Spaces:
Sleeping
Sleeping
File size: 178,442 Bytes
16ed9fd |
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 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 |
library(shiny)
library(shinyjs)
library(bslib)
library(dplyr)
library(ggplot2)
library(tm)
library(SnowballC)
library(plotly)
library(text2vec)
library(tokenizers)
library(dplyr)
library(tidyr)
library(igraph)
library(ggraph)
library(reshape2)
library(SnowballC)
library(RColorBrewer)
library(syuzhet)
library(cluster)
library(Rtsne)
library(umap)
library(MASS)
library(koRpus)
library(openxlsx)
library(tools)
library(shinyWidgets)
library(readxl)
library(scales)
library(caret)
library(BBmisc)
library(glmnet)
library(pROC)
library(ROCR)
library(car)
library(ResourceSelection)
library(tree)
library(ggplotify)
library(lmtest)
library(gridExtra)
library(patchwork)
library(caret)
library(randomForest)
library(gbm)
library(earth)
library(broom)
library(rlang)
library(ggdendro)
library(pastecs)
options(width = 150)
options(digits = 4, scipen = 1000000000)
options(shiny.maxRequestSize=30*1024^2)
# Function to process a chunk of lines and update word counts
process_chunk <- function(chunk, word_counts) {
max_word_length <- 1000 # Set a maximum word length
for (line in chunk) {
words <- unlist(strsplit(line, "\\s+")) # Splitting line into words
for (word in words) {
word <- as.character(word) # Ensure 'word' is a character string
if (nchar(word) == 0 || nchar(word) > max_word_length) {
next # Skip empty words or words that are too long
}
# Check if word exists and get the current count
if (!is.null(word_counts[[word]])) {
current_count <- word_counts[[word]]
} else {
current_count <- 0
}
word_counts[[word]] <- current_count + 1
}
}
return(word_counts)
}
# Main function to count word frequencies in the file
count_word_frequencies <- function(file_path) {
con <- file(file_path, "r") # Open file connection
word_counts <- new.env(hash = TRUE, size = 600000) # Initialize environment for counting
while(TRUE) {
lines <- readLines(con, n = 5000) # Adjust 'n' based on system capability
if (length(lines) == 0) {
break
}
word_counts <- process_chunk(lines, word_counts)
}
close(con) # Close file connection
return(as.list(word_counts)) # Convert environment to list for easy access
}
ui <- fluidPage(
theme = bs_theme(version = 5, bootswatch = "spacelab"),
useShinyjs(), # Initialize shinyjs
titlePanel("PtteM Data Science"),
tags$head(tags$link(rel = "stylesheet", href="https://fonts.googleapis.com/css?family=Montserrat:100,300,400,700&display=swap"),
tags$style(HTML("
body, h1, h2, h3, h4, h5, h6, .nav, p, a, .shiny-input-container {
font-family: 'Montserrat'; /* Font type for the title attribute */
font-weight: 385;
color: #007c9e !important;
}
* {
font-family: 'Montserrat', sans-serif;
font-weight: 385;
color: #195576; /* Blue color */
}
body {
background-color: #f7f7f7; /* Light gray background */
}
.icon-btn {
border: 1px solid #0d6efd; /* Example border: solid, 2 pixels, #555 color */
border-radius: 15%; /* Circular border */
color: #00969e; /* Icon color */
font-family: 'Montserrat'; /* Font type for the title attribute */
font-weight: 385;
background-color: #f7f7f7;
padding: 125px; /* Space around the icon */
margin: 25px; /* Space around the button */
font-size: 24px; /* Icon size */
box-shadow: 0 2px 4px rgba(0,0,0,0.2);
}
.icon-btn:hover {
color: #00969e; /* Icon color on hover */
border-color: #007c9e;
background-color: #ebfbfd;/* Border color on hover */
}
/* Add custom styles here */
.shiny-input-container {
margin-bottom: 15px;
}
.box {
border: 1px solid #ddd;
padding: 20px;
border-radius: 50px;
margin-bottom: 200px;
gap: 200px;
align-items: center;
}
#statsTable_wrapper {
margin: 0 auto;
}
.shiny-output-error {
border: 1px solid #FF0000; /* Red border on error */
}
/* If you want to change the font size of the tooltip, you can add custom CSS for the 'title' attribute's default styling. */
"))),
tags$head(
# Include JavaScript to reload the page
tags$script(HTML("
document.addEventListener('DOMContentLoaded', function() {
document.getElementById('myElement').style.color = '#0d6efd'; // Change to your desired color
});
"))
),
tags$head(
tags$script(HTML("
function reloadPage() {
window.location.reload();
}
"))
),
# Refresh button that calls the JavaScript function
actionButton("refresh", "Refresh Analysis", onclick = "reloadPage();"),
# Help Text or Information for the user
helpText("Bu uygulama ile metin analizi başlığı altındaki veri bilimi fonksiyonlarına erişebilirsiniz."),
#Supervised Learning
h2("Supervised Learning Section"),
tabsetPanel(
tabPanel("Simple Linear Regression",
sidebarLayout(
sidebarPanel(
fileInput("slrinput", "Choose a CSV or XLSX file", accept = c(".csv", ".xlsx")),
actionButton("loadslr", "Load Data"),
selectInput("targetslr", "Select Target Column", choices = NULL),
selectizeInput("independentVar", "Select Independent Variable", choices = NULL, multiple = FALSE),
sliderInput("dataSplitslr",
"Data Split Ratio",
min = 0.1,
max = 0.9,
value = 0.7, # Default value, for instance, 70% for training and 30% for testing
step = 0.05,
ticks = FALSE,
animate = TRUE),
actionButton("slrassumption", "Run Assumption"),
actionButton("slrmodel", "Run SLR Model"),
HTML("<div>
<h2>Basit Doğrusal Regresyon Paneli</h2>
<h3>Çıktı Nedir ve Neden Kullanılır?</h3> Bu panel, bir hedef değişken ile bir veya birden fazla bağımsız değişken arasındaki ilişkiyi modellemek için basit doğrusal regresyon (SLR) analizi yapar. SLR, iki değişken arasındaki ilişkinin doğasını ve gücünü anlamak için kullanılır.</p>
<h3>Kullanım Adımları:</h3></p>
<ol>
<li><strong>Veri Dosyası Yükleme:</strong> SLR analizi için bir CSV veya XLSX dosyasını <code>fileInput</code> aracılığıyla yükleyin.</li>
<li><strong>Hedef ve Bağımsız Değişken Seçimi:</strong> Analiz için hedef değişkeni ve bağımsız değişkeni seçin.</li>
<li><strong>Analizi Çalıştırma:</strong> <code>actionButton</code> butonlarına tıklayarak SLR modelini ve varsayım kontrollerini çalıştırın.</li>
</ol>
<h3>Kullanıcı Etkileşimi:</h3> Kullanıcılar, dosya yükledikten ve gerekli değişkenleri seçtikten sonra analizi başlatır ve sonuçlar ana panelde görselleştirilir.</p>
<h3>Veri Bilimi Alanındaki Kullanımı:</h3> Basit doğrusal regresyon, özellikle iki değişken arasındaki ilişkiyi keşfetmek ve bu ilişkinin gücünü ve yönünü belirlemek için önemli bir yöntemdir. SLR, tahmin modelleri oluşturma, trend analizi ve değişkenler arasındaki ilişkilerin değerlendirilmesi gibi çeşitli alanlarda kullanılır.</p>
<h3>Desteklenen Dosya Tipleri:</h3> Kullanıcılar, analiz için CSV (.csv) veya Excel (.xlsx) formatında dosyalar yükleyebilirler.</p>
<h3>Sonuçların Yorumlanması:</h3> Elde edilen model özeti, regresyon katsayıları, p-değerleri, R-kare gibi istatistiklerle modelin anlamlılığını ve açıklayıcılığını değerlendirir. Ayrıca, varsayım testleri ve diyagnostik grafikler modelin varsayımlara uygunluğunu kontrol etmek için kullanılır.</p>
<ul>
<li><strong>Model Özeti:</strong> Modelin istatistiksel anlamlılığını ve açıklayıcılığını değerlendirir.</li>
<li><strong>Varsayım Testleri:</strong> Modelin normal dağılım, homoskedastisite, bağımsızlık ve doğrusallık gibi temel varsayımlara uygunluğunu test eder.</li>
<li><strong>Regresyon Çizgisi Grafiği:</strong> Hedef ve bağımsız değişken arasındaki ilişkiyi görsel olarak gösterir.</li>
</ul>
<p>Bu özellikler, basit doğrusal regresyon analizinin, veri setinden önemli içgörüler elde etmek ve değişkenler arasındaki ilişkileri anlamak için nasıl kullanılabileceğini gösterir.</p>
</div>
")
),
mainPanel(
tabsetPanel(
tabPanel("Data Summary", verbatimTextOutput("slrsummary")),
tabPanel("Assumptions for SLR Model",
tabsetPanel(
tabPanel("Diagnostics",
plotlyOutput("residualsFittedPlot"),
plotlyOutput("qqPlot"),
plotlyOutput("scaleLocationPlot"),
plotlyOutput("residualsLeveragePlot")
),
tabPanel("Shapiro-Wilk Test", verbatimTextOutput("shapiroTest")),
tabPanel("Breusch-Pagan Test", verbatimTextOutput("ncvTest")),
tabPanel("Linearity Plot", plotlyOutput("linearityPlotOutput", width = "100%", height = "700px")),
tabPanel("Durbin-Watson Test", verbatimTextOutput("durbinWatsonTest"))
)
),
tabPanel("SLR Model Evaluation",
tabsetPanel(
tabPanel("Model Summary", verbatimTextOutput("slrmodeleva")),
tabPanel("Correlation Coefficient Between the Variables", verbatimTextOutput("corcoefslr")),
tabPanel("Confidence Interval", verbatimTextOutput("confintslr")),
tabPanel("Regression Line Plot", plotlyOutput("slrregressPlot", width = "100%", height = "625px"))
)
)
)
)
)
),
tabPanel("Multiple Linear Regression",
sidebarLayout(
sidebarPanel(
fileInput("mlrinput", "Choose a CSV or XLSX file", accept = c(".csv", ".xslx")),
actionButton("loadmlr", "Load Data"),
selectInput("targetmlr", "Select Target Column", choices = NULL),
selectizeInput("independentVarmlr", "Select Independent Variable", choices = NULL, multiple = TRUE),
sliderInput("dataSplitmlr",
"Data Split Ratio",
min = 0.1,
max = 0.9,
value = 0.7, # Default value, for instance, 70% for training and 30% for testing
step = 0.05,
ticks = FALSE,
animate = TRUE),
actionButton("mlrassumption", "Run Assumption"),
actionButton("mlrmodel", "Run MLR Model"),
HTML("<div>
<h2>Çoklu Doğrusal Regresyon Paneli</h2>
<h3>Çıktı Nedir ve Neden Kullanılır?</h3> Bu panel, bir hedef değişken ile birden fazla bağımsız değişken arasındaki ilişkiyi modellemek için çoklu doğrusal regresyon (MLR) analizi yapar. MLR, değişkenler arasındaki ilişkilerin karmaşıklığını anlamak ve birden çok bağımsız değişkenin hedef değişken üzerindeki etkisini keşfetmek için kullanılır.</p>
<h3>Kullanım Adımları:</h3></p>
<ol>
<li><strong>Veri Dosyası Yükleme:</strong> MLR analizi için bir CSV veya XLSX dosyasını <code>fileInput</code> aracılığıyla yükleyin.</li>
<li><strong>Hedef ve Bağımsız Değişkenlerin Seçimi:</strong> Analiz için hedef değişkeni ve birden fazla bağımsız değişkeni seçin.</li>
<li><strong>Analizi Çalıştırma:</strong> <code>actionButton</code> butonlarına tıklayarak MLR modelini ve varsayım kontrollerini çalıştırın.</li>
</ol>
<h3>Kullanıcı Etkileşimi:</h3> Kullanıcılar, dosya yükledikten ve gerekli değişkenleri seçtikten sonra analizi başlatır ve sonuçlar ana panelde görselleştirilir.</p>
<h3>Veri Bilimi Alanındaki Kullanımı:</h3> Çoklu doğrusal regresyon, tahmin modelleri oluşturma, çok faktörlü etki analizi ve değişkenler arasındaki ilişkilerin değerlendirilmesi gibi çeşitli alanlarda kullanılır. MLR, birden çok bağımsız değişkenin hedef değişken üzerindeki etkisini ve ilişkilerin yapısını anlamak için tercih edilen bir yöntemdir.</p>
<h3>Desteklenen Dosya Tipleri:</h3> Kullanıcılar, analiz için CSV (.csv) veya Excel (.xlsx) formatında dosyalar yükleyebilirler.</p>
<h3>Sonuçların Yorumlanması:</h3> Elde edilen model özeti, regresyon katsayıları, p-değerleri, R-kare gibi istatistiklerle modelin anlamlılığını ve açıklayıcılığını değerlendirir. Ayrıca, varsayım testleri ve diyagnostik grafikler modelin varsayımlara uygunluğunu kontrol etmek için kullanılır.</p>
<ul>
<li><strong>Model Özeti:</strong> Modelin istatistiksel anlamlılığını ve açıklayıcılığını değerlendirir.</li>
<li><strong>Varsayım Testleri:</strong> Modelin normal dağılım, homoskedastisite, bağımsızlık, doğrusallık ve çoklu bağlantı gibi temel varsayımlara uygunluğunu test eder.</li>
<li><strong>Regresyon Çizgisi Grafiği:</strong> Hedef ve bağımsız değişkenler arasındaki ilişkiyi görsel olarak gösterir.</li>
</ul>
<p>Bu özellikler, çoklu doğrusal regresyon analizinin, veri setinden derinlemesine içgörüler elde etmek ve değişkenler arasındaki ilişkileri anlamak için nasıl kullanılabileceğini gösterir.</p>
</div>
")
),
mainPanel(
tabsetPanel(
tabPanel("Data Summary", verbatimTextOutput("mlrsummary")),
tabPanel("Assumptions for MLR Model",
tabsetPanel(
tabPanel("Diagnostics",
plotlyOutput("resFitmlrPlot"),
plotlyOutput("qqPlotmlr"),
plotlyOutput("scaleLocmlrPlot"),
plotlyOutput("resLevmlrPlot")
),
tabPanel("Shapiro-Wilk Test", verbatimTextOutput("shapTestmlr")),
tabPanel("Breusch-Pagan Test", verbatimTextOutput("ncvTestmlr")),
tabPanel("Linearity Plot", plotlyOutput("linPlotmlr", width = "100%", height = "725px")),
tabPanel("Durbin-Watson Test", verbatimTextOutput("dWTestmlr")),
tabPanel("Variance Inflation Factor", verbatimTextOutput("vifmlr"))
)
),
tabPanel("MLR Model Evaluation",
tabsetPanel(
tabPanel("Model Summary", verbatimTextOutput("mlrmodeleva")),
tabPanel("Correlation Coefficient Between the Variables", verbatimTextOutput("corcoefmlr")),
tabPanel("Confidence Interval", verbatimTextOutput("confintmlr")),
tabPanel("Model Evaluation Metrics", verbatimTextOutput("modelevamet")),
tabPanel("Regression Line Plot", plotlyOutput("mlrregressPlot", width = "100%", height = "625px"))
)
),
),
)
)
),
tabPanel("Logistic Regression",
sidebarLayout(
sidebarPanel(
fileInput("glmfile", "Choose a CSV or XLSX file", accept = c(".csv", ".xlsx")),
actionButton("loadData", "Load Data"),
selectInput("targetglm", "Select Target Column", choices = NULL),
selectizeInput("independentVars", "Select Independent Variables", choices = NULL, multiple = TRUE),
sliderInput("dataSplit",
"Data Split Ratio",
min = 0.1,
max = 0.9,
value = 0.7, # Default value, for instance, 70% for training and 30% for testing
step = 0.05,
ticks = FALSE,
animate = TRUE),
actionButton("glmassumption", "Run Assumption"),
actionButton("runLogisticRegression", "Run Logistic Regression"),
HTML("<div>
<h2>Lojistik Regresyon Paneli</h2>
<h3>Çıktı Nedir ve Neden Kullanılır?</h3> Bu panel, bir veya birden fazla bağımsız değişken ile kategorik bir hedef değişken arasındaki ilişkiyi modellemek için lojistik regresyon analizi yapar. Lojistik regresyon, özellikle ikili (binary) sonuçlar için tercih edilen bir yöntemdir ve olasılıkların tahmin edilmesinde kullanılır.</p>
<h3>Kullanım Adımları:</h3></p>
<ol>
<li><strong>Veri Dosyası Yükleme:</strong> Lojistik regresyon analizi için bir CSV veya XLSX dosyasını <code>fileInput</code> aracılığıyla yükleyin.</li>
<li><strong>Hedef ve Bağımsız Değişkenlerin Seçimi:</strong> Analiz için kategorik hedef değişkeni ve bir veya birden fazla bağımsız değişkeni seçin.</li>
<li><strong>Analizi Çalıştırma:</strong> <code>actionButton</code> butonlarına tıklayarak lojistik regresyon modelini ve varsayım kontrollerini çalıştırın.</li>
</ol>
<h3>Kullanıcı Etkileşimi:</h3> Kullanıcılar, dosya yükledikten ve gerekli değişkenleri seçtikten sonra analizi başlatır ve sonuçlar ana panelde görselleştirilir.</p>
<h3>Veri Bilimi Alanındaki Kullanımı:</h3> Lojistik regresyon, sınıflandırma, olasılık tahmini ve risk faktörlerinin incelenmesi gibi çeşitli alanlarda kullanılır. Özellikle, kategorik sonuçların (örneğin, evet/hayır, başarılı/başarısız) olasılıklarının tahmin edilmesinde tercih edilen bir yöntemdir.</p>
<h3>Desteklenen Dosya Tipleri:</h3> Kullanıcılar, analiz için CSV (.csv) veya Excel (.xlsx) formatında dosyalar yükleyebilirler.</p>
<h3>Sonuçların Yorumlanması:</h3> Elde edilen model özeti, regresyon katsayıları, p-değerleri, ROC eğrisi gibi istatistiklerle modelin anlamlılığını ve performansını değerlendirir. Ayrıca, varsayım testleri modelin varsayımlara uygunluğunu kontrol etmek için kullanılır.</p>
<ul>
<li><strong>Model Özeti:</strong> Modelin istatistiksel anlamlılığını ve performansını değerlendirir.</li>
<li><strong>Varsayım Testleri:</strong> Modelin normal dağılım, homoskedastisite, bağımsızlık gibi temel varsayımlara uygunluğunu test eder.</li>
<li><strong>ROC Eğrisi:</strong> Modelin sınıflandırma performansını değerlendirir ve AUC (Alan Altında Kalan Alan) değeri ile modelin ayırt edici gücünü gösterir.</li>
</ul>
<p>Bu özellikler, lojistik regresyon analizinin, veri setinden derinlemesine içgörüler elde etmek ve kategorik sonuçların olasılıklarını tahmin etmek için nasıl kullanılabileceğini gösterir.</p>
</div>
")
),
mainPanel(
tabsetPanel(
tabPanel("Data Summary", verbatimTextOutput("dataSummary")),
tabPanel("Assumptions for Model", verbatimTextOutput("glmassumption")),
tabPanel("Logistic Regression Output", verbatimTextOutput("logisticOutput")),
tabPanel("Cross Validation GLM Output", plotlyOutput("glmcvplot")),
tabPanel("Area Under the Curve Plot", plotlyOutput("glmaucplot"))
)
)
)
),
tabPanel("Decision Tree",
sidebarLayout(
sidebarPanel(
fileInput("treedecfile", "Choose a CSV or XLSX file", accept = c(".csv", ".xlsx")),
selectInput("targetdectree", "Select Target Column", choices = NULL),
sliderInput("dataSplittree",
"Data Split Ratio",
min = 0.1,
max = 0.9,
value = 0.7, # Default value, for instance, 70% for training and 30% for testing
step = 0.05,
ticks = FALSE,
animate = TRUE),
actionButton("rundectree", "Run Prior Steps"),
HTML("<div>
<h2>Karar Ağacı Paneli</h2>
<h3>Çıktı Nedir ve Neden Kullanılır?</h3> Bu panel, sınıflandırma ve regresyon problemleri için karar ağacı modellemesi yapar. Karar ağacı, veri setindeki özelliklerin farklı kombinasyonlarını kullanarak sonuçları tahmin eder ve bu tahminlerin nasıl yapıldığını açıklayabilir bir şekilde görselleştirir.</p>
