420 \n",
"463276 261 0 0 2200 \n",
"268352 3567 1 0 860 \n",
"67308 791 1 0 7180 \n",
"482458 480 0 0 4510 \n",
"... ... ... ... ... \n",
"259178 217 0 0 630 \n",
"365838 1394 1 0 960 \n",
"131932 796 0 0 160 \n",
"671155 885 0 0 19960 \n",
"121958 684 1 0 340 \n",
"\n",
" CompetitionOpenSinceMonth CompetitionOpenSinceYear \n",
"795018 10 2012 \n",
"463276 12 2009 \n",
"268352 10 1999 \n",
"67308 11 2012 \n",
"482458 3 2015 \n",
"... ... ... \n",
"259178 2 2015 \n",
"365838 11 2011 \n",
"131932 8 2012 \n",
"671155 3 2006 \n",
"121958 10 2000 \n",
"\n",
"[633253 rows x 11 columns]"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_train"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"PromoInterval\n",
"0 423292\n",
"Jan,Apr,Jul,Oct 242397\n",
"Feb,May,Aug,Nov 97998\n",
"Mar,Jun,Sept,Dec 80651\n",
"Name: count, dtype: int64"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[\"PromoInterval\"].value_counts()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Pipeline"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style>#sk-container-id-1 {\n",
" /* Definition of color scheme common for light and dark mode */\n",
" --sklearn-color-text: black;\n",
" --sklearn-color-line: gray;\n",
" /* Definition of color scheme for unfitted estimators */\n",
" --sklearn-color-unfitted-level-0: #fff5e6;\n",
" --sklearn-color-unfitted-level-1: #f6e4d2;\n",
" --sklearn-color-unfitted-level-2: #ffe0b3;\n",
" --sklearn-color-unfitted-level-3: chocolate;\n",
" /* Definition of color scheme for fitted estimators */\n",
" --sklearn-color-fitted-level-0: #f0f8ff;\n",
" --sklearn-color-fitted-level-1: #d4ebff;\n",
" --sklearn-color-fitted-level-2: #b3dbfd;\n",
" --sklearn-color-fitted-level-3: cornflowerblue;\n",
"\n",
" /* Specific color for light theme */\n",
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
" --sklearn-color-icon: #696969;\n",
"\n",
" @media (prefers-color-scheme: dark) {\n",
" /* Redefinition of color scheme for dark theme */\n",
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
" --sklearn-color-icon: #878787;\n",
" }\n",
"}\n",
"\n",
"#sk-container-id-1 {\n",
" color: var(--sklearn-color-text);\n",
"}\n",
"\n",
"#sk-container-id-1 pre {\n",
" padding: 0;\n",
"}\n",
"\n",
"#sk-container-id-1 input.sk-hidden--visually {\n",
" border: 0;\n",
" clip: rect(1px 1px 1px 1px);\n",
" clip: rect(1px, 1px, 1px, 1px);\n",
" height: 1px;\n",
" margin: -1px;\n",
" overflow: hidden;\n",
" padding: 0;\n",
" position: absolute;\n",
" width: 1px;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-dashed-wrapped {\n",
" border: 1px dashed var(--sklearn-color-line);\n",
" margin: 0 0.4em 0.5em 0.4em;\n",
" box-sizing: border-box;\n",
" padding-bottom: 0.4em;\n",
" background-color: var(--sklearn-color-background);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-container {\n",
" /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
" but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
" so we also need the `!important` here to be able to override the\n",
" default hidden behavior on the sphinx rendered scikit-learn.org.\n",
" See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
" display: inline-block !important;\n",
" position: relative;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-text-repr-fallback {\n",
" display: none;\n",
"}\n",
"\n",
"div.sk-parallel-item,\n",
"div.sk-serial,\n",
"div.sk-item {\n",
" /* draw centered vertical line to link estimators */\n",
" background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
" background-size: 2px 100%;\n",
" background-repeat: no-repeat;\n",
" background-position: center center;\n",
"}\n",
"\n",
"/* Parallel-specific style estimator block */\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item::after {\n",
" content: \"\";\n",
" width: 100%;\n",
" border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
" flex-grow: 1;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel {\n",
" display: flex;\n",
" align-items: stretch;\n",