<h3>Kullanım Adımları:</h3></p>
<ol>
<li><strong>Veri Dosyası Yükleme:</strong> Karar ağacı modellemesi için bir CSV veya XLSX dosyasını <code>fileInput</code> aracılığıyla yükleyin.</li>
<li><strong>Hedef Değişken Seçimi:</strong> Modelde tahmin edilecek hedef değişkeni seçin.</li>
<li><strong>Modellemeyi Çalıştırma:</strong> <code>actionButton</code> butonuna tıklayarak karar ağacı modellemesini ve ilgili ön adımları çalıştırın.</li>
</ol>
<h3>Kullanıcı Etkileşimi:</h3> Kullanıcılar, dosya yükledikten ve hedef değişkeni seçtikten sonra modellemeyi başlatır ve sonuçlar ana panelde görselleştirilir.</p>
<h3>Veri Bilimi Alanındaki Kullanımı:</h3> Karar ağacı, sınıflandırma ve regresyon problemlerinde yaygın olarak kullanılan bir yöntemdir. Ağaç yapısı, modelin kararlarını ve tahminlerini açıklayıcı bir şekilde sunar, bu da modelin yorumlanabilirliğini artırır.</p>
<h3>Desteklenen Dosya Tipleri:</h3> Kullanıcılar, analiz için CSV (.csv) veya Excel (.xlsx) formatında dosyalar yükleyebilirler.</p>
<h3>Sonuçların Yorumlanması:</h3> Elde edilen karar ağacı modeli, veri setindeki özelliklerin nasıl birleştirildiğini ve sonuçların nasıl tahmin edildiğini gösterir. Model özeti, karar ağacının performansını ve doğruluğunu değerlendirir. Ayrıca, ağacın budanması ve çapraz doğrulama gibi tekniklerle modelin genelleştirilmesi incelenir.</p>
<ul>
<li><strong>Model Özeti:</strong> Modelin performansını ve doğruluğunu değerlendirir.</li>
<li><strong>Karar Ağacı Görselleştirme:</strong> Karar ağacının nasıl yapılandırıldığını ve tahminlerin nasıl yapıldığını görsel olarak sunar.</li>
<li><strong>Çapraz Doğrulama:</strong> Modelin farklı veri setleri üzerindeki performansını test eder ve genelleştirme yeteneğini değerlendirir.</li>
<li><strong>Karışıklık Matrisi:</strong> Modelin sınıflandırma performansını detaylı bir şekilde gösterir.</li>
</ul>
<p>Bu özellikler, karar ağacı modellemesinin, veri setinden derinlemesine içgörüler elde etmek ve tahminler yapmak için nasıl kullanılabileceğini gösterir.</p>
</div>
")
),
mainPanel(
tabsetPanel(
tabPanel("Finding Right Model",
tabsetPanel(
tabPanel("Data Summary", verbatimTextOutput("dataSummarydt")),
tabPanel("Run First Model", verbatimTextOutput("rundectree")),
tabPanel("Before Pruning Model's Plot", plotOutput("dectreeplot", width = "100%", height = "750px")),
tabPanel("Cross-validation Plot", plotOutput("cvplot", width = "100%", height = "750px")),
tabPanel("Confusion Matrix", verbatimTextOutput("confMatrix")),
tabPanel("Pruned Tree", plotOutput("pruneddtree", width = "100%", height = "725px")),
)
),
tabPanel("Decision Tree Model Evaluation",
tabsetPanel(
tabPanel("Model Evaluation", verbatimTextOutput("cfdtpteva")),
))
)
),
)
),
tabPanel("Random Forest",
sidebarLayout(
sidebarPanel(
fileInput("rfinput", "Choose a CSV or XLSX file", accept = c(".csv", ".xlsx")),
actionButton("loadrf", "Load Data"),
selectInput("targetrf", "Select Target Column", choices = NULL),
selectizeInput("independentVarrf", "Select Independent Variables", choices = NULL, multiple = TRUE),
sliderInput("dataSplitrf",
"Data Split Ratio",
min = 0.1,
max = 0.9,
value = 0.7, # Default value, for instance, 70% for training and 30% for testing
step = 0.05,
ticks = FALSE,
animate = TRUE),
numericInput("mtryInput", "Mtry Value", value = 3, min = 1),
numericInput("ntreeInput", "Ntree Value", value = 14, min = 1),
actionButton("runrf", "Run Prior Steps"),
actionButton("predictBtn", "Predict"),
HTML("<div>
<h2>Rastgele Orman Paneli</h2>
<h3>Çıktı Nedir ve Neden Kullanılır?</h3> Bu panel, sınıflandırma ve regresyon problemleri için rastgele orman modellemesi yapar. Rastgele orman, birden fazla karar ağacını birleştirerek oluşturulan bir topluluk öğrenme yöntemidir. Bu yöntem, modelin genel hatası üzerindeki varyansı azaltır ve aşırı uyuma karşı dirençli olmasını sağlar.</p>
<h3>Kullanım Adımları:</h3></p>
<ol>
<li><strong>Veri Dosyası Yükleme:</strong> Rastgele orman modellemesi için bir CSV veya XLSX dosyasını <code>fileInput</code> aracılığıyla yükleyin.</li>
<li><strong>Hedef Değişken ve Bağımsız Değişkenler Seçimi:</strong> Modelde tahmin edilecek hedef değişkeni ve kullanılacak bağımsız değişkenleri seçin.</li>
<li><strong>Model Parametreleri Ayarlama:</strong> Modelin <code>mtry</code> ve <code>ntree</code> değerlerini ayarlayın.</li>
<li><strong>Modellemeyi Çalıştırma:</strong> <code>actionButton</code> butonlarına tıklayarak rastgele orman modellemesini ve tahmin işlemini çalıştırın.</li>
</ol>
<h3>Kullanıcı Etkileşimi:</h3> Kullanıcılar, dosya yükledikten, değişkenleri seçtikten ve model parametrelerini ayarladıktan sonra modellemeyi başlatır ve sonuçlar ana panelde görselleştirilir.</p>
<h3>Veri Bilimi Alanındaki Kullanımı:</h3> Rastgele orman, sınıflandırma ve regresyon gibi çeşitli makine öğrenmesi problemlerinde kullanılır. Modelin oluşturduğu birden fazla karar ağacının sonuçlarını birleştirerek daha doğru tahminler yapılmasını sağlar.</p>
<h3>Desteklenen Dosya Tipleri:</h3> Kullanıcılar, analiz için CSV (.csv) veya Excel (.xlsx) formatında dosyalar yükleyebilirler.</p>
<h3>Sonuçların Yorumlanması:</h3> Elde edilen rastgele orman modeli, bağımsız değişkenlerin hedef değişken üzerindeki etkilerini ve önem derecelerini gösterir. Model özeti, rastgele ormanın performansını ve doğruluğunu değerlendirir. Ayrıca, modelin tahminlerini ve bu tahminlerin gerçek değerlerle karşılaştırılmasını içeren görselleştirmeler sunar.</p>
<ul>
<li><strong>Model Özeti:</strong> Modelin performansını ve doğruluğunu değerlendirir.</li>
<li><strong>Özellik Önemi:</strong> Bağımsız değişkenlerin model üzerindeki etkisinin ve öneminin değerlendirilmesi.</li>
<li><strong>Model Tahminleri:</strong> Modelin tahmin ettiği sonuçlar ve bu tahminlerin gerçek değerlerle karşılaştırılması.</li>
</ul>
<p>Bu özellikler, rastgele orman modellemesinin, veri setinden derinlemesine içgörüler elde etmek ve tahminler yapmak için nasıl kullanılabileceğini gösterir.</p>
</div>
")
),
mainPanel(
tabsetPanel(
tabPanel("Data Summary", verbatimTextOutput("dataSummaryrf")),
tabPanel("Run First Model", verbatimTextOutput("runrf")),
tabPanel("Feature Importance Plot", plotlyOutput("importancePlot", width = "100%", height = "625px")),
tabPanel("Model Prediction",
tabsetPanel(
tabPanel("Predicted Result", verbatimTextOutput("predictionOutput")),
tabPanel("Predicted Plot", plotlyOutput("performancePlot", width = "100%", height = "625px"))
)
)
)
)
)
),
tabPanel("Bagging",
sidebarLayout(
sidebarPanel(
fileInput("bginput", "Choose a CSV or XLSX file", accept = c(".csv", ".xlsx")),
actionButton("loadbg", "Load Data"),
selectInput("targetbg", "Select Target Column", choices = NULL),
selectizeInput("independentVarbg", "Select Independent Variables", choices = NULL, multiple = TRUE),
sliderInput("dataSplitbg",
"Data Split Ratio",
min = 0.1,
max = 0.9,
value = 0.7, # Default value, for instance, 70% for training and 30% for testing
step = 0.05,
ticks = FALSE,
animate = TRUE),
numericInput("nbaggInput", "Nbagg Value", value = 14, min = 1),
actionButton("runbg", "Run Prior Steps"),
actionButton("baggingBtn", "Predict"),
HTML("<div>
<h2>Çanta (Bagging) Paneli</h2>
<h3>Çıktı Nedir ve Neden Kullanılır?</h3>
<p>Bu panel, çok sayıda karar ağacı modelini birleştirerek güçlü bir makine öğrenimi modeli oluşturan çanta (bagging) yöntemini kullanır. Çanta yöntemi, modelin genel hatasını azaltarak ve aşırı uyum (overfitting) riskini minimize ederek tahminlerin doğruluğunu artırır.</p>
<h3>Kullanım Adımları:</h3>
<ol>
<li><strong>Veri Dosyası Yükleme:</strong> CSV veya XLSX formatında bir dosya yükleyerek analize başlayın.</li>
<li><strong>Hedef ve Bağımsız Değişkenlerin Seçilmesi:</strong> Modelde kullanılacak hedef ve bağımsız değişkenleri seçin.</li>
<li><strong>Model Parametrelerinin Ayarlanması:</strong> Modelin performansını etkileyen parametreleri (örneğin, çanta iterasyon sayısı) ayarlayın.</li>
<li><strong>Modelin Eğitilmesi ve Tahmin Yapılması:</strong> Modeli eğitin ve test veri seti üzerinde tahminlerde bulunun.</li>
</ol>
<h3>Kullanıcı Etkileşimi:</h3>
<p>Kullanıcılar, veri setini yükledikten ve gerekli seçimleri yaptıktan sonra, modeli eğitmek ve tahminler yapmak için belirtilen butonlara tıklar. Sonuçlar, ana panelde görselleştirilir ve detaylı analizler sunulur.</p>
<h3>Veri Bilimi ve Makine Öğrenmesindeki Uygulamaları:</h3>
<p>Çanta yöntemi, hem sınıflandırma hem de regresyon problemleri için yaygın olarak kullanılan bir topluluk öğrenme yöntemidir. Bu yöntem, veri setlerinden elde edilen bilgiyi maksimize eder ve modelin genel performansını iyileştirir.</p>
<h3>Desteklenen Dosya Tipleri ve Seçenekler:</h3>
<p>Panel, kullanıcıların CSV (.csv) veya Excel (.xlsx) formatındaki dosyaları yüklemesine izin verir. Bu, veri bilimcilerin ve analistlerin çeşitli veri setleri üzerinde çalışabilmesi için esneklik sağlar.</p>
<h3>Sonuçların Yorumlanması:</h3>
<p>Modelin performansı, çeşitli metrikler kullanılarak değerlendirilir. Özellik önem dereceleri, hangi değişkenlerin model tahminlerini en çok etkilediğini gösterir. Ayrıca, tahmin edilen sonuçlar ve modelin genel doğruluğu hakkında bilgiler sunulur.</p>
<ul>
<li><strong>Model Özeti:</strong> Modelin performans metrikleri ve ayarlanan parametreler hakkında bilgi verir.</li>
<li><strong>Özellik Önemi:</strong> Model tahminlerinde hangi bağımsız değişkenlerin önemli olduğunu gösterir.</li>
<li><strong>Tahmin Sonuçları:</strong> Modelin test veri seti üzerinde yaptığı tahminler ve bu tahminlerin gerçek değerlerle karşılaştırılması.</li>
</ul>
<p>Bu özellikler, çanta yönteminin veri setlerinden maksimum bilgiyi çıkararak tahminlerin doğruluğunu artırma potansiyelini gösterir.</p>
</div>")
),
mainPanel(
tabsetPanel(
tabPanel("Data Summary", verbatimTextOutput("dataSummarybg")),
tabPanel("Run First Model", verbatimTextOutput("runbg")),
tabPanel("Feature Importance Plot", plotlyOutput("importancePlotbg", width = "100%", height = "625px")),
tabPanel("Model Prediction",
tabsetPanel(
tabPanel("Predicted Result", verbatimTextOutput("predictionOutputbg")),
tabPanel("Predicted Plot", plotlyOutput("performancePlotbg", width = "100%", height = "625px"))
)
)
)
)
)
),
tabPanel("Boosting",
sidebarLayout(
sidebarPanel(
fileInput("bsinput", "Choose a CSV or XLSX file", accept = c(".csv", ".xlsx")),
actionButton("loadbs", "Load Data"),
selectInput("targetbs", "Select Target Column", choices = NULL),
selectizeInput("independentVarbs", "Select Independent Variables", choices = NULL, multiple = TRUE),
sliderInput("dataSplitbs",
"Data Split Ratio",
min = 0.1,
max = 0.9,
value = 0.7, # Default value, for instance, 70% for training and 30% for testing
step = 0.05,
ticks = FALSE,
animate = TRUE),
numericInput("nbsInput", "N Trees Value", value = 14, min = 1),
numericInput("nbsdepth", "Interaction Depth", value = 4, min = 1),
numericInput("nbshr", "Shrinkage", value = 0.03, min = 0.0001),
actionButton("runbs", "Run Prior Steps"),
actionButton("boostingBtn", "Predict"),
HTML("<div>
<h2>Artırma (Boosting) Paneli</h2>
<h3>Çıktı Nedir ve Neden Kullanılır?</h3>
<p>Bu panel, zayıf öğrenicileri güçlü bir model oluşturmak üzere birleştiren artırma (boosting) yöntemini kullanır. Artırma, bir dizi zayıf modeli sıralı olarak eğitir ve her birini öncekinin hatalarını düzeltmeye odaklanır, böylece modelin genel performansı artar.</p>
<h3>Kullanım Adımları:</h3>
<ol>
<li><strong>Veri Dosyası Yükleme:</strong> CSV veya XLSX formatında bir dosya yükleyerek analize başlayın.</li>
<li><strong>Hedef ve Bağımsız Değişkenlerin Seçilmesi:</strong> Modelde kullanılacak hedef ve bağımsız değişkenleri seçin.</li>
<li><strong>Model Parametrelerinin Ayarlanması:</strong> Modelin performansını etkileyen parametreleri (örneğin, ağaç sayısı, etkileşim derinliği, küçültme) ayarlayın.</li>
<li><strong>Modelin Eğitilmesi ve Tahmin Yapılması:</strong> Modeli eğitin ve test veri seti üzerinde tahminlerde bulunun.</li>
</ol>
<h3>Kullanıcı Etkileşimi:</h3>
<p>Kullanıcılar, veri setini yükledikten ve gerekli seçimleri yaptıktan sonra, modeli eğitmek ve tahminler yapmak için belirtilen butonlara tıklar. Sonuçlar, ana panelde görselleştirilir ve detaylı analizler sunulur.</p>
<h3>Veri Bilimi ve Makine Öğrenmesindeki Uygulamaları:</h3>
<p>Artırma yöntemi, genellikle sınıflandırma ve regresyon problemlerinde kullanılır ve modelin aşırı uyuma (overfitting) eğilimini azaltırken tahmin doğruluğunu artırır.</p>
<h3>Desteklenen Dosya Tipleri ve Seçenekler:</h3>
<p>Panel, kullanıcıların CSV (.csv) veya Excel (.xlsx) formatındaki dosyaları yüklemesine izin verir. Bu, veri bilimcilerin ve analistlerin çeşitli veri setleri üzerinde çalışabilmesi için esneklik sağlar.</p>
<h3>Sonuçların Yorumlanması:</h3>
<p>Modelin performansı, çeşitli metrikler kullanılarak değerlendirilir. Özellik önem dereceleri, hangi değişkenlerin model tahminlerini en çok etkilediğini gösterir. Ayrıca, tahmin edilen sonuçlar ve modelin genel doğruluğu hakkında bilgiler sunulur.</p>
<ul>
<li><strong>Model Özeti:</strong> Modelin performans metrikleri ve ayarlanan parametreler hakkında bilgi verir.</li>
<li><strong>Özellik Önemi:</strong> Model tahminlerinde hangi bağımsız değişkenlerin önemli olduğunu gösterir.</li>
<li><strong>Tahmin Sonuçları:</strong> Modelin test veri seti üzerinde yaptığı tahminler ve bu tahminlerin gerçek değerlerle karşılaştırılması.</li>
</ul>
<p>Bu özellikler, artırma yönteminin veri setlerinden maksimum bilgiyi çıkararak tahminlerin doğruluğunu artırma potansiyelini gösterir.</p>
</div>")
),
mainPanel(
tabsetPanel(
tabPanel("Data Summary", verbatimTextOutput("dataSummarybs")),
tabPanel("Run First Model", verbatimTextOutput("runbs")),
tabPanel("Feature Importance Plot", plotlyOutput("importancePlotbs", width = "100%", height = "625px")),
tabPanel("Model Prediction",
tabsetPanel(
tabPanel("Predicted Result", verbatimTextOutput("predictionOutputbs")),
tabPanel("Predicted Plot", plotlyOutput("performancePlotbs", width = "100%", height = "625px"))
)
)
)
)
)
),
tabPanel("MARS",
sidebarLayout(
sidebarPanel(
fileInput("msinput", "Choose a CSV or XLSX file", accept = c(".csv", ".xlsx")),
actionButton("loadms", "Load Data"),
selectInput("targetms", "Select Target Column", choices = NULL),
selectizeInput("independentVarms", "Select Independent Variables", choices = NULL, multiple = TRUE),
sliderInput("dataSplitms",
"Data Split Ratio",
min = 0.1,
max = 0.9,
value = 0.7, # Default value, for instance, 70% for training and 30% for testing
step = 0.05,
ticks = FALSE,
animate = TRUE),
actionButton("runms", "Run Prior Steps"),
actionButton("marsBtn", "Predict"),
HTML("<div>
<h2>MARS Paneli</h2>
<h3>Çıktı Nedir ve Neden Kullanılır?</h3>
<p>Bu panel, Çoklu Adaptif Regresyon Spline'ları (MARS) kullanarak veri setinden karmaşık ilişkileri ve etkileşimleri yakalayabilen bir model oluşturur. MARS, lineer olmayan ilişkileri ve değişkenler arasındaki etkileşimleri otomatik olarak tanımlayabilen esnek bir yöntemdir.</p>
<h3>Kullanım Adımları:</h3>
<ol>
<li><strong>Veri Dosyası Yükleme:</strong> Analize başlamak için CSV veya XLSX formatında bir dosya yükleyin.</li>
<li><strong>Hedef ve Bağımsız Değişkenlerin Seçilmesi:</strong> Modelde kullanılacak hedef ve bağımsız değişkenleri belirleyin.</li>
<li><strong>Veri Bölme Oranının Ayarlanması:</strong> Modelin eğitim ve test veri setlerine bölünme oranını ayarlayın.</li>
<li><strong>Modelin Eğitilmesi ve Değerlendirilmesi:</strong> Modeli eğitip performansını değerlendirin. Modelin doğruluğunu ve bağımsız değişkenlerin önemini inceleyin.</li>
</ol>
<h3>Kullanıcı Etkileşimi:</h3>
<p>Kullanıcılar, analiz için gerekli veri ve parametreleri girer ve modeli eğitmek için belirtilen adımları takip eder. Sonuçlar, kullanıcıya modelin performansı ve değişkenlerin önemi hakkında detaylı bilgiler sunar.</p>
<h3>Veri Bilimi ve Makine Öğrenmesindeki Uygulamaları:</h3>
<p>MARS yöntemi, özellikle karmaşık ilişkilerin ve değişken etkileşimlerinin olduğu durumlarda tercih edilen bir modelleme tekniğidir. Hem sınıflandırma hem de regresyon problemleri için uygundur.</p>
<h3>Desteklenen Dosya Tipleri ve Seçenekler:</h3>
<p>Panel, kullanıcıların analiz için CSV (.csv) veya Excel (.xlsx) formatlarında veri dosyaları yüklemesine olanak tanır, bu da farklı veri setleri üzerinde çalışmayı kolaylaştırır.</p>
<h3>Sonuçların Yorumlanması:</h3>
<p>Modelin performansı, çeşitli metrikler kullanılarak değerlendirilir. Bağımsız değişkenlerin model üzerindeki etkisi, özellik önem dereceleriyle gösterilir. Ayrıca, modelin genel doğruluğu ve tahmin edilen sonuçlar hakkında bilgiler sağlanır.</p>
<ul>
<li><strong>Model Özeti:</strong> Modelin performans metrikleri ve ayarlanan parametreler hakkında bilgi sağlar.</li>
<li><strong>Özellik Önemi:</strong> Hangi bağımsız değişkenlerin model tahminlerini en çok etkilediğini gösterir.</li>
<li><strong>Tahmin Sonuçları:</strong> Modelin test veri seti üzerinde yaptığı tahminler ve bu tahminlerin gerçek değerlerle karşılaştırılması.</li>
</ul>
<p>Bu panel, MARS modelinin veri setlerinden karmaşık ilişkileri çıkararak tahminlerin doğruluğunu artırma potansiyeline sahip olduğunu gösterir.</p>
</div>")
),
mainPanel(
tabsetPanel(
tabPanel("Data Summary", verbatimTextOutput("dataSummaryms")),
tabPanel("Run First Model", verbatimTextOutput("runms")),
tabPanel("Feature Importance Plot", plotlyOutput("importancePlotms", width = "100%", height = "625px")),
tabPanel("Model Prediction",
tabsetPanel(
tabPanel("Predicted Result", verbatimTextOutput("predictionOutputms")),
tabPanel("Predicted Plot", plotlyOutput("performancePlotms", width = "100%", height = "625px"))
)
)
)
)
)
),
tabPanel("Ridge Regression",
sidebarLayout(
sidebarPanel(
fileInput("rrinput", "Choose a CSV or XLSX file", accept = c(".csv", ".xlsx")),
actionButton("loadrr", "Load Data"),
selectInput("targetrr", "Select Target Column", choices = NULL),
selectizeInput("independentVarrr", "Select Independent Variables", choices = NULL, multiple = TRUE),
sliderInput("dataSplitrr",
"Data Split Ratio",
min = 0.1,
max = 0.9,
value = 0.7, # Default value, for instance, 70% for training and 30% for testing
step = 0.05,
ticks = FALSE,
animate = TRUE),
actionButton("runrr", "Run Prior Steps"),
actionButton("RidgeBtn", "Predict"),
HTML("<div>
<h2>Ridge Regresyon Paneli</h2>
<h3>Çıktı Nedir ve Neden Kullanılır?</h3>
<p>Ridge Regresyonu, çoklu doğrusal regresyon modellerinde aşırı uyumun önlenmesine yardımcı olan bir düzenlileştirme tekniğidir. Bu panel, yüksek boyutlu veri setlerinde bile değişkenler arası ilişkileri daha iyi anlamak için Ridge Regresyon modelini kullanır.</p>
<h3>Kullanım Adımları:</h3>
<ol>
<li><strong>Veri Dosyası Yükleme:</strong> Analize başlamak için uygun bir CSV veya XLSX dosyası yükleyin.</li>
<li><strong>Hedef ve Bağımsız Değişkenlerin Seçimi:</strong> Modelde hedef değişken olarak neyin tahmin edileceğini ve hangi bağımsız değişkenlerin kullanılacağını seçin.</li>
<li><strong>Veri Bölme Oranı Ayarlama:</strong> Veri setinin eğitim ve test seti olarak nasıl bölüneceğini belirleyin.</li>
<li><strong>Model Eğitimi ve Değerlendirme:</strong> Modeli eğitin ve performansını değerlendirin. Modelin nasıl performans gösterdiğini ve hangi değişkenlerin önemli olduğunu öğrenin.</li>
</ol>
<h3>Kullanıcı Etkileşimi:</h3>
<p>Kullanıcılar, panel aracılığıyla veri setlerini yükleyebilir, model parametrelerini ayarlayabilir ve modelin performansını değerlendirme sonuçlarını görüntüleyebilir. Bu süreç, veri bilimi projelerinde kritik öneme sahip olan modelleme ve analiz işlemlerini kolaylaştırır.</p>
<h3>Veri Bilimi ve Makine Öğrenmesindeki Uygulamaları:</h3>
<p>Ridge Regresyonu, özellikle çok sayıda özellik içeren veri setlerinde ve değişkenler arasında yüksek korelasyon olduğunda kullanışlıdır. Model karmaşıklığını kontrol ederek aşırı uyumu azaltır ve modelin genelleştirme yeteneğini artırır.</p>
<h3>Desteklenen Dosya Tipleri ve Seçenekler:</h3>
<p>Panel, CSV (.csv) ve Excel (.xlsx) formatlarındaki veri dosyalarını destekler, bu da kullanıcıların çeşitli veri kaynaklarından kolayca veri yüklemesine olanak tanır.</p>
<h3>Sonuçların Yorumlanması:</h3>
<p>Modelin başarısı, RMSE, R-kare gibi metriklerle değerlendirilir. Ayrıca, değişkenlerin model üzerindeki etkisi ve önemi hakkında bilgiler sunulur, bu da hangi özelliklerin hedef değişkeni en çok etkilediğini anlamaya yardımcı olur.</p>
<ul>
<li><strong>Model Özeti:</strong> Modelin ayar parametreleri, performans metrikleri ve doğrulama sonuçları hakkında ayrıntılı bilgi sağlar.</li>
<li><strong>Özellik Önemi:</strong> Model tahminlerinde hangi bağımsız değişkenlerin daha etkili olduğunu gösterir.</li>
<li><strong>Tahmin Sonuçları:</strong> Modelin test veri seti üzerindeki tahminleri ve bu tahminlerin gerçek değerlerle olan karşılaştırması.</li>
</ul>
<p>Ridge Regresyon paneli, modelin veri setindeki özellikler arasındaki karmaşık ilişkileri nasıl yakaladığını ve tahminlerin doğ
ruluğunu nasıl artırdığını gösterir.</p>
</div>")
),
mainPanel(
tabsetPanel(
tabPanel("Data Summary", verbatimTextOutput("dataSummaryrr")),
tabPanel("Run First Model", verbatimTextOutput("runrr")),
tabPanel("Feature Importance Plot", plotlyOutput("importancePlotrr", width = "100%", height = "625px")),
tabPanel("Model Prediction",
tabsetPanel(
tabPanel("Predicted Result", verbatimTextOutput("predictionOutputrr")),
tabPanel("Predicted Plot", plotlyOutput("performancePlotrr", width = "100%", height = "625px"))
)
)
)
)
)
),
tabPanel("LASSO Regression",
sidebarLayout(
sidebarPanel(
fileInput("lsinput", "Choose a CSV or XLSX file", accept = c(".csv", ".xlsx")),
actionButton("loadls", "Load Data"),
selectInput("targetls", "Select Target Column", choices = NULL),
selectizeInput("independentVarls", "Select Independent Variables", choices = NULL, multiple = TRUE),
sliderInput("dataSplitls",
"Data Split Ratio",
min = 0.1,
max = 0.9,
value = 0.7, # Default value, for instance, 70% for training and 30% for testing
step = 0.05,
ticks = FALSE,
animate = TRUE),
actionButton("runls", "Run Prior Steps"),
actionButton("LassoBtn", "Predict"),
HTML("<div>
<h2>LASSO Regresyon Paneli</h2>
<h3>Çıktı Nedir ve Neden Kullanılır?</h3>
<p>LASSO Regresyonu, özellik seçimi ve düzenlileştirme sağlayarak modelin karmaşıklığını azaltır ve genelleştirme kabiliyetini artırır. Bu panel, veri setlerindeki değişkenler arasındaki ilişkileri anlamak ve önemli özellikleri belirlemek için LASSO Regresyon modelini kullanır.</p>
<h3>Kullanım Adımları:</h3>
<ol>
<li><strong>Veri Dosyası Yükleme:</strong> Analize başlamak için bir CSV veya XLSX dosyası yükleyin.</li>
<li><strong>Hedef ve Bağımsız Değişkenlerin Seçimi:</strong> Modelin neyi tahmin edeceğini ve hangi bağımsız değişkenlerin kullanılacağını seçin.</li>
<li><strong>Veri Bölme Oranı Ayarlama:</strong> Eğitim ve test setlerinin nasıl bölüneceğini belirleyin.</li>
<li><strong>Model Eğitimi ve Değerlendirme:</strong> Modeli eğitin, performansını değerlendirin ve önemli özellikleri keşfedin.</li>
</ol>
<h3>Kullanıcı Etkileşimi:</h3>
<p>Kullanıcılar, veri setlerini yükleyebilir, model parametrelerini ayarlayabilir ve modelin nasıl performans gösterdiğini anlayabilir. Panel, modelleme ve analiz işlemlerini kolaylaştırarak veri bilimi projelerinde değerli bir araç sunar.</p>
<h3>Veri Bilimi ve Makine Öğrenmesindeki Uygulamaları:</h3>
<p>LASSO Regresyonu, özellikle çok sayıda özelliği olan ve değişkenler arasında yüksek korelasyon bulunan veri setlerinde kullanışlıdır. Model, önemsiz özellikleri sıfıra yaklaştırarak özellik seçimi yapar ve daha anlamlı tahminler sağlar.</p>
<h3>Desteklenen Dosya Tipleri ve Seçenekler:</h3>
<p>Panel, CSV (.csv) ve Excel (.xlsx) formatlarını destekler, bu da kullanıcıların farklı veri kaynaklarından kolaylıkla veri yüklemesine olanak tanır.</p>
<h3>Sonuçların Yorumlanması:</h3>
<p>Modelin başarısı, RMSE, R-kare gibi metriklerle değerlendirilir. Ayrıca, modelin hangi değişkenleri önemli bulduğu ve tahminlerin doğruluğu hakkında bilgi sunulur.</p>
<ul>
<li><strong>Model Özeti:</strong> Modelin performans metrikleri, ayar parametreleri ve doğrulama sonuçları hakkında detaylı bilgiler sağlar.</li>
<li><strong>Özellik Önemi:</strong> Model tahminlerinde hangi bağımsız değişkenlerin daha etkili olduğunu belirler.</li>
<li><strong>Tahmin Sonuçları:</strong> Modelin test veri seti üzerindeki tahmin sonuçları ve bu tahminlerin gerçek değerlerle karşılaştırılması.</li>
</ul>
<p>LASSO Regresyon paneli, modelin veri setindeki özellikler arasındaki ilişkileri nasıl çözümlendiğini ve tahminlerin doğruluğunu nasıl artırdığını gösterir.</p>
</div>")
),
mainPanel(
tabsetPanel(
tabPanel("Data Summary", verbatimTextOutput("dataSummaryls")),
tabPanel("Run First Model", verbatimTextOutput("runls")),
tabPanel("Feature Importance Plot", plotlyOutput("importancePlotls", width = "100%", height = "625px")),
tabPanel("Model Prediction",
tabsetPanel(
tabPanel("Predicted Result", verbatimTextOutput("predictionOutputls")),
tabPanel("Predicted Plot", plotlyOutput("performancePlotls", width = "100%", height = "625px"))
)
)
)
)
)
)
)
)
server <- function(input, output, session) {
##Supervised Learning
###Simple Linear Regression
# Define reactive values for each assumption test
shapiroTestResult <- reactiveVal()
ncvTestResult <- reactiveVal()
linearityPlot <- reactiveVal()
durbinWatsonTestResult <- reactiveVal()
modelslr <- reactiveVal()
dataslr <- reactiveVal(NULL)
modelslreva <- reactiveVal(NULL)
dataslreva <- reactiveVal(NULL)
# Fix the data loading and cleaning part
observeEvent(input$loadslr, {
file <- input$slrinput
if (!is.null(file)) {
data_slr <- read_data(file$datapath)
data_slr <- clean_column_names(data_slr)
dataslr(data_slr) # Update the reactive value correctly
updateSelectInput(session, "targetslr", choices = colnames(data_slr))
updateSelectizeInput(session, "independentVar", choices = setdiff(colnames(data_slr), input$targetslr))
}
})
output$slrsummary <- renderPrint({
req(dataslr())
summary(dataslr())
})
# Observe the action button for triggering assumption tests
observeEvent(input$slrassumption, {
req(dataslr(), input$targetslr, input$independentVar)
data_slr <- dataslr()
target_col <- input$targetslr
independent_var <- input$independentVar
# Ensure the target and independent variables are available
if (is.null(data_slr[[target_col]]) || is.null(data_slr[[independent_var]])) {
return("Target or independent variable not found in the data.")
}
# Filter out rows where any character column is an empty string
data_slr <- data_slr %>% dplyr::select(all_of(target_col), all_of(independent_var)) %>%
na.omit()
# Split the data into training and testing sets
set.seed(123)
split_ratio <- input$dataSplitslr
training.samples <- createDataPartition(data_slr[[target_col]], p = split_ratio, list = FALSE)
train_data <- data_slr[training.samples, ]
test_data <- data_slr[-training.samples, ]
# Fit the linear regression model
fitted_model <- lm(reformulate(independent_var, target_col), data = train_data)
modelslr(fitted_model) # Update the reactive value
# Print the summary of the model
summary(fitted_model)
})
output$shapiroTest <- renderPrint({
req(dataslr(), input$targetslr, input$independentVar)
data_slr <- dataslr()
target_col <- input$targetslr
independent_var <- input$independentVar
# Ensure the target and independent variables are available
if (is.null(data_slr[[target_col]]) || is.null(data_slr[[independent_var]])) {
return("Target or independent variable not found in the data.")
}
# Filter out rows where any character column is an empty string
data_slr <- data_slr %>% dplyr::select(all_of(target_col), all_of(independent_var)) %>%
na.omit()
# Split the data into training and testing sets
set.seed(123)
split_ratio <- input$dataSplitslr
training.samples <- createDataPartition(data_slr[[target_col]], p = split_ratio, list = FALSE)
train_data <- data_slr[training.samples, ]
test_data <- data_slr[-training.samples, ]
# Fit the linear regression model
fitted_model <- lm(reformulate(independent_var, target_col), data = train_data)
modelslr(fitted_model) # Update the reactive value
# Print the summary of the model
summary(fitted_model)
# Shapiro-Wilk Test for Normality
cat("\nShapiro-Wilk Test for Normality of Residuals:\n")
shap_Test <- shapiro.test(fitted_model$residuals)
print(shap_Test)
if (shap_Test$p.value > 0.05) {
cat("Result: Residuals appear to be normally distributed.\n")
} else {
cat("Result: Residuals may not be normally distributed.\n")
}
})
output$ncvTest <- renderPrint({
req(modelslr()) # Ensure modelslr is available
fitted_model <- modelslr() # Access the model
# Perform Breusch-Pagan Test for Heteroscedasticity
cat("\nBreusch-Pagan Test for Heteroscedasticity:\n")
bp_test_result <- tryCatch({
bptest(fitted_model)
}, error = function(e) {
cat("Error in conducting Breusch-Pagan test: ", e$message, "\n")
NULL # Return NULL in case of error
})
if (!is.null(bp_test_result) && !is.na(bp_test_result$p.value)) {
print(bp_test_result)
if (bp_test_result$p.value > 0.05) {
cat("Result: No evidence of heteroscedasticity.\n")
} else {
cat("Result: There may be heteroscedasticity.\n")
}
} else {
cat("Result: Breusch-Pagan test could not be conducted.\n")
}
})
output$linearityPlotOutput <- renderPlotly({
req(dataslr(), input$targetslr, input$independentVar)
data_slr <- dataslr()
target_col <- input$targetslr
independent_var <- input$independentVar
# Ensure the target and independent variables are available
if (is.null(data_slr[[target_col]]) || is.null(data_slr[[independent_var]])) {
return("Target or independent variable not found in the data.")
}
# Filter out rows where any character column is an empty string
data_slr <- data_slr %>% dplyr::select(all_of(target_col), all_of(independent_var)) %>%
na.omit()
# Split the data into training and testing sets
set.seed(123)
split_ratio <- input$dataSplitslr
training.samples <- createDataPartition(data_slr[[target_col]], p = split_ratio, list = FALSE)
train_data <- data_slr[training.samples, ]
test_data <- data_slr[-training.samples, ]
# Fit the linear regression model
fitted_model <- lm(reformulate(independent_var, target_col), data = train_data)
# Create the ggplot object for the linearity plot
ggplot_object <- ggplot(train_data, aes_string(x = independent_var, y = target_col)) +
geom_point(color = "darkorange") +
geom_smooth(method = "lm", se = FALSE, color = "dodgerblue") +
ggtitle("Linearity") +
scale_x_continuous(name = independent_var) +
scale_y_continuous(name = target_col)
# Convert ggplot object to plotly and render
ggplotly(ggplot_object)
})
output$durbinWatsonTest <- renderPrint({
req(modelslr()) # Ensure modelslr is available
fitted_model <- modelslr() # Access the model
# Perform Durbin-Watson Test for Autocorrelation
dw_test_result <- tryCatch({
lmtest::dwtest(fitted_model)
}, error = function(e) {
cat("Error in conducting Durbin-Watson test: ", e$message, "\n")
NULL # Return NULL in case of error
})
if (!is.null(dw_test_result) && !is.na(dw_test_result$p.value)) {
cat("\nDurbin-Watson Test for Autocorrelation:\n")
print(dw_test_result)
if (dw_test_result$p.value > 0.05) {
cat("Result: No evidence of autocorrelation.\n")
} else {
cat("Result: There may be autocorrelation in the residuals.\n")
}
} else {
cat("Result: Durbin-Watson test could not be conducted.\n")
}
})
# Server function to create diagnostic plots
output$residualsFittedPlot <- renderPlotly({
req(modelslr())
fitted_model <- modelslr()
p <- ggplot(fitted_model, aes(.fitted, .resid)) +
geom_point(color = "darkorange") +
geom_smooth(method = "lm", se = FALSE, color = "dodgerblue") +
labs(title = "Residuals vs Fitted", x = "Fitted Values", y = "Residuals")
ggplotly(p)
})
output$qqPlot <- renderPlotly({
req(modelslr())
fitted_model <- modelslr()
p <- ggplot(fitted_model, aes(sample = .stdresid)) +
stat_qq(color = "darkorange") +
stat_qq_line(color = "dodgerblue") +
labs(title = "Normal Q-Q")
ggplotly(p)
})
output$scaleLocationPlot <- renderPlotly({
req(modelslr())
fitted_model <- modelslr()
p <- ggplot(fitted_model, aes(.fitted, sqrt(abs(.resid)))) +
geom_point(color = "darkorange") +
geom_smooth(method = "lm", se = FALSE, color = "dodgerblue") +
labs(title = "Scale-Location", x = "Fitted Values", y = "Sqrt(|Residuals|)")
ggplotly(p)
})
output$residualsLeveragePlot <- renderPlotly({
req(modelslr())
fitted_model <- modelslr()
p <- ggplot(fitted_model, aes(.hat, .stdresid)) +
geom_point(aes(size = .cooksd), shape = 1, color = "darkorange") +
geom_smooth(method = "lm", se = FALSE, color = "dodgerblue") +
labs(title = "Residuals vs Leverage", x = "Leverage", y = "Standardized Residuals")
ggplotly(p)
})
# Define the reactive value for the data and model at the top of the server function
dataslreva <- reactiveVal(NULL)
modelslreva <- reactiveVal(NULL)
test_data_slr <- reactiveVal(NULL)
# Load and clean data
observeEvent(input$loadslr, {
req(input$slrinput)
file <- input$slrinput
if (!is.null(file)) {
data_slreva <- read_data(file$datapath)
data_slreva <- clean_column_names(data_slreva)
dataslreva(data_slreva) # Update the reactive value correctly
updateSelectInput(session, "targetslr", choices = colnames(data_slreva))
updateSelectizeInput(session, "independentVar", choices = setdiff(colnames(data_slreva), input$targetslr))
}
})
observeEvent(input$slrmodel, {
req(dataslreva(), input$targetslr, input$independentVar)
data_slreva <- dataslreva()
target_col <- input$targetslr
independent_var <- input$independentVar
# Ensure the target and independent variables are available
if (is.null(data_slreva[[target_col]]) || is.null(data_slreva[[independent_var]])) {
return("Target or independent variable not found in the data.")