" justify-content: center;\n",
" background-color: var(--sklearn-color-background);\n",
" position: relative;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item {\n",
" display: flex;\n",
" flex-direction: column;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
" align-self: flex-end;\n",
" width: 50%;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
" align-self: flex-start;\n",
" width: 50%;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
" width: 0;\n",
"}\n",
"\n",
"/* Serial-specific style estimator block */\n",
"\n",
"#sk-container-id-1 div.sk-serial {\n",
" display: flex;\n",
" flex-direction: column;\n",
" align-items: center;\n",
" background-color: var(--sklearn-color-background);\n",
" padding-right: 1em;\n",
" padding-left: 1em;\n",
"}\n",
"\n",
"\n",
"/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
"clickable and can be expanded/collapsed.\n",
"- Pipeline and ColumnTransformer use this feature and define the default style\n",
"- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
"*/\n",
"\n",
"/* Pipeline and ColumnTransformer style (default) */\n",
"\n",
"#sk-container-id-1 div.sk-toggleable {\n",
" /* Default theme specific background. It is overwritten whether we have a\n",
" specific estimator or a Pipeline/ColumnTransformer */\n",
" background-color: var(--sklearn-color-background);\n",
"}\n",
"\n",
"/* Toggleable label */\n",
"#sk-container-id-1 label.sk-toggleable__label {\n",
" cursor: pointer;\n",
" display: block;\n",
" width: 100%;\n",
" margin-bottom: 0;\n",
" padding: 0.5em;\n",
" box-sizing: border-box;\n",
" text-align: center;\n",
"}\n",
"\n",
"#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
" /* Arrow on the left of the label */\n",
" content: \"▸\";\n",
" float: left;\n",
" margin-right: 0.25em;\n",
" color: var(--sklearn-color-icon);\n",
"}\n",
"\n",
"#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
" color: var(--sklearn-color-text);\n",
"}\n",
"\n",
"/* Toggleable content - dropdown */\n",
"\n",
"#sk-container-id-1 div.sk-toggleable__content {\n",
" max-height: 0;\n",
" max-width: 0;\n",
" overflow: hidden;\n",
" text-align: left;\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-toggleable__content pre {\n",
" margin: 0.2em;\n",
" border-radius: 0.25em;\n",
" color: var(--sklearn-color-text);\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
" /* Expand drop-down */\n",
" max-height: 200px;\n",
" max-width: 100%;\n",
" overflow: auto;\n",
"}\n",
"\n",
"#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
" content: \"▾\";\n",
"}\n",
"\n",
"/* Pipeline/ColumnTransformer-specific style */\n",
"\n",
"#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Estimator-specific style */\n",
"\n",
"/* Colorize estimator box */\n",
"#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
"#sk-container-id-1 div.sk-label label {\n",
" /* The background is the default theme color */\n",
" color: var(--sklearn-color-text-on-default-background);\n",
"}\n",
"\n",
"/* On hover, darken the color of the background */\n",
"#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"/* Label box, darken color on hover, fitted */\n",
"#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Estimator label */\n",
"\n",
"#sk-container-id-1 div.sk-label label {\n",
" font-family: monospace;\n",
" font-weight: bold;\n",
" display: inline-block;\n",
" line-height: 1.2em;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-label-container {\n",
" text-align: center;\n",
"}\n",
"\n",
"/* Estimator-specific */\n",
"#sk-container-id-1 div.sk-estimator {\n",
" font-family: monospace;\n",
" border: 1px dotted var(--sklearn-color-border-box);\n",
" border-radius: 0.25em;\n",
" box-sizing: border-box;\n",
" margin-bottom: 0.5em;\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-estimator.fitted {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"/* on hover */\n",
"#sk-container-id-1 div.sk-estimator:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
"\n",
"/* Common style for \"i\" and \"?\" */\n",