}
# Filter out rows with NAs and split the data
data_slreva <- na.omit(data_slreva[, c(target_col, independent_var)])
set.seed(123)
split_ratio <- input$dataSplitslr
training.samples <- createDataPartition(data_slreva[[target_col]], p = split_ratio, list = FALSE)
train_data <- data_slreva[training.samples, ]
test_data <- data_slreva[-training.samples, ]
# Fit the linear regression model and update the reactive value
fitted_modelslr <- lm(reformulate(independent_var, target_col), data = train_data)
modelslreva(fitted_modelslr)
# After fitting the model, update test_data_slr reactive value
test_data_slr(test_data) # Store test_data in the reactive value
})
output$slrmodeleva <- renderPrint({
req(modelslreva())
fitted_modelslr <- modelslreva()
if (inherits(fitted_modelslr, "lm")) {
# Model Summary
cat("Model Summary:\n")
print(summary(fitted_modelslr))
# Interpretation of the key components
cat("\nInterpretation:\n")
cat("1. Coefficients: Estimates of the model parameters.\n")
cat(" - Intercept: Represents the predicted value of the dependent variable when all independent variables are zero.\n")
cat(" - Slope: Represents the change in the dependent variable for a one-unit change in the independent variable.\n")
cat("2. Residual standard error: Measures the quality of the linear regression fit.\n")
cat(" - Lower values indicate a better fit.\n")
cat("3. Multiple R-squared: Indicates the proportion of variance in the dependent variable explained by the model.\n")
cat(" - Values closer to 1 suggest a better explanatory power of the model.\n")
cat("4. F-statistic and p-value: Test the overall significance of the model.\n")
cat(" - A low p-value (< 0.05) indicates that the model is statistically significant.\n")
# Additional specific interpretations can be added here
} else {
"Model has not been run or is not a linear model."
}
})
# Render print for correlation coefficient
output$corcoefslr <- renderPrint({
req(modelslreva(), test_data_slr()) # Ensure model and test data are available
fitted_modelslr <- modelslreva()
test_data <- test_data_slr() # Access the test data
target_col <- input$targetslr
independent_var <- input$independentVar
# Prediction and calculation of correlation coefficient
lm_predict <- predict(fitted_modelslr, newdata = test_data)
actual_pred <- data.frame(actuals = test_data[[target_col]], predicted = lm_predict)
cor_accuracy <- cor(actual_pred$actuals, actual_pred$predicted)
# Output with interpretation
cat("Correlation Coefficient between Actual and Predicted Values:\n")
cat(cor_accuracy, "\n\n")
# Interpretation of the correlation coefficient
cat("Interpretation:\n")
if(cor_accuracy > 0.75) {
cat("The model has a strong positive correlation between actual and predicted values.\n")
} else if(cor_accuracy > 0.5) {
cat("The model has a moderate positive correlation between actual and predicted values.\n")
} else if(cor_accuracy > 0.25) {
cat("The model has a weak positive correlation between actual and predicted values.\n")
} else {
cat("The model shows little to no correlation between actual and predicted values.\n")
}
cat("Note: A correlation coefficient close to 1 indicates a strong positive relationship, while values closer to 0 indicate weaker relationships.\n")
})
output$confintslr <- renderPrint({
req(modelslreva(), test_data_slr()) # Ensure model and test data are available
fitted_modelslr <- modelslreva()
test_data <- test_data_slr() # Access the test data
target_col <- input$targetslr
independent_var <- input$independentVar
# Model Confidence Intervals
cat("Model Confidence Intervals (95% Level):\n")
conf_intervals <- confint(fitted_modelslr, level=0.95)
print(conf_intervals)
cat("\nInterpretation of Model Confidence Intervals:\n")
cat("The intervals represent the range within which the true model coefficients are likely to fall with 95% confidence.\n")
cat("For each coefficient, the lower and upper bounds indicate the plausible range of values.\n")
# Predicted Confidence Intervals for Test Data
cat("\nPredicted Confidence Intervals for Test Data (First 10 Observations):\n")
conf_int_predictions <- predict(fitted_modelslr, newdata = test_data, interval = 'confidence')
print(head(conf_int_predictions, n=10))
cat("\nInterpretation of Predicted Confidence Intervals:\n")
cat("These intervals provide a range within which the true value of the dependent variable is expected to fall for each observation, with 95% confidence.\n")
cat("The 'fit' column represents the predicted value, while 'lwr' and 'upr' represent the lower and upper bounds of the confidence interval, respectively.\n")
})
output$slrregressPlot <- renderPlotly({
req(modelslreva(), dataslreva())
fitted_model <- modelslreva()
data_for_plot <- dataslreva()
# Ensure the target and independent variables are provided
target_col <- input$targetslr
independent_var <- input$independentVar
if (is.null(data_for_plot[[target_col]]) || is.null(data_for_plot[[independent_var]])) {
return("Target or independent variable not found in the data.")
}
# Creating the plot with added color
p <- ggplot(data_for_plot, aes_string(x = independent_var, y = target_col)) +
geom_point(color = "darkorange") + # Change color of points
geom_smooth(method = "lm", se = FALSE, color = "dodgerblue") + # Change color of regression line
ggtitle("Regression Line Plot") +
xlab(independent_var) +
ylab(target_col) +
theme_minimal() + # Adding a minimal theme for a cleaner look
theme(legend.position = "none") # Remove legend if not needed
# Convert ggplot object to Plotly for an interactive plot
ggplotly(p)
})
###Multiple Linear Regression
# Define reactive values for each assumption test
shapTestmlr <- reactiveVal()
ncvTestmlrmlr <- reactiveVal()
linPlotmlr <- reactiveVal()
dWTestmlr <- reactiveVal()
vifmlr <- reactiveVal()
modelmlr <- reactiveVal()
datamlr <- reactiveVal(NULL)
modelmlreva <- reactiveVal(NULL)
datamlreva <- reactiveVal(NULL)
# Fix the data loading and cleaning part
observeEvent(input$loadmlr, {
file <- input$mlrinput
if (!is.null(file)) {
data_mlr <- read_data(file$datapath)
data_mlr <- clean_column_names(data_mlr)
datamlr(data_mlr) # Update the reactive value correctly
updateSelectInput(session, "targetmlr", choices = colnames(data_mlr))
updateSelectizeInput(session, "independentVarmlr", choices = setdiff(colnames(data_mlr), input$targetmlr))
}
})
output$mlrsummary <- renderPrint({
req(datamlr())
summary(datamlr())
})
# Observe the action button for triggering model fitting and assumption tests
observeEvent(input$mlrassumption, {
req(datamlr(), input$targetmlr, input$independentVarmlr)
data_mlr <- datamlr()
target_col <- input$targetmlr
independent_vars <- input$independentVarmlr
# Check if independent variables are selected
if (length(independent_vars) == 0) {
return("Please select independent variables.")
}
# Check for NAs and remove rows with NAs in relevant columns
data_mlr <- na.omit(data_mlr[, c(target_col, independent_vars)])
# Check if the dataset is large enough
if (nrow(data_mlr) < 10) {
return("Dataset is too small after removing NA values.")
}
# Ensure split ratio is valid
split_ratio <- input$dataSplitmlr
if (split_ratio <= 0 || split_ratio >= 1) {
return("Invalid split ratio. Please choose a value between 0 and 1.")
}
# Partition the data
set.seed(123)
training.samples <- createDataPartition(data_mlr[[target_col]], p = split_ratio, list = FALSE)
train_data <- data_mlr[training.samples, ]
test_data <- data_mlr[-training.samples, ]
# Fit the MLR model
formula_mlr <- as.formula(paste(target_col, "~", paste(independent_vars, collapse = "+")))
fitted_model_mlr <- lm(formula_mlr, data = train_data)
modelmlr(fitted_model_mlr)
})
output$shapTestmlr <- renderPrint({
req(datamlr(), input$targetmlr, input$independentVarmlr)
data_mlr <- datamlr()
target_col <- input$targetmlr
independent_vars <- input$independentVarmlr
# Ensure that independent variables are selected
if (length(independent_vars) == 0) {
return("Please select independent variables.")
}
# Concatenate independent variables into a formula string
independent_vars_str <- paste(independent_vars, collapse = "+")
# Filter out rows with NAs in relevant columns
data_mlr_filtered <- na.omit(data_mlr[, c(target_col, independent_vars)])
# Check if the dataset is sufficient after NA removal
if (nrow(data_mlr_filtered) < 10) {
return("Dataset is too small after removing NA values.")
}
# Split the data
set.seed(123)
split_ratio <- input$dataSplitmlr
training.samples <- createDataPartition(data_mlr_filtered[[target_col]], p = split_ratio, list = FALSE)
train_data <- data_mlr_filtered[training.samples, ]
test_data <- data_mlr_filtered[-training.samples, ]
# Fit the multiple linear regression model
formula_mlr <- as.formula(paste(target_col, "~", independent_vars_str))
fitted_model_mlr <- lm(formula_mlr, data = train_data)
modelmlr(fitted_model_mlr) # Update the reactive value with the fitted model
# Perform Shapiro-Wilk Test for Normality
cat("\nShapiro-Wilk Test for Normality of Residuals:\n")
shap_Test <- shapiro.test(residuals(fitted_model_mlr)) # Perform the test on the model's residuals
print(shap_Test)
# Interpret the test results for the user
if (shap_Test$p.value > 0.05) {
cat("Interpretation: With a p-value greater than 0.05, there is no statistical evidence to reject the null hypothesis that the residuals are normally distributed.
This suggests that the residuals of the model do not deviate significantly from a normal distribution, meeting one of the key assumptions of linear regression.\n")
} else {
cat("Interpretation: A p-value less than or equal to 0.05 suggests that the residuals are not normally distributed.
This could potentially violate the normality assumption of linear regression. In such cases, consider transforming the dependent variable,
adding polynomial terms or interaction effects, or using a non-linear modeling approach.\n")
}
})
output$ncvTestmlr <- renderPrint({
req(modelmlr()) # Ensure the MLR model is available for the test
fitted_model <- modelmlr() # Retrieve the fitted model
# Execute the Breusch-Pagan Test for Heteroscedasticity
cat("\nBreusch-Pagan Test for Heteroscedasticity:\n")
bp_test_result <- tryCatch({
bptest(fitted_model) # bptest() function from the lmtest package
}, error = function(e) {
cat("Error in conducting Breusch-Pagan test: ", e$message, "\n")
NULL # Return NULL if there's an error to handle it gracefully
})
# Interpret the test results for the user
if (!is.null(bp_test_result) && !is.na(bp_test_result$p.value)) {
print(bp_test_result)
if (bp_test_result$p.value > 0.05) {
cat("Interpretation: With a p-value greater than 0.05, there is no statistical evidence of heteroscedasticity.
This suggests that the variance of residuals is constant across the levels of the independent variables,
which is a desirable property in regression models.\n")
} else {
cat("Interpretation: A p-value less than or equal to 0.05 indicates the presence of heteroscedasticity.
It suggests that the variance of residuals varies across levels of the independent variables.
This can impact the reliability of the regression coefficients' standard errors and the model's predictions.
Consider using weighted least squares or other forms of heteroscedasticity-consistent standard errors.\n")
}
} else {
cat("Result: The Breusch-Pagan test could not be conducted. Check if the model is correctly specified, or consider other diagnostic tests for heteroscedasticity.\n")
}
})
# Render plot for each independent variable
output$linPlotmlr <- renderPlotly({
req(datamlr(), modelmlr(), input$targetmlr, input$independentVarmlr)
data_mlr <- datamlr()
fitted_model_mlr <- modelmlr()
independent_vars <- input$independentVarmlr
target_col <- input$targetmlr
# Generate plots for each independent variable
plots <- lapply(independent_vars, function(var) {
ggplot_object <- ggplot(data_mlr, aes_string(x = var, y = target_col)) +
geom_point() +
geom_smooth(method = "lm", se = FALSE, color = "dodgerblue") +
labs(title = paste("Linearity with", var), x = var, y = target_col) +
theme(
plot.title = element_text(size = 12, hjust = 0.5),
plot.margin = margin(5, 5, 5, 5)
) +
geom_text(aes(label = var), hjust = 0, vjust = 1, size = 2.35, color = "darkorange")
ggplotly(ggplot_object) %>% layout(title = paste("Linearity with", var))
})
# Combine plots (if multiple) or return single plot
if (length(plots) > 1) {
combined_plot <- subplot(
plots,
nrows = length(plots),
shareX = TRUE,
titleX = FALSE,
margin = 0.05
) %>% layout(title = "Linearity Plots", margin = list(t = 40, b = 80, l = 40, r = 40))
return(combined_plot)
} else {
return(plots[[1]])
}
})
output$dWTestmlr <- renderPrint({
req(modelmlr()) # Ensure modelmlr is available
fitted_model <- modelmlr() # Access the model
# Perform Durbin-Watson Test for Autocorrelation
cat("\nDurbin-Watson Test for Autocorrelation:\n")
dw_test_result <- tryCatch({
lmtest::dwtest(fitted_model)
}, error = function(e) {
cat("Error in conducting Durbin-Watson test: ", e$message, "\n")
NULL # Return NULL in case of error
})
# Check the test results and provide interpretation
if (!is.null(dw_test_result) && !is.na(dw_test_result$p.value)) {
print(dw_test_result)
if (dw_test_result$p.value > 0.05) {
cat("Interpretation: With a p-value greater than 0.05, there is no statistical evidence of autocorrelation in the residuals.
This suggests that the residuals are independent of each other, which is an assumption of the linear regression model.\n")
} else {
cat("Interpretation: A p-value less than or equal to 0.05 suggests that there is statistical evidence of autocorrelation in the residuals.
This could mean that the model is missing important predictors, there is a time series structure not accounted for, or the data is not being captured by the model adequately.
Consider investigating time series models, adding lagged variables, or exploring other model specifications.\n")
}
} else {
cat("Result: The Durbin-Watson test could not be conducted. This could be due to computational issues or other data-related problems.\n")
}
})
output$vifmlr <- renderPrint({
# VIF - to check for multicollinearity
# Hosmer-Lemeshow test - to check goodness of fit
req(modelmlr()) # Ensure modelmlr is available
fitted_model <- modelmlr() # Access the model
cat("Variance Inflation Factor (VIF) Results:\n")
vif_results <- vif(fitted_model)
print(vif_results)
# Interpretation for the user
if(any(vif_results > 10)) {
cat("Note: High VIF values (greater than 10) indicate potential multicollinearity issues among predictors.\n")
cat("This can affect the reliability of the regression coefficients. Consider removing or combining variables, or using dimensionality reduction techniques like PCA.\n")
} else {
cat("VIF values less than 10 are generally considered acceptable, indicating no severe multicollinearity between the predictors.\n")
}
})
# Server function to create diagnostic plots
output$resFitmlrPlot <- renderPlotly({
req(modelmlr())
fitted_model <- modelmlr()
p <- ggplot(fitted_model, aes(.fitted, .resid)) +
geom_point(color = "darkorange") +
geom_smooth(method = "lm", se = FALSE, color = "dodgerblue") +
labs(title = "Residuals vs Fitted", x = "Fitted Values", y = "Residuals")
ggplotly(p)
})
####Diagnostic Plots
output$qqPlotmlr <- renderPlotly({
req(modelmlr())
fitted_model <- modelmlr()
p <- ggplot(fitted_model, aes(sample = .stdresid)) +
stat_qq(color = "darkorange") +
stat_qq_line(color = "dodgerblue") +
labs(title = "Normal Q-Q")
ggplotly(p)
})
output$scaleLocmlrPlot <- renderPlotly({
req(modelmlr())
fitted_model <- modelmlr()
p <- ggplot(fitted_model, aes(.fitted, sqrt(abs(.resid)))) +
geom_point(color = "darkorange") +
geom_smooth(method = "lm", se = FALSE, color = "dodgerblue") +
labs(title = "Scale-Location", x = "Fitted Values", y = "Sqrt(|Residuals|)")
ggplotly(p)
})
output$resLevmlrPlot <- renderPlotly({
req(modelmlr())
fitted_model <- modelmlr()
p <- ggplot(fitted_model, aes(.hat, .stdresid)) +
geom_point(aes(size = .cooksd), shape = 1, color = "darkorange") +
geom_smooth(method = "lm", se = FALSE, color = "dodgerblue") +
labs(title = "Residuals vs Leverage", x = "Leverage", y = "Standardized Residuals")
ggplotly(p)
})
# Define the reactive value for the data and model at the top of the server function
datamlreva <- reactiveVal(NULL)
mlrmodeleva <- reactiveVal(NULL)
test_data_mlr <- reactiveVal(NULL)
# Load and clean data
observeEvent(input$loadmlr, {
req(input$mlrinput)
file <- input$mlrinput
if (!is.null(file)) {
data_mlreva <- read_data(file$datapath)
data_mlreva <- clean_column_names(data_mlreva)
datamlreva(data_mlreva) # Update the reactive value correctly
updateSelectInput(session, "targetmlr", choices = colnames(data_mlreva))
updateSelectizeInput(session, "independentVarmlr", choices = setdiff(colnames(data_mlreva), input$targetmlr))
}
})
observeEvent(input$mlrmodel, {
req(datamlreva(), input$targetmlr, input$independentVarmlr)
data_mlreva <- datamlreva()
target_col <- input$targetmlr
independent_vars <- input$independentVarmlr
# Check if independent variables are selected
if (length(independent_vars) == 0) {
return("Please select independent variables.")
}
# Concatenate independent variables into one string
independent_vars_str <- paste(independent_vars, collapse = "+")
# Filter out rows with NAs and split the data
data_mlreva <- na.omit(data_mlreva[, c(target_col, independent_vars)])
set.seed(123)
split_ratio <- input$dataSplitmlr
training.samples <- createDataPartition(data_mlreva[[target_col]], p = split_ratio, list = FALSE)
train_data <- data_mlreva[training.samples, ]
test_data <- data_mlreva[-training.samples, ]
# Fit the linear regression model
formula_str <- paste(target_col, "~", independent_vars_str)
fitted_modelmlr <- lm(as.formula(formula_str), data = train_data)
modelmlreva(fitted_modelmlr)
# Store test_data in the reactive value
test_data_mlr(test_data)
})
output$mlrmodeleva <- renderPrint({
req(modelmlreva())
fitted_modelmlr <- modelmlreva()
if (inherits(fitted_modelmlr, "lm")) {
# Model Summary
cat("Model Summary:\n")
print(summary(fitted_modelmlr))
# Interpretation of the key components
cat("\nInterpretation:\n")
cat("1. Coefficients: Estimates of the model parameters.\n")
cat(" - Intercept: Represents the predicted value of the dependent variable when all independent variables are zero.\n")
cat(" - Slope: Represents the change in the dependent variable for a one-unit change in the independent variable.\n")
cat("2. Residual standard error: Measures the quality of the linear regression fit.\n")
cat(" - Lower values indicate a better fit.\n")
cat("3. Multiple R-squared: Indicates the proportion of variance in the dependent variable explained by the model.\n")
cat(" - Values closer to 1 suggest a better explanatory power of the model.\n")
cat("4. F-statistic and p-value: Test the overall significance of the model.\n")
cat(" - A low p-value (< 0.05) indicates that the model is statistically significant.\n")
# Additional specific interpretations can be added here
} else {
"Model has not been run or is not a linear model."
}
})
# Render print for correlation coefficient
output$corcoefmlr <- renderPrint({
req(modelmlreva(), test_data_mlr()) # Ensure model and test data are available
fitted_modelmlr <- modelmlreva()
test_data <- test_data_mlr() # Access the test data
target_col <- input$targetmlr
independent_vars <- input$independentVar
# Prediction and calculation of correlation coefficient
lm_predict <- predict(fitted_modelmlr, newdata = test_data)
actual_pred <- data.frame(actuals = test_data[[target_col]], predicted = lm_predict)
cor_accuracy <- cor(actual_pred$actuals, actual_pred$predicted)
# Output with interpretation
cat("Correlation Coefficient between Actual and Predicted Values:\n")
cat(cor_accuracy, "\n\n")
# Interpretation of the correlation coefficient
cat("Interpretation:\n")
if(cor_accuracy > 0.75) {
cat("The model has a strong positive correlation between actual and predicted values.\n")
} else if(cor_accuracy > 0.5) {
cat("The model has a moderate positive correlation between actual and predicted values.\n")
} else if(cor_accuracy > 0.25) {
cat("The model has a weak positive correlation between actual and predicted values.\n")
} else {
cat("The model shows little to no correlation between actual and predicted values.\n")
}
cat("Note: A correlation coefficient close to 1 indicates a strong positive relationship, while values closer to 0 indicate weaker relationships.\n")
})
output$confintmlr <- renderPrint({
req(modelmlreva(), test_data_mlr()) # Ensure model and test data are available
fitted_modelmlr <- modelmlreva()
test_data <- test_data_mlr() # Access the test data
target_col <- input$targetmlr
independent_vars <- input$independentVarmlr
# Model Confidence Intervals
cat("Model Confidence Intervals (95% Level):\n")
conf_intervals <- confint(fitted_modelmlr, level=0.95)
print(conf_intervals)
cat("\nInterpretation of Model Confidence Intervals:\n")
cat("The intervals represent the range within which the true model coefficients are likely to fall with 95% confidence.\n")
cat("For each coefficient, the lower and upper bounds indicate the plausible range of values.\n")
# Predicted Confidence Intervals for Test Data
cat("\nPredicted Confidence Intervals for Test Data (First 10 Observations):\n")
conf_int_predictions <- predict(fitted_modelmlr, newdata = test_data, interval = 'confidence')
print(head(conf_int_predictions, n=10))
cat("\nInterpretation of Predicted Confidence Intervals:\n")
cat("These intervals provide a range within which the true value of the dependent variable is expected to fall for each observation, with 95% confidence.\n")
cat("The 'fit' column represents the predicted value, while 'lwr' and 'upr' represent the lower and upper bounds of the confidence interval, respectively.\n")
})
output$modelevamet <- renderPrint({
req(modelmlreva(), test_data_mlr()) # Ensure model and test data are available
fitted_modelmlr <- modelmlreva()
test_data <- test_data_mlr() # Access the test data
target_col_name <- input$targetmlr
# Check if the target column exists in test_data
if (!target_col_name %in% names(test_data)) {
cat("Target column not found in test data.\n")
return()
}
# Predictions
predictions <- predict(fitted_modelmlr, newdata = test_data)
# Check for NA values in predictions
if (any(is.na(predictions))) {
cat("NA values found in predictions.\n")
return()
}
# Calculate metrics
R2_adj <- summary(fitted_modelmlr)$adj.r.squared # Adjusted R-squared
MSE <- mean((test_data[[target_col_name]] - predictions)^2, na.rm = TRUE) # Mean Squared Error
RMSE <- sqrt(MSE) # Root Mean Squared Error
MAE <- mean(abs(test_data[[target_col_name]] - predictions), na.rm = TRUE) # Mean Absolute Error
# MAPE function with check for zero values
mape <- function(actual, predicted){
if (any(actual == 0)) {
cat("MAPE calculation: Actual values contain zero.\n")
return(NA)
}
mean(abs((actual - predicted) / actual), na.rm = TRUE) * 100
}
MAPE <- mape(test_data[[target_col_name]], predictions) # Mean Absolute Percentage Error
# Output with interpretation
cat("Multiple Linear Regression Evaluation Metrics:\n\n")
cat("Adjusted R-squared:\n")
cat("Value: ", R2_adj, "\n")
cat("Interpretation: Adjusted R-squared accounts for the number of predictors in the model. A higher value closer to 1 indicates a strong explanatory power of the model.\n\n")
cat("Mean Squared Error (MSE):\n")
cat("Value: ", MSE, "\n")
cat("Interpretation: MSE represents the average of the squares of the errors. Lower values indicate that the model's predictions are more accurate.\n\n")
cat("Root Mean Squared Error (RMSE):\n")
cat("Value: ", RMSE, "\n")
cat("Interpretation: RMSE is the square root of MSE and gives an estimate of the error magnitude in the same units as the response variable. Lower values suggest a closer fit of the model to the data.\n\n")
cat("Mean Absolute Error (MAE):\n")
cat("Value: ", MAE, "\n")
cat("Interpretation: MAE measures the average magnitude of the errors in the predictions. A lower MAE value suggests a better fit of the model to the observed data.\n\n")
cat("Mean Absolute Percentage Error (MAPE):\n")
cat("Value: ", MAPE, "\n")
cat("Interpretation: MAPE indicates the prediction accuracy as a percentage. Lower values close to 0% indicate high predictive accuracy of the model.\n")
cat("\nNote: While evaluating these metrics, it's crucial to contextualize them within the specific domain and objectives of your model. Statistical significance may not always equate to practical significance.")
})
output$mlrregressPlot <- renderPlotly({
req(modelmlreva(), datamlreva(), input$targetmlr, input$independentVarmlr)
data_for_plot <- datamlreva()
target_col <- input$targetmlr
independent_vars <- input$independentVarmlr
# Check if variables are selected and dataset is valid
if (is.null(data_for_plot) || is.null(data_for_plot[[target_col]]) || length(independent_vars) == 0) {
return("Please ensure target and independent variables are selected and the dataset is valid.")
}
# Create a list of plots, one for each independent variable
plots_list <- lapply(independent_vars, function(var) {
p <- ggplot(data_for_plot, aes_string(x = var, y = target_col)) +
geom_point(color = "darkorange") +
geom_smooth(method = "lm", se = FALSE, color = "dodgerblue") +
ggtitle(paste("Regression Line with", var)) +
xlab(var) +
ylab(target_col) +
theme_minimal() +
theme(legend.position = "none")
ggplotly(p)
})
# Combine plots if there are multiple independent variables
if (length(plots_list) > 1) {
combined_plot <- subplot(plots_list, nrows = length(plots_list), shareX = TRUE, titleX = FALSE)
return(combined_plot)
} else {
return(plots_list[[1]])
}
})
### Logistic Regression
data <- reactiveVal(NULL)
observeEvent(input$loadData, {
file <- input$glmfile
if (!is.null(file)) {
data_df <- read_data(file$datapath)
data_df <- clean_column_names(data_df)
data(data_df)
updateSelectInput(session, "targetglm", choices = colnames(data_df))
updateSelectizeInput(session, "independentVars", choices = setdiff(colnames(data_df), input$targetglm))
}
})
clean_column_names <- function(dataframe) {
colnames(dataframe) <- gsub("[^[:alnum:]_]", "", make.names(colnames(dataframe), unique = TRUE))
return(dataframe)
}
output$dataSummary <- renderPrint({
req(data())
summary(data())
})
output$glmassumption <- renderPrint({
req(data())
target_col <- input$targetglm
independent_vars <- input$independentVars
data_df <- data() # Original data
# Check if the target column is numeric and mutate it
if (is.numeric(data_df[[target_col]])) {
median_val <- median(data_df[[target_col]], na.rm = TRUE)
data_df[[target_col]] <- as.factor(ifelse(data_df[[target_col]] < median_val, "No", "Yes"))
}
# Filter out rows where any character column is an empty string
data_df <- data_df %>% dplyr::select(all_of(target_col), all_of(independent_vars)) %>%
na.omit()
# Example: Splitting the data, normalizing, and running glm
set.seed(123)
split_ratio <- input$dataSplit
training.samples <- createDataPartition(data_df[[target_col]], p = split_ratio, list = FALSE)
train_data <- data_df[training.samples, ]
test_data <- data_df[-training.samples, ]
train_data <- normalize(train_data, method = "standardize", range = c(0, 1), margin = 1L, on.constant = "quiet")
test_data <- normalize(test_data, method = "standardize", range = c(0, 1), margin = 1L, on.constant = "quiet")
formula <- as.formula(paste(target_col, "~", paste(independent_vars, collapse = "+")))
x <- as.matrix(train_data[, setdiff(names(train_data), target_col)])
y <- train_data[[target_col]]
# Fit a standard logistic regression model with increased max iterations
glm_model <- glm(formula, data = train_data, family = binomial(),
control = glm.control(maxit = 50)) # Increase max iterations
# Check if the model has converged
if(!glm_model$converged) {
cat("Warning: The logistic regression model did not converge.\n")
}
# VIF - to check for multicollinearity
# Hosmer-Lemeshow test - to check goodness of fit
cat("Variance Inflation Factor (VIF) Results:\n")
vif_results <- vif(glm_model)
print(vif_results)
if(any(vif_results > 10)) {
cat("Note: High VIF values indicate potential multicollinearity issues among predictors.\n")
}
cat("\nHosmer-Lemeshow Goodness of Fit Test:\n")
tryCatch({
hl_test <- hoslem.test(glm_model$y, fitted(glm_model), g = 5) # Adjusted g value
print(hl_test)
}, error = function(e) {
cat("Note: Hosmer-Lemeshow test could not be conducted. This may indicate issues with model fit or data.\n")
})
})
observeEvent(input$runLogisticRegression, {
req(data())
target_col <- input$targetglm
independent_vars <- input$independentVars
data_df <- data() # Original data
# Check if the target column is numeric and mutate it
if (is.numeric(data_df[[target_col]])) {
median_val <- median(data_df[[target_col]], na.rm = TRUE)
data_df[[target_col]] <- as.factor(ifelse(data_df[[target_col]] < median_val, "No", "Yes"))
}
# Rest of your code...
# Filter out rows where any character column is an empty string
data_df <- data_df %>% dplyr::select(all_of(target_col), all_of(independent_vars)) %>%
na.omit()
# Example: Splitting the data, normalizing, and running glm
set.seed(123)
split_ratio <- input$dataSplit
training.samples <- createDataPartition(data_df[[target_col]], p = split_ratio, list = FALSE)
train_data <- data_df[training.samples, ]
test_data <- data_df[-training.samples, ]
train_data <- normalize(train_data, method = "standardize", range = c(0, 1), margin = 1L, on.constant = "quiet")
test_data <- normalize(test_data, method = "standardize", range = c(0, 1), margin = 1L, on.constant = "quiet")
formula <- as.formula(paste(target_col, "~", paste(independent_vars, collapse = "+")))
x <- as.matrix(train_data[, setdiff(names(train_data), target_col)])
y <- train_data[[target_col]]
# Perform cross-validation to find the optimal lambda
cv_model <- cv.glmnet(x, y, family = "binomial", alpha = 1)
# Extract the coefficients at the optimal lambda
optimal_lambda <- cv_model$lambda.min
# Extract coefficients at the optimal lambda
coefficients <- coef(cv_model, s = optimal_lambda)
# Convert the sparse matrix to a regular matrix and then to a dataframe
coef_matrix <- as.matrix(coefficients)
coef_df <- as.data.frame(coef_matrix)
# Give meaningful names to the dataframe columns
names(coef_df) <- c("Coefficients")
rownames(coef_df) <- names(coefficients)
# Assuming 'model' is your trained glmnet model, and 'test_data' is your test dataset
# Prepare test data for prediction
x_test <- as.matrix(test_data[, independent_vars]) # independent variables
y_test <- as.factor(test_data[[target_col]]) # actual outcomes
# Predict using the model
predictions <- predict(cv_model, newx = x_test, type = "response", s = optimal_lambda)
# Convert predictions to a binary factor based on a threshold (e.g., 0.5)
predicted_class <- ifelse(predictions > 0.5, "Yes", "No")
# Calculate accuracy
accuracy <- mean(predicted_class == y_test)
# Get predicted probabilities (make sure to use 'type = "response"')
predicted_probs <- predict(cv_model, newx = x_test, type = "response", s = optimal_lambda)
# Calculate AUC
roc_curve <- roc(response = y_test, predictor = as.numeric(predicted_probs))
auc_value <- auc(roc_curve)
# Convert predicted classes and actual outcomes to factor if they are not already
predicted_class <- factor(predicted_class, levels = c("No", "Yes"))
y_test <- factor(y_test, levels = c("No", "Yes"))
# Calculate the confusion matrix
conf_matrix <- confusionMatrix(predicted_class, y_test)
# Creating a prediction object for ROC analysis
pred <- ROCR::prediction(predicted_probs, y_test)
# Creating a performance object for ROC curve
perf <- ROCR::performance(pred, "tpr", "fpr")
# Calculating AUC
auc_value <- ROCR::performance(pred, "auc")@y.values[[1]]
# Output coefficients and optimal lambda
output$logisticOutput <- renderPrint({
cat("Optimal Lambda Value:", optimal_lambda, "\n")
cat("This is the value of the regularization parameter lambda that minimizes the cross-validated error.\n\n")
cat("Coefficients:\n")
print(coef_df)
cat("Each coefficient represents the change in the log odds of the outcome for a one-unit change in the predictor variable.\n\n")
cat("Accuracy:", accuracy, "\n")
cat("This is the proportion of correctly predicted instances out of the total instances in the dataset.\n\n")
cat("AUC (Area Under the Curve):", auc_value, "\n")
cat("AUC ranges from 0 to 1 with higher values indicating better model performance. A model with an AUC close to 0.5 has no discriminative ability.\n\n")
cat("Confusion Matrix:\n")
print(conf_matrix$table)
cat("The confusion matrix shows the number of correct and incorrect predictions compared with the actual outcomes.\n")
cat("- True Positives (TP): Actual Yes predicted as Yes\n")
cat("- False Positives (FP): Actual No predicted as Yes\n")
cat("- True Negatives (TN): Actual No predicted as No\n")
cat("- False Negatives (FN): Actual Yes predicted as No\n\n")
cat("Additional Metrics:\n")
cat("- Sensitivity (True Positive Rate): ", conf_matrix$byClass['Sensitivity'], "\n")
cat(" The proportion of actual positives that were correctly identified.\n")
cat("- Specificity (True Negative Rate): ", conf_matrix$byClass['Specificity'], "\n")
cat(" The proportion of actual negatives that were correctly identified.\n")
cat("- Positive Predictive Value (Precision): ", conf_matrix$byClass['Positive Predictive Value'], "\n")
cat(" The proportion of positive identifications that were actually correct.\n")
cat("- Negative Predictive Value: ", conf_matrix$byClass['Negative Predictive Value'], "\n")
cat(" The proportion of negative identifications that were actually correct.\n")
cat("- F1 Score: ", conf_matrix$byClass['F1'], "\n")
cat(" The harmonic mean of Precision and Sensitivity, useful for unbalanced classes.\n")
})
output$glmcvplot <- renderPlotly({
req(cv_model) # Ensure cv_model is available
# Extract necessary data from cv_model
lambda <- cv_model$lambda
cvm <- cv_model$cvm
cvsd <- cv_model$cvsd
# Create a plotly plot
plot_ly(x = lambda, y = cvm, type = 'scatter', mode = 'lines') %>%
add_trace(y = cvm + cvsd, name = 'Upper CI', mode = 'lines', line = list(dash = 'dash')) %>%
add_trace(y = cvm - cvsd, name = 'Lower CI', mode = 'lines', line = list(dash = 'dash')) %>%
layout(
xaxis = list(type = 'log', title = 'Lambda'),
yaxis = list(title = 'Cross-Validated Error'),
title = 'Cross-Validation Plot for GLMNET Model'
)
})
# Render AUC plot in Shiny
output$glmaucplot <- renderPlotly({
# Ensure the performance object is available
req(perf, auc_value)
# Prepare the data for the plot
data <- data.frame(
FPR = perf@x.values[[1]],
TPR = perf@y.values[[1]]
)
# Create the ROC curve plot with Plotly
p <- plot_ly(data, x = ~FPR, y = ~TPR, type = 'scatter', mode = 'lines',
line = list(color = 'blue'), name = 'ROC Curve') %>%
add_trace(x = 0:1, y = 0:1, type = 'scatter', mode = 'lines',
line = list(color = 'red', dash = 'dash'), name = 'Chance') %>%
layout(title = paste("ROC Curve (AUC =", round(auc_value, 2), ")"),
xaxis = list(title = "False Positive Rate"),
yaxis = list(title = "True Positive Rate"))
return(p)
})
})
read_data <- function(filepath) {
ext <- tools::file_ext(filepath)
if (ext %in% c("csv", "xlsx")) {
if (ext == "csv") {
read.csv(filepath, stringsAsFactors = FALSE)
} else if (ext == "xlsx") {
read_excel(filepath)
}
} else {
stop("Invalid file format. Please select a CSV or XLSX file.")
}
}
###Decision Tree
# Reactive values for the decision tree model and training data
treedecision <- reactiveVal(NULL)
train_data_rv <- reactiveVal(NULL)
train_data_reactive <- reactiveVal(NULL)
target_col_rv <- reactiveVal(NULL)
test_data_reactive <- reactiveVal(NULL)
# Define the function to clean column names
cl_column_names <- function(dataframe) {
colnames(dataframe) <- gsub("[^[:alnum:]_]", "", make.names(colnames(dataframe), unique = TRUE))
return(dataframe)
}
# Reactive expression to read and process the data
datadectree <- reactive({
req(input$treedecfile)
inFile <- input$treedecfile
ext <- tools::file_ext(inFile$name)
if (ext == "csv") {
df <- read.csv(inFile$datapath, stringsAsFactors = FALSE, na.strings = c("", "NA", "na"))
} else if (ext == "xlsx") {
df <- readxl::read_xlsx(inFile$datapath, na = c("", "NA", "na"))
}
cl_column_names(df)
})
# Observer to update the select inputs
observe({
req(datadectree())
updateSelectInput(session, "targetdectree", choices = names(datadectree()))
})
observe({
req(input$targetdectree)
target_col_rv(input$targetdectree)
})
output$dataSummarydt <- renderPrint({
req(datadectree())
summary(datadectree())
})
# Define the reactive expression for train data
train_data_reactive <- reactive({
req(datadectree())
data_df <- datadectree()
target_col <- target_col_rv() # Use the reactive value
# Numeric to factor conversion (if necessary)
if (is.numeric(data_df[[target_col]])) {
median_val <- median(data_df[[target_col]], na.rm = TRUE)
data_df[[target_col]] <- as.factor(ifelse(data_df[[target_col]] < median_val, "No", "Yes"))
}
# Filter out rows with NA and split the data
data_df <- data_df %>% filter(!is.na(.[[target_col]]))
set.seed(123)
split_ratio <- input$dataSplittree
training.samples <- createDataPartition(data_df[[target_col]], p = split_ratio, list = FALSE)
train_data <- data_df[training.samples, ]
train_data_rv(train_data) # This line was missing
return(train_data)
})
# Trigger to fit the decision tree model
observeEvent(input$rundectree, {
req(train_data_reactive())
local_train_data <- train_data_rv() # Now it will have the updated data
# Fit the decision tree model
tree_formula <- as.formula(paste(target_col_rv(), "~ ."))