"\n",
".sk-estimator-doc-link,\n",
"a:link.sk-estimator-doc-link,\n",
"a:visited.sk-estimator-doc-link {\n",
" float: right;\n",
" font-size: smaller;\n",
" line-height: 1em;\n",
" font-family: monospace;\n",
" background-color: var(--sklearn-color-background);\n",
" border-radius: 1em;\n",
" height: 1em;\n",
" width: 1em;\n",
" text-decoration: none !important;\n",
" margin-left: 1ex;\n",
" /* unfitted */\n",
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-unfitted-level-1);\n",
"}\n",
"\n",
".sk-estimator-doc-link.fitted,\n",
"a:link.sk-estimator-doc-link.fitted,\n",
"a:visited.sk-estimator-doc-link.fitted {\n",
" /* fitted */\n",
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-fitted-level-1);\n",
"}\n",
"\n",
"/* On hover */\n",
"div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
".sk-estimator-doc-link:hover,\n",
"div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
".sk-estimator-doc-link:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
"div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
".sk-estimator-doc-link.fitted:hover,\n",
"div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
".sk-estimator-doc-link.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
"/* Span, style for the box shown on hovering the info icon */\n",
".sk-estimator-doc-link span {\n",
" display: none;\n",
" z-index: 9999;\n",
" position: relative;\n",
" font-weight: normal;\n",
" right: .2ex;\n",
" padding: .5ex;\n",
" margin: .5ex;\n",
" width: min-content;\n",
" min-width: 20ex;\n",
" max-width: 50ex;\n",
" color: var(--sklearn-color-text);\n",
" box-shadow: 2pt 2pt 4pt #999;\n",
" /* unfitted */\n",
" background: var(--sklearn-color-unfitted-level-0);\n",
" border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
"}\n",
"\n",
".sk-estimator-doc-link.fitted span {\n",
" /* fitted */\n",
" background: var(--sklearn-color-fitted-level-0);\n",
" border: var(--sklearn-color-fitted-level-3);\n",
"}\n",
"\n",
".sk-estimator-doc-link:hover span {\n",
" display: block;\n",
"}\n",
"\n",
"/* \"?\"-specific style due to the `<a>` HTML tag */\n",
"\n",
"#sk-container-id-1 a.estimator_doc_link {\n",
" float: right;\n",
" font-size: 1rem;\n",
" line-height: 1em;\n",
" font-family: monospace;\n",
" background-color: var(--sklearn-color-background);\n",
" border-radius: 1rem;\n",
" height: 1rem;\n",
" width: 1rem;\n",
" text-decoration: none;\n",
" /* unfitted */\n",
" color: var(--sklearn-color-unfitted-level-1);\n",
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
"}\n",
"\n",
"#sk-container-id-1 a.estimator_doc_link.fitted {\n",
" /* fitted */\n",
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-fitted-level-1);\n",
"}\n",
"\n",
"/* On hover */\n",
"#sk-container-id-1 a.estimator_doc_link:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
"#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-3);\n",
"}\n",
"</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[('encoding',\n",
" ColumnTransformer(remainder='passthrough',\n",
" transformers=[('ohe',\n",
" OneHotEncoder(handle_unknown='ignore'),\n",
" ['PromoInterval', 'StoreType',\n",
" 'Assortment'])])),\n",
" ('scaler', StandardScaler()),\n",
" ('model',\n",
" XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
" colsample_bylevel=None, colsample_bynode=None,\n",
" colsample_bytree=None, device=None,...\n",
" feature_types=None, gamma=None, grow_policy=None,\n",
" importance_type=None,\n",
" interaction_constraints=None, learning_rate=0.1,\n",
" max_bin=None, max_cat_threshold=None,\n",
" max_cat_to_onehot=None, max_delta_step=None,\n",
" max_depth=13, max_leaves=None,\n",
" min_child_weight=None, missing=nan,\n",
" monotone_constraints=None, multi_strategy=None,\n",
" n_estimators=None, n_jobs=None,\n",
" num_parallel_tree=None, random_state=None, ...))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> Pipeline<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.pipeline.Pipeline.html\">?<span>Documentation for Pipeline</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>Pipeline(steps=[('encoding',\n",