treedecision(tree(tree_formula, data = local_train_data)) # Ensure local_train_data is correctly passed
})
# Summarize the decision tree model
output$rundectree <- renderPrint({
req(treedecision())
decision_tree_model <- treedecision() # Retrieve the decision tree model
# Check if the decision tree model is correctly retrieved
if(is.null(decision_tree_model)) {
cat("Decision tree model is not available.\n")
return()
}
# Print model summary
cat("Decision Tree Model Summary:\n\n")
tryCatch({
print(summary(decision_tree_model))
}, error = function(e) {
cat("Error in printing model summary: ", e$message, "\n")
})
cat("\nInterpretation:\n")
cat("1. Node Number: Each number represents a node in the tree.\n")
cat("2. Split Variable: The variable used to split the node. If 'leaf', it indicates the node is a terminal node (leaf).\n")
cat("3. Split Point: The value of the split variable that divides the node.\n")
cat("4. n: The number of observations in the node.\n")
cat("5. Deviance: Measures the variability of the response variable within the node. Lower values indicate better model fit.\n")
cat("6. Prediction: The predicted class (or value for regression trees) for each node.\n")
cat("\nHow to Read the Tree:\n")
cat("- Start at the top node (Root Node) and make decisions based on the split variables and points.\n")
cat("- Follow the branches to reach the leaf nodes, which contain the final predictions.\n")
cat("- Each path from the root to a leaf represents a decision rule.\n")
cat("\nNote:\n")
cat("- A simpler tree (fewer nodes) with good predictive accuracy is generally preferable to avoid overfitting.\n")
cat("- Decision trees are intuitive but can become complex with many splits (consider pruning if needed).\n")
})
# Tree Plot
output$dectreeplot <- renderPlot({
req(treedecision())
plot(treedecision())
text(treedecision(), pretty = 0)
})
# Cross-validation Plot
# Define cv_errors as a reactive expression
cv_errors <- reactive({
local_train_data <- train_data_rv() # Your dataset
req(local_train_data)
target_column <- target_col_rv() # Your target column
req(target_column)
folds <- createFolds(local_train_data[[target_column]], k = 10, list = TRUE)
errors <- numeric(length(folds))
for(i in seq_along(folds)) {
training_set <- local_train_data[-folds[[i]], ]
testing_set <- local_train_data[folds[[i]], ]
# Assuming that your model formula is correct and uses the target column
tree_model <- tree(paste(target_column, "~ ."), data = training_set)
predictions <- predict(tree_model, testing_set, type = "class")
errors[i] <- mean(predictions != testing_set[[target_column]])
}
return(errors) # Return the vector of errors
})
# Plot for cross-validation errors
output$cvplot <- renderPlot({
errors <- cv_errors() # Retrieve the vector of CV errors
req(errors) # Make sure errors are available before proceeding
# Plot the errors against fold numbers
plot(seq_along(errors), errors, type = "b",
xlab = "Fold Number", ylab = "Misclassification Error",
main = "Cross-Validation Error by Fold")
})
#Pruned Tree
# Define pruned_dtree as a reactive expression
pruned_dtree <- reactive({
decision_tree_model <- treedecision()
req(decision_tree_model)
req(cv_errors()) # Access cv_errors as a reactive expression
optimal_size <- which.min(cv_errors())
prune.tree(decision_tree_model, best = optimal_size)
})
# Pruned Tree Plot
output$pruneddtree <- renderPlot({
req(pruned_dtree())
plot(pruned_dtree())
text(pruned_dtree(), pretty = 0)
})
# Confusion Matrix
output$confMatrix <- renderPrint({
req(treedecision(), train_data_rv())
local_train_data <- train_data_rv()
# Prediction
tree_pred <- tryCatch({
predict(treedecision(), local_train_data, type = "class")
}, error = function(e) {
cat("Error in prediction:", e$message, "\n")
return(NULL)
})
# Ensure tree_pred and the target column have the same length
if (length(tree_pred) != nrow(local_train_data)) {
cat("Error: Prediction length does not match the number of rows in training data.\n")
return()
}
# Compute the confusion matrix
cm <- table(tree_pred, local_train_data[[target_col_rv()]])
# Print the confusion matrix
cat("Confusion Matrix:\n")
print(cm)
cat("The confusion matrix shows the number of correct and incorrect predictions compared with the actual outcomes.\n")
cat("- True Positives (TP): Actual Yes predicted as Yes\n")
cat("- False Positives (FP): Actual No predicted as Yes\n")
cat("- True Negatives (TN): Actual No predicted as No\n")
cat("- False Negatives (FN): Actual Yes predicted as No\n\n")
cat("Additional Metrics:\n")
cat("- Sensitivity (True Positive Rate): ", "\n")
cat(" The proportion of actual positives that were correctly identified.\n")
cat("- Specificity (True Negative Rate): ", "\n")
cat(" The proportion of actual negatives that were correctly identified.\n")
cat("- Positive Predictive Value (Precision): ", "\n")
cat(" The proportion of positive identifications that were actually correct.\n")
cat("- Negative Predictive Value: ", "\n")
cat(" The proportion of negative identifications that were actually correct.\n")
cat("- F1 Score: ", "\n")
cat(" The harmonic mean of Precision and Sensitivity, useful for unbalanced classes.\n")
# Interpretation of the confusion matrix
cat("\nInterpretation:\n")
cat("- Each row of the matrix represents the instances in a predicted class.\n")
cat("- Each column represents the instances in an actual class.\n")
cat("- The diagonal elements (top left to bottom right) represent the number of correct classifications.\n")
cat("- Off-diagonal elements are those that were misclassified by the model.\n")
cat("- Higher values on the diagonal indicate better performance.\n")
# Additional specific interpretations can be added here based on the context and the data
})
# Define the reactive expression for train data
test_data_reactive <- reactive({
req(datadectree(), input$targetdectree, input$dataSplittree)
data_df <- datadectree()
target_col <- target_col_rv() # Use the reactive value
# Numeric to factor conversion (if necessary)
if (is.numeric(data_df[[target_col]])) {
median_val <- median(data_df[[target_col]], na.rm = TRUE)
data_df[[target_col]] <- as.factor(ifelse(data_df[[target_col]] < median_val, "No", "Yes"))
}
data_df <- data_df %>% filter(!is.na(.[[target_col]]))
# Split the data into training and testing sets
set.seed(123) # It's good you're setting a seed for reproducibility
split_ratio <- input$dataSplittree # The ratio for splitting, e.g., 0.7 for 70% training data
training.samples <- createDataPartition(data_df[[target_col]], p = split_ratio, list = FALSE)
# Assuming that training.samples is a vector of indices for the training set
test_data <- data_df[-training.samples, ] # Use negative indexing to get the test set
return(test_data)
})
# Assuming 'predictions' and 'local_eval_data' are available as they were in the previous step
output$cfdtpteva <- renderPrint({
# Retrieve the pruned decision tree model
pruned_model <- pruned_dtree()
req(pruned_model)
# Retrieve the evaluation dataset from the reactive expression
local_eval_data <- test_data_reactive() # Using test_data_reactive
req(local_eval_data)
# Make predictions using the pruned tree model
predictions <- predict(pruned_model, local_eval_data, type = "class")
# Generate the confusion matrix
cm <- table(True = local_eval_data[[target_col_rv()]], Predicted = predictions)
# Calculate metrics
accuracy <- sum(diag(cm)) / sum(cm)
precision <- cm[2, 2] / sum(cm[2, ])
recall <- cm[2, 2] / sum(cm[, 2])
F1_score <- 2 * precision * recall / (precision + recall)
# Print the evaluation metrics
cat("Confusion Matrix:\n")
print(cm)
cat("\n")
cat("Accuracy:", accuracy, "\n")
cat("Precision:", precision, "\n")
cat("Recall:", recall, "\n")
cat("F1 Score:", F1_score, "\n")
# Enhanced interpretation
cat("\nDetailed Interpretation and Decision Insights:\n")
cat("1. Accuracy reflects the overall correctness of the model and is a good initial indicator of performance. However, it may not fully capture the nuances in imbalanced datasets.\n")
cat("2. Precision measures the reliability of the model's positive predictions. High precision indicates that when the model predicts a positive outcome, it is likely correct. This is critical in scenarios where false positives carry a high cost.\n")
cat("3. Recall assesses the model's ability to detect all relevant cases. High recall means the model is effective at capturing the majority of positive instances, which is crucial in situations where missing a positive case is detrimental.\n")
cat("4. F1 Score provides a balance between precision and recall. A high F1 score suggests the model effectively balances the trade-off between not missing positive cases and maintaining high accuracy in its positive predictions.\n")
cat("\n")
cat("Decision-Making Insights:\n")
cat("- The model's performance should be considered in the context of your specific application. For instance, if missing a positive case has serious consequences, prioritize improving recall.\n")
cat("- If your focus is on the accuracy of the positive predictions (to avoid false alarms or unnecessary actions), aim to improve precision.\n")
cat("- The F1 Score is particularly informative when you need a single metric to assess the model's balance between precision and recall, especially in cases of class imbalance.\n")
cat("- Consider the model's limitations and strengths in the context of your dataset, and use these insights to guide your decision-making process or further model refinement.\n")
cat("\n")
cat("Remember, no model is perfect. It's crucial to continuously evaluate the model's performance in real-world scenarios and update it as new data becomes available to ensure its ongoing effectiveness.\n")
})
###Random Forest
datarf <- reactiveVal(NULL)
rf_model_reactive <- reactiveVal()
pred_rf_reactive <- reactiveVal()
results_reactive <- reactiveVal()
# Load and clean data
observeEvent(input$loadrf, {
req(input$rfinput)
file <- input$rfinput
if (!is.null(file)) {
# Reading and cleaning data
data_df <- read_data(file$datapath)
data_df <- clean_column_names(data_df)
# Setting the reactive value
datarf(data_df)
# Updating UI elements
updateSelectInput(session, "targetrf", choices = colnames(data_df))
updateSelectizeInput(session, "independentVarrf", choices = setdiff(colnames(data_df), input$targetrf))
}
})
output$dataSummaryrf <- renderPrint({
req(datarf())
summary(datarf())
})
observeEvent(input$runrf, {
req(datarf(), input$targetrf, input$independentVarrf)
data_rf <- datarf() %>%
dplyr::select(all_of(c(input$targetrf, input$independentVarrf))) %>%
na.omit()
withProgress(message = 'Model is being trained...', value = 0, {
# Increment progress
incProgress(0.1) # Initial progress
# Early return if conditions are not met
if (length(input$independentVarrf) == 0) {
output$modelOutputrf <- renderPrint({ "Please select independent variables." })
return()
}
if (nrow(data_rf) < 10) {
output$modelOutputrf <- renderPrint({ "Dataset is too small after removing NA values." })
return()
}
split_ratio <- input$dataSplitrf
if (split_ratio <= 0 || split_ratio >= 1) {
output$modelOutputrf <- renderPrint({ "Invalid split ratio. Please choose a value between 0 and 1." })
return()
}
incProgress(0.3) # Increment progress
# Partition the data
set.seed(123)
train <- data_rf %>% sample_frac(split_ratio)
test <- data_rf %>% setdiff(train)
incProgress(0.6) # Increment progress
formula_rf <- as.formula(paste(input$targetrf, "~", paste(input$independentVarrf, collapse = "+")))
# Fit the Random Forest model
rf_model <- randomForest(formula_rf,
data = train,
mtry = input$mtryInput,
ntree = input$ntreeInput)
rf_model_reactive(rf_model)
# Model summary
output$runrf <- renderPrint({
print(rf_model)
# Feature Importance
cat("Feature Importance:\n")
importance_vals <- importance(rf_model)
print(importance_vals)
})
# Finalize progress
incProgress(1.0) # Complete the progress
})
})
output$importancePlot <- renderPlotly({
req(datarf(), input$targetrf, input$independentVarrf)
# Access the model from the reactive value
rf_model <- rf_model_reactive()
req(rf_model) # Ensure the model is available
# Extracting feature importance
importance_vals <- importance(rf_model)
# Converting to a data frame for plotting
importance_df <- as.data.frame(importance_vals)
importance_df$Feature <- rownames(importance_df)
# For example, if the correct column name is "Importance"
ggplot(importance_df, aes(x = reorder(Feature, IncNodePurity), y = IncNodePurity)) +
geom_bar(stat = "identity", fill = "dodgerblue") +
theme_minimal() +
coord_flip() + # Flipping coordinates for horizontal bars
labs(title = "Feature Importance", x = "Features", y = "Importance")
})
# Define the Mean Squared Error function
mse <- function(actual, predicted) {
mean((actual - predicted) ^ 2)
}
# Define the Mean Absolute Error function
mae <- function(actual, predicted) {
mean(abs(actual - predicted))
}
observeEvent(input$predictBtn, {
req(datarf(), input$targetrf, input$independentVarrf)
data_rf <- datarf() %>%
dplyr::select(all_of(c(input$targetrf, input$independentVarrf))) %>%
na.omit()
withProgress(message = 'Model is being trained...', value = 0, {
# Increment progress
incProgress(0.1) # Initial progress
# Early return if conditions are not met
if (length(input$independentVarrf) == 0) {
output$modelOutputrf <- renderPrint({ "Please select independent variables." })
return()
}
if (nrow(data_rf) < 10) {
output$modelOutputrf <- renderPrint({ "Dataset is too small after removing NA values." })
return()
}
split_ratio <- input$dataSplitrf
if (split_ratio <= 0 || split_ratio >= 1) {
output$modelOutputrf <- renderPrint({ "Invalid split ratio. Please choose a value between 0 and 1." })
return()
}
incProgress(0.3) # Increment progress
# Partition the data
set.seed(123)
train <- data_rf %>% sample_frac(split_ratio)
test <- data_rf %>% setdiff(train)
# Assuming train dataset is already prepared
control <- trainControl(method="cv", number=10)
tunegrid <- expand.grid(.mtry = input$mtryInput)
set.seed(2)
formula_rf <- as.formula(paste(input$targetrf, "~", paste(input$independentVarrf, collapse = "+")))
rf_model <- randomForest(formula_rf,
data=train,
metric="RMSE",
tuneGrid=tunegrid,
ntree = input$ntreeInput,
trControl=control,
importance = TRUE)
# Make predictions for the entire dataset
pred_rf <- predict(rf_model, newdata = train)
# Calculate metrics
MSE_rf <- mse(actual = train[[input$targetrf]], predicted = pred_rf)
# For R_square_rf, ensure you have a function or package that provides R2
R_square_rf <- R2(pred_rf, train[[input$targetrf]])
# For MAE_rf, ensure you have a function or package that provides mae
MAE_rf <- mae(actual = train[[input$targetrf]], predicted = pred_rf)
output$predictionOutput <- renderPrint({
cat("Mean Squared Error (MSE):\n\n", MSE_rf, "\n\n", "Interpretation: MSE measures the average squared difference between actual and predicted values.
Lower values indicate better model performance.
A value of 0 means perfect predictions.")
cat("\n\nR-squared (R²):\n\n", R_square_rf, "\n\n", "Interpretation: R² represents the proportion of variance in the dependent variable that's predictable from the independent variables.
It ranges from 0 to 1, with higher values indicating better model fit.")
cat("\n\nMean Absolute Error (MAE):\n\n", MAE_rf, "\n\n", "Interpretation: MAE measures the average absolute difference between actual and predicted values.
Like MSE, lower MAE values indicate better model performance.")
})
# Finalize progress
incProgress(1.0) # Complete the progress
# Store results in a reactive value
results_reactive(list(actual = train[[input$targetrf]], predicted = pred_rf))
})
})
output$performancePlot <- renderPlotly({
# Access the stored results
results <- results_reactive()
req(results) # Ensure results are available
# Creating the plot
plot_data <- data.frame(Actual = results$actual, Predicted = results$predicted)
p <- ggplot(plot_data, aes(x = Actual, y = Predicted)) +
geom_point(alpha = 0.5) +
geom_abline(intercept = 0, slope = 1, color = "red", linetype = "dashed") +
labs(x = "Actual Values", y = "Predicted Values", title = "Actual vs. Predicted Values") +
theme_minimal()
ggplotly(p)
})
datarf <- reactiveVal(NULL)
rf_model_reactive <- reactiveVal()
pred_rf_reactive <- reactiveVal()
results_reactive <- reactiveVal()
# Load and clean data
observeEvent(input$loadrf, {
req(input$rfinput)
file <- input$rfinput
if (!is.null(file)) {
# Reading and cleaning data
data_df <- read_data(file$datapath)
data_df <- clean_column_names(data_df)
# Setting the reactive value
datarf(data_df)
# Updating UI elements
updateSelectInput(session, "targetrf", choices = colnames(data_df))
updateSelectizeInput(session, "independentVarrf", choices = setdiff(colnames(data_df), input$targetrf))
}
})
output$dataSummaryrf <- renderPrint({
req(datarf())
summary(datarf())
})
observeEvent(input$runrf, {
req(datarf(), input$targetrf, input$independentVarrf)
data_rf <- datarf() %>%
dplyr::select(all_of(c(input$targetrf, input$independentVarrf))) %>%
na.omit()
withProgress(message = 'Model is being trained...', value = 0, {
# Increment progress
incProgress(0.1) # Initial progress
# Early return if conditions are not met
if (length(input$independentVarrf) == 0) {
output$modelOutputrf <- renderPrint({ "Please select independent variables." })
return()
}
if (nrow(data_rf) < 10) {
output$modelOutputrf <- renderPrint({ "Dataset is too small after removing NA values." })
return()
}
incProgress(0.3) # Increment progress
split_ratio <- input$dataSplitrf
if (split_ratio <= 0 || split_ratio >= 1) {
output$modelOutputrf <- renderPrint({ "Invalid split ratio. Please choose a value between 0 and 1." })
return()
}
# Partition the data
set.seed(123)
train <- data_rf %>% sample_frac(split_ratio)
test <- data_rf %>% setdiff(train)
# Fit the Random Forest model
formula_rf <- as.formula(paste(input$targetrf, "~", paste(input$independentVarrf, collapse = "+")))
incProgress(0.6) # Increment progress
# Fit the Random Forest model
rf_model <- randomForest(formula_rf,
data = train,
mtry = input$mtryInput,
ntree = input$ntreeInput)
rf_model_reactive(rf_model)
# Model summary
output$runrf <- renderPrint({
print(rf_model)
# Feature Importance
cat("Feature Importance:\n")
importance_vals <- importance(rf_model)
print(importance_vals)
})
# Finalize progress
incProgress(1.0) # Complete the progress
})
})
output$importancePlot <- renderPlotly({
req(datarf(), input$targetrf, input$independentVarrf)
# Access the model from the reactive value
rf_model <- rf_model_reactive()
req(rf_model) # Ensure the model is available
# Extracting feature importance
importance_vals <- importance(rf_model)
# Converting to a data frame for plotting
importance_df <- as.data.frame(importance_vals)
importance_df$Feature <- rownames(importance_df)
# For example, if the correct column name is "Importance"
ggplot(importance_df, aes(x = reorder(Feature, IncNodePurity), y = IncNodePurity)) +
geom_bar(stat = "identity", fill = "dodgerblue") +
theme_minimal() +
coord_flip() + # Flipping coordinates for horizontal bars
labs(title = "Feature Importance", x = "Features", y = "Importance")
})
# Define the Mean Squared Error function
mse <- function(actual, predicted) {
mean((actual - predicted) ^ 2)
}
# Define the Mean Absolute Error function
mae <- function(actual, predicted) {
mean(abs(actual - predicted))
}
observeEvent(input$predictBtn, {
req(datarf(), input$targetrf, input$independentVarrf)
data_rf <- datarf() %>%
dplyr::select(all_of(c(input$targetrf, input$independentVarrf))) %>%
na.omit()
withProgress(message = 'Model is being trained...', value = 0, {
# Increment progress
incProgress(0.1) # Initial progress
# Early return if conditions are not met
if (length(input$independentVarrf) == 0) {
output$modelOutputrf <- renderPrint({ "Please select independent variables." })
return()
}
incProgress(0.3) # Increment progress
if (nrow(data_rf) < 10) {
output$modelOutputrf <- renderPrint({ "Dataset is too small after removing NA values." })
return()
}
split_ratio <- input$dataSplitrf
if (split_ratio <= 0 || split_ratio >= 1) {
output$modelOutputrf <- renderPrint({ "Invalid split ratio. Please choose a value between 0 and 1." })
return()
}
# Assuming train dataset is already prepared
control <- trainControl(method="cv", number=10)
tunegrid <- expand.grid(.mtry = input$mtryInput)
# Partition the data
set.seed(2)
train <- data_rf %>% sample_frac(split_ratio)
test <- data_rf %>% setdiff(train)
incProgress(0.6) # Increment progress
formula_rf <- as.formula(paste(input$targetrf, "~", paste(input$independentVarrf, collapse = "+")))
# Fit the Random Forest model
rf_model <- train(formula_rf,
data=train, method="rf",
metric="RMSE",
tuneGrid=tunegrid,
ntree = input$ntreeInput,
trControl=control,
importance = TRUE)
# Make predictions for the entire dataset
pred_rf <- predict(rf_model, newdata = train)
# Calculate metrics
MSE_rf <- mse(actual = train[[input$targetrf]], predicted = pred_rf)
# For R_square_rf, ensure you have a function or package that provides R2
R_square_rf <- R2(pred_rf, train[[input$targetrf]])
# For MAE_rf, ensure you have a function or package that provides mae
MAE_rf <- mae(actual = train[[input$targetrf]], predicted = pred_rf)
output$predictionOutput <- renderPrint({
cat("Mean Squared Error (MSE):\n\n", MSE_rf, "\n\n", "Interpretation: MSE measures the average squared difference between actual and predicted values.
Lower values indicate better model performance.
A value of 0 means perfect predictions.")
cat("\n\nR-squared (R²):\n\n", R_square_rf, "\n\n", "Interpretation: R² represents the proportion of variance in the dependent variable that's predictable from the independent variables.
It ranges from 0 to 1, with higher values indicating better model fit.")
cat("\n\nMean Absolute Error (MAE):\n\n", MAE_rf, "\n\n", "Interpretation: MAE measures the average absolute difference between actual and predicted values.
Like MSE, lower MAE values indicate better model performance.")
})
# Finalize progress
incProgress(1.0) # Complete the progress
# Store results in a reactive value
results_reactive(list(actual = train[[input$targetrf]], predicted = pred_rf))
})
})
output$performancePlot <- renderPlotly({
# Access the stored results
results <- results_reactive()
req(results) # Ensure results are available
# Creating the plot
plot_data <- data.frame(Actual = results$actual, Predicted = results$predicted)
p <- ggplot(plot_data, aes(x = Actual, y = Predicted)) +
geom_point(alpha = 0.5) +
geom_abline(intercept = 0, slope = 1, color = "red", linetype = "dashed") +
labs(x = "Actual Values", y = "Predicted Values", title = "Actual vs. Predicted Values") +
theme_minimal()
ggplotly(p)
})
###Bagging
databg <- reactiveVal(NULL)
bg_model_reactive <- reactiveVal()
pred_bg_reactive <- reactiveVal()
results_reactive_bg <- reactiveVal()
# Load and clean data
observeEvent(input$loadbg, {
req(input$bginput)
file <- input$bginput
if (!is.null(file)) {
# Reading and cleaning data
data_df <- read_data(file$datapath)
data_df <- clean_column_names(data_df)
# Setting the reactive value
databg(data_df)
# Updating UI elements
updateSelectInput(session, "targetbg", choices = colnames(data_df))
updateSelectizeInput(session, "independentVarbg", choices = setdiff(colnames(data_df), input$targetbg))
}
})
output$dataSummarybg <- renderPrint({
req(databg())
summary(databg())
})
observeEvent(input$runbg, {
req(databg(), input$targetbg, input$independentVarbg)
data_bg <- databg() %>%
dplyr::select(all_of(c(input$targetbg, input$independentVarbg))) %>%
na.omit()
# Early return if conditions are not met
if (length(input$independentVarbg) == 0) {
output$modelOutputbg <- renderPrint({ "Please select independent variables." })
return()
}
if (nrow(data_bg) < 10) {
output$modelOutputbg <- renderPrint({ "Dataset is too small after removing NA values." })
return()
}
split_ratio <- input$dataSplitbg
if (split_ratio <= 0 || split_ratio >= 1) {
output$modelOutputbg <- renderPrint({ "Invalid split ratio. Please choose a value between 0 and 1." })
return()
}
# Partition the data
set.seed(123)
train <- data_bg %>% sample_frac(split_ratio)
test <- data_bg %>% setdiff(train)
# Fit the Bagging model
formula_bg <- as.formula(paste(input$targetbg, "~", paste(input$independentVarbg, collapse = "+")))
# Fit the Random Forest model
ctrl <- trainControl(method = "cv", number = 10)
bg_model <- caret::train(formula_bg,
data = train,
method = "treebag",
nbagg = input$nbaggInput,
trControl = ctrl,
importance = TRUE)
bg_model_reactive(bg_model)
# Model summary
output$runbg <- renderPrint({
print(bg_model)
# Add interpretations
cat("\nModel Interpretation:\n")
cat("1. Best-Tuned Parameters: These parameters, such as the number of bagging iterations (nbagg), were found to be most effective during the training process.\n")
cat("2. Performance Metrics: These numbers indicate how well the model predicts the target variable. For a regression model, metrics like RMSE or MAE are common, where lower values are better. For a classification model, metrics like Accuracy or AUC are used, where higher values indicate better performance.\n")
cat("3. Resampling Results: The cross-validation results show how the model's performance varied across different subsets of the training data. Consistent performance across folds suggests a robust model.\n")
# If the model includes variable importance
if ("importance" %in% names(bg_model)) {
cat("4. Variable Importance: This shows which predictors are most influential in the model. Higher values indicate more important predictors.\n")
}
})
})
output$importancePlotbg <- renderPlotly({
req(bg_model_reactive) # Ensure the model is available
# Access the model from the reactive value
bg_model <- bg_model_reactive()
# Extracting feature importance using varImp from caret
importance_vals <- varImp(bg_model, scale = FALSE)
# Converting to a data frame for plotting
importance_df <- as.data.frame(importance_vals$importance)
importance_df$Feature <- rownames(importance_df)
# Plot using ggplot
p <- ggplot(importance_df, aes(x = reorder(Feature, Overall), y = Overall)) +
geom_bar(stat = "identity", fill = "dodgerblue") +
theme_minimal() +
coord_flip() + # Flipping coordinates for horizontal bars
labs(title = "Feature Importance", x = "Features", y = "Importance")
# Convert to Plotly for an interactive plot
ggplotly(p)
})
observeEvent(input$baggingBtn, {
req(databg(), input$targetbg, input$independentVarbg)
data_bg <- databg() %>%
dplyr::select(all_of(c(input$targetbg, input$independentVarbg))) %>%
na.omit()
withProgress(message = 'Model is being trained...', value = 0, {
# Increment progress
incProgress(0.1) # Initial progress
# Early return if conditions are not met
if (length(input$independentVarbg) == 0) {
output$modelOutputbg <- renderPrint({ "Please select independent variables." })
return()
}
incProgress(0.3) # Increment progress
if (nrow(data_bg) < 10) {
output$modelOutputbg <- renderPrint({ "Dataset is too small after removing NA values." })
return()
}
split_ratio <- input$dataSplitbg
if (split_ratio <= 0 || split_ratio >= 1) {
output$modelOutputbg <- renderPrint({ "Invalid split ratio. Please choose a value between 0 and 1." })
return()
}
# Assuming train dataset is already prepared
control <- trainControl(method="cv", number=10)
set.seed(2)
train <- data_bg %>% sample_frac(split_ratio)
test <- data_bg %>% setdiff(train)
formula_bg <- as.formula(paste(input$targetbg, "~", paste(input$independentVarbg, collapse = "+")))
bg_model <- caret::train(formula_bg,
data=train,
method="treebag",
ntree = input$nbaggInput,
trControl=control,
importance = TRUE)
incProgress(0.6) # Increment progress
# Make predictions for the entire dataset
pred_bg <- predict(bg_model, newdata = train)
# Calculate metrics
MSE_bg <- mse(actual = train[[input$targetbg]], predicted = pred_bg)
# For R_square_bg, ensure you have a function or package that provides R2
R_square_bg <- R2(pred_bg, train[[input$targetbg]])
# For MAE_bg, ensure you have a function or package that provides mae
MAE_bg <- mae(actual = train[[input$targetbg]], predicted = pred_bg)
output$predictionOutputbg <- renderPrint({
cat("Mean Squared Error (MSE):\n\n", MSE_bg, "\n\n", "Interpretation: MSE measures the average squared difference between actual and predicted values.
Lower values indicate better model performance.
A value of 0 means perfect predictions.")
cat("\n\nR-squared (R²):\n\n", R_square_bg, "\n\n", "Interpretation: R² represents the proportion of variance in the dependent variable that's predictable from the independent variables.
It ranges from 0 to 1, with higher values indicating better model fit.")
cat("\n\nMean Absolute Error (MAE):\n\n", MAE_bg, "\n\n", "Interpretation: MAE measures the average absolute difference between actual and predicted values.
Like MSE, lower MAE values indicate better model performance.")
})
# Finalize progress
incProgress(1.0) # Complete the progress
# Store results in a reactive value
results_reactive_bg(list(actual = train[[input$targetbg]], predicted = pred_bg))
})
})
output$performancePlotbg <- renderPlotly({
# Access the stored results
results <- results_reactive_bg()
req(results) # Ensure results are available
# Creating the plot
plot_data <- data.frame(Actual = results$actual, Predicted = results$predicted)
p <- ggplot(plot_data, aes(x = Actual, y = Predicted)) +
geom_point(alpha = 0.5) +
geom_abline(intercept = 0, slope = 1, color = "red", linetype = "dashed") +
labs(x = "Actual Values", y = "Predicted Values", title = "Actual vs. Predicted Values") +
theme_minimal()
ggplotly(p)
})
###Boosting
databs <- reactiveVal(NULL)
bs_model_reactive <- reactiveVal()
pred_bs_reactive <- reactiveVal()
results_reactive_bs <- reactiveVal()
# Load and clean data
observeEvent(input$loadbs, {
req(input$bsinput)
file <- input$bsinput
if (!is.null(file)) {
# Reading and cleaning data
data_df <- read_data(file$datapath)
data_df <- clean_column_names(data_df)
# Setting the reactive value
databs(data_df)
# Updating UI elements
updateSelectInput(session, "targetbs", choices = colnames(data_df))
updateSelectizeInput(session, "independentVarbs", choices = setdiff(colnames(data_df), input$targetbs))
}
})
output$dataSummarybs <- renderPrint({
req(databs())
summary(databs())
})
observeEvent(input$runbs, {
req(databs(), input$targetbs, input$independentVarbs)
# Start the progress bar
withProgress(message = 'Model is being trained...', value = 0, {
# Increment progress
incProgress(0.1) # Initial progress
data_bs <- databs() %>%
dplyr::select(all_of(c(input$targetbs, input$independentVarbs))) %>%
na.omit()
# Early return if conditions are not met
if (length(input$independentVarbs) == 0) {
output$modelOutputbs <- renderPrint({ "Please select independent variables." })
return()
}
incProgress(0.3) # Increment progress
if (nrow(data_bs) < 10) {
output$modelOutputbs <- renderPrint({ "Dataset is too small after removing NA values." })
return()
}
split_ratio <- input$dataSplitbs
if (split_ratio <= 0 || split_ratio >= 1) {
output$modelOutputbs <- renderPrint({ "Invalid split ratio. Please choose a value between 0 and 1." })
return()
}
# Partition the data
set.seed(123)
train <- data_bs %>% sample_frac(split_ratio)
test <- data_bs %>% setdiff(train)
incProgress(0.5) # Increment progress
# Fit the Boosting model
formula_bs <- as.formula(paste(input$targetbs, "~", paste(input$independentVarbs, collapse = "+")))
# Fit the Boosting model
ctrl <- trainControl(method = "cv", number = 10)
bs_model <- gbm(formula_bs,
data = train,
distribution = "gaussian",
n.trees = input$nbsInput,
interaction.depth = input$nbsdepth,
cv.folds = 10,
shrinkage = input$nbshr,
verbose = F)
bs_model_reactive(bs_model)
# Model summary
output$runbs <- renderPrint({
summary <- summary(bs_model)
print(summary)
# Add interpretations
cat("\nModel Interpretation:\n")
cat("1. Variable Importance: The summary shows the relative influence of each predictor variable in the model.
Variables with higher values have more influence on the model's predictions.\n")
})
# Finalize progress
incProgress(1.0) # Complete the progress
})
})
output$importancePlotbs <- renderPlotly({
req(bs_model_reactive) # Ensure the model is available
# Access the model from the reactive value
bs_model <- bs_model_reactive()
# Extracting feature importance
# Note: The 'n.trees' argument should be set to the number of trees used in the model
importance_vals <- summary(bs_model, n.trees = input$nbsInput, plot = FALSE)
# Preparing the data frame for ggplot
importance_df <- data.frame(
Feature = rownames(importance_vals),
Overall = importance_vals$rel.inf
)
# Plot using ggplot
p <- ggplot(importance_df, aes(x = reorder(Feature, Overall), y = Overall)) +
geom_bar(stat = "identity", fill = "dodgerblue") +
theme_minimal() +
coord_flip() + # Flipping coordinates for horizontal bars
labs(title = "Feature Importance", x = "Features", y = "Relative Influence")
# Convert to Plotly for an interactive plot
ggplotly(p)
})
observeEvent(input$boostingBtn, {
req(databs(), input$targetbs, input$independentVarbs)
# Start the progress bar
withProgress(message = 'Model is being trained...', value = 0, {
# Increment progress
incProgress(0.1) # Initial progress
df <- databs() %>%
dplyr::select(all_of(c(input$targetbs, input$independentVarbs))) %>%
na.omit()
# Early return if conditions are not met
if (length(input$independentVarbs) == 0) {
output$modelOutputbs <- renderPrint({ "Please select independent variables." })
return()
}
if (nrow(df) < 10) {
output$modelOutputbs <- renderPrint({ "Dataset is too small after removing NA values." })
return()
}
split_ratio <- input$dataSplitbs
if (split_ratio <= 0 || split_ratio >= 1) {
output$modelOutputbs <- renderPrint({ "Invalid split ratio. Please choose a value between 0 and 1." })
return()
}
incProgress(0.3) # Increment progress
# Partition the data
set.seed(123) # For reproducibility
train <- df %>% sample_frac(split_ratio)
test <- df %>% setdiff(train)
# Fit the Boosting model
formula_bs <- as.formula(paste(input$targetbs, "~", paste(input$independentVarbs, collapse = "+")))
bs_model <- gbm(formula_bs,
data = train,
distribution = "gaussian",
n.trees = input$nbsInput,
interaction.depth = input$nbsdepth,
cv.folds = 10,
shrinkage = input$nbshr,
verbose = F)
incProgress(0.7) # Increment progress
# Make predictions for the entire dataset
pred_bs <- predict(bs_model, newdata = train)
# Calculate metrics
MSE_bs <- mse(actual = train[[input$targetbs]], predicted = pred_bs)
# For R_square_bs, ensure you have a function or package that provides R2
R_square_bs <- R2(pred_bs, train[[input$targetbs]])
# For MAE_bs, ensure you have a function or package that provides mae
MAE_bs <- mae(actual = train[[input$targetbs]], predicted = pred_bs)
# Finalize progress
incProgress(1.0) # Complete the progress
output$predictionOutputbs <- renderPrint({
cat("Mean Squared Error (MSE):\n\n", MSE_bs, "\n\n", "Interpretation: MSE measures the average squared difference between actual and predicted values.
Lower values indicate better model performance.
A value of 0 means perfect predictions.")
cat("\n\nR-squared (R²):\n\n", R_square_bs, "\n\n", "Interpretation: R² represents the proportion of variance in the dependent variable that's predictable from the independent variables.
It ranges from 0 to 1, with higher values indicating better model fit.")
cat("\n\nMean Absolute Error (MAE):\n\n", MAE_bs, "\n\n", "Interpretation: MAE measures the average absolute difference between actual and predicted values.
Like MSE, lower MAE values indicate better model performance.")
})
# Store results in a reactive value
results_reactive_bs(list(actual = train[[input$targetbs]], predicted = pred_bs))
})
})
output$performancePlotbs <- renderPlotly({
# Access the stored results
results <- results_reactive_bs()
req(results) # Ensure results are available
# Creating the plot
plot_data <- data.frame(Actual = results$actual, Predicted = results$predicted)
p <- ggplot(plot_data, aes(x = Actual, y = Predicted)) +
geom_point(alpha = 0.5) +
geom_abline(intercept = 0, slope = 1, color = "red", linetype = "dashed") +
labs(x = "Actual Values", y = "Predicted Values", title = "Actual vs. Predicted Values") +
theme_minimal()
ggplotly(p)
})
###MARS
datams <- reactiveVal(NULL)
ms_model_reactive <- reactiveVal()
pred_ms_reactive <- reactiveVal()
results_reactive_ms <- reactiveVal()
# Load and clean data
observeEvent(input$loadms, {
req(input$msinput)
file <- input$msinput
if (!is.null(file)) {
# Reading and cleaning data
data_df <- read_data(file$datapath)
data_df <- clean_column_names(data_df)
# Setting the reactive value
datams(data_df)
# Updating UI elements
updateSelectInput(session, "targetms", choices = colnames(data_df))
updateSelectizeInput(session, "independentVarms", choices = setdiff(colnames(data_df), input$targetms))
}
})
output$dataSummaryms <- renderPrint({
req(datams())
summary(datams())
})
observeEvent(input$runms, {
req(datams(), input$targetms, input$independentVarms)
withProgress(message = 'Model is being trained...', value = 0, {
# Increment progress
incProgress(0.1) # Initial progress
data_ms <- datams() %>%
dplyr::select(all_of(c(input$targetms, input$independentVarms))) %>%
na.omit()
# Early return if conditions are not met
if (length(input$independentVarms) == 0) {
output$modelOutputms <- renderPrint({ "Please select independent variables." })
return()
}
incProgress(0.3) # Increment progress
if (nrow(data_ms) < 10) {
output$modelOutputms <- renderPrint({ "Dataset is too small after removing NA values." })
return()
}
split_ratio <- input$dataSplitms
if (split_ratio <= 0 || split_ratio >= 1) {
output$modelOutputms <- renderPrint({ "Invalid split ratio. Please choose a value between 0 and 1." })
return()
}
incProgress(0.6) # Increment progress
# Partition the data
set.seed(123)
train <- data_ms %>% sample_frac(split_ratio)
test <- data_ms %>% setdiff(train)
# Fit the Random Forest model
formula_ms <- as.formula(paste(input$targetms, "~", paste(input$independentVarms, collapse = "+")))
# Fit the Random Forest model
# Define the range of values for .nk and other parameters
marsGrid <- expand.grid(.degree = 1:2, .nprune = 2:20)
ms_model <- train(formula_ms, data = train, method = "earth", tuneGrid = marsGrid,
trControl = trainControl(method = "cv", verboseIter = T))
ms_model_reactive(ms_model)
# Model summary
output$runms <- renderPrint({
print(ms_model)
cat("\nModel Summary Interpretation:\n")
cat("\n1. Tuned Parameters: This section shows the best parameters found during the training process,
such as the degree of interactions and the number of terms/pruning in the MARS model.
These parameters are crucial for the model's ability to capture complex relationships in the data.\n")
cat("\n2. Model Performance: The summary will also include performance metrics.
For regression tasks, look for metrics like RMSE or R-squared, where a lower RMSE or a higher R-squared indicates better performance.
For classification, metrics like Accuracy or AUC are common.\n")
cat("\n3. Cross-Validation Results: If cross-validation was used,
the summary may show how the model performed across different subsets of the data, which can be an indicator of the model's robustness.\n")
# Feature Importance
cat("Feature Importance:\n")
importance_vals <- varImp(ms_model, scale = FALSE)
print(importance_vals)
cat("\nFeature Importance Interpretation:\n")
cat("\nThis table shows the importance of each predictor variable in the model.
Variables with higher values have more influence on the model's predictions.
In the context of MARS, this importance can be seen as how much each variable contributes to the model's ability to fit the data and make accurate predictions.