" ColumnTransformer(remainder='passthrough',\n",
" transformers=[('ohe',\n",
" OneHotEncoder(handle_unknown='ignore'),\n",
" ['PromoInterval', 'StoreType',\n",
" 'Assortment'])])),\n",
" ('scaler', StandardScaler()),\n",
" ('model',\n",
" XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
" colsample_bylevel=None, colsample_bynode=None,\n",
" colsample_bytree=None, device=None,...\n",
" feature_types=None, gamma=None, grow_policy=None,\n",
" importance_type=None,\n",
" interaction_constraints=None, learning_rate=0.1,\n",
" max_bin=None, max_cat_threshold=None,\n",
" max_cat_to_onehot=None, max_delta_step=None,\n",
" max_depth=13, max_leaves=None,\n",
" min_child_weight=None, missing=nan,\n",
" monotone_constraints=None, multi_strategy=None,\n",
" n_estimators=None, n_jobs=None,\n",
" num_parallel_tree=None, random_state=None, ...))])</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> encoding: ColumnTransformer<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.compose.ColumnTransformer.html\">?<span>Documentation for encoding: ColumnTransformer</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>ColumnTransformer(remainder='passthrough',\n",
" transformers=[('ohe', OneHotEncoder(handle_unknown='ignore'),\n",
" ['PromoInterval', 'StoreType', 'Assortment'])])</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">ohe</label><div class=\"sk-toggleable__content fitted\"><pre>['PromoInterval', 'StoreType', 'Assortment']</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> OneHotEncoder<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.preprocessing.OneHotEncoder.html\">?<span>Documentation for OneHotEncoder</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>OneHotEncoder(handle_unknown='ignore')</pre></div> </div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">remainder</label><div class=\"sk-toggleable__content fitted\"><pre>['StateHoliday', 'Store', 'Customers', 'Promo', 'SchoolHoliday', 'CompetitionDistance', 'CompetitionOpenSinceMonth', 'CompetitionOpenSinceYear']</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">passthrough</label><div class=\"sk-toggleable__content fitted\"><pre>passthrough</pre></div> </div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> StandardScaler<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.preprocessing.StandardScaler.html\">?<span>Documentation for StandardScaler</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>StandardScaler()</pre></div> </div></div><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">XGBRegressor</label><div class=\"sk-toggleable__content fitted\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
" colsample_bylevel=None, colsample_bynode=None,\n",
" colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
" enable_categorical=False, eval_metric=None, feature_types=None,\n",
" gamma=None, grow_policy=None, importance_type=None,\n",
" interaction_constraints=None, learning_rate=0.1, max_bin=None,\n",
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
" max_delta_step=None, max_depth=13, max_leaves=None,\n",
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
" multi_strategy=None, n_estimators=None, n_jobs=None,\n",
" num_parallel_tree=None, random_state=None, ...)</pre></div> </div></div></div></div></div></div>"
],
"text/plain": [
"Pipeline(steps=[('encoding',\n",
" ColumnTransformer(remainder='passthrough',\n",
" transformers=[('ohe',\n",
" OneHotEncoder(handle_unknown='ignore'),\n",
" ['PromoInterval', 'StoreType',\n",
" 'Assortment'])])),\n",
" ('scaler', StandardScaler()),\n",
" ('model',\n",
" XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
" colsample_bylevel=None, colsample_bynode=None,\n",
" colsample_bytree=None, device=None,...\n",
" feature_types=None, gamma=None, grow_policy=None,\n",
" importance_type=None,\n",
" interaction_constraints=None, learning_rate=0.1,\n",
" max_bin=None, max_cat_threshold=None,\n",