High-importance variables are key drivers of the target variable, while low-importance variables have less impact.\n")
})
# Finalize progress
incProgress(1.0) # Complete the progress
})
})
output$importancePlotms <- renderPlotly({
req(ms_model_reactive) # Ensure the model is available
# Access the model from the reactive value
ms_model <- ms_model_reactive()
# Extracting feature importance using caret's varImp function
importance_vals <- varImp(ms_model, scale = FALSE)
# Preparing the data frame for ggplot
importance_df <- as.data.frame(importance_vals$importance)
importance_df$Feature <- rownames(importance_df)
# Plot using ggplot
p <- ggplot(importance_df, aes(x = reorder(Feature, Overall), y = Overall)) +
geom_bar(stat = "identity", fill = "dodgerblue") +
theme_minimal() +
coord_flip() + # Flipping coordinates for horizontal bars
labs(title = "Feature Importance", x = "Features", y = "Relative Importance")
# Convert to Plotly for an interactive plot
ggplotly(p)
})
# Define the Mean Squared Error function
mse <- function(actual, predicted) {
mean((actual - predicted) ^ 2)
}
# Define the Mean Absolute Error function
mae <- function(actual, predicted) {
mean(abs(actual - predicted))
}
observeEvent(input$marsBtn, {
req(datams(), input$targetms, input$independentVarms)
data_ms <- datams() %>%
dplyr::select(all_of(c(input$targetms, input$independentVarms))) %>%
na.omit()
withProgress(message = 'Model is being trained...', value = 0, {
# Increment progress
incProgress(0.1) # Initial progress
# Early return if conditions are not met
if (length(input$independentVarms) == 0) {
output$modelOutputms <- renderPrint({ "Please select independent variables." })
return()
}
if (nrow(data_ms) < 10) {
output$modelOutputms <- renderPrint({ "Dataset is too small after removing NA values." })
return()
}
incProgress(0.3) # Increment progress
split_ratio <- input$dataSplitms
if (split_ratio <= 0 || split_ratio >= 1) {
output$modelOutputms <- renderPrint({ "Invalid split ratio. Please choose a value between 0 and 1." })
return()
}
# Partition the data
set.seed(123)
train <- data_ms %>% sample_frac(split_ratio)
test <- data_ms %>% setdiff(train)
# Fit the Random Forest model
formula_ms <- as.formula(paste(input$targetms, "~", paste(input$independentVarms, collapse = "+")))
# Fit the Random Forest model
# Define the range of values for .nk and other parameters
set.seed(2)
marsGrid <- expand.grid(.degree = 1:2, .nprune = 2:20)
ms_model <- train(formula_ms, data = train, method = "earth", tuneGrid = marsGrid,
trControl = trainControl(method = "cv", verboseIter = T))
incProgress(0.7) # Increment progress
# Make predictions for the entire dataset
pred_ms <- predict(ms_model, newdata = train)
# Calculate metrics
MSE_ms <- mse(actual = train[[input$targetms]], predicted = pred_ms)
# For R_square_rf, ensure you have a function or package that provides R2
R_square_ms <- R2(pred_ms, train[[input$targetms]])
# For MAE_rf, ensure you have a function or package that provides mae
MAE_ms <- mae(actual = train[[input$targetms]], predicted = pred_ms)
# Finalize progress
incProgress(1.0) # Complete the progress
output$predictionOutputms <- renderPrint({
cat("Mean Squared Error (MSE):\n\n", MSE_ms, "\n\n", "Interpretation: MSE measures the average squared difference between actual and predicted values.
Lower values indicate better model performance.
A value of 0 means perfect predictions.")
cat("\n\nR-squared (R²):\n\n", R_square_ms, "\n\n", "Interpretation: R² represents the proportion of variance in the dependent variable that's predictable from the independent variables.
It ranges from 0 to 1, with higher values indicating better model fit.")
cat("\n\nMean Absolute Error (MAE):\n\n", MAE_ms, "\n\n", "Interpretation: MAE measures the average absolute difference between actual and predicted values.
Like MSE, lower MAE values indicate better model performance.")
})
# Store results in a reactive value
results_reactive_ms(list(actual = train[[input$targetms]], predicted = pred_ms))
})
})
output$performancePlotms <- renderPlotly({
# Access the stored results
results <- results_reactive_ms()
req(results) # Ensure results are available
# Extract the 'y' column from the 'predicted' matrix and rename it to 'Predicted'
predicted_vector <- results$predicted[, "y"]
# Creating the plot data frame with 'Actual' and 'Predicted'
plot_data <- data.frame(Actual = results$actual, Predicted = predicted_vector)
p <- ggplot(plot_data, aes(x = Actual, y = Predicted)) +
geom_point(alpha = 0.5) +
geom_abline(intercept = 0, slope = 1, color = "red", linetype = "dashed") +
labs(x = "Actual Values", y = "Predicted Values", title = "Actual vs. Predicted Values") +
theme_minimal()
ggplotly(p)
})
###Ridge Regression
datarr <- reactiveVal(NULL)
rr_model_reactive <- reactiveVal()
pred_rr_reactive <- reactiveVal()
results_reactive_rr <- reactiveVal()
# Load and clean data
observeEvent(input$loadrr, {
req(input$rrinput)
file <- input$rrinput
if (!is.null(file)) {
# Reading and cleaning data
data_df <- read_data(file$datapath)
data_df <- clean_column_names(data_df)
# Setting the reactive value
datarr(data_df)
# Updating UI elements
updateSelectInput(session, "targetrr", choices = colnames(data_df))
updateSelectizeInput(session, "independentVarrr", choices = setdiff(colnames(data_df), input$targetrr))
}
})
output$dataSummaryrr <- renderPrint({
req(datarr())
summary(datarr())
})
observeEvent(input$runrr, {
req(datarr(), input$targetrr, input$independentVarrr)
withProgress(message = 'Model is being trained...', value = 0, {
# Increment progress
incProgress(0.1) # Initial progress
data_rr <- datarr() %>%
dplyr::select(all_of(c(input$targetrr, input$independentVarrr))) %>%
na.omit()
# Early return if conditions are not met
if (length(input$independentVarrr) == 0) {
output$modelOutputrr <- renderPrint({ "Please select independent variables." })
return()
}
incProgress(0.3) # Increment progress
if (nrow(data_rr) < 10) {
output$modelOutputrr <- renderPrint({ "Dataset is too small after removing NA values." })
return()
}
split_ratio <- input$dataSplitrr
if (split_ratio <= 0 || split_ratio >= 1) {
output$modelOutputrr <- renderPrint({ "Invalid split ratio. Please choose a value between 0 and 1." })
return()
}
incProgress(0.6) # Increment progress
# Partition the data
set.seed(123)
train <- data_rr %>% sample_frac(split_ratio)
test <- data_rr %>% setdiff(train)
# Define the tuning grid for Ridge Regression
ridgeGrid <- expand.grid(.lambda = 10^seq(-3, 3, length = 100),
.alpha = 0) # alpha = 0 for Ridge
formula_rr <- as.formula(paste(input$targetrr, "~", paste(input$independentVarrr, collapse = "+")))
# Fit the Random Forest model
rr_model <- train(
formula_rr,
data = train,
method = "glmnet",
tuneGrid = ridgeGrid,
trControl = trainControl(method = "cv", number = 10, verboseIter = TRUE)
)
rr_model_reactive(rr_model)
# Model summary
output$runrr <- renderPrint({
print(rr_model)
cat("\nModel Summary Interpretation:\n")
cat("\n1. Tuned Parameters: This section shows the best parameters found during the training process,
such as the degree of interactions and the number of terms/pruning in the MARS model.
These parameters are crucial for the model's ability to capture complex relationships in the data.\n")
cat("\n2. Model Performance: The summary will also include performance metrics.
For regression tasks, look for metrics like RMSE or R-squared, where a lower RMSE or a higher R-squared indicates better performance.
For classification, metrics like Accuracy or AUC are common.\n")
cat("\n3. Cross-Validation Results: If cross-validation was used,
the summary may show how the model performed across different subsets of the data, which can be an indicator of the model's robustness.\n")
# Feature Importance
cat("Feature Importance:\n")
importance_vals <- varImp(rr_model, scale = FALSE)
print(importance_vals)
cat("\nFeature Importance Interpretation:\n")
cat("\nThis table shows the importance of each predictor variable in the model.
Variables with higher values have more influence on the model's predictions.
In the context of MARS, this importance can be seen as how much each variable contributes to the model's ability to fit the data and make accurate predictions.
High-importance variables are key drivers of the target variable, while low-importance variables have less impact.\n")
})
# Finalize progress
incProgress(1.0) # Complete the progress
})
})
output$importancePlotrr <- renderPlotly({
req(rr_model_reactive) # Ensure the model is available
# Access the model from the reactive value
rr_model <- rr_model_reactive()
# Extracting feature importance using caret's varImp function
importance_vals <- varImp(rr_model, scale = FALSE)
# Preparing the data frame for ggplot
importance_df <- as.data.frame(importance_vals$importance)
importance_df$Feature <- rownames(importance_df)
# Plot using ggplot
p <- ggplot(importance_df, aes(x = reorder(Feature, Overall), y = Overall)) +
geom_bar(stat = "identity", fill = "dodgerblue") +
theme_minimal() +
coord_flip() + # Flipping coordinates for horizontal bars
labs(title = "Feature Importance", x = "Features", y = "Relative Importance")
# Convert to Plotly for an interactive plot
ggplotly(p)
})
# Define the Mean Squared Error function
mse <- function(actual, predicted) {
mean((actual - predicted) ^ 2)
}
# Define the Mean Absolute Error function
mae <- function(actual, predicted) {
mean(abs(actual - predicted))
}
observeEvent(input$RidgeBtn, {
req(datarr(), input$targetrr, input$independentVarrr)
data_rr <- datarr() %>%
dplyr::select(all_of(c(input$targetrr, input$independentVarrr))) %>%
na.omit()
withProgress(message = 'Model is being trained...', value = 0, {
# Increment progress
incProgress(0.1) # Initial progress
# Early return if conditions are not met
if (length(input$independentVarrr) == 0) {
output$modelOutputrr <- renderPrint({ "Please select independent variables." })
return()
}
if (nrow(data_rr) < 10) {
output$modelOutputrr <- renderPrint({ "Dataset is too small after removing NA values." })
return()
}
incProgress(0.3) # Increment progress
split_ratio <- input$dataSplitrr
if (split_ratio <= 0 || split_ratio >= 1) {
output$modelOutputrr <- renderPrint({ "Invalid split ratio. Please choose a value between 0 and 1." })
return()
}
# Partition the data
set.seed(123)
train <- data_rr %>% sample_frac(split_ratio)
test <- data_rr %>% setdiff(train)
# Define the tuning grid for Ridge Regression
ridgeGrid <- expand.grid(.lambda = 10^seq(-3, 3, length = 100),
.alpha = 0) # alpha = 0 for Ridge
formula_rr <- as.formula(paste(input$targetrr, "~", paste(input$independentVarrr, collapse = "+")))
# Fit the Random Forest model
rr_model <- train(
formula_rr,
data = train,
method = "glmnet",
tuneGrid = ridgeGrid,
trControl = trainControl(method = "cv", number = 10, verboseIter = TRUE)
)
incProgress(0.7) # Increment progress
# Make predictions for the entire dataset
pred_rr <- predict(rr_model, newdata = train)
# Calculate metrics
MSE_rr <- mse(actual = train[[input$targetrr]], predicted = pred_rr)
# For R_square_rf, ensure you have a function or package that provides R2
R_square_rr <- R2(pred_rr, train[[input$targetrr]])
# For MAE_rf, ensure you have a function or package that provides mae
MAE_rr <- mae(actual = train[[input$targetrr]], predicted = pred_rr)
# Finalize progress
incProgress(1.0) # Complete the progress
output$predictionOutputrr <- renderPrint({
cat("Mean Squared Error (MSE):\n\n", MSE_rr, "\n\n", "Interpretation: MSE measures the average squared difference between actual and predicted values.
Lower values indicate better model performance.
A value of 0 means perfect predictions.")
cat("\n\nR-squared (R²):\n\n", R_square_rr, "\n\n", "Interpretation: R² represents the proportion of variance in the dependent variable that's predictable from the independent variables.
It ranges from 0 to 1, with higher values indicating better model fit.")
cat("\n\nMean Absolute Error (MAE):\n\n", MAE_rr, "\n\n", "Interpretation: MAE measures the average absolute difference between actual and predicted values.
Like MSE, lower MAE values indicate better model performance.")
})
# Store results in a reactive value
results_reactive_rr(list(actual = train[[input$targetrr]], predicted = pred_rr))
})
})
output$performancePlotrr <- renderPlotly({
# Access the stored results
results <- results_reactive_rr()
req(results) # Ensure results are available
# Since results$predicted is a vector, use it directly
plot_data <- data.frame(Actual = results$actual, Predicted = results$predicted)
p <- ggplot(plot_data, aes(x = Actual, y = Predicted)) +
geom_point(alpha = 0.5) +
geom_abline(intercept = 0, slope = 1, color = "red", linetype = "dashed") +
labs(x = "Actual Values", y = "Predicted Values", title = "Actual vs. Predicted Values") +
theme_minimal()
ggplotly(p)
})
###LASSO Regression
datals <- reactiveVal(NULL)
ls_model_reactive <- reactiveVal()
pred_ls_reactive <- reactiveVal()
results_reactive_ls <- reactiveVal()
# Load and clean data
observeEvent(input$loadls, {
req(input$lsinput)
file <- input$lsinput
if (!is.null(file)) {
# Reading and cleaning data
data_df <- read_data(file$datapath)
data_df <- clean_column_names(data_df)
# Setting the reactive value
datals(data_df)
# Updating UI elements
updateSelectInput(session, "targetls", choices = colnames(data_df))
updateSelectizeInput(session, "independentVarls", choices = setdiff(colnames(data_df), input$targetls))
}
})
output$dataSummaryls <- renderPrint({
req(datals())
summary(datals())
})
observeEvent(input$runls, {
req(datals(), input$targetls, input$independentVarls)
withProgress(message = 'Model is being trained...', value = 0, {
# Increment progress
incProgress(0.1) # Initial progress
data_ls <- datals() %>%
dplyr::select(all_of(c(input$targetls, input$independentVarls))) %>%
na.omit()
# Early return if conditions are not met
if (length(input$independentVarls) == 0) {
output$modelOutputls <- renderPrint({ "Please select independent variables." })
return()
}
incProgress(0.3) # Increment progress
if (nrow(data_ls) < 10) {
output$modelOutputls <- renderPrint({ "Dataset is too small after removing NA values." })
return()
}
split_ratio <- input$dataSplitls
if (split_ratio <= 0 || split_ratio >= 1) {
output$modelOutputls <- renderPrint({ "Invalid split ratio. Please choose a value between 0 and 1." })
return()
}
incProgress(0.6) # Increment progress
# Partition the data
set.seed(123)
train <- data_ls %>% sample_frac(split_ratio)
test <- data_ls %>% setdiff(train)
# Define the tuning grid for Ridge Regression
ridgeGrid <- expand.grid(.lambda = 10^seq(-3, 3, length = 100),
.alpha = 1) # alpha = 0 for Ridge
formula_ls <- as.formula(paste(input$targetls, "~", paste(input$independentVarls, collapse = "+")))
# Fit the Random Forest model
ls_model <- train(
formula_ls,
data = train,
method = "glmnet",
tuneGrid = ridgeGrid,
trControl = trainControl(method = "cv", number = 10, verboseIter = TRUE)
)
ls_model_reactive(ls_model)
# Model summary
output$runls <- renderPrint({
print(ls_model)
cat("\nModel Summary Interpretation:\n")
cat("\n1. Tuned Parameters: This section shows the best parameters found during the training process,
such as the degree of interactions and the number of terms/pruning in the MARS model.
These parameters are crucial for the model's ability to capture complex relationships in the data.\n")
cat("\n2. Model Performance: The summary will also include performance metrics.
For regression tasks, look for metrics like RMSE or R-squared, where a lower RMSE or a higher R-squared indicates better performance.
For classification, metrics like Accuracy or AUC are common.\n")
cat("\n3. Cross-Validation Results: If cross-validation was used,
the summary may show how the model performed across different subsets of the data, which can be an indicator of the model's robustness.\n")
# Feature Importance
cat("Feature Importance:\n")
importance_vals <- varImp(ls_model, scale = FALSE)
print(importance_vals)
cat("\nFeature Importance Interpretation:\n")
cat("\nThis table shows the importance of each predictor variable in the model.
Variables with higher values have more influence on the model's predictions.
In the context of MARS, this importance can be seen as how much each variable contributes to the model's ability to fit the data and make accurate predictions.
High-importance variables are key drivers of the target variable, while low-importance variables have less impact.\n")
})
# Finalize progress
incProgress(1.0) # Complete the progress
})
})
output$importancePlotls <- renderPlotly({
req(ls_model_reactive) # Ensure the model is available
# Access the model from the reactive value
ls_model <- ls_model_reactive()
# Extracting feature importance using caret's varImp function
importance_vals <- varImp(ls_model, scale = FALSE)
# Preparing the data frame for ggplot
importance_df <- as.data.frame(importance_vals$importance)
importance_df$Feature <- rownames(importance_df)
# Plot using ggplot
p <- ggplot(importance_df, aes(x = reorder(Feature, Overall), y = Overall)) +
geom_bar(stat = "identity", fill = "dodgerblue") +
theme_minimal() +
coord_flip() + # Flipping coordinates for horizontal bars
labs(title = "Feature Importance", x = "Features", y = "Relative Importance")
# Convert to Plotly for an interactive plot
ggplotly(p)
})
# Define the Mean Squared Error function
mse <- function(actual, predicted) {
mean((actual - predicted) ^ 2)
}
# Define the Mean Absolute Error function
mae <- function(actual, predicted) {
mean(abs(actual - predicted))
}
observeEvent(input$LassoBtn, {
req(datals(), input$targetls, input$independentVarls)
data_ls <- datals() %>%
dplyr::select(all_of(c(input$targetls, input$independentVarls))) %>%
na.omit()
withProgress(message = 'Model is being trained...', value = 0, {
# Increment progress
incProgress(0.1) # Initial progress
# Early return if conditions are not met
if (length(input$independentVarls) == 0) {
output$modelOutputls <- renderPrint({ "Please select independent variables." })
return()
}
if (nrow(data_ls) < 10) {
output$modelOutputls <- renderPrint({ "Dataset is too small after removing NA values." })
return()
}
incProgress(0.3) # Increment progress
split_ratio <- input$dataSplitls
if (split_ratio <= 0 || split_ratio >= 1) {
output$modelOutputls <- renderPrint({ "Invalid split ratio. Please choose a value between 0 and 1." })
return()
}
# Partition the data
set.seed(123)
train <- data_ls %>% sample_frac(split_ratio)
test <- data_ls %>% setdiff(train)
# Define the tuning grid for Ridge Regression
ridgeGrid <- expand.grid(.lambda = 10^seq(-3, 3, length = 100),
.alpha = 1) # alpha = 0 for Ridge
formula_ls <- as.formula(paste(input$targetls, "~", paste(input$independentVarls, collapse = "+")))
# Fit the Random Forest model
ls_model <- train(
formula_ls,
data = train,
method = "glmnet",
tuneGrid = ridgeGrid,
trControl = trainControl(method = "cv", number = 10, verboseIter = TRUE)
)
incProgress(0.7) # Increment progress
# Make predictions for the entire dataset
pred_ls <- predict(ls_model, newdata = train)
# Calculate metrics
MSE_ls <- mse(actual = train[[input$targetls]], predicted = pred_ls)
# For R_square_rf, ensure you have a function or package that provides R2
R_square_ls <- R2(pred_ls, train[[input$targetls]])
# For MAE_rf, ensure you have a function or package that provides mae
MAE_ls <- mae(actual = train[[input$targetls]], predicted = pred_ls)
# Finalize progress
incProgress(1.0) # Complete the progress
output$predictionOutputls <- renderPrint({
cat("Mean Squared Error (MSE):\n\n", MSE_ls, "\n\n", "Interpretation: MSE measures the average squared difference between actual and predicted values.
Lower values indicate better model performance.
A value of 0 means perfect predictions.")
cat("\n\nR-squared (R²):\n\n", R_square_ls, "\n\n", "Interpretation: R² represents the proportion of variance in the dependent variable that's predictable from the independent variables.
It ranges from 0 to 1, with higher values indicating better model fit.")
cat("\n\nMean Absolute Error (MAE):\n\n", MAE_ls, "\n\n", "Interpretation: MAE measures the average absolute difference between actual and predicted values.
Like MSE, lower MAE values indicate better model performance.")
})
# Store results in a reactive value
results_reactive_ls(list(actual = train[[input$targetls]], predicted = pred_ls))
})
})
output$performancePlotls <- renderPlotly({
# Access the stored results
results <- results_reactive_ls()
req(results) # Ensure results are available
# Since results$predicted is a vector, use it directly
plot_data <- data.frame(Actual = results$actual, Predicted = results$predicted)
p <- ggplot(plot_data, aes(x = Actual, y = Predicted)) +
geom_point(alpha = 0.5) +
geom_abline(intercept = 0, slope = 1, color = "red", linetype = "dashed") +
labs(x = "Actual Values", y = "Predicted Values", title = "Actual vs. Predicted Values") +
theme_minimal()
ggplotly(p)
})
}
shinyApp(ui, server) |