" max_cat_to_onehot=None, max_delta_step=None,\n",
" max_depth=13, max_leaves=None,\n",
" min_child_weight=None, missing=nan,\n",
" monotone_constraints=None, multi_strategy=None,\n",
" n_estimators=None, n_jobs=None,\n",
" num_parallel_tree=None, random_state=None, ...))])"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Define the ColumnTransformer\n",
"ohe_col = [\"PromoInterval\", \"StoreType\", \"Assortment\"]\n",
"\n",
"ct_encoding = ColumnTransformer(\n",
" transformers=[\n",
" (\"ohe\", OneHotEncoder(handle_unknown=\"ignore\"), ohe_col)\n",
" ],\n",
" remainder=\"passthrough\"\n",
")\n",
"\n",
"\n",
"# Define the XGBRegressor model\n",
"model = XGBRegressor(learning_rate=0.1, max_depth=13)\n",
"\n",
"# Define the pipeline\n",
"pipe = Pipeline(steps=[\n",
" (\"encoding\", ct_encoding),\n",
" (\"scaler\", StandardScaler()),\n",
" (\"model\", model)\n",
"])\n",
"\n",
"# Now you can fit your pipeline with your data\n",
"pipe.fit(X_train, y_train)\n"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([5674.2217, 7922.6377, 9180.126 , ..., 7287.449 , 3228.0945,\n",
" 4453.9897], dtype=float32)"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"y_pred = pipe.predict(X_test)\n",
"y_pred"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"43879 5934\n",
"562681 7800\n",
"239643 9111\n",
"689976 7831\n",
"397240 10046\n",
" ... \n",
"512864 13692\n",
"750784 6958\n",
"192729 6785\n",
"755727 2925\n",
"604917 4178\n",
"Name: Sales, Length: 211085, dtype: int64"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"y_test"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['PromoInterval', 'StoreType', 'Assortment', 'StateHoliday', 'Store',\n",
" 'Customers', 'Promo', 'SchoolHoliday', 'CompetitionDistance',\n",
" 'CompetitionOpenSinceMonth', 'CompetitionOpenSinceYear'],\n",
" dtype='object')"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_train.columns"
]
},
{
"cell_type": "code",
"execution_count": 24,
"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>PromoInterval</th>\n",
" <th>StoreType</th>\n",
" <th>Assortment</th>\n",
" <th>StateHoliday</th>\n",
" <th>Store</th>\n",
" <th>Customers</th>\n",
" <th>Promo</th>\n",
" <th>SchoolHoliday</th>\n",
" <th>CompetitionDistance</th>\n",
" <th>CompetitionOpenSinceMonth</th>\n",
" <th>CompetitionOpenSinceYear</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>795018</th>\n",
" <td>Jan,Apr,Jul,Oct</td>\n",
" <td>Small Shop</td>\n",
" <td>basic</td>\n",
" <td>0</td>\n",
" <td>650</td>\n",
" <td>636</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1420</td>\n",
" <td>10</td>\n",
" <td>2012</td>\n",
" </tr>\n",
" <tr>\n",
" <th>463276</th>\n",
" <td>Jan,Apr,Jul,Oct</td>\n",
" <td>Small Shop</td>\n",
" <td>basic</td>\n",
" <td>0</td>\n",
" <td>72</td>\n",
" <td>261</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>2200</td>\n",
" <td>12</td>\n",
" <td>2009</td>\n",
" </tr>\n",
" <tr>\n",
" <th>268352</th>\n",
" <td>0</td>\n",
" <td>Medium Store</td>\n",
" <td>extra</td>\n",
" <td>0</td>\n",
" <td>733</td>\n",
" <td>3567</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>860</td>\n",
" <td>10</td>\n",
" <td>1999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>67308</th>\n",
" <td>0</td>\n",
" <td>Small Shop</td>\n",
" <td>extended</td>\n",
" <td>0</td>\n",
" <td>796</td>\n",
" <td>791</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>7180</td>\n",
" <td>11</td>\n",
" <td>2012</td>\n",
" </tr>\n",
" <tr>\n",
" <th>482458</th>\n",
" <td>0</td>\n",
" <td>Small Shop</td>\n",
" <td>extended</td>\n",
" <td>0</td>\n",
" <td>301</td>\n",
" <td>480</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4510</td>\n",
" <td>3</td>\n",
" <td>2015</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" PromoInterval StoreType Assortment StateHoliday Store \\\n",
"795018 Jan,Apr,Jul,Oct Small Shop basic 0 650 \n",
"463276 Jan,Apr,Jul,Oct Small Shop basic 0 72 \n",
"268352 0 Medium Store extra 0 733 \n",
"67308 0 Small Shop extended 0 796 \n",
"482458 0 Small Shop extended 0 301 \n",
"\n",
" Customers Promo SchoolHoliday CompetitionDistance \\\n",
"795018 636 1 0 1420 \n",
"463276 261 0 0 2200 \n",
"268352 3567 1 0 860 \n",
"67308 791 1 0 7180 \n",
"482458 480 0 0 4510 \n",
"\n",
" CompetitionOpenSinceMonth CompetitionOpenSinceYear \n",
"795018 10 2012 \n",
"463276 12 2009 \n",
"268352 10 1999 \n",
"67308 11 2012 \n",
"482458 3 2015 "
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_train.head()"
]
},
{
"cell_type": "code",
"execution_count": 26,
"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>PromoInterval</th>\n",
" <th>StoreType</th>\n",
" <th>Assortment</th>\n",
" <th>StateHoliday</th>\n",
" <th>Store</th>\n",
" <th>Customers</th>\n",
" <th>Promo</th>\n",
" <th>SchoolHoliday</th>\n",
" <th>CompetitionDistance</th>\n",
" <th>CompetitionOpenSinceMonth</th>\n",
" <th>CompetitionOpenSinceYear</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Jan,Apr,Jul,Oct</td>\n",
" <td>Small Shop</td>\n",
" <td>basic</td>\n",
" <td>0</td>\n",
" <td>650</td>\n",
" <td>636</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1420</td>\n",
" <td>10</td>\n",
" <td>2012</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" PromoInterval StoreType Assortment StateHoliday Store Customers Promo \\\n",
"0 Jan,Apr,Jul,Oct Small Shop basic 0 650 636 1 \n",
"\n",
" SchoolHoliday CompetitionDistance CompetitionOpenSinceMonth \\\n",
"0 0 1420 10 \n",
"\n",
" CompetitionOpenSinceYear \n",
"0 2012 "
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 795018\n",
"temp_df = pd.DataFrame(data = [[\"Jan,Apr,Jul,Oct\",\"Small Shop\",\"basic\",\"0\",\"650\",\"636\",\"1\",\"0\",\"1420\",\"10\",\"2012\"]], columns = X_test.columns)\n",
"temp_df"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([6357.158], dtype=float32)"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pipe.predict(temp_df)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Record at index 795018:\n",
"PromoInterval Jan,Apr,Jul,Oct\n",
"StoreType Small Shop\n",
"Assortment basic\n",
"StateHoliday 0\n",
"Store 650\n",
"Customers 636\n",
"Promo 1\n",
"SchoolHoliday 0\n",
"CompetitionDistance 1420\n",
"CompetitionOpenSinceMonth 10\n",
"CompetitionOpenSinceYear 2012\n",
"Sales 6322\n",
"Name: 795018, dtype: object\n"
]
}
],
"source": [
"# Assuming your DataFrame is named df\n",
"record = df.iloc[795018]\n",
"\n",
"print(\"Record at index 795018:\")\n",
"print(record)\n"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Unique values in PromoInterval: ['0' 'Jan,Apr,Jul,Oct' 'Feb,May,Aug,Nov' 'Mar,Jun,Sept,Dec']\n",
"Unique values in StoreType: ['Large Store' 'Small Shop' 'Hypermarket' 'Medium Store']\n",
"Unique values in Assortment: ['basic' 'extended' 'extra']\n",
"Unique values in StateHoliday: [0 1]\n",
"Unique values in Store: [ 1 2 3 ... 1115 876 292]\n",
"Unique values in Customers: [ 555 625 821 ... 3900 36 4065]\n",
"Unique values in Promo: [1 0]\n",
"Unique values in SchoolHoliday: [1 0]\n",
"Unique values in CompetitionDistance: [ 1270 570 14130 620 29910 310 24000 7520 2030 3160 960 1070\n",
" 1300 4110 3270 50 13840 3240 2340 550 1040 4060 4590 430\n",
" 2300 60 1200 2170 40 9800 2910 1320 2240 7660 540 4230\n",
" 1090 260 180 1180 290 4880 9710 270 1060 18010 6260 10570\n",
" 450 30360 7170 720 6620 420 7340 2840 5540 350 2050 3700\n",
" 22560 410 250 1130 4840 17500 2200 1650 330 22440 19960 3510\n",
" 3320 7910 2370 22390 2710 11810 1870 480 560 10690 2380 2410\n",
" 240 16690 14620 1890 8780 8980 15140 17930 2440 150 5210 390\n",
" 6190 1390 1930 2190 3300 46590 7890 1630 20930 4510 5740 680\n",
" 3450 3580 2100 2290 3570 58260 16760 1410 760 3370 1350 2000\n",
" 2460 900 920 5190 1730 25360 1700 1540 2930 16570 280 8050\n",
" 8540 2090 2610 31830 4360 1780 16240 16420 3050 2020 2950 11840\n",
" 8530 17110 2970 5340 1480 1160 3720 100 140 12540 980 2640\n",
" 110 13090 4130 3770 1250 1710 5800 12610 9670 3560 1860 19360\n",
" 850 5760 1470 1100 2770 520 16970 220 3850 4210 6360 20260\n",
" 5140 490 5630 380 6870 300 11680 970 15050 4030 8650 190\n",
" 3150 640 1640 1000 13530 2920 7930 10180 10800 17410 6680 3840\n",
" 13570 4370 5710 1420 320 610 1110 780 6880 710 1310 4660\n",
" 70 340 3520 22330 4630 80 27190 210 15340 1140 4580 360\n",
" 4520 1450 16180 8480 3640 2960 7840 9260 2320 18640 6970 1220\n",
" 2260 1290 1460 2740 800 6540 4150 2325 9580 19840 38630 120\n",
" 15430 1950 2470 5100 18660 8740 11300 14160 38710 9000 3140 32330\n",
" 8140 8400 13140 10070 3130 370 670 1840 4040 90 10600 1590\n",
" 2280 8080 15770 18650 8090 9360 16490 1490 8880 5290 1500 9720\n",
" 8970 2060 2890 2040 4490 13620 6470 5870 8250 1970 11120 1150\n",
" 15710 160 2140 6630 1800 26130 130 6690 1600 460 2120 4820\n",
" 10850 3620 23130 5360 9200 5830 4970 1080 8240 5890 1560 840\n",
" 8460 4460 6210 6910 4650 1620 3530 2880 16350 12870 810 30030\n",
" 13020 910 3900 2530 500 11400 1510 3970 5780 1850 75860 26450\n",
" 3390 34050 1790 44320 4160 10890 3110 20390 5260 5300 5030 14810\n",
" 8300 770 1940 7470 2550 2310 14300 2180 14960 660 4680 1740\n",
" 1260 5470 2780 1610 990 13080 820 9070 1280 4740 8260 590\n",
" 400 11260 20 22490 3330 2510 6900 18610 7160 40860 20620 12920\n",
" 18160 5950 4700 600 650 7280 5020 580 8990 3760 2330 4260\n",
" 3040 3000 3910 1910 1210 700 1010 4270 1340 2110 9230 1190\n",
" 4400 2270 12700 20970 170 7250 1360 440 15720 3340 2540 33060\n",
" 17340 8220 10950 10310 18370 2070 2490 730 8940 9910 5440 30\n",
" 4080 6920 1170 10740 510 1690 2870 3350 11640 27530 9790 10170\n",
" 7780 8040 530 230 7420 2130 14570 200 6930 7860 1680 2700\n",
" 17080 15170 3250 4140 2850 20050 18760 15040 3030 3780 830 8550\n",
" 7830 2900 11470 4870 12070 3200 8190 15320 3590 5650 5900 17540\n",
" 40540 13990 15270 35280 860 1920 5980 6400 11900 4380 6710 1370\n",
" 17650 4330 45740 3410 8670 13130 19780 2390 32240 26490 25430 9820\n",
" 2630 20640 16990 630 5390 15490 3210 1530 9770 17280 5090 7180\n",
" 9560 48330 1760 24770 3870 18620 12770 9640 2590 24530 16210 17570\n",
" 7980 3290 6320 5070 3470 2720 14600 6890 27650 8860 5000 1120\n",
" 940 14040 4770 3440 3020 6270 21770 740 21370 1020 9680 21810\n",
" 10620 3860 29190 4570 7550 12430 19700 4450 18670 19370 18540 3920\n",
" 3170 7290 1980 12480 3100 7240 18710 2620 6420 470 5150 15700\n",
" 5460 22350 2810 2820 6860 18020 1670 2220 1430 870 6300 19830\n",
" 9430 23620 9630 4180 3890 4420 21930 2480 3460 6560 5840 2230\n",
" 19640 6480 4610 6330 1520 3740 1990 36410 7680 13750 27150 17290\n",
" 26990 29070 3750 13170 5080 13190 5350 3230 3380 3430 8110 6250\n",
" 12020 5010 18050 5380 16680 11540 2210 4300 5220 9990 10450 690\n",
" 1830 5330 1400 3490 1900 1880 21790]\n",
"Unique values in CompetitionOpenSinceMonth: [ 9 11 12 4 10 8 3 6 5 1 2 7]\n",
"Unique values in CompetitionOpenSinceYear: [2008 2007 2006 2009 2015 2013 2014 2000 2011 2010 2005 1999 2003 2012\n",
" 2004 2002 1961 1995 2001 1990 1994 1900 1998]\n",
"Unique values in Sales: [ 5263 6064 8314 ... 660 17815 23303]\n"
]
}
],
"source": [
"def print_unique_values(dataframe):\n",
" for column in dataframe.columns:\n",
" unique_values = dataframe[column].unique()\n",
" print(f\"Unique values in {column}: {unique_values}\")\n",
"\n",
"# Example usage:\n",
"print_unique_values(df)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Save The Model "
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['model2.pkl']"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import joblib\n",
"\n",
"# joblib.dump(pipe, 'model2.pkl')"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
"model1 = joblib.load(\"../models/model2.pkl\")"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([6357.158], dtype=float32)"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model1.predict(temp_df)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# ..."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<hr>\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.11"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